chore: port to MIMIC-III using AI

paper2_festung_teil3.py

@@ -9,12 +9,25 @@ Benutzt die Full-Pop-Prädiktionen aus dem vorherigen Lauf.
 Basilakis 2026 · chicxulub.ai
 """
 
-import json, sys, math, time, random
+import json, os, sys, math, time, random
 from collections import defaultdict
 
-BQ_PROJECT   = "goddard-gap"
-DATA_PROJECT = "physionet-data"
-NE_ITEMID    = 221906
+# PostgreSQL connection string (libpq DSN). Override with env var.
+# e.g. "host=localhost port=5432 dbname=mimic user=postgres password=..."
+PG_DSN         = os.environ.get("MIMIC_PG_DSN", "dbname=mimic3")
+# Schema holding the stock MIMIC-III v1.3 tables (admissions, icustays,
+# labevents, chartevents, inputevents_mv, inputevents_cv, prescriptions,
+# diagnoses_icd, d_items, ...).
+MIMIC_SCHEMA   = os.environ.get("MIMIC_SCHEMA", "mimiciii")
+# Schema holding the locally built derived tables (sapsii, sepsis3, ...);
+# see sql/schemas.sql.  Defaults to the same schema as MIMIC-III itself.
+DERIVED_SCHEMA = os.environ.get("DERIVED_SCHEMA", MIMIC_SCHEMA)
+
+# MIMIC-III stores Norepinephrine under different itemids in CareVue
+# (inputevents_cv: 30047, 30120) and MetaVision (inputevents_mv: 221906).
+NE_ITEMIDS_MV  = [221906]
+NE_ITEMIDS_CV  = [30047, 30120]
+
 SAPS_WINDOW  = 10
 PARAM_KEYS = ["lactate","creatinine","ph","troponin","hemoglobin",
               "heart_rate","map_bp","spo2","temperature","ne_dose"]
@@ -52,10 +65,24 @@ GALAXY_PRIORITY = ["sepsis","cardiogenic_shock","post_cardiac_arrest","ards",
     "acute_mi","aki","liver_failure","gi_bleeding","stroke","pe","dka",
     "heart_failure","pneumonia","copd","afib","post_cardiac_surgery"]
 
-def run_bq(sql):
-    from google.cloud import bigquery
-    client = bigquery.Client(project=BQ_PROJECT)
-    return [dict(r.items()) for r in client.query(sql).result()]
+_PG_CONN = None
+def _pg_conn():
+    global _PG_CONN
+    if _PG_CONN is None or getattr(_PG_CONN, "closed", 0):
+        import psycopg2
+        _PG_CONN = psycopg2.connect(PG_DSN)
+        _PG_CONN.set_session(readonly=True, autocommit=True)
+    return _PG_CONN
+
+def run_pg(sql):
+    """Execute a read-only SQL query and return rows as list[dict]."""
+    import psycopg2.extras
+    conn = _pg_conn()
+    with conn.cursor(cursor_factory=psycopg2.extras.RealDictCursor) as cur:
+        cur.execute(sql)
+        if cur.description is None:
+            return []
+        return [dict(r) for r in cur.fetchall()]
 
 def auc_fast(preds):
     if not preds: return 0.5
@@ -99,33 +126,63 @@ def td(pv,centroid,weights):
 
 def load_all_icu():
     print("  Loading ALL ICU patients...")
+    ne_mv = ",".join(str(i) for i in NE_ITEMIDS_MV)
+    ne_cv = ",".join(str(i) for i in NE_ITEMIDS_CV)
     sql=f"""WITH icu_pts AS (
         SELECT DISTINCT a.hadm_id,a.hospital_expire_flag AS died,s.sapsii,icu.intime,
             s.sapsii_prob AS saps_prob
-        FROM `{DATA_PROJECT}.mimiciv_3_1_hosp.admissions` a
-        JOIN `{DATA_PROJECT}.mimiciv_3_1_icu.icustays` icu ON a.hadm_id=icu.hadm_id
-        JOIN `{DATA_PROJECT}.mimiciv_3_1_derived.sapsii` s ON icu.stay_id=s.stay_id
+        FROM {MIMIC_SCHEMA}.admissions a
+        JOIN {MIMIC_SCHEMA}.icustays icu ON a.hadm_id=icu.hadm_id
+        JOIN {DERIVED_SCHEMA}.sapsii s ON icu.icustay_id=s.icustay_id
