feat: deep statistical analytics — clinical, symptoms, incidence, env correlation, weekday

Adds a substantial layer of data-backed statistics (all grounded in verified,
clean source data — no fabricated metrics).

Backend (new routers/statistics.py, prefix /api/stats; +106 pytest still green):
- /inpatient-clinical: LOS dist + by-disease quartiles, cost dist + by-disease +
  cost-vs-LOS, outcome counts, admission-route counts, BMI-by-age, KPIs
  (5822 admissions, median LOS 4d, mean ¥6294, cure 99.1%, emergency 47%)
- /symptoms: 主诉 keyword frequencies (发热/咳嗽/肺炎…) + revisit ratio (36%)
- /incidence-rate: per-10k-population standardized rate by district (cases ÷ pop)
- /env-correlation: pollutant×cases Pearson + 7×7 pairwise matrix + PM2.5 scatter
- /temporal: weekday distribution (+ month/yoy returned but UI omits them — data
  is December-only, so seasonality/YoY would be misleading)

Frontend:
- NEW 住院临床分析 page (/analysis/clinical, nav 临床分析): 9 charts + KPI row —
  LOS histogram + box-by-disease, cost histogram + scatter + by-disease, outcome
  donut (severity-colored), admission-route donut, age-band BMI box
- DiseaseAnalysis: 主诉症状词频 horizontal bar + revisit ratio
- DistrictComparison: 标化发病率（每万人）with 病例数↔发病率 toggle (rate is
  epidemiologically correct; raw counts mislead by population)
- EnvironmentalHealth: pollutant-cases correlation bar + 7×7 correlation heatmap +
  PM2.5×cases scatter with least-squares regression line
- TrendAnalysis: 星期就诊分布 + honest "data is December-only" note
- statsApi client + types

Gates: tsc 0 · build ok · functional e2e 43/43 (incl 2 new clinical) · verified
live against real backend data via dev proxy

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

backend/main.py

@@ -13,7 +13,7 @@ from logging_config import setup_logging
 from middleware.request_logger import RequestLoggerMiddleware
 from auth.router import router as auth_router
 from auth.service import seed_default_admin
-from routers import risk, alerts, analysis, insights, reports, cases, geocoded, grid, chat, environment
+from routers import risk, alerts, analysis, insights, reports, cases, geocoded, grid, chat, environment, statistics
 
 
 setup_logging()
@@ -59,6 +59,7 @@ app.include_router(geocoded.router)
 app.include_router(grid.router)
 app.include_router(chat.router)
 app.include_router(environment.router)
+app.include_router(statistics.router)
 
 
 @app.get("/")