         WHERE s.sapsii BETWEEN 20 AND 90),
-    l_lac AS (SELECT le.hadm_id,MAX(le.valuenum) AS val FROM `{DATA_PROJECT}.mimiciv_3_1_hosp.labevents` le JOIN icu_pts ip ON le.hadm_id=ip.hadm_id WHERE le.itemid=50813 AND le.valuenum IS NOT NULL AND le.charttime BETWEEN ip.intime AND TIMESTAMP_ADD(ip.intime,INTERVAL 24 HOUR) GROUP BY le.hadm_id),
-    l_krea AS (SELECT le.hadm_id,MAX(le.valuenum) AS val FROM `{DATA_PROJECT}.mimiciv_3_1_hosp.labevents` le JOIN icu_pts ip ON le.hadm_id=ip.hadm_id WHERE le.itemid=50912 AND le.valuenum IS NOT NULL AND le.charttime BETWEEN ip.intime AND TIMESTAMP_ADD(ip.intime,INTERVAL 24 HOUR) GROUP BY le.hadm_id),
-    l_ph AS (SELECT le.hadm_id,MIN(le.valuenum) AS val FROM `{DATA_PROJECT}.mimiciv_3_1_hosp.labevents` le JOIN icu_pts ip ON le.hadm_id=ip.hadm_id WHERE le.itemid IN (50820,50831) AND le.valuenum IS NOT NULL AND le.charttime BETWEEN ip.intime AND TIMESTAMP_ADD(ip.intime,INTERVAL 24 HOUR) GROUP BY le.hadm_id),
-    l_trop AS (SELECT le.hadm_id,MAX(le.valuenum) AS val FROM `{DATA_PROJECT}.mimiciv_3_1_hosp.labevents` le JOIN icu_pts ip ON le.hadm_id=ip.hadm_id WHERE le.itemid IN (51002,51003) AND le.valuenum IS NOT NULL AND le.charttime BETWEEN ip.intime AND TIMESTAMP_ADD(ip.intime,INTERVAL 24 HOUR) GROUP BY le.hadm_id),
-    l_hb AS (SELECT le.hadm_id,MIN(le.valuenum) AS val FROM `{DATA_PROJECT}.mimiciv_3_1_hosp.labevents` le JOIN icu_pts ip ON le.hadm_id=ip.hadm_id WHERE le.itemid=51222 AND le.valuenum IS NOT NULL AND le.charttime BETWEEN ip.intime AND TIMESTAMP_ADD(ip.intime,INTERVAL 24 HOUR) GROUP BY le.hadm_id),
-    c_hr AS (SELECT ce.hadm_id,MAX(ce.valuenum) AS val FROM `{DATA_PROJECT}.mimiciv_3_1_icu.chartevents` ce JOIN icu_pts ip ON ce.hadm_id=ip.hadm_id JOIN `{DATA_PROJECT}.mimiciv_3_1_icu.icustays` icu ON ce.stay_id=icu.stay_id WHERE ce.itemid=220045 AND ce.valuenum BETWEEN 20 AND 250 AND ce.charttime BETWEEN icu.intime AND TIMESTAMP_ADD(icu.intime,INTERVAL 24 HOUR) GROUP BY ce.hadm_id),
-    c_map AS (SELECT ce.hadm_id,MIN(ce.valuenum) AS val FROM `{DATA_PROJECT}.mimiciv_3_1_icu.chartevents` ce JOIN icu_pts ip ON ce.hadm_id=ip.hadm_id JOIN `{DATA_PROJECT}.mimiciv_3_1_icu.icustays` icu ON ce.stay_id=icu.stay_id WHERE ce.itemid IN (220052,220181,225312) AND ce.valuenum BETWEEN 20 AND 200 AND ce.charttime BETWEEN icu.intime AND TIMESTAMP_ADD(icu.intime,INTERVAL 24 HOUR) GROUP BY ce.hadm_id),
-    c_spo2 AS (SELECT ce.hadm_id,MIN(ce.valuenum) AS val FROM `{DATA_PROJECT}.mimiciv_3_1_icu.chartevents` ce JOIN icu_pts ip ON ce.hadm_id=ip.hadm_id JOIN `{DATA_PROJECT}.mimiciv_3_1_icu.icustays` icu ON ce.stay_id=icu.stay_id WHERE ce.itemid=220277 AND ce.valuenum BETWEEN 50 AND 100 AND ce.charttime BETWEEN icu.intime AND TIMESTAMP_ADD(icu.intime,INTERVAL 24 HOUR) GROUP BY ce.hadm_id),
-    c_temp AS (SELECT ce.hadm_id,MIN(ce.valuenum) AS val FROM `{DATA_PROJECT}.mimiciv_3_1_icu.chartevents` ce JOIN icu_pts ip ON ce.hadm_id=ip.hadm_id JOIN `{DATA_PROJECT}.mimiciv_3_1_icu.icustays` icu ON ce.stay_id=icu.stay_id WHERE ce.itemid=223762 AND ce.valuenum BETWEEN 28 AND 43 AND ce.charttime BETWEEN icu.intime AND TIMESTAMP_ADD(icu.intime,INTERVAL 24 HOUR) GROUP BY ce.hadm_id),
-    ne AS (SELECT ie.hadm_id,MAX(ie.rate) AS val FROM `{DATA_PROJECT}.mimiciv_3_1_icu.inputevents` ie JOIN icu_pts ip ON ie.hadm_id=ip.hadm_id JOIN `{DATA_PROJECT}.mimiciv_3_1_icu.icustays` icu ON ie.stay_id=icu.stay_id WHERE ie.itemid={NE_ITEMID} AND ie.rate>0 AND ie.starttime BETWEEN icu.intime AND TIMESTAMP_ADD(icu.intime,INTERVAL 24 HOUR) GROUP BY ie.hadm_id)
+    l_lac AS (SELECT le.hadm_id,MAX(le.valuenum) AS val FROM {MIMIC_SCHEMA}.labevents le JOIN icu_pts ip ON le.hadm_id=ip.hadm_id WHERE le.itemid=50813 AND le.valuenum IS NOT NULL AND le.charttime BETWEEN ip.intime AND ip.intime + INTERVAL '24 hours' GROUP BY le.hadm_id),
+    l_krea AS (SELECT le.hadm_id,MAX(le.valuenum) AS val FROM {MIMIC_SCHEMA}.labevents le JOIN icu_pts ip ON le.hadm_id=ip.hadm_id WHERE le.itemid=50912 AND le.valuenum IS NOT NULL AND le.charttime BETWEEN ip.intime AND ip.intime + INTERVAL '24 hours' GROUP BY le.hadm_id),
+    l_ph AS (SELECT le.hadm_id,MIN(le.valuenum) AS val FROM {MIMIC_SCHEMA}.labevents le JOIN icu_pts ip ON le.hadm_id=ip.hadm_id WHERE le.itemid IN (50820,50831) AND le.valuenum IS NOT NULL AND le.charttime BETWEEN ip.intime AND ip.intime + INTERVAL '24 hours' GROUP BY le.hadm_id),
+    l_trop AS (SELECT le.hadm_id,MAX(le.valuenum) AS val FROM {MIMIC_SCHEMA}.labevents le JOIN icu_pts ip ON le.hadm_id=ip.hadm_id WHERE le.itemid IN (51002,51003) AND le.valuenum IS NOT NULL AND le.charttime BETWEEN ip.intime AND ip.intime + INTERVAL '24 hours' GROUP BY le.hadm_id),
+    l_hb AS (SELECT le.hadm_id,MIN(le.valuenum) AS val FROM {MIMIC_SCHEMA}.labevents le JOIN icu_pts ip ON le.hadm_id=ip.hadm_id WHERE le.itemid=51222 AND le.valuenum IS NOT NULL AND le.charttime BETWEEN ip.intime AND ip.intime + INTERVAL '24 hours' GROUP BY le.hadm_id),
+    c_hr AS (SELECT ce.hadm_id,MAX(ce.valuenum) AS val FROM {MIMIC_SCHEMA}.chartevents ce JOIN icu_pts ip ON ce.hadm_id=ip.hadm_id JOIN {MIMIC_SCHEMA}.icustays icu ON ce.icustay_id=icu.icustay_id WHERE ce.itemid IN (211,220045) AND ce.valuenum BETWEEN 20 AND 250 AND ce.charttime BETWEEN icu.intime AND icu.intime + INTERVAL '24 hours' GROUP BY ce.hadm_id),
+    c_map AS (SELECT ce.hadm_id,MIN(ce.valuenum) AS val FROM {MIMIC_SCHEMA}.chartevents ce JOIN icu_pts ip ON ce.hadm_id=ip.hadm_id JOIN {MIMIC_SCHEMA}.icustays icu ON ce.icustay_id=icu.icustay_id WHERE ce.itemid IN (52,456,6702,220052,220181,225312) AND ce.valuenum BETWEEN 20 AND 200 AND ce.charttime BETWEEN icu.intime AND icu.intime + INTERVAL '24 hours' GROUP BY ce.hadm_id),
+    c_spo2 AS (SELECT ce.hadm_id,MIN(ce.valuenum) AS val FROM {MIMIC_SCHEMA}.chartevents ce JOIN icu_pts ip ON ce.hadm_id=ip.hadm_id JOIN {MIMIC_SCHEMA}.icustays icu ON ce.icustay_id=icu.icustay_id WHERE ce.itemid IN (646,220277) AND ce.valuenum BETWEEN 50 AND 100 AND ce.charttime BETWEEN icu.intime AND icu.intime + INTERVAL '24 hours' GROUP BY ce.hadm_id),
+    -- Temperature: pull all four MIMIC-III itemids (676/223762 nominally
+    -- Celsius, 678/223761 nominally Fahrenheit) and decide the unit from
+    -- the value itself.  Plausible body temperature in C is ~28..43 and
+    -- in F is ~82..110; the two ranges don't overlap, so a value in the
+    -- F band can be safely converted to C even if it was charted under a
+    -- "Celsius" itemid (and vice versa).  Anything outside both bands is
+    -- treated as sensor noise and dropped.