backend/routers/statistics.py

@@ -0,0 +1,621 @@
+"""
+统计分析 API 路由 (prefix /api/stats)
+
+为前端统计仪表盘提供聚合后的临床、症状、发病率、环境相关性和时序数据。
+所有数据从 processed/*.parquet 计算得出（文件型后端，无数据库）。
+
+设计原则：
+- 模块级缓存载入的 parquet（与其他路由一致）。
+- 仅返回聚合结果，绝不直接 dump 原始行，保持 payload 小。
+- 每个端点用 try/except 包裹，失败时返回合法的空结构（绝不让 UI 收到 500）。
+- pandas 计算放入线程池 (asyncio.to_thread)，避免阻塞事件循环。
+"""
+
+import asyncio
+import glob
+import logging
+import threading
+from pathlib import Path
+from typing import Optional, cast
+
+import numpy as np
+import pandas as pd
+from fastapi import APIRouter, Query
+from pydantic import BaseModel
+
+from data.case_loader import (
+    get_inpatient_data,
+    get_outpatient_data,
+    get_combined_data,
+    load_cases_by_district_daily,
+    normalize_district,
+)
+
+logger = logging.getLogger("cbpoa.statistics")
+
+router = APIRouter(prefix="/api/stats", tags=["statistics"])
+
+PROJECT_ROOT = Path(__file__).parent.parent.parent
+PROCESSED_DIR = PROJECT_ROOT / "processed"
+
+# ============== Module-level caches ==============
+
+_cache: dict[str, object] = {}
+_cache_lock = threading.RLock()
+
+# 7 个污染物（与 feature snapshot 列名一致）
+POLLUTANTS = ["AQI", "PM25", "PM10", "SO2", "NO2", "O3", "CO"]
+
+# 主诉症状关键词（固定列表，子串匹配）。注意顺序：更具体的在前避免被宽泛词吞掉，
+# 但因为是独立子串计数，顺序不影响结果，仅为可读性分组。
+SYMPTOM_KEYWORDS = [
+    "发热", "咳嗽", "咳", "喘息", "喘", "流涕", "鼻塞", "咽痛", "咽喉",
+    "痰", "气促", "呼吸困难", "肺炎", "复诊", "随诊", "复查",
+    "腹泻", "呕吐", "头痛", "乏力", "胸闷", "鼻涕", "发烧", "感冒",
+]
+REVISIT_KEYWORDS = ["复诊", "随诊", "复查"]
+
+
+def _district_population() -> pd.Series:
+    """各区人口（population_density 求和，按 grid_district_mapping 归属）。
+
+    返回 index 为规范化区名(13)、值为人口的 Series。结果缓存。
+    """
+    cached = _cache.get("district_population")
+    if cached is not None:
+        return cast(pd.Series, cached)
+    with _cache_lock:
+        cached = _cache.get("district_population")
+        if cached is not None:
+            return cast(pd.Series, cached)
+        mapping = pd.read_parquet(PROCESSED_DIR / "grid_district_mapping.parquet")
+        grid = pd.read_parquet(
+            PROCESSED_DIR / "grid_100m_with_dem_pop.parquet",
+            columns=["grid_id", "population_density"],
+        )
+        joined = mapping.merge(grid, on="grid_id", how="inner")
+        joined = joined.dropna(subset=["district_name"])
+        joined["district_name"] = joined["district_name"].map(normalize_district)
+        pop = joined.groupby("district_name")["population_density"].sum()
+        _cache["district_population"] = pop
+        return pop
+
+
+def _feature_snapshots() -> pd.DataFrame:
+    """合并所有可用的 features_*.parquet 快照（缓存）。
+
+    用于污染物 vs 病例的相关性分析。每个快照按格点给出污染物 + 病例计数 + 区。
+    """
+    cached = _cache.get("features")
+    if cached is not None:
+        return cast(pd.DataFrame, cached)
+    with _cache_lock:
+        cached = _cache.get("features")
+        if cached is not None:
+            return cast(pd.DataFrame, cached)
+        paths = sorted(glob.glob(str(PROCESSED_DIR / "features_*.parquet")))
+        if not paths:
+            df = pd.DataFrame(
+                columns=POLLUTANTS + ["outpatient_count", "inpatient_count", "total_cases", "district"]
+            )
+        else:
+            frames = [pd.read_parquet(p) for p in paths]
+            df = pd.concat(frames, ignore_index=True)
+        _cache["features"] = df
+        return df
+
+
+# ============== Response Models ==============
+
+
+class KeyValueCount(BaseModel):
+    bin_label: str
+    count: int
+
+
+class InpatientKpis(BaseModel):
+    total_admissions: int
+    median_los_days: float
+    mean_cost: float
+    cure_rate: float
+    emergency_admit_ratio: float
+
+
+class LosByDisease(BaseModel):
+    diagnosis: str
+    p25: float
+    median: float
+    p75: float
+    n: int
+
+
+class CostByDisease(BaseModel):
+    diagnosis: str
+    mean_cost: float
+    n: int
+
+
+class CostVsLos(BaseModel):
+    los: int
+    cost: float
+
+
+class LabelCount(BaseModel):
+    outcome: Optional[str] = None
+    route: Optional[str] = None
+    count: int
+
+
+class OutcomeCount(BaseModel):
+    outcome: str
+    count: int
+
+
+class RouteCount(BaseModel):
+    route: str
+    count: int
+
+
+class BmiByAge(BaseModel):
+    age_band: str
+    p25: float
+    median: float
+    p75: float
+    n: int
+
+
+class InpatientClinicalResponse(BaseModel):
+    kpis: InpatientKpis
+    los_histogram: list[KeyValueCount]
+    los_by_disease: list[LosByDisease]
+    cost_histogram: list[KeyValueCount]
+    cost_by_disease: list[CostByDisease]
+    cost_vs_los: list[CostVsLos]
+    outcome_counts: list[OutcomeCount]
+    admission_route_counts: list[RouteCount]
+    bmi_by_age_band: list[BmiByAge]
+
+
+class SymptomItem(BaseModel):
+    keyword: str
+    count: int
+
+
+class SymptomsResponse(BaseModel):
+    symptoms: list[SymptomItem]
+    revisit_ratio: float
+
+
+class IncidenceItem(BaseModel):
+    district: str
+    total_cases: int
+    population: float
+    rate_per_10k: float
+
+
+class IncidenceResponse(BaseModel):
+    districts: list[IncidenceItem]
+
+
+class CorrItem(BaseModel):
+    pollutant: str
+    corr_with_cases: float
+
+
+class ScatterPoint(BaseModel):
+    pm25: float
+    aqi: float
+    cases: float
+
+
+class PairwiseCorr(BaseModel):
+    a: str
+    b: str
+    corr: float
+
+
+class EnvCorrelationResponse(BaseModel):
+    correlation_matrix: list[CorrItem]
+    scatter: list[ScatterPoint]
+    pollutant_pairwise: list[PairwiseCorr]
+
+
+class WeekdayPoint(BaseModel):
+    weekday: str
+    outpatient: int
+    inpatient: int
+    total: int
+
+
+class MonthYearPoint(BaseModel):
+    year: int
+    month: int
+    total: int
+
+
+class YoYPoint(BaseModel):
+    period: str
+    current: int
+    previous: int
+    growth_pct: float
+
+
+class TemporalResponse(BaseModel):
+    weekday: list[WeekdayPoint]
+    month_year: list[MonthYearPoint]
+    yoy: list[YoYPoint]
+
+
+# ============== Helpers ==============
+
+
+def _empty_inpatient_clinical() -> InpatientClinicalResponse:
+    return InpatientClinicalResponse(
+        kpis=InpatientKpis(
+            total_admissions=0, median_los_days=0.0, mean_cost=0.0,
+            cure_rate=0.0, emergency_admit_ratio=0.0,
+        ),
+        los_histogram=[], los_by_disease=[], cost_histogram=[],
+        cost_by_disease=[], cost_vs_los=[], outcome_counts=[],
+        admission_route_counts=[], bmi_by_age_band=[],
+    )
+
+
+def _safe_float(v) -> float:
+    try:
+        f = float(v)
+        if np.isnan(f) or np.isinf(f):
+            return 0.0
+        return round(f, 4)
+    except (TypeError, ValueError):
+        return 0.0
+
+
+# ============== Endpoint 1: inpatient clinical ==============
+
+
+def _compute_inpatient_clinical() -> InpatientClinicalResponse:
+    df = get_inpatient_data().copy()
+    if df.empty:
+        return _empty_inpatient_clinical()
+
+    # LOS = (出院日期 - 入院日期).days, valid 0-60
+    in_date = pd.to_datetime(df["入院日期"], errors="coerce")
+    out_date = pd.to_datetime(df["出院日期"], errors="coerce")
+    df["los"] = (out_date - in_date).dt.days
+    df_los = df[(df["los"] >= 0) & (df["los"] <= 60)]
+
+    total = len(df)
+    median_los = float(df_los["los"].median()) if len(df_los) else 0.0
+    cost = pd.to_numeric(df["住院总费用"], errors="coerce")
+    mean_cost = float(cost.mean()) if cost.notna().any() else 0.0
+
+    outcome = df["出院情况"].fillna("未知")
+    cure_n = int(outcome.isin(["治愈", "好转"]).sum())
+    cure_rate = cure_n / total if total else 0.0
+
+    route = df["入院途径"].fillna("未知")
+    emerg_n = int((route == "急诊").sum())
+    emerg_ratio = emerg_n / total if total else 0.0
+
+    kpis = InpatientKpis(
+        total_admissions=total,
+        median_los_days=round(median_los, 2),
+        mean_cost=round(mean_cost, 2),
+        cure_rate=round(cure_rate, 4),
+        emergency_admit_ratio=round(emerg_ratio, 4),
+    )
+
+    # LOS histogram bins: 0,1,2,3,4,5,6,7,8-14,15+
+    los_histogram: list[KeyValueCount] = []
+    los_vals = df_los["los"]
+    for b in range(0, 8):
+        los_histogram.append(KeyValueCount(bin_label=str(b), count=int((los_vals == b).sum())))
+    los_histogram.append(KeyValueCount(bin_label="8-14", count=int(((los_vals >= 8) & (los_vals <= 14)).sum())))
+    los_histogram.append(KeyValueCount(bin_label="15+", count=int((los_vals >= 15).sum())))
+
+    # LOS by disease (top 8 diagnoses by n)
+    los_by_disease: list[LosByDisease] = []
+    if len(df_los):
+        top_diag = df_los["诊断名称"].value_counts().head(8).index.tolist()
+        for d in top_diag:
+            grp = df_los[df_los["诊断名称"] == d]["los"]
+            los_by_disease.append(LosByDisease(
+                diagnosis=str(d),
+                p25=round(float(grp.quantile(0.25)), 2),
+                median=round(float(grp.median()), 2),
+                p75=round(float(grp.quantile(0.75)), 2),
+                n=int(len(grp)),
+            ))
+
+    # Cost histogram: 0-2k,2-4k,4-6k,6-8k,8-10k,10k+
+    cost_valid = cost.dropna()
+    cost_bins = [(0, 2000, "0-2k"), (2000, 4000, "2-4k"), (4000, 6000, "4-6k"),
+                 (6000, 8000, "6-8k"), (8000, 10000, "8-10k")]
+    cost_histogram: list[KeyValueCount] = []
+    for lo, hi, label in cost_bins:
+        cost_histogram.append(KeyValueCount(
+            bin_label=label, count=int(((cost_valid >= lo) & (cost_valid < hi)).sum())))
+    cost_histogram.append(KeyValueCount(bin_label="10k+", count=int((cost_valid >= 10000).sum())))
+
+    # Cost by disease (top 8 by n)
+    cost_by_disease: list[CostByDisease] = []
+    df_cost = df[cost.notna()].copy()
+    df_cost["_cost"] = cost[cost.notna()]
+    if len(df_cost):
+        top_cd = df_cost["诊断名称"].value_counts().head(8).index.tolist()
+        for d in top_cd:
+            grp = df_cost[df_cost["诊断名称"] == d]["_cost"]
+            cost_by_disease.append(CostByDisease(
+                diagnosis=str(d),
+                mean_cost=round(float(grp.mean()), 2),
+                n=int(len(grp)),
+            ))
+
+    # cost vs los scatter (up to 500 points)
+    cost_vs_los: list[CostVsLos] = []
+    scatter_df = df_los[cost.reindex(df_los.index).notna()].copy()
+    scatter_df["_cost"] = cost.reindex(scatter_df.index)
+    if len(scatter_df) > 500:
+        scatter_df = scatter_df.sample(n=500, random_state=42)
+    for _, r in scatter_df.iterrows():
+        cost_vs_los.append(CostVsLos(los=int(r["los"]), cost=round(float(r["_cost"]), 2)))
+
+    # outcome counts
+    outcome_counts = [
+        OutcomeCount(outcome=str(k), count=int(v))
+        for k, v in outcome.value_counts().items()
+    ]
+
+    # admission route counts
+    admission_route_counts = [
+        RouteCount(route=str(k), count=int(v))
+        for k, v in route.value_counts().items()
+    ]
+
+    # BMI by age band. BMI = 体重kg / (身高m)^2; plausible 8-40.
+    bmi_by_age_band: list[BmiByAge] = []
+    h = pd.to_numeric(df["身高"], errors="coerce")  # cm
+    w = pd.to_numeric(df["体重"], errors="coerce")   # kg
+    age = pd.to_numeric(df["年龄"], errors="coerce")
+    bmi = w / ((h / 100.0) ** 2)
+    bmi_df = pd.DataFrame({"age": age, "bmi": bmi})
+    bmi_df = bmi_df[(bmi_df["bmi"] >= 8) & (bmi_df["bmi"] <= 40) & bmi_df["age"].notna()]
+    age_bands = [(0, 3, "0-2"), (3, 6, "3-5"), (6, 9, "6-8"),
+                 (9, 12, "9-11"), (12, 15, "12-14"), (15, 19, "15-18")]
+    for lo, hi, label in age_bands:
+        grp = bmi_df[(bmi_df["age"] >= lo) & (bmi_df["age"] < hi)]["bmi"]
+        if len(grp) == 0:
+            continue
+        bmi_by_age_band.append(BmiByAge(
+            age_band=label,
+            p25=round(float(grp.quantile(0.25)), 2),
+            median=round(float(grp.median()), 2),
+            p75=round(float(grp.quantile(0.75)), 2),
+            n=int(len(grp)),
+        ))
+
+    return InpatientClinicalResponse(
+        kpis=kpis,
+        los_histogram=los_histogram,
+        los_by_disease=los_by_disease,
+        cost_histogram=cost_histogram,
+        cost_by_disease=cost_by_disease,
+        cost_vs_los=cost_vs_los,
+        outcome_counts=outcome_counts,
+        admission_route_counts=admission_route_counts,
+        bmi_by_age_band=bmi_by_age_band,
+    )
+
+
+@router.get("/inpatient-clinical", response_model=InpatientClinicalResponse, summary="住院临床统计")
+async def inpatient_clinical():
+    """住院临床概览：KPI、住院天数(LOS)分布、费用分布、转归、入院途径、BMI 分布。"""
+    try:
+        return await asyncio.to_thread(_compute_inpatient_clinical)
+    except Exception:
+        logger.exception("inpatient-clinical failed")
+        return _empty_inpatient_clinical()
+
+
+# ============== Endpoint 2: symptoms ==============
+
+
+def _compute_symptoms(top: int) -> SymptomsResponse:
+    df = get_outpatient_data()
+    if df.empty or "主诉" not in df.columns:
+        return SymptomsResponse(symptoms=[], revisit_ratio=0.0)
+    chief = df["主诉"].dropna().astype(str)
+    total = len(chief)
+    if total == 0:
+        return SymptomsResponse(symptoms=[], revisit_ratio=0.0)
+
+    counts: list[SymptomItem] = []
+    for kw in SYMPTOM_KEYWORDS:
+        c = int(chief.str.contains(kw, regex=False).sum())
+        if c > 0:
+            counts.append(SymptomItem(keyword=kw, count=c))
+    counts.sort(key=lambda x: x.count, reverse=True)
+    counts = counts[:top]
+
+    revisit_mask = chief.str.contains("|".join(REVISIT_KEYWORDS), regex=True)
+    revisit_ratio = float(revisit_mask.sum()) / total if total else 0.0
+
+    return SymptomsResponse(symptoms=counts, revisit_ratio=round(revisit_ratio, 4))
+
+
+@router.get("/symptoms", response_model=SymptomsResponse, summary="门诊主诉症状词频")
+async def symptoms(top: int = Query(20, ge=1, le=50, description="返回前 N 个症状词")):
+    """从门诊主诉中提取固定症状关键词的出现频次，并计算复诊比例。"""
+    try:
+        return await asyncio.to_thread(_compute_symptoms, top)
+    except Exception:
+        logger.exception("symptoms failed")
+        return SymptomsResponse(symptoms=[], revisit_ratio=0.0)
+
+
+# ============== Endpoint 3: incidence rate ==============
+
+
+def _compute_incidence() -> IncidenceResponse:
+    daily = load_cases_by_district_daily()
+    if daily.empty:
+        return IncidenceResponse(districts=[])
+    case_totals = daily.groupby("district")["total_cases"].sum()
+    pop = _district_population()
+
+    items: list[IncidenceItem] = []
+    for district in case_totals.index:
+        total_cases = int(case_totals.get(district, 0))
+        population = float(pop.get(district, 0.0))
+        rate = (total_cases / population * 10000) if population > 0 else 0.0
+        items.append(IncidenceItem(
+            district=str(district),
+            total_cases=total_cases,
+            population=round(population, 1),
+            rate_per_10k=round(rate, 2),
+        ))
+    items.sort(key=lambda x: x.rate_per_10k, reverse=True)
+    return IncidenceResponse(districts=items)
+
+
+@router.get("/incidence-rate", response_model=IncidenceResponse, summary="各区发病率")
+async def incidence_rate():
+    """各区病例总数 / 区人口 * 10000，得到每万人发病率（13 区）。"""
+    try:
+        return await asyncio.to_thread(_compute_incidence)
+    except Exception:
+        logger.exception("incidence-rate failed")
+        return IncidenceResponse(districts=[])
+
+
+# ============== Endpoint 4: env correlation ==============
+
+
+def _compute_env_correlation() -> EnvCorrelationResponse:
+    df = _feature_snapshots()
+    if df.empty or "total_cases" not in df.columns:
+        return EnvCorrelationResponse(correlation_matrix=[], scatter=[], pollutant_pairwise=[])
+
+    # 污染物 vs 病例 的 Pearson 相关（按格点，汇集所有快照）
+    correlation_matrix: list[CorrItem] = []
+    cases = pd.to_numeric(df["total_cases"], errors="coerce")
+    for p in POLLUTANTS:
+        if p not in df.columns:
+            continue
+        series = pd.to_numeric(df[p], errors="coerce")
+        valid = series.notna() & cases.notna()
+        if valid.sum() < 2 or series[valid].std() == 0 or cases[valid].std() == 0:
+            corr = 0.0
+        else:
+            corr = float(series[valid].corr(cases[valid]))
+        correlation_matrix.append(CorrItem(pollutant=p, corr_with_cases=_safe_float(corr)))
+
+    # scatter: 采样 cases>0 的格点（up to 500）
+    scatter: list[ScatterPoint] = []
+    has_cols = all(c in df.columns for c in ["PM25", "AQI", "total_cases"])
+    if has_cols:
+        sdf = df[["PM25", "AQI", "total_cases"]].copy()
+        sdf = sdf[pd.to_numeric(sdf["total_cases"], errors="coerce") > 0].dropna()
+        if len(sdf) > 500:
+            sdf = sdf.sample(n=500, random_state=42)
+        for _, r in sdf.iterrows():
+            scatter.append(ScatterPoint(
+                pm25=_safe_float(r["PM25"]),
+                aqi=_safe_float(r["AQI"]),
+                cases=_safe_float(r["total_cases"]),
+            ))
+
+    # pollutant pairwise (upper triangle)
+    pollutant_pairwise: list[PairwiseCorr] = []
+    present = [p for p in POLLUTANTS if p in df.columns]
+    pol_df = df[present].apply(pd.to_numeric, errors="coerce")
+    corr_mat = pol_df.corr()
+    for i, a in enumerate(present):
+        for b in present[i + 1:]:
+            try:
+                v = corr_mat.loc[a, b]
+            except KeyError:
+                v = 0.0
+            pollutant_pairwise.append(PairwiseCorr(a=a, b=b, corr=_safe_float(v)))
+
+    return EnvCorrelationResponse(
+        correlation_matrix=correlation_matrix,
+        scatter=scatter,
+        pollutant_pairwise=pollutant_pairwise,
+    )
+
+
+@router.get("/env-correlation", response_model=EnvCorrelationResponse, summary="环境-病例相关性")
+async def env_correlation():
+    """污染物与病例的相关矩阵、PM2.5/AQI 散点、污染物两两相关（热力图）。"""
+    try:
+        return await asyncio.to_thread(_compute_env_correlation)
+    except Exception:
+        logger.exception("env-correlation failed")
+        return EnvCorrelationResponse(correlation_matrix=[], scatter=[], pollutant_pairwise=[])
+
+
+# ============== Endpoint 5: temporal ==============
+
+_WEEKDAY_LABELS = ["周一", "周二", "周三", "周四", "周五", "周六", "周日"]
+
+
+def _compute_temporal() -> TemporalResponse:
+    df = get_combined_data().copy()
+    if df.empty:
+        return TemporalResponse(weekday=[], month_year=[], yoy=[])
+    df["date"] = pd.to_datetime(df["date"], errors="coerce")
+    df = df[df["date"].notna()]
+    if df.empty:
+        return TemporalResponse(weekday=[], month_year=[], yoy=[])
+
+    # weekday (0=周一..6=周日)
+    df["wd"] = df["date"].dt.weekday
+    weekday: list[WeekdayPoint] = []
+    for wd in range(7):
+        sub = df[df["wd"] == wd]
+        out = int((sub["type"] == "outpatient").sum())
+        inp = int((sub["type"] == "inpatient").sum())
+        weekday.append(WeekdayPoint(
+            weekday=_WEEKDAY_LABELS[wd], outpatient=out, inpatient=inp, total=out + inp,
+        ))
+
+    # month_year (seasonality grid)
+    df["year"] = df["date"].dt.year
+    df["month"] = df["date"].dt.month
+    my = df.groupby(["year", "month"]).size()
+    month_year = [
+        MonthYearPoint(year=int(y), month=int(m), total=int(c))
+        for (y, m), c in my.items()
+    ]
+    month_year.sort(key=lambda x: (x.year, x.month))
+
+    # yoy: monthly current vs same-month-prior-year (only if multiple years exist)
+    yoy: list[YoYPoint] = []
+    years = sorted(df["year"].unique().tolist())
+    if len(years) > 1:
+        monthly_totals = {(int(y), int(m)): int(c) for (y, m), c in my.items()}
+        for (y, m), cur in sorted(monthly_totals.items()):
+            prev = monthly_totals.get((y - 1, m))
+            if prev is None:
+                continue
+            growth = ((cur - prev) / prev * 100) if prev else 0.0
+            yoy.append(YoYPoint(
+                period=f"{y}-{m:02d}",
+                current=cur,
+                previous=prev,
+                growth_pct=round(growth, 2),
+            ))
+
+    return TemporalResponse(weekday=weekday, month_year=month_year, yoy=yoy)
+
+
+@router.get("/temporal", response_model=TemporalResponse, summary="时序统计")
+async def temporal():
+    """按星期、年-月（季节性网格）聚合，以及同比(YoY)增长（若有多年数据）。"""
+    try:
+        return await asyncio.to_thread(_compute_temporal)
+    except Exception:
+        logger.exception("temporal failed")
+        return TemporalResponse(weekday=[], month_year=[], yoy=[])

frontend/e2e/clinical.spec.ts

@@ -0,0 +1,104 @@
+/**
+ * 住院临床分析页（/analysis/clinical）验收测试。
+ * 与 user-flows.spec.ts 一致的鉴权策略：addInitScript 注入 cbpoa_token，
+ * 用 page.route 拦截 /api/**，对 inpatient-clinical 返回合法小样本，其余返回 {}。
+ */
+import { test, expect, Page } from '@playwright/test';
+import { TESTIDS } from '../src/utils/testids';
+
+const CLINICAL_FIXTURE = {
+  kpis: {
+    total_admissions: 5822,
+    median_los_days: 4,
+    mean_cost: 6294,
+    cure_rate: 0.991,
+    emergency_admit_ratio: 0.47,
+  },
+  los_histogram: [
+    { bin_label: '1-2', count: 1200 },
+    { bin_label: '3-4', count: 2100 },
+    { bin_label: '5-7', count: 1500 },
+  ],
+  los_by_disease: [
+    { diagnosis: '肺炎', p25: 3, median: 5, p75: 7, n: 800 },
+    { diagnosis: '支气管炎', p25: 2, median: 4, p75: 6, n: 600 },
+  ],
+  cost_histogram: [
+    { bin_label: '0-3k', count: 1800 },
+    { bin_label: '3k-6k', count: 2200 },
+  ],
+  cost_by_disease: [
+    { diagnosis: '肺炎', mean_cost: 7200, n: 800 },
+    { diagnosis: '支气管炎', mean_cost: 5100, n: 600 },
+  ],
+  cost_vs_los: [
+    { los: 3, cost: 5000 },
+    { los: 5, cost: 7200 },
+    { los: 7, cost: 9100 },
+  ],
+  outcome_counts: [
+    { outcome: '治愈', count: 3474 },
+    { outcome: '好转', count: 2298 },
+    { outcome: '其他', count: 35 },
+    { outcome: '未愈', count: 12 },
+    { outcome: '死亡', count: 3 },
+  ],
+  admission_route_counts: [
+    { route: '急诊', count: 2700 },
+    { route: '门诊', count: 3122 },
+  ],
+  bmi_by_age_band: [
+    { age_band: '0-2', p25: 14, median: 16, p75: 18, n: 400 },
+    { age_band: '3-6', p25: 15, median: 17, p75: 19, n: 500 },
+  ],
+};
+
+async function seedAuthAndMockApi(page: Page) {
+  await page.addInitScript(() => {
+    localStorage.setItem('cbpoa_token', 'e2e-test-token');
+  });
+
+  await page.route('/api/**', (route) => {
+    const url = route.request().url();
+
+    if (url.includes('/stats/inpatient-clinical')) {
+      route.fulfill({
+        status: 200,
+        contentType: 'application/json',
+        body: JSON.stringify(CLINICAL_FIXTURE),
+      });
+      return;
+    }
+
+    // 其余接口返回空对象，本页不依赖。
+    route.fulfill({
+      status: 200,
+      contentType: 'application/json',
+      body: JSON.stringify({}),
+    });
+  });
+}
+
+test.describe('住院临床分析页', () => {
+  test.beforeEach(async ({ page }) => {
+    await seedAuthAndMockApi(page);
+  });
+
+  test('deep-link /analysis/clinical mounts page-clinical + clinical-kpis', async ({ page }) => {
+    await page.goto('/analysis/clinical');
+    await expect(page.locator(`[data-testid="${TESTIDS.pageClinical}"]`)).toBeVisible();
+    await expect(page.locator(`[data-testid="${TESTIDS.clinicalKpis}"]`)).toBeVisible();
+  });
+
+  test('no horizontal scroll at 375px', async ({ page }) => {
+    await page.setViewportSize({ width: 375, height: 812 });
+    await page.goto('/analysis/clinical');
+    await expect(page.locator(`[data-testid="${TESTIDS.pageClinical}"]`)).toBeVisible();
+    await expect(page.locator(`[data-testid="${TESTIDS.clinicalKpis}"]`)).toBeVisible();
+
+    const noHorizontalScroll = await page.evaluate(
+      () => document.documentElement.scrollWidth <= document.documentElement.clientWidth
+    );
+    expect(noHorizontalScroll).toBe(true);
+  });
+});

frontend/src/components/SideNav.tsx

@@ -55,6 +55,7 @@ const modules: { id: string; label: string; icon: React.ReactNode; items: NavIte
       { to: '/analysis/reports', label: '报表中心', testid: TESTIDS.navReports },
       { to: '/analysis/demographics', label: '人群分析', testid: TESTIDS.navDemographics },
       { to: '/analysis/disease', label: '疾病分析', testid: TESTIDS.navDisease },
+      { to: '/analysis/clinical', label: '临床分析', testid: TESTIDS.navClinical },
       { to: '/analysis/environment', label: '环境健康', testid: TESTIDS.navEnvironment },
     ],
   },

frontend/src/components/clinical/BoxPlotRows.tsx

@@ -0,0 +1,87 @@
+import { memo } from 'react';
+import { CLINICAL_COLORS } from './chartColors';
+
+export interface BoxRow {
+  label: string;
+  p25: number;
+  median: number;
+  p75: number;
+  n: number;
+}
+
+interface BoxPlotRowsProps {
+  rows: BoxRow[];
+  /** 数值单位后缀，如 "天" / ""。 */
+  unit?: string;
+  /** 标签列宽（px）。 */
+  labelWidth?: number;
+}
+
+/**
+ * 横向箱线图（p25–中位–p75）。Recharts 无原生 box plot，
+ * 故用纯 div 渲染：每行一条从 p25 到 p75 的横条，中位处一根竖向刻度。
+ * 复用于「各病种住院天数」与「年龄别BMI」。
+ */
+export const BoxPlotRows = memo(function BoxPlotRows({
+  rows,
+  unit = '',
+  labelWidth = 96,
+}: BoxPlotRowsProps) {
+  if (!rows || rows.length === 0) {
+    return <div className="text-center py-8 text-text-muted text-sm">暂无数据</div>;
+  }
+
+  // 统一横轴域：覆盖所有行的 p25..p75，留一点边距。
+  const domainMin = Math.min(...rows.map((r) => r.p25));
+  const domainMax = Math.max(...rows.map((r) => r.p75));
+  const span = domainMax - domainMin || 1;
+  const pct = (v: number) => ((v - domainMin) / span) * 100;
+
+  return (
+    <div className="space-y-2.5">
+      {rows.map((r) => {
+        const left = pct(r.p25);
+        const right = pct(r.p75);
+        const width = Math.max(right - left, 0.5);
+        const medianLeft = pct(r.median);
+        return (
+          <div key={r.label} className="flex items-center gap-2 text-[11px]">
+            <div
+              className="shrink-0 truncate text-text-secondary text-right"
+              style={{ width: labelWidth }}
+              title={r.label}
+            >
+              {r.label}
+            </div>
+            <div className="relative flex-1 h-5 rounded bg-bg-hover">
+              {/* p25–p75 箱体 */}
+              <div
+                className="absolute top-1 bottom-1 rounded-sm"
+                style={{
+                  left: `${left}%`,
+                  width: `${width}%`,
+                  backgroundColor: CLINICAL_COLORS.box,
+                  opacity: 0.35,
+                }}
+              />
+              {/* 中位刻度 */}
+              <div
+                className="absolute top-0.5 bottom-0.5 w-[2px] rounded"
+                style={{
+                  left: `${medianLeft}%`,
+                  backgroundColor: CLINICAL_COLORS.boxMedian,
+                }}
+                title={`中位 ${r.median}${unit}`}
+              />
+            </div>
+            <div className="shrink-0 w-28 text-text-muted tabular-nums">
+              {r.p25}–<span className="font-semibold text-text-secondary">{r.median}</span>–{r.p75}
+              {unit}
+              <span className="ml-1 text-[10px] text-text-muted">n={r.n}</span>
+            </div>
+          </div>
+        );
+      })}
+    </div>
+  );
+});