+    c_temp AS (
+        SELECT ce.hadm_id,
+               MIN(CASE
+                     WHEN ce.valuenum BETWEEN 28  AND 43  THEN ce.valuenum
+                     WHEN ce.valuenum BETWEEN 82  AND 110 THEN (ce.valuenum - 32.0) / 1.8
+                   END) AS val
+          FROM {MIMIC_SCHEMA}.chartevents ce
+          JOIN icu_pts ip ON ce.hadm_id=ip.hadm_id
+          JOIN {MIMIC_SCHEMA}.icustays icu ON ce.icustay_id=icu.icustay_id
+         WHERE ce.itemid IN (676, 223762, 678, 223761)
+           AND ce.valuenum IS NOT NULL
+           AND (ce.valuenum BETWEEN 28 AND 43 OR ce.valuenum BETWEEN 82 AND 110)
+           AND ce.charttime BETWEEN icu.intime AND icu.intime + INTERVAL '24 hours'
+         GROUP BY ce.hadm_id),
+    ne_all AS (
+        SELECT ie.hadm_id, ie.icustay_id, ie.rate, ie.starttime AS evttime
+            FROM {MIMIC_SCHEMA}.inputevents_mv ie
+            WHERE ie.itemid IN ({ne_mv}) AND ie.rate>0
+        UNION ALL
+        SELECT ie.hadm_id, ie.icustay_id, ie.rate, ie.charttime AS evttime
+            FROM {MIMIC_SCHEMA}.inputevents_cv ie
+            WHERE ie.itemid IN ({ne_cv}) AND ie.rate>0),
+    ne AS (SELECT ie.hadm_id,MAX(ie.rate) AS val FROM ne_all ie JOIN icu_pts ip ON ie.hadm_id=ip.hadm_id JOIN {MIMIC_SCHEMA}.icustays icu ON ie.icustay_id=icu.icustay_id WHERE ie.evttime BETWEEN icu.intime AND icu.intime + INTERVAL '24 hours' GROUP BY ie.hadm_id)
     SELECT ip.hadm_id,ip.died,ip.sapsii,ip.saps_prob,
         ll.val AS lactate,lk.val AS creatinine,lp.val AS ph,lt.val AS troponin,lh.val AS hemoglobin,
-        chr.val AS heart_rate,cma.val AS map_bp,csp.val AS spo2,cte.val AS temperature,ne.val AS ne_dose
+        chr_.val AS heart_rate,cma.val AS map_bp,csp.val AS spo2,cte.val AS temperature,ne.val AS ne_dose
     FROM icu_pts ip
     LEFT JOIN l_lac ll ON ip.hadm_id=ll.hadm_id LEFT JOIN l_krea lk ON ip.hadm_id=lk.hadm_id
     LEFT JOIN l_ph lp ON ip.hadm_id=lp.hadm_id LEFT JOIN l_trop lt ON ip.hadm_id=lt.hadm_id
-    LEFT JOIN l_hb lh ON ip.hadm_id=lh.hadm_id LEFT JOIN c_hr chr ON ip.hadm_id=chr.hadm_id
+    LEFT JOIN l_hb lh ON ip.hadm_id=lh.hadm_id LEFT JOIN c_hr chr_ ON ip.hadm_id=chr_.hadm_id
     LEFT JOIN c_map cma ON ip.hadm_id=cma.hadm_id LEFT JOIN c_spo2 csp ON ip.hadm_id=csp.hadm_id
     LEFT JOIN c_temp cte ON ip.hadm_id=cte.hadm_id LEFT JOIN ne ON ip.hadm_id=ne.hadm_id"""
-    rows=run_bq(sql)
+    rows=run_pg(sql)
     pts=[{k:r.get(k) for k in ["hadm_id","died","sapsii","saps_prob"]+PARAM_KEYS}
          for r in rows if sum(1 for k in PARAM_KEYS if r.get(k) is not None)>=3 and r.get("died") is not None]
     print(f"  -> {len(pts)} patients"); return pts
@@ -135,10 +192,13 @@ def assign_galaxies(pts):
     hids=[p["hadm_id"] for p in pts];ps=defaultdict(set)
     for i in range(0,len(hids),10000):
         chunk=hids[i:i+10000]
-        for r in run_bq(f"SELECT hadm_id,icd_code,icd_version FROM `{DATA_PROJECT}.mimiciv_3_1_hosp.diagnoses_icd` WHERE hadm_id IN ({','.join(str(h) for h in chunk)})"):
+        # MIMIC-III v1.3 only carries ICD-9 codes (column `icd9_code`).