frontend/src/components/clinical/ClinicalKpiRow.tsx

@@ -0,0 +1,47 @@
+import { memo } from 'react';
+import { Users, CalendarDays, Wallet, HeartPulse, Siren } from 'lucide-react';
+import { StatCard } from '@/components/StatCard';
+import { TESTIDS } from '@/utils/testids';
+import type { InpatientClinicalResponse } from '@/services/api';
+
+interface ClinicalKpiRowProps {
+  kpis: InpatientClinicalResponse['kpis'];
+}
+
+/** 住院临床 5 项核心指标。375px 下 2 列，sm 起 5 列。 */
+export const ClinicalKpiRow = memo(function ClinicalKpiRow({ kpis }: ClinicalKpiRowProps) {
+  return (
+    <div
+      data-testid={TESTIDS.clinicalKpis}
+      className="grid grid-cols-2 sm:grid-cols-5 gap-3"
+    >
+      <StatCard
+        icon={<Users className="w-4 h-4 text-primary" />}
+        label="住院总人次"
+        value={kpis.total_admissions.toLocaleString()}
+      />
+      <StatCard
+        icon={<CalendarDays className="w-4 h-4 text-primary" />}
+        label="中位住院日"
+        value={`${kpis.median_los_days} 天`}
+      />
+      <StatCard
+        icon={<Wallet className="w-4 h-4 text-primary" />}
+        label="人均费用"
+        value={`¥${Math.round(kpis.mean_cost).toLocaleString()}`}
+      />
+      <StatCard
+        icon={<HeartPulse className="w-4 h-4 text-success" />}
+        label="治愈好转率"
+        value={`${(kpis.cure_rate * 100).toFixed(1)}%`}
+        color="#16A34A"
+      />
+      <StatCard
+        icon={<Siren className="w-4 h-4 text-warning" />}
+        label="急诊入院占比"
+        value={`${(kpis.emergency_admit_ratio * 100).toFixed(1)}%`}
+        color="#D97706"
+      />
+    </div>
+  );
+});

frontend/src/components/clinical/CostByDiseaseChart.tsx

@@ -0,0 +1,62 @@
+import { memo } from 'react';
+import {
+  BarChart,
+  Bar,
+  XAxis,
+  YAxis,
+  CartesianGrid,
+  Tooltip,
+  ResponsiveContainer,
+} from 'recharts';
+import { CLINICAL_COLORS, TOOLTIP_STYLE } from './chartColors';
+
+interface CostByDiseaseChartProps {
+  data: { diagnosis: string; mean_cost: number; n: number }[];
+}
+
+function truncate(s: string, max: number): string {
+  return s.length > max ? s.slice(0, max) + '…' : s;
+}
+
+/** 各病种平均费用横向柱状图。 */
+export const CostByDiseaseChart = memo(function CostByDiseaseChart({
+  data,
+}: CostByDiseaseChartProps) {
+  if (!data || data.length === 0) {
+    return <div className="text-center py-8 text-text-muted text-sm">暂无数据</div>;
+  }
+
+  const chartData = [...data]
+    .sort((a, b) => a.mean_cost - b.mean_cost)
+    .map((d) => ({ ...d, displayName: truncate(d.diagnosis, 8) }));
+
+  return (
+    <ResponsiveContainer width="100%" height={Math.max(240, chartData.length * 34)}>
+      <BarChart
+        data={chartData}
+        layout="vertical"
+        margin={{ top: 5, right: 20, left: 12, bottom: 5 }}
+      >
+        <CartesianGrid strokeDasharray="3 3" stroke={CLINICAL_COLORS.grid} horizontal={false} />
+        <XAxis
+          type="number"
+          tick={{ fontSize: 10, fill: CLINICAL_COLORS.axis }}
+          tickFormatter={(v: number) => `¥${(v / 1000).toFixed(0)}k`}
+        />
+        <YAxis
+          type="category"
+          dataKey="displayName"
+          tick={{ fontSize: 10, fill: CLINICAL_COLORS.axisLabel }}
+          width={72}
+          axisLine={false}
+          tickLine={false}
+        />
+        <Tooltip
+          contentStyle={TOOLTIP_STYLE}
+          formatter={(v: number) => [`¥${Math.round(v).toLocaleString()}`, '人均费用']}
+        />
+        <Bar dataKey="mean_cost" fill={CLINICAL_COLORS.cost} barSize={16} radius={[0, 3, 3, 0]} />
+      </BarChart>
+    </ResponsiveContainer>
+  );
+});

frontend/src/components/clinical/CostVsLosScatter.tsx

@@ -0,0 +1,55 @@
+import { memo } from 'react';
+import {
+  ScatterChart,
+  Scatter,
+  XAxis,
+  YAxis,
+  CartesianGrid,
+  Tooltip,
+  ResponsiveContainer,
+} from 'recharts';
+import { CLINICAL_COLORS, TOOLTIP_STYLE } from './chartColors';
+
+interface CostVsLosScatterProps {
+  data: { los: number; cost: number }[];
+}
+
+/** 费用 vs 住院天数散点。 */
+export const CostVsLosScatter = memo(function CostVsLosScatter({ data }: CostVsLosScatterProps) {
+  if (!data || data.length === 0) {
+    return <div className="text-center py-8 text-text-muted text-sm">暂无数据</div>;
+  }
+
+  return (
+    <ResponsiveContainer width="100%" height={300}>
+      <ScatterChart margin={{ top: 10, right: 16, left: 6, bottom: 16 }}>
+        <CartesianGrid strokeDasharray="3 3" stroke={CLINICAL_COLORS.grid} />
+        <XAxis
+          type="number"
+          dataKey="los"
+          name="住院天数"
+          unit="天"
+          tick={{ fontSize: 10, fill: CLINICAL_COLORS.axis }}
+        />
+        <YAxis
+          type="number"
+          dataKey="cost"
+          name="费用"
+          tick={{ fontSize: 10, fill: CLINICAL_COLORS.axis }}
+          width={52}
+          tickFormatter={(v: number) => `¥${(v / 1000).toFixed(0)}k`}
+        />
+        <Tooltip
+          contentStyle={TOOLTIP_STYLE}
+          cursor={{ strokeDasharray: '3 3' }}
+          formatter={(value: number, name: string) =>
+            name === '费用'
+              ? [`¥${value.toLocaleString()}`, name]
+              : [`${value} 天`, name]
+          }
+        />
+        <Scatter data={data} fill={CLINICAL_COLORS.scatter} fillOpacity={0.5} />
+      </ScatterChart>
+    </ResponsiveContainer>
+  );
+});

frontend/src/components/clinical/DonutChart.tsx

@@ -0,0 +1,56 @@
+import { memo } from 'react';
+import { PieChart, Pie, Cell, Tooltip, Legend, ResponsiveContainer } from 'recharts';
+import { CLINICAL_COLORS, TOOLTIP_STYLE } from './chartColors';
+
+export interface DonutSlice {
+  name: string;
+  value: number;
+}
+
+interface DonutChartProps {
+  data: DonutSlice[];
+  /** name -> color。未命中时按 palette 顺序回退。 */
+  colorMap?: Record<string, string>;
+}
+
+/** 通用环形图。复用于「出院结局构成」与「入院途径构成」。 */
+export const DonutChart = memo(function DonutChart({ data, colorMap }: DonutChartProps) {
+  if (!data || data.length === 0) {
+    return <div className="text-center py-8 text-text-muted text-sm">暂无数据</div>;
+  }
+
+  const total = data.reduce((s, d) => s + d.value, 0);
+  const colorFor = (name: string, idx: number) =>
+    colorMap?.[name] ??
+    CLINICAL_COLORS.routePalette[idx % CLINICAL_COLORS.routePalette.length] ??
+    CLINICAL_COLORS.outcomeFallback;
+
+  return (
+    <ResponsiveContainer width="100%" height={280}>
+      <PieChart>
+        <Pie
+          data={data}
+          dataKey="value"
+          nameKey="name"
+          cx="50%"
+          cy="50%"
+          innerRadius={56}
+          outerRadius={88}
+          paddingAngle={2}
+        >
+          {data.map((d, idx) => (
+            <Cell key={d.name} fill={colorFor(d.name, idx)} />
+          ))}
+        </Pie>
+        <Tooltip
+          contentStyle={TOOLTIP_STYLE}
+          formatter={(v: number, name: string) => [
+            `${v.toLocaleString()}（${total > 0 ? ((v / total) * 100).toFixed(1) : '0'}%）`,
+            name,
+          ]}
+        />
+        <Legend wrapperStyle={{ fontSize: '11px' }} />
+      </PieChart>
+    </ResponsiveContainer>
+  );
+});

frontend/src/components/clinical/HistogramChart.tsx

@@ -0,0 +1,51 @@
+import { memo } from 'react';
+import {
+  BarChart,
+  Bar,
+  XAxis,
+  YAxis,
+  CartesianGrid,
+  Tooltip,
+  ResponsiveContainer,
+} from 'recharts';
+import { CLINICAL_COLORS, TOOLTIP_STYLE } from './chartColors';
+
+interface HistogramChartProps {
+  data: { bin_label: string; count: number }[];
+  color?: string;
+  /** tooltip 中数量的标签，如 "住院天数" / "费用区间"。 */
+  countLabel?: string;
+}
+
+/** 通用直方图。复用于「住院天数分布」与「住院费用分布」。 */
+export const HistogramChart = memo(function HistogramChart({
+  data,
+  color = CLINICAL_COLORS.los,
+  countLabel = '人次',
+}: HistogramChartProps) {
+  if (!data || data.length === 0) {
+    return <div className="text-center py-8 text-text-muted text-sm">暂无数据</div>;
+  }
+
+  return (
+    <ResponsiveContainer width="100%" height={300}>
+      <BarChart data={data} margin={{ top: 5, right: 12, left: 0, bottom: 5 }}>
+        <CartesianGrid strokeDasharray="3 3" stroke={CLINICAL_COLORS.grid} vertical={false} />
+        <XAxis
+          dataKey="bin_label"
+          tick={{ fontSize: 10, fill: CLINICAL_COLORS.axis }}
+          interval={0}
+          angle={-30}
+          textAnchor="end"
+          height={50}
+        />
+        <YAxis tick={{ fontSize: 10, fill: CLINICAL_COLORS.axis }} width={40} />
+        <Tooltip
+          contentStyle={TOOLTIP_STYLE}
+          formatter={(v: number) => [`${v.toLocaleString()}`, countLabel]}
+        />
+        <Bar dataKey="count" fill={color} radius={[3, 3, 0, 0]} />
+      </BarChart>
+    </ResponsiveContainer>
+  );
+});

frontend/src/components/clinical/chartColors.ts

@@ -0,0 +1,36 @@
+/**
+ * 住院临床分析页图表字面色值集中处。
+ * Recharts 需要原始 hex，无法用 Tailwind class，故在此集中定义，避免散落 magic hex。
+ */
+export const CLINICAL_COLORS = {
+  primary: '#2563EB', // primary
+  los: '#2563EB',
+  cost: '#0891B2', // cyan — 费用维度
+  scatter: '#7C3AED', // violet — 散点
+  box: '#3B82F6', // 箱体填充
+  boxMedian: '#1D4ED8', // 中位刻度
+  grid: '#E2E8F0',
+  axis: '#64748B',
+  axisLabel: '#374151',
+  tooltipBorder: '#E2E8F0',
+  tooltipText: '#1E293B',
+  // 出院结局按严重程度配色：治愈/好转偏绿，未愈/死亡偏红，其他中性
+  outcome: {
+    治愈: '#16A34A',
+    好转: '#4ADE80',
+    其他: '#94A3B8',
+    未愈: '#F97316',
+    死亡: '#DC2626',
+  } as Record<string, string>,
+  outcomeFallback: '#94A3B8',
+  // 入院途径 donut 顺序色板
+  routePalette: ['#2563EB', '#0891B2', '#7C3AED', '#D97706', '#16A34A', '#DC2626'],
+} as const;
+
+/** Recharts tooltip 通用样式。 */
+export const TOOLTIP_STYLE = {
+  backgroundColor: '#FFFFFF',
+  border: `1px solid ${CLINICAL_COLORS.tooltipBorder}`,
+  borderRadius: '8px',
+  fontSize: '12px',
+} as const;

frontend/src/pages/ClinicalAnalysis.tsx

@@ -0,0 +1,175 @@
+import { useEffect, useState } from 'react';
+import { Activity } from 'lucide-react';
+import { statsApi, type InpatientClinicalResponse } from '@/services/api';
+import { Card, LoadingState, EmptyState } from '@/components/ui';
+import { ErrorBanner } from '@/components/ErrorBanner';
+import { TESTIDS } from '@/utils/testids';
+import { ClinicalKpiRow } from '@/components/clinical/ClinicalKpiRow';
+import { HistogramChart } from '@/components/clinical/HistogramChart';
+import { BoxPlotRows, type BoxRow } from '@/components/clinical/BoxPlotRows';
+import { CostVsLosScatter } from '@/components/clinical/CostVsLosScatter';
+import { CostByDiseaseChart } from '@/components/clinical/CostByDiseaseChart';
+import { DonutChart, type DonutSlice } from '@/components/clinical/DonutChart';
+import { CLINICAL_COLORS } from '@/components/clinical/chartColors';
+
+/** 数据是否完全为空（KPI 0 人次且各序列均空）。 */
+function isEmpty(d: InpatientClinicalResponse): boolean {
+  return (
+    (!d.kpis || d.kpis.total_admissions === 0) &&
+    (d.los_histogram?.length ?? 0) === 0 &&
+    (d.outcome_counts?.length ?? 0) === 0
+  );
+}
+
+export function ClinicalAnalysis() {
+  const [data, setData] = useState<InpatientClinicalResponse | null>(null);
+  const [isLoading, setIsLoading] = useState(true);
+  const [error, setError] = useState<string | null>(null);
+
+  useEffect(() => {
+    let cancelled = false;
+
+    const fetchData = async () => {
+      setIsLoading(true);
+      setError(null);
+      try {
+        const res = await statsApi.getInpatientClinical();
+        if (cancelled) return;
+        setData(res);
+      } catch {
+        if (cancelled) return;
+        setError('住院临床数据加载失败');
+      } finally {
+        if (!cancelled) setIsLoading(false);
+      }
+    };
+
+    fetchData();
+
+    return () => {
+      cancelled = true;
+    };
+  }, []);
+
+  const header = (
+    <div>
+      <h1 className="font-display text-[18px] font-semibold mb-1 flex items-center gap-2">
+        <Activity className="w-5 h-5 text-primary" />
+        住院临床分析
+      </h1>
+      <p className="text-[12px] text-text-secondary">
+        住院天数、费用、出院结局与入院途径等临床特征分析
+      </p>
+    </div>
+  );
+
+  if (isLoading) {
+    return (
+      <div data-testid={TESTIDS.pageClinical} className="flex flex-col h-full overflow-auto p-6 space-y-6">
+        {header}
+        <LoadingState label="正在加载住院临床数据…" />
+      </div>
+    );
+  }
+
+  if (error || !data) {
+    return (
+      <div data-testid={TESTIDS.pageClinical} className="flex flex-col h-full overflow-auto p-6 space-y-6">
+        {header}
+        <ErrorBanner
+          error={error ?? '住院临床数据加载失败'}
+          onRetry={() => window.location.reload()}
+          onDismiss={() => setError(null)}
+        />
+      </div>
+    );
+  }
+
+  if (isEmpty(data)) {
+    return (
+      <div data-testid={TESTIDS.pageClinical} className="flex flex-col h-full overflow-auto p-6 space-y-6">
+        {header}
+        <EmptyState title="暂无住院临床数据" description="当前筛选范围内没有可用的住院记录。" />
+      </div>
+    );
+  }
+
+  // 出院结局：治愈/好转在前（按严重程度排序展示更直观）。
+  const outcomeSlices: DonutSlice[] = (data.outcome_counts ?? []).map((o) => ({
+    name: o.outcome,
+    value: o.count,
+  }));
+  const routeSlices: DonutSlice[] = (data.admission_route_counts ?? []).map((r) => ({
+    name: r.route,
+    value: r.count,
+  }));
+
+  const losBox: BoxRow[] = (data.los_by_disease ?? []).map((d) => ({
+    label: d.diagnosis,
+    p25: d.p25,
+    median: d.median,
+    p75: d.p75,
+    n: d.n,
+  }));
+  const bmiBox: BoxRow[] = (data.bmi_by_age_band ?? []).map((d) => ({
+    label: d.age_band,
+    p25: d.p25,
+    median: d.median,
+    p75: d.p75,
+    n: d.n,
+  }));
+
+  return (
+    <div
+      data-testid={TESTIDS.pageClinical}
+      className="flex flex-col h-full overflow-auto"
+    >
+      <div className="p-6 space-y-6">
+        {header}
+
+        {/* KPI 行 */}
+        <ClinicalKpiRow kpis={data.kpis} />
+
+        {/* 住院天数：分布 + 各病种箱线 */}
+        <div className="grid grid-cols-1 lg:grid-cols-2 gap-6">
+          <Card title="住院天数分布">
+            <HistogramChart data={data.los_histogram ?? []} color={CLINICAL_COLORS.los} countLabel="人次" />
+          </Card>
+          <Card title="各病种住院天数（P25–中位–P75）">
+            <BoxPlotRows rows={losBox} unit="天" />
+          </Card>
+        </div>
+
+        {/* 费用：分布 + 各病种平均费用 */}
+        <div className="grid grid-cols-1 lg:grid-cols-2 gap-6">
+          <Card title="住院费用分布">
+            <HistogramChart data={data.cost_histogram ?? []} color={CLINICAL_COLORS.cost} countLabel="人次" />
+          </Card>
+          <Card title="各病种平均费用">
+            <CostByDiseaseChart data={data.cost_by_disease ?? []} />
+          </Card>
+        </div>
+
+        {/* 费用 vs 住院天数 散点 */}
+        <Card title="费用 vs 住院天数">
+          <CostVsLosScatter data={data.cost_vs_los ?? []} />
+        </Card>
+
+        {/* 出院结局 + 入院途径 双环 */}
+        <div className="grid grid-cols-1 lg:grid-cols-2 gap-6">
+          <Card title="出院结局构成">
+            <DonutChart data={outcomeSlices} colorMap={CLINICAL_COLORS.outcome} />
+          </Card>
+          <Card title="入院途径构成">
+            <DonutChart data={routeSlices} />
+          </Card>
+        </div>
+
+        {/* 年龄别 BMI 箱线 */}
+        <Card title="年龄别 BMI（P25–中位–P75）">
+          <BoxPlotRows rows={bmiBox} />
+        </Card>
+      </div>
+    </div>
+  );
+}

frontend/src/pages/DiseaseAnalysis.tsx

@@ -11,8 +11,9 @@ import {
   Cell,
   ReferenceLine,
 } from 'recharts';
-import { Stethoscope, Activity } from 'lucide-react';
+import { Stethoscope, Activity, MessageSquareText } from 'lucide-react';
-import { caseApi } from '@/services/api';
+import { caseApi, statsApi } from '@/services/api';
+import type { SymptomsResponse } from '@/services/api';
 import { ErrorBanner } from '@/components/ErrorBanner';
 import type {
   DiagnosisDistributionItem,
@@ -374,12 +375,64 @@ function DiagnosisSummaryTable({
   );
 }
 
+// --- Chart 5: Outpatient Symptom Keyword Frequency ---
+
+function SymptomFrequencyChart({ data }: { data: SymptomsResponse['symptoms'] }) {
+  if (!data || data.length === 0) {
+    return <div className="text-center py-8 text-gray-400 text-sm">暂无数据</div>;
+  }
+
+  // Sort by count desc; chart renders bottom-up so reverse for top-at-top display.
+  const sorted = [...data].sort((a, b) => b.count - a.count);
+  const chartData = sorted.map((d) => ({
+    ...d,
+    displayName: truncate(d.keyword, 8),
+  }));
+
+  return (
+    <ResponsiveContainer width="100%" height={Math.max(320, chartData.length * 22)}>
+      <BarChart
+        data={[...chartData].reverse()}
+        layout="vertical"
+        margin={{ top: 5, right: 20, left: 40, bottom: 5 }}
+      >
+        <CartesianGrid strokeDasharray="3 3" stroke="#E2E8F0" horizontal={false} />
+        <XAxis
+          type="number"
+          tick={{ fontSize: 10, fill: '#64748B' }}
+          tickFormatter={(v) => v.toLocaleString()}
+        />
+        <YAxis
+          type="category"
+          dataKey="displayName"
+          tick={{ fontSize: 10, fill: '#374151' }}
+          width={70}
+          axisLine={false}
+          tickLine={false}
+        />
+        <Tooltip
+          contentStyle={{
+            backgroundColor: '#FFFFFF',
+            border: '1px solid #E2E8F0',
+            borderRadius: '8px',
+            fontSize: '12px',
+          }}
+          formatter={(value: number) => [value.toLocaleString(), '出现次数']}
+        />
+        <Bar dataKey="count" name="count" fill="#3B82F6" barSize={14} radius={[0, 3, 3, 0]} />
+      </BarChart>
+    </ResponsiveContainer>
+  );
+}
+
 // --- Page Component ---
 
 export function DiseaseAnalysis() {
   const [diagDistribution, setDiagDistribution] = useState<DiagnosisDistributionItem[]>([]);
   const [seasonality, setSeasonality] = useState<DiseaseSeasonalityPoint[]>([]);
   const [districts, setDistricts] = useState<DistrictCaseData[]>([]);
+  const [symptoms, setSymptoms] = useState<SymptomsResponse['symptoms']>([]);
+  const [revisitRatio, setRevisitRatio] = useState<number | null>(null);
   const [isLoading, setIsLoading] = useState(true);
   const [errors, setErrors] = useState<string[]>([]);
 