+        for r in run_pg(f"SELECT hadm_id,icd9_code FROM {MIMIC_SCHEMA}.diagnoses_icd WHERE hadm_id IN ({','.join(str(h) for h in chunk)})"):
+            code = r.get("icd9_code")
+            if code is None: continue
             for sk,sd in SYNDROME_ICDS.items():
-                for rc in sd.get(f"icd_{r['icd_version']}",[]):
-                    if r["icd_code"].startswith(rc): ps[r["hadm_id"]].add(sk);break
+                for rc in sd.get("icd_9",[]):
+                    if code.startswith(rc): ps[r["hadm_id"]].add(sk);break
     for p in pts:
         p["galaxy"]=None
         for g in GALAXY_PRIORITY:
@@ -147,14 +207,33 @@ def assign_galaxies(pts):
 def load_therapy_hadmids(tkey):
     t=THERAPIES[tkey]
     if tkey=="ne_high":
-        return set(r["hadm_id"] for r in run_bq(f"SELECT DISTINCT ie.hadm_id FROM `{DATA_PROJECT}.mimiciv_3_1_icu.inputevents` ie JOIN `{DATA_PROJECT}.mimiciv_3_1_icu.icustays` icu ON ie.stay_id=icu.stay_id WHERE ie.itemid={NE_ITEMID} AND ie.rate>=0.5 AND ie.starttime BETWEEN icu.intime AND TIMESTAMP_ADD(icu.intime,INTERVAL 24 HOUR)"))
+        ne_mv = ",".join(str(i) for i in NE_ITEMIDS_MV)
+        ne_cv = ",".join(str(i) for i in NE_ITEMIDS_CV)
+        sql = f"""
+            SELECT DISTINCT ie.hadm_id
+              FROM {MIMIC_SCHEMA}.inputevents_mv ie
+              JOIN {MIMIC_SCHEMA}.icustays icu ON ie.icustay_id=icu.icustay_id
+             WHERE ie.itemid IN ({ne_mv}) AND ie.rate>=0.5
+               AND ie.starttime BETWEEN icu.intime AND icu.intime + INTERVAL '24 hours'
+            UNION
+            SELECT DISTINCT ie.hadm_id
+              FROM {MIMIC_SCHEMA}.inputevents_cv ie
+              JOIN {MIMIC_SCHEMA}.icustays icu ON ie.icustay_id=icu.icustay_id
+             WHERE ie.itemid IN ({ne_cv}) AND ie.rate>=0.5
+               AND ie.charttime BETWEEN icu.intime AND icu.intime + INTERVAL '24 hours'
+        """
+        return set(r["hadm_id"] for r in run_pg(sql))
     clauses=[]
+    # MIMIC-III splits inputevents across MetaVision (starttime) and CareVue
+    # (charttime); we have to query both and UNION the hadm_ids.
     for d in t.get("drugs_input",[]):
-        clauses.append(f"SELECT DISTINCT ie.hadm_id FROM `{DATA_PROJECT}.mimiciv_3_1_icu.inputevents` ie JOIN `{DATA_PROJECT}.mimiciv_3_1_icu.d_items` di ON ie.itemid=di.itemid JOIN `{DATA_PROJECT}.mimiciv_3_1_icu.icustays` icu ON ie.stay_id=icu.stay_id WHERE di.label LIKE '%{d}%' AND ie.starttime BETWEEN icu.intime AND TIMESTAMP_ADD(icu.intime,INTERVAL 24 HOUR)")
+        clauses.append(f"SELECT DISTINCT ie.hadm_id FROM {MIMIC_SCHEMA}.inputevents_mv ie JOIN {MIMIC_SCHEMA}.d_items di ON ie.itemid=di.itemid JOIN {MIMIC_SCHEMA}.icustays icu ON ie.icustay_id=icu.icustay_id WHERE di.label ILIKE '%{d}%' AND ie.starttime BETWEEN icu.intime AND icu.intime + INTERVAL '24 hours'")
+        clauses.append(f"SELECT DISTINCT ie.hadm_id FROM {MIMIC_SCHEMA}.inputevents_cv ie JOIN {MIMIC_SCHEMA}.d_items di ON ie.itemid=di.itemid JOIN {MIMIC_SCHEMA}.icustays icu ON ie.icustay_id=icu.icustay_id WHERE di.label ILIKE '%{d}%' AND ie.charttime BETWEEN icu.intime AND icu.intime + INTERVAL '24 hours'")
+    # MIMIC-III prescriptions uses DATE-precision `startdate` (not `starttime`).
     for d in t.get("drugs_rx",[]):
-        clauses.append(f"SELECT DISTINCT p.hadm_id FROM `{DATA_PROJECT}.mimiciv_3_1_hosp.prescriptions` p JOIN `{DATA_PROJECT}.mimiciv_3_1_icu.icustays` icu ON p.hadm_id=icu.hadm_id WHERE p.drug LIKE '%{d}%' AND p.starttime BETWEEN icu.intime AND TIMESTAMP_ADD(icu.intime,INTERVAL 24 HOUR)")
+        clauses.append(f"SELECT DISTINCT p.hadm_id FROM {MIMIC_SCHEMA}.prescriptions p JOIN {MIMIC_SCHEMA}.icustays icu ON p.hadm_id=icu.hadm_id WHERE p.drug ILIKE '%{d}%' AND p.startdate BETWEEN icu.intime AND icu.intime + INTERVAL '24 hours'")
     if not clauses: return set()
-    return set(r["hadm_id"] for r in run_bq(" UNION DISTINCT ".join(clauses)))
+    return set(r["hadm_id"] for r in run_pg(" UNION ".join(clauses)))
 
 def run_loo(test_pts,ref_pts,therapy_hids,by_gal,label):
     """Returns list of {a, p, g, hadm_id} — includes hadm_id for fair comparison."""

sql/schemas.sql

@@ -0,0 +1,605 @@
+-- ------------------------------------------------------------------
+-- Reference CREATE TABLE schemas for every derived table produced by
+--   sql/build_sapsii.sql
+--   sql/build_sepsis3.sql
+--
+-- This file is documentation only.  The actual build scripts use
+-- `DROP TABLE IF EXISTS ...; CREATE TABLE ... AS SELECT ...`, so
+-- column types are inferred by PostgreSQL at build time from the
+-- MIMIC-III v1.3 base schema and from the expressions in the SELECT.
+-- The types below match what PostgreSQL infers when the build is run
+-- on a stock MIMIC-III v1.3 PostgreSQL restore (where for example
+-- chartevents.valuenum is DOUBLE PRECISION, outputevents.value is
+-- DOUBLE PRECISION, *.charttime is TIMESTAMP(0), etc.).
+--
+-- Use this file as:
+--   * a quick reference for column names and types of each derived
+--     table (handy for downstream consumers that need to know the
+--     output schema without grep'ing through the build SQL);
+--   * a stub for declaring empty derived tables ahead of time (e.g.
+--     in a migration that just `CREATE TABLE IF NOT EXISTS ...`s
+--     them, then later runs the build to populate them);
+--   * a checklist when porting these scripts to another flavor of
+--     MIMIC (e.g. MIMIC-III v1.4 or MIMIC-IV).
+-- ------------------------------------------------------------------
+
+
+-- ==================================================================
+--                            SAPS-II
+-- ==================================================================
+
+-- 1. Helper: all-time urine output (from outputevents).
+DROP TABLE IF EXISTS urine_output;
+CREATE TABLE urine_output (
+    icustay_id  INTEGER,
+    charttime   TIMESTAMP(0),
+    value       DOUBLE PRECISION
+);
+
+-- 2. Ventilation: classification (per charttime) and durations
+--    (per ventilation episode).
+DROP TABLE IF EXISTS ventilation_classification;
+CREATE TABLE ventilation_classification (
+    icustay_id     INTEGER,
+    charttime      TIMESTAMP(0),
+    mechvent       INTEGER,
+    oxygentherapy  INTEGER,
+    extubated      INTEGER,
+    selfextubated  INTEGER
+);
+
+DROP TABLE IF EXISTS ventilation_durations;
+CREATE TABLE ventilation_durations (
+    icustay_id      INTEGER,
+    ventnum         BIGINT,
+    starttime       TIMESTAMP(0),
+    endtime         TIMESTAMP(0),
+    duration_hours  NUMERIC
+);
+
+-- 3. First-day pivots feeding SAPS-II.
+DROP TABLE IF EXISTS blood_gas_first_day;
+CREATE TABLE blood_gas_first_day (
+    subject_id        INTEGER,
+    hadm_id           INTEGER,
+    icustay_id        INTEGER,
+    charttime         TIMESTAMP(0),
+    specimen          VARCHAR(200),
+    aado2             DOUBLE PRECISION,
+    baseexcess        DOUBLE PRECISION,
+    bicarbonate       DOUBLE PRECISION,
+    totalco2          DOUBLE PRECISION,
+    carboxyhemoglobin DOUBLE PRECISION,
+    chloride          DOUBLE PRECISION,
+    calcium           DOUBLE PRECISION,
+    glucose           DOUBLE PRECISION,
+    hematocrit        DOUBLE PRECISION,
+    hemoglobin        DOUBLE PRECISION,
+    intubated         DOUBLE PRECISION,
+    lactate           DOUBLE PRECISION,
+    methemoglobin     DOUBLE PRECISION,
+    o2flow            DOUBLE PRECISION,
+    fio2              DOUBLE PRECISION,
+    so2               DOUBLE PRECISION,
+    pco2              DOUBLE PRECISION,
+    peep              DOUBLE PRECISION,
+    ph                DOUBLE PRECISION,
+    po2               DOUBLE PRECISION,
+    potassium         DOUBLE PRECISION,
+    requiredo2        DOUBLE PRECISION,
+    sodium            DOUBLE PRECISION,
+    temperature       DOUBLE PRECISION,
+    tidalvolume       DOUBLE PRECISION,
+    ventilationrate   DOUBLE PRECISION,
+    ventilator        DOUBLE PRECISION
+);
+
+DROP TABLE IF EXISTS blood_gas_first_day_arterial;
+CREATE TABLE blood_gas_first_day_arterial (
+    subject_id        INTEGER,
+    hadm_id           INTEGER,
+    icustay_id        INTEGER,
+    charttime         TIMESTAMP(0),
+    specimen          VARCHAR(200),
+    specimen_pred     VARCHAR(200),
+    specimen_prob     DOUBLE PRECISION,
+    so2               DOUBLE PRECISION,
+    spo2              DOUBLE PRECISION,
+    po2               DOUBLE PRECISION,
+    pco2              DOUBLE PRECISION,
+    fio2_chartevents  DOUBLE PRECISION,