@@ -390,10 +443,11 @@ export function DiseaseAnalysis() {
       setIsLoading(true);
       setErrors([]);
 
-      const [distR, seasonR, districtR] = await Promise.allSettled([
+      const [distR, seasonR, districtR, symptomR] = await Promise.allSettled([
         caseApi.getDiagnosisDistribution(15),
         caseApi.getDiseaseSeasonality(),
         caseApi.getDistricts(),
+        statsApi.getSymptoms(20),
       ]);
 
       if (cancelled) return;
@@ -418,6 +472,15 @@ export function DiseaseAnalysis() {
         newErrors.push('区县数据加载失败');
       }
 
+      if (symptomR.status === 'fulfilled') {
+        setSymptoms(symptomR.value.symptoms || []);
+        setRevisitRatio(
+          typeof symptomR.value.revisit_ratio === 'number' ? symptomR.value.revisit_ratio : null,
+        );
+      } else {
+        newErrors.push('症状词频数据加载失败');
+      }
+
       setErrors(newErrors);
       setIsLoading(false);
     };
@@ -497,6 +560,26 @@ export function DiseaseAnalysis() {
           </div>
           <DiagnosisSummaryTable diagnoses={diagDistribution} districtsData={districts} />
         </div>
+
+        {/* Chart 5: Outpatient Symptom Keyword Frequency */}
+        <div data-testid="symptom-freq" className="card p-4">
+          <div className="text-[11px] font-medium text-gray-500 uppercase tracking-wide mb-1 flex items-center gap-2">
+            <MessageSquareText className="w-3.5 h-3.5 text-gray-400" />
+            门诊主诉症状词频
+          </div>
+          <div className="text-[11px] text-gray-500 mb-4">
+            主诉文本高频词（含复诊/随诊等就诊类型词）
+            {revisitRatio !== null && (
+              <span className="ml-2">
+                复诊占比：
+                <span className="font-semibold text-gray-700">
+                  {(revisitRatio * 100).toFixed(1)}%
+                </span>
+              </span>
+            )}
+          </div>
+          <SymptomFrequencyChart data={symptoms} />
+        </div>
       </div>
     </div>
   );

frontend/src/pages/DistrictComparison.tsx

@@ -1,5 +1,5 @@
 import { useEffect, useMemo, useState } from 'react';
-import { LoadingState } from '@/components/ui';
+import { LoadingState, Segmented } from '@/components/ui';
 import {
   BarChart,
   Bar,
@@ -12,7 +12,8 @@ import {
   ReferenceLine,
 } from 'recharts';
 import { useAnalysisStore } from '@/stores/analysisStore';
-import { caseApi } from '@/services/api';
+import { caseApi, statsApi } from '@/services/api';
+import type { IncidenceRateResponse } from '@/services/api';
 import { ErrorBanner } from '@/components/ErrorBanner';
 import { MetricHeatmapTable } from '@/components/MetricHeatmapTable';
 import { BarChart3, MapPin, Users, Shield } from 'lucide-react';
@@ -36,6 +37,10 @@ export function DistrictComparison() {
   const [caseDistrictData, setCaseDistrictData] = useState<DistrictCaseData[]>([]);
   const [caseDataLoading, setCaseDataLoading] = useState(false);
   const [caseDataError, setCaseDataError] = useState<string | null>(null);
+  const [incidence, setIncidence] = useState<IncidenceRateResponse['districts']>([]);
+  const [incidenceLoading, setIncidenceLoading] = useState(false);
+  const [incidenceError, setIncidenceError] = useState<string | null>(null);
+  const [incidenceMetric, setIncidenceMetric] = useState<'rate' | 'count'>('rate');
 
   useEffect(() => {
     fetchDistricts();
@@ -61,6 +66,26 @@ export function DistrictComparison() {
     return () => { cancelled = true; };
   }, []);
 
+  useEffect(() => {
+    let cancelled = false;
+    setIncidenceLoading(true);
+    setIncidenceError(null);
+    statsApi.getIncidenceRate()
+      .then((res) => {
+        if (!cancelled) {
+          setIncidence(res.districts || []);
+          setIncidenceLoading(false);
+        }
+      })
+      .catch((e) => {
+        if (!cancelled) {
+          setIncidenceError((e as Error).message || '加载发病率数据失败');
+          setIncidenceLoading(false);
+        }
+      });
+    return () => { cancelled = true; };
+  }, []);
+
   const metricConfig = {
     avg_aqi: { label: '平均AQI', color: '#2563EB', unit: '' },
     avg_risk: { label: '平均风险', color: '#DC2626', unit: '' },
@@ -104,6 +129,12 @@ export function DistrictComparison() {
     return { data, cityOIAvg };
   }, [caseDistrictData]);
 
+  const incidenceChart = useMemo(() => {
+    const valueKey = incidenceMetric === 'rate' ? 'rate_per_10k' : 'total_cases';
+    const data = [...incidence].sort((a, b) => b[valueKey] - a[valueKey]);
+    return { data, valueKey };
+  }, [incidence, incidenceMetric]);
+
   const heatmapMetrics = useMemo(() => {
     const caseMap = new Map(caseDistrictData.map((d) => [d.district, d]));
     const rows: string[] = [];
@@ -155,6 +186,25 @@ export function DistrictComparison() {
           onDismiss={() => setCaseDataError(null)}
         />
       )}
+      {incidenceError && (
+        <ErrorBanner
+          error={incidenceError}
+          onRetry={() => {
+            setIncidenceError(null);
+            setIncidenceLoading(true);
+            statsApi.getIncidenceRate()
+              .then((res) => {
+                setIncidence(res.districts || []);
+                setIncidenceLoading(false);
+              })
+              .catch((e) => {
+                setIncidenceError((e as Error).message || '加载发病率数据失败');
+                setIncidenceLoading(false);
+              });
+          }}
+          onDismiss={() => setIncidenceError(null)}
+        />
+      )}
       <div className="mb-5">
         <h1 className="font-display text-[18px] font-semibold mb-1 flex items-center gap-2">
           <BarChart3 className="w-5 h-5 text-primary" />
@@ -380,6 +430,79 @@ export function DistrictComparison() {
         )}
       </div>
 
+      {/* Standardized Incidence Rate (per 10k) with count/rate toggle */}
+      <div data-testid="incidence-rate" className="card p-4 mb-4">
+        <div className="flex items-center justify-between gap-2 mb-4 flex-wrap">
+          <div className="text-[11px] font-medium text-text-muted uppercase tracking-wide">
+            {incidenceMetric === 'rate' ? '标化发病率（每万人）区域排名' : '病例数 区域排名'}
+          </div>
+          <Segmented
+            testid="incidence-rate-toggle"
+            size="sm"
+            value={incidenceMetric}
+            onChange={setIncidenceMetric}
+            options={[
+              { value: 'count', label: '病例数' },
+              { value: 'rate', label: '每万人发病率' },
+            ]}
+          />
+        </div>
+        <p className="text-[11px] text-text-muted mb-4">
+          标化发病率按人口归一化，可避免人口规模差异造成的误读（原始病例数会高估人口大区）。
+        </p>
+        {incidenceLoading && <LoadingState />}
+        {!incidenceLoading && incidenceChart.data.length > 0 ? (
+          <ResponsiveContainer width="100%" height={380}>
+            <BarChart
+              data={incidenceChart.data}
+              margin={{ top: 5, right: 20, left: 10, bottom: 5 }}
+              layout="vertical"
+            >
+              <CartesianGrid strokeDasharray="3 3" stroke="#E2E8F0" horizontal={false} />
+              <XAxis
+                type="number"
+                tick={{ fontSize: 12, fill: '#64748B' }}
+                axisLine={{ stroke: '#E2E8F0' }}
+                tickFormatter={(v: number) => v.toLocaleString()}
+              />
+              <YAxis
+                type="category"
+                dataKey="district"
+                tick={{ fontSize: 12, fill: '#1E293B', fontWeight: 500 }}
+                axisLine={{ stroke: '#E2E8F0' }}
+                width={80}
+              />
+              <Tooltip
+                contentStyle={{
+                  backgroundColor: '#FFFFFF',
+                  border: '1px solid #E2E8F0',
+                  borderRadius: '8px',
+                  fontSize: '12px',
+                }}
+                formatter={(_value: number, _name, item) => {
+                  const p = item?.payload as IncidenceRateResponse['districts'][number];
+                  return [
+                    `病例数 ${p.total_cases.toLocaleString()} · 人口 ${p.population.toLocaleString()} · 每万人 ${p.rate_per_10k.toLocaleString()}`,
+                    incidenceMetric === 'rate' ? '标化发病率' : '病例数',
+                  ];
+                }}
+              />
+              <Bar
+                dataKey={incidenceChart.valueKey}
+                name={incidenceMetric === 'rate' ? '每万人发病率' : '病例数'}
+                radius={[0, 4, 4, 0]}
+                maxBarSize={32}
+                fill={incidenceMetric === 'rate' ? '#DC2626' : '#2563EB'}
+              />
+            </BarChart>
+          </ResponsiveContainer>
+        ) : (
+          !incidenceLoading && (
+            <div className="text-center py-8 text-text-secondary">无发病率数据</div>
+          )
+        )}
+      </div>
+
       {/* O/I Ratio Comparison Bar Chart */}
       <div className="card p-4 mb-4">
         <div className="text-[11px] font-medium text-text-muted uppercase tracking-wide mb-4">

frontend/src/pages/EnvironmentalHealth.tsx

@@ -1,4 +1,4 @@
-import { useEffect, useState, useMemo } from 'react';
+import { useEffect, useState, useMemo, Fragment } from 'react';
 import {
   LineChart,
   Line,
@@ -12,9 +12,13 @@ import {
   ResponsiveContainer,
   ReferenceLine,
   Cell,
+  ScatterChart,
+  Scatter,
+  ZAxis,
 } from 'recharts';
 import { Wind } from 'lucide-react';
-import { envApi, caseApi } from '@/services/api';
+import { envApi, caseApi, statsApi } from '@/services/api';
+import type { EnvCorrelationResponse } from '@/services/api';
 import { ErrorBanner } from '@/components/ErrorBanner';
 import { CalendarHeatmap } from '@/components/CalendarHeatmap';
 import type {
@@ -58,6 +62,55 @@ function getAQICategory(aqi: number): typeof AQI_CATEGORIES[number] {
   return AQI_CATEGORIES[AQI_CATEGORIES.length - 1];
 }
 