+    fio2              DOUBLE PRECISION,
+    aado2             DOUBLE PRECISION,
+    aado2_calc        DOUBLE PRECISION,
+    pao2fio2          DOUBLE PRECISION,
+    ph                DOUBLE PRECISION,
+    baseexcess        DOUBLE PRECISION,
+    bicarbonate       DOUBLE PRECISION,
+    totalco2          DOUBLE PRECISION,
+    hematocrit        DOUBLE PRECISION,
+    hemoglobin        DOUBLE PRECISION,
+    carboxyhemoglobin DOUBLE PRECISION,
+    methemoglobin     DOUBLE PRECISION,
+    chloride          DOUBLE PRECISION,
+    calcium           DOUBLE PRECISION,
+    temperature       DOUBLE PRECISION,
+    potassium         DOUBLE PRECISION,
+    sodium            DOUBLE PRECISION,
+    lactate           DOUBLE PRECISION,
+    glucose           DOUBLE PRECISION,
+    intubated         DOUBLE PRECISION,
+    tidalvolume       DOUBLE PRECISION,
+    ventilationrate   DOUBLE PRECISION,
+    ventilator        DOUBLE PRECISION,
+    peep              DOUBLE PRECISION,
+    o2flow            DOUBLE PRECISION,
+    requiredo2        DOUBLE PRECISION
+);
+
+DROP TABLE IF EXISTS gcs_first_day;
+CREATE TABLE gcs_first_day (
+    subject_id    INTEGER,
+    hadm_id       INTEGER,
+    icustay_id    INTEGER,
+    mingcs        DOUBLE PRECISION,
+    gcsmotor      DOUBLE PRECISION,
+    gcsverbal     DOUBLE PRECISION,
+    gcseyes       DOUBLE PRECISION,
+    endotrachflag INTEGER
+);
+
+DROP TABLE IF EXISTS labs_first_day;
+CREATE TABLE labs_first_day (
+    subject_id      INTEGER,
+    hadm_id         INTEGER,
+    icustay_id      INTEGER,
+    aniongap_min    DOUBLE PRECISION,
+    aniongap_max    DOUBLE PRECISION,
+    albumin_min     DOUBLE PRECISION,
+    albumin_max     DOUBLE PRECISION,
+    bands_min       DOUBLE PRECISION,
+    bands_max       DOUBLE PRECISION,
+    bicarbonate_min DOUBLE PRECISION,
+    bicarbonate_max DOUBLE PRECISION,
+    bilirubin_min   DOUBLE PRECISION,
+    bilirubin_max   DOUBLE PRECISION,
+    creatinine_min  DOUBLE PRECISION,
+    creatinine_max  DOUBLE PRECISION,
+    chloride_min    DOUBLE PRECISION,
+    chloride_max    DOUBLE PRECISION,
+    glucose_min     DOUBLE PRECISION,
+    glucose_max     DOUBLE PRECISION,
+    hematocrit_min  DOUBLE PRECISION,
+    hematocrit_max  DOUBLE PRECISION,
+    hemoglobin_min  DOUBLE PRECISION,
+    hemoglobin_max  DOUBLE PRECISION,
+    lactate_min     DOUBLE PRECISION,
+    lactate_max     DOUBLE PRECISION,
+    platelet_min    DOUBLE PRECISION,
+    platelet_max    DOUBLE PRECISION,
+    potassium_min   DOUBLE PRECISION,
+    potassium_max   DOUBLE PRECISION,
+    ptt_min         DOUBLE PRECISION,
+    ptt_max         DOUBLE PRECISION,
+    inr_min         DOUBLE PRECISION,
+    inr_max         DOUBLE PRECISION,
+    pt_min          DOUBLE PRECISION,
+    pt_max          DOUBLE PRECISION,
+    sodium_min      DOUBLE PRECISION,
+    sodium_max      DOUBLE PRECISION,
+    bun_min         DOUBLE PRECISION,
+    bun_max         DOUBLE PRECISION,
+    wbc_min         DOUBLE PRECISION,
+    wbc_max         DOUBLE PRECISION
+);
+
+DROP TABLE IF EXISTS urine_output_first_day;
+CREATE TABLE urine_output_first_day (
+    subject_id  INTEGER,
+    hadm_id     INTEGER,
+    icustay_id  INTEGER,
+    urineoutput DOUBLE PRECISION
+);
+
+DROP TABLE IF EXISTS vitals_first_day;
+CREATE TABLE vitals_first_day (
+    subject_id     INTEGER,
+    hadm_id        INTEGER,
+    icustay_id     INTEGER,
+    heartrate_min  DOUBLE PRECISION,
+    heartrate_max  DOUBLE PRECISION,
+    heartrate_mean DOUBLE PRECISION,
+    sysbp_min      DOUBLE PRECISION,
+    sysbp_max      DOUBLE PRECISION,
+    sysbp_mean     DOUBLE PRECISION,
+    diasbp_min     DOUBLE PRECISION,
+    diasbp_max     DOUBLE PRECISION,
+    diasbp_mean    DOUBLE PRECISION,
+    meanbp_min     DOUBLE PRECISION,
+    meanbp_max     DOUBLE PRECISION,
+    meanbp_mean    DOUBLE PRECISION,
+    resprate_min   DOUBLE PRECISION,
+    resprate_max   DOUBLE PRECISION,
+    resprate_mean  DOUBLE PRECISION,
+    tempc_min      DOUBLE PRECISION,
+    tempc_max      DOUBLE PRECISION,
+    tempc_mean     DOUBLE PRECISION,
+    spo2_min       DOUBLE PRECISION,
+    spo2_max       DOUBLE PRECISION,
+    spo2_mean      DOUBLE PRECISION,
+    glucose_min    DOUBLE PRECISION,
+    glucose_max    DOUBLE PRECISION,
+    glucose_mean   DOUBLE PRECISION
+);
+
+-- 4. Final SAPS-II score table (one row per ICU stay).