+// Canonical pollutant order for the 7×7 correlation matrix.
+const CORR_POLLUTANTS = ['AQI', 'PM25', 'PM10', 'SO2', 'NO2', 'O3', 'CO'];
+
+function pollutantLabel(key: string): string {
+  switch (key) {
+    case 'PM25':
+      return 'PM2.5';
+    case 'SO2':
+      return 'SO₂';
+    case 'NO2':
+      return 'NO₂';
+    case 'O3':
+      return 'O₃';
+    default:
+      return key;
+  }
+}
+
+// Diverging color scale for a correlation value in [-1, 1].
+// Blue (negative) → white (0) → red (positive); opacity scales with |corr|.
+function corrColor(corr: number): string {
+  const v = Math.max(-1, Math.min(1, corr));
+  if (v >= 0) return `rgba(220, 38, 38, ${0.12 + 0.88 * v})`;
+  return `rgba(37, 99, 235, ${0.12 + 0.88 * -v})`;
+}
+
+// Least-squares linear regression: returns slope/intercept over (x, y) points.
+function linearRegression(
+  points: { x: number; y: number }[],
+): { slope: number; intercept: number } | null {
+  const n = points.length;
+  if (n < 2) return null;
+  let sx = 0;
+  let sy = 0;
+  let sxx = 0;
+  let sxy = 0;
+  for (const p of points) {
+    sx += p.x;
+    sy += p.y;
+    sxx += p.x * p.x;
+    sxy += p.x * p.y;
+  }
+  const denom = n * sxx - sx * sx;
+  if (Math.abs(denom) < 1e-9) return null;
+  const slope = (n * sxy - sx * sy) / denom;
+  const intercept = (sy - slope * sx) / n;
+  return { slope, intercept };
+}
+
 function findMaxLag(correlations: LagCorrelationItem[], pollutant: string): number | null {
   if (correlations.length === 0) return null;
   const pollData = correlations.filter(
@@ -83,6 +136,7 @@ export function EnvironmentalHealth() {
   const [pollutants365, setPollutants365] = useState<PollutantPoint[]>([]);
   const [pollutants30, setPollutants30] = useState<PollutantPoint[]>([]);
   const [caseTrend, setCaseTrend] = useState<CaseTrendPoint[]>([]);
+  const [envCorr, setEnvCorr] = useState<EnvCorrelationResponse | null>(null);
 
   // UI states
   const [isLoading, setIsLoading] = useState(true);
@@ -104,11 +158,12 @@ export function EnvironmentalHealth() {
       setIsLoading(true);
       setErrors([]);
 
-      const [lagR, p365R, p30R, caseTrendR] = await Promise.allSettled([
+      const [lagR, p365R, p30R, caseTrendR, envCorrR] = await Promise.allSettled([
         envApi.getLagCorrelations(),
         envApi.getPollutants(365),
         envApi.getPollutants(30),
         caseApi.getTrend({ group_by: 'day' }),
+        statsApi.getEnvCorrelation(),
       ]);
 
       if (cancelled) return;
@@ -145,6 +200,12 @@ export function EnvironmentalHealth() {
         newErrors.push('病例趋势数据加载失败');
       }
 
+      if (envCorrR.status === 'fulfilled') {
+        setEnvCorr(envCorrR.value);
+      } else {
+        newErrors.push('污染物关联分析数据加载失败');
+      }
+
       setErrors(newErrors);
       setIsLoading(false);
     };
@@ -266,6 +327,61 @@ export function EnvironmentalHealth() {
     }));
   }, [pollutants30]);
 
+  // --- Correlation: pollutant × cases (grid-level Pearson) ---
+  const corrWithCases = useMemo(() => {
+    const matrix = envCorr?.correlation_matrix ?? [];
+    return matrix
+      .map((m) => ({
+        pollutant: m.pollutant,
+        label: pollutantLabel(m.pollutant),
+        corr: m.corr_with_cases,
+      }))
+      .sort((a, b) => Math.abs(b.corr) - Math.abs(a.corr));
+  }, [envCorr]);
+
+  // --- Correlation: pollutant pairwise 7×7 heatmap ---
+  // pollutant_pairwise carries the upper triangle (21 pairs); we mirror it into
+  // a symmetric lookup and fill the diagonal with 1.
+  const pairwiseGrid = useMemo(() => {
+    const pairs = envCorr?.pollutant_pairwise ?? [];
+    if (pairs.length === 0) return null;
+    const lookup = new Map<string, number>();
+    for (const p of pairs) {
+      lookup.set(`${p.a}|${p.b}`, p.corr);
+      lookup.set(`${p.b}|${p.a}`, p.corr);
+    }
+    return CORR_POLLUTANTS.map((rowKey) =>
+      CORR_POLLUTANTS.map((colKey) => {
+        if (rowKey === colKey) return 1;
+        return lookup.get(`${rowKey}|${colKey}`) ?? null;
+      }),
+    );
+  }, [envCorr]);
+
+  // --- Scatter: PM2.5 × cases + least-squares regression line ---
+  const scatterPoints = useMemo(() => {
+    return (envCorr?.scatter ?? []).map((s) => ({ pm25: s.pm25, cases: s.cases }));
+  }, [envCorr]);
+
+  const regression = useMemo(() => {
+    return linearRegression(scatterPoints.map((p) => ({ x: p.pm25, y: p.cases })));
+  }, [scatterPoints]);
+
+  // Two endpoints across the observed PM2.5 range to draw the trend line.
+  const regressionLine = useMemo(() => {
+    if (!regression || scatterPoints.length === 0) return [];
+    let minX = Infinity;
+    let maxX = -Infinity;
+    for (const p of scatterPoints) {
+      if (p.pm25 < minX) minX = p.pm25;
+      if (p.pm25 > maxX) maxX = p.pm25;
+    }
+    return [
+      { pm25: minX, cases: regression.slope * minX + regression.intercept },
+      { pm25: maxX, cases: regression.slope * maxX + regression.intercept },
+    ];
+  }, [regression, scatterPoints]);
+
   // --- Loading state ---
   if (isLoading) {
     return (
@@ -706,6 +822,229 @@ export function EnvironmentalHealth() {
             </div>
           )}
         </div>
+
+        {/* === 污染物-病例关联分析 === */}
+        <div data-testid="env-correlation" className="space-y-6">
+          <div>
+            <h2 className="font-display text-[15px] font-semibold mb-1">
+              污染物-病例关联分析
+            </h2>
+            <p className="text-[11px] text-text-muted">
+              基于网格级 Pearson 相关系数（grid-level）
+            </p>
+          </div>
+
+          {/* (a) Pollutant × Cases correlation */}
+          <div className="card p-4">
+            <div className="text-[11px] font-medium text-text-muted uppercase tracking-wide mb-4">
+              污染物 × 病例相关性
+            </div>
+            {corrWithCases.length > 0 ? (
+              <>
+                <ResponsiveContainer width="100%" height={300}>
+                  <BarChart
+                    data={corrWithCases}
+                    layout="vertical"
+                    margin={{ top: 5, right: 20, left: 50, bottom: 5 }}
+                  >
+                    <CartesianGrid
+                      strokeDasharray="3 3"
+                      stroke="#E2E8F0"
+                      horizontal={false}
+                    />
+                    <XAxis
+                      type="number"
+                      domain={[-1, 1]}
+                      tick={{ fontSize: 11, fill: '#64748B' }}
+                      axisLine={{ stroke: '#E2E8F0' }}
+                    />
+                    <YAxis
+                      type="category"
+                      dataKey="label"
+                      tick={{ fontSize: 11, fill: '#374151' }}
+                      width={50}
+                      axisLine={false}
+                      tickLine={false}
+                    />
+                    <Tooltip
+                      contentStyle={{
+                        backgroundColor: '#FFFFFF',
+                        border: '1px solid #E2E8F0',
+                        borderRadius: '8px',
+                        fontSize: '12px',
+                      }}
+                      formatter={(value: number) => [value.toFixed(3), '相关系数']}
+                    />
+                    <ReferenceLine x={0} stroke="#94A3B8" strokeWidth={1} />
+                    <Bar dataKey="corr" barSize={20} radius={[0, 4, 4, 0]}>
+                      {corrWithCases.map((entry, idx) => (
+                        <Cell key={idx} fill={corrColor(entry.corr)} />
+                      ))}
+                    </Bar>
+                  </BarChart>
+                </ResponsiveContainer>
+                <p className="text-[10px] text-text-muted mt-3 text-center">
+                  网格级 Pearson 相关系数（红=正相关，蓝=负相关，颜色深浅表示强度）
+                </p>
+              </>
+            ) : (
+              <div className="text-center py-8 text-text-muted text-sm">
+                暂无数据
+              </div>
+            )}
+          </div>
+
+          {/* (b) Pollutant pairwise correlation heatmap */}
+          <div className="card p-4">
+            <div className="text-[11px] font-medium text-text-muted uppercase tracking-wide mb-4">
+              污染物两两相关热力图
+            </div>
+            {pairwiseGrid ? (
+              <>
+                <div className="overflow-x-auto">
+                  <div
+                    className="grid gap-px min-w-[320px]"
+                    style={{
+                      gridTemplateColumns: `48px repeat(${CORR_POLLUTANTS.length}, minmax(0, 1fr))`,
+                    }}
+                  >
+                    {/* Header row */}
+                    <div />
+                    {CORR_POLLUTANTS.map((key) => (
+                      <div
+                        key={`h-${key}`}
+                        className="text-[10px] font-medium text-text-muted text-center py-1"
+                      >
+                        {pollutantLabel(key)}
+                      </div>
+                    ))}
+                    {/* Body rows */}
+                    {pairwiseGrid.map((row, ri) => (
+                      <Fragment key={`r-${CORR_POLLUTANTS[ri]}`}>
+                        <div className="text-[10px] font-medium text-text-muted flex items-center justify-end pr-2">
+                          {pollutantLabel(CORR_POLLUTANTS[ri])}
+                        </div>
+                        {row.map((val, ci) => (
+                          <div
+                            key={`c-${ri}-${ci}`}
+                            className="aspect-square flex items-center justify-center text-[9px] font-medium rounded-sm"
+                            style={{
+                              backgroundColor:
+                                val === null ? '#F1F5F9' : corrColor(val),
+                              color:
+                                val !== null && Math.abs(val) > 0.55
+                                  ? '#FFFFFF'
+                                  : '#475569',
+                            }}
+                            title={`${pollutantLabel(CORR_POLLUTANTS[ri])} × ${pollutantLabel(
+                              CORR_POLLUTANTS[ci],
+                            )}: ${val === null ? 'N/A' : val.toFixed(2)}`}
+                          >
+                            {val === null ? '-' : val.toFixed(2)}
+                          </div>
+                        ))}
+                      </Fragment>
+                    ))}
+                  </div>
+                </div>
+                <p className="text-[10px] text-text-muted mt-3 text-center">
+                  对角线为自相关（=1.00）；红=正相关，蓝=负相关
+                </p>
+              </>
+            ) : (
+              <div className="text-center py-8 text-text-muted text-sm">
+                暂无数据
+              </div>
+            )}
+          </div>
+
+          {/* (c) PM2.5 × cases scatter + regression line */}
+          <div className="card p-4">
+            <div className="text-[11px] font-medium text-text-muted uppercase tracking-wide mb-4">
+              PM2.5 × 病例 散点 + 回归线
+            </div>
+            {scatterPoints.length > 0 ? (
+              <>
+                <ResponsiveContainer width="100%" height={320}>
+                  <ScatterChart margin={{ top: 5, right: 20, left: 10, bottom: 15 }}>
+                    <CartesianGrid strokeDasharray="3 3" stroke="#E2E8F0" />
+                    <XAxis
+                      type="number"
+                      dataKey="pm25"
+                      name="PM2.5"
+                      unit="μg/m³"
+                      tick={{ fontSize: 11, fill: '#64748B' }}
+                      axisLine={{ stroke: '#E2E8F0' }}
+                      label={{
+                        value: 'PM2.5 (μg/m³)',
+                        position: 'insideBottom',
+                        offset: -8,
+                        fontSize: 11,
+                        fill: '#64748B',
+                      }}
+                    />
+                    <YAxis
+                      type="number"
+                      dataKey="cases"
+                      name="病例数"
+                      tick={{ fontSize: 11, fill: '#64748B' }}
+                      axisLine={{ stroke: '#E2E8F0' }}
+                      label={{
+                        value: '病例数',
+                        angle: -90,
+                        position: 'insideLeft',
+                        offset: 0,
+                        fontSize: 11,
+                        fill: '#64748B',
+                      }}
+                    />
+                    <ZAxis range={[30, 30]} />
+                    <Tooltip
+                      cursor={{ strokeDasharray: '3 3' }}
+                      contentStyle={{
+                        backgroundColor: '#FFFFFF',
+                        border: '1px solid #E2E8F0',
+                        borderRadius: '8px',
+                        fontSize: '12px',
+                      }}
+                      formatter={(value: number, name: string) => [
+                        Math.round(value).toLocaleString(),
+                        name,
+                      ]}
+                    />
+                    <Scatter
+                      name="网格点"
+                      data={scatterPoints}
+                      fill="#7C3AED"
+                      fillOpacity={0.4}
+                    />
+                    {regressionLine.length === 2 && (
+                      <Scatter
+                        name="回归线"
+                        data={regressionLine}
+                        line={{ stroke: '#DC2626', strokeWidth: 2 }}
+                        lineType="joint"
+                        fill="#DC2626"
+                        shape={() => <g />}
+                        legendType="none"
+                      />
+                    )}
+                  </ScatterChart>
+                </ResponsiveContainer>
+                {regression && (
+                  <p className="text-[10px] text-text-muted mt-3 text-center">
+                    最小二乘回归：病例 ≈ {regression.slope.toFixed(2)} × PM2.5 +{' '}
+                    {regression.intercept.toFixed(1)}
+                  </p>
+                )}
+              </>
+            ) : (
+              <div className="text-center py-8 text-text-muted text-sm">
+                暂无数据
+              </div>
+            )}
+          </div>
+        </div>
       </div>
     </div>
   );

frontend/src/pages/TrendAnalysis.tsx

@@ -16,7 +16,8 @@ import {
   ReferenceLine,
 } from 'recharts';
 import { useAnalysisStore } from '@/stores/analysisStore';
-import { caseApi } from '@/services/api';
+import { caseApi, statsApi } from '@/services/api';
+import type { TemporalResponse } from '@/services/api';
 import { ErrorBanner } from '@/components/ErrorBanner';
 import { TrendingUp, Calendar, Activity } from 'lucide-react';
 import type { CaseTrendPoint } from '@/types';
@@ -48,6 +49,7 @@ export function TrendAnalysis() {
   const [selectedPollutants, setSelectedPollutants] = useState<string[]>(['aqi', 'pm25']);
   const [multiYearData, setMultiYearData] = useState<Record<string, CaseTrendPoint[]>>({});
   const [multiYearLoading, setMultiYearLoading] = useState(false);
+  const [weekdayData, setWeekdayData] = useState<TemporalResponse['weekday']>([]);
 
   useEffect(() => {
     fetchTrend(selectedDays);
@@ -82,6 +84,19 @@ export function TrendAnalysis() {
     return () => { cancelled = true; };
   }, []);
 
+  useEffect(() => {
+    let cancelled = false;
+    statsApi
+      .getTemporal()
+      .then((res) => {
+        if (!cancelled) setWeekdayData(res.weekday || []);
+      })
+      .catch(() => {
+        // weekday distribution is supplementary — fail silently
+      });
+    return () => { cancelled = true; };
+  }, []);
+
   // Merge multi-year data by month (data is monthly) over a fixed 1..12 sequence
   const mergedMultiYearData = (() => {
     const yearColors: Record<string, string> = { '2022': '#94A3B8', '2023': '#3B82F6', '2024': '#EF4444' };
@@ -444,6 +459,52 @@ export function TrendAnalysis() {
           </BarChart>
         </ResponsiveContainer>
       </div>
+
+      {/* Weekday case distribution (门诊/住院) */}
+      <div data-testid="weekday-dist" className="card p-4 mb-4">
+        <div className="text-[11px] font-medium text-text-muted uppercase tracking-wide mb-4">
+          星期就诊分布
+        </div>
+        {weekdayData.length > 0 ? (
+          <>
+            <ResponsiveContainer width="100%" height={280}>
+              <BarChart
+                data={weekdayData}
+                margin={{ top: 5, right: 20, left: 10, bottom: 5 }}
+              >
+                <CartesianGrid strokeDasharray="3 3" stroke="#E2E8F0" />
+                <XAxis
+                  dataKey="weekday"
+                  tick={{ fontSize: 12, fill: '#64748B' }}
+                  axisLine={{ stroke: '#E2E8F0' }}
+                />
+                <YAxis
+                  tick={{ fontSize: 12, fill: '#64748B' }}
+                  axisLine={{ stroke: '#E2E8F0' }}
+                  label={{ value: '就诊量', angle: -90, position: 'insideLeft', offset: 0, fontSize: 11, fill: '#64748B' }}
+                />
+                <Tooltip
+                  contentStyle={{
+                    backgroundColor: '#FFFFFF',
+                    border: '1px solid #E2E8F0',
+                    borderRadius: '8px',
+                    fontSize: '12px',
+                  }}
+                  formatter={(value: number, name: string) => [value.toLocaleString(), name]}
+                />
+                <Legend wrapperStyle={{ fontSize: '12px', paddingTop: '12px' }} />
+                <Bar dataKey="outpatient" name="门诊" stackId="visits" fill="#3B82F6" radius={[0, 0, 0, 0]} />
+                <Bar dataKey="inpatient" name="住院" stackId="visits" fill="#EF4444" radius={[4, 4, 0, 0]} />
+              </BarChart>
+            </ResponsiveContainer>
+            <p className="text-[10px] text-text-muted mt-3 text-center">
+              注：现有病例数据集中在12月，季节性/同比分析待更多月份数据
+            </p>
+          </>
+        ) : (
+          <div className="text-center py-8 text-text-muted text-sm">暂无就诊分布数据</div>
+        )}
+      </div>
     </div>
   );
 }

frontend/src/routes.tsx

@@ -33,6 +33,9 @@ const DiseaseAnalysis = lazy(() =>
 const EnvironmentalHealth = lazy(() =>
   import('@/pages/EnvironmentalHealth').then((m) => ({ default: m.EnvironmentalHealth }))
 );
+const ClinicalAnalysis = lazy(() =>
+  import('@/pages/ClinicalAnalysis').then((m) => ({ default: m.ClinicalAnalysis }))
+);
 
 // 用 Suspense 包裹懒加载页面，统一加载态。
 function lazyElement(Page: ComponentType): JSX.Element {
@@ -56,6 +59,7 @@ export const appRoutes: RouteObject[] = [
   { path: 'analysis/demographics', element: lazyElement(DemographicAnalysis) },
   { path: 'analysis/disease', element: lazyElement(DiseaseAnalysis) },
   { path: 'analysis/environment', element: lazyElement(EnvironmentalHealth) },
+  { path: 'analysis/clinical', element: lazyElement(ClinicalAnalysis) },
   // 未知路径回退到监测面板。
   { path: '*', element: <Navigate to="/monitoring" replace /> },
 ];

frontend/src/services/api.ts

@@ -343,4 +343,48 @@ export const reportApi = {
   getLatestSummary: (): Promise<ReportSummary> => cachedGet('/reports/summary/latest'),
 };
 
+// ===== 深度统计分析（/api/stats）=====
+export interface InpatientClinicalResponse {
+  kpis: {
+    total_admissions: number;
+    median_los_days: number;
+    mean_cost: number;
+    cure_rate: number;
+    emergency_admit_ratio: number;
+  };
+  los_histogram: { bin_label: string; count: number }[];
+  los_by_disease: { diagnosis: string; p25: number; median: number; p75: number; n: number }[];
+  cost_histogram: { bin_label: string; count: number }[];
+  cost_by_disease: { diagnosis: string; mean_cost: number; n: number }[];
+  cost_vs_los: { los: number; cost: number }[];
+  outcome_counts: { outcome: string; count: number }[];
+  admission_route_counts: { route: string; count: number }[];
+  bmi_by_age_band: { age_band: string; p25: number; median: number; p75: number; n: number }[];
+}
+export interface SymptomsResponse {
+  symptoms: { keyword: string; count: number }[];
+  revisit_ratio: number;
+}
+export interface IncidenceRateResponse {
+  districts: { district: string; total_cases: number; population: number; rate_per_10k: number }[];
+}
+export interface EnvCorrelationResponse {
+  correlation_matrix: { pollutant: string; corr_with_cases: number }[];
+  scatter: { pm25: number; aqi: number; cases: number }[];
+  pollutant_pairwise: { a: string; b: string; corr: number }[];
+}
+export interface TemporalResponse {
+  weekday: { weekday: string; outpatient: number; inpatient: number; total: number }[];
+  month_year: { year: number; month: number; total: number }[];
+  yoy: { period: string; current: number; previous: number; growth_pct: number }[];
+}
+
+export const statsApi = {
+  getInpatientClinical: (): Promise<InpatientClinicalResponse> => cachedGet('/stats/inpatient-clinical'),
+  getSymptoms: (top: number = 20): Promise<SymptomsResponse> => cachedGet('/stats/symptoms', { top }),
+  getIncidenceRate: (): Promise<IncidenceRateResponse> => cachedGet('/stats/incidence-rate'),
+  getEnvCorrelation: (): Promise<EnvCorrelationResponse> => cachedGet('/stats/env-correlation'),
+  getTemporal: (): Promise<TemporalResponse> => cachedGet('/stats/temporal'),
+};
+
 export default api;

frontend/src/utils/testids.ts

@@ -22,6 +22,7 @@ export const TESTIDS = {
   navDemographics: 'nav-demographics',
   navDisease: 'nav-disease',
   navEnvironment: 'nav-environment',
+  navClinical: 'nav-clinical',
 
   // 页面挂载点
   pageMonitoring: 'page-monitoring',
@@ -34,6 +35,8 @@ export const TESTIDS = {
   pageDemographics: 'page-demographics',
   pageDisease: 'page-disease',
   pageEnvironment: 'page-environment',
+  pageClinical: 'page-clinical',
+  clinicalKpis: 'clinical-kpis',
 
   // 综合概览 大屏
   kpiRow: 'kpi-row',