+DROP TABLE IF EXISTS sapsii;
+CREATE TABLE sapsii (
+    subject_id           INTEGER,
+    hadm_id              INTEGER,
+    icustay_id           INTEGER,
+    sapsii               INTEGER,
+    sapsii_prob          DOUBLE PRECISION,
+    age_score            INTEGER,
+    hr_score             INTEGER,
+    sysbp_score          INTEGER,
+    temp_score           INTEGER,
+    pao2fio2_score       INTEGER,
+    uo_score             INTEGER,
+    bun_score            INTEGER,
+    wbc_score            INTEGER,
+    potassium_score      INTEGER,
+    sodium_score         INTEGER,
+    bicarbonate_score    INTEGER,
+    bilirubin_score      INTEGER,
+    gcs_score            INTEGER,
+    comorbidity_score    INTEGER,
+    admissiontype_score  INTEGER
+);
+
+
+-- ==================================================================
+--                            Sepsis-3
+-- ==================================================================
+--
+-- Sepsis-3 reuses these SAPS-II tables:
+--   urine_output, ventilation_classification, ventilation_durations
+-- (defined above).  The tables below are the ones added by
+-- build_sepsis3.sql.
+
+-- 1. Echo extraction (used to impute weight when chartevents weight
+--    is missing; also keyed by ROW_ID to the noteevents row).
+DROP TABLE IF EXISTS echo_data;
+CREATE TABLE echo_data (
+    row_id           INTEGER,
+    subject_id       INTEGER,
+    hadm_id          INTEGER,
+    chartdate        TIMESTAMP(0),
+    charttime        TIMESTAMP(3),
+    indication       TEXT,
+    height           NUMERIC,
+    weight           NUMERIC,
+    bsa              NUMERIC,
+    bp               TEXT,
+    bpsys            NUMERIC,
+    bpdias           NUMERIC,
+    hr               NUMERIC,
+    status           TEXT,
+    test             TEXT,
+    doppler          TEXT,
+    contrast         TEXT,
+    technicalquality TEXT
+);
+
+-- 2. Per-stay weight durations (admit + daily + neonate + echo
+--    imputed); used for mcg/kg/min vasopressor unit conversion.
+DROP TABLE IF EXISTS weight_durations;
+CREATE TABLE weight_durations (
+    icustay_id INTEGER,
+    starttime  TIMESTAMP(0),
+    endtime    TIMESTAMP(0),
+    weight     DOUBLE PRECISION
+);
+
+-- 3. Vasopressor dose tables.  All four have the same schema; rates
+--    are merged CareVue + MetaVision and converted to mcg/kg/min.
+DROP TABLE IF EXISTS dobutamine_dose;
+CREATE TABLE dobutamine_dose (
+    icustay_id  INTEGER,
+    starttime   TIMESTAMP(0),
+    endtime     TIMESTAMP(0),
+    vaso_rate   DOUBLE PRECISION,
+    vaso_amount DOUBLE PRECISION
+);
+
+DROP TABLE IF EXISTS dopamine_dose;
+CREATE TABLE dopamine_dose (
+    icustay_id  INTEGER,
+    starttime   TIMESTAMP(0),
+    endtime     TIMESTAMP(0),
+    vaso_rate   DOUBLE PRECISION,
+    vaso_amount DOUBLE PRECISION
+);
+
+DROP TABLE IF EXISTS epinephrine_dose;
+CREATE TABLE epinephrine_dose (
+    icustay_id  INTEGER,
+    starttime   TIMESTAMP(0),
+    endtime     TIMESTAMP(0),
+    vaso_rate   DOUBLE PRECISION,
+    vaso_amount DOUBLE PRECISION
+);
+
+DROP TABLE IF EXISTS norepinephrine_dose;
+CREATE TABLE norepinephrine_dose (
+    icustay_id  INTEGER,
+    starttime   TIMESTAMP(0),
+    endtime     TIMESTAMP(0),
+    vaso_rate   DOUBLE PRECISION,
+    vaso_amount DOUBLE PRECISION
+);
+
+-- 4. All-time pivots feeding hourly SOFA.
+DROP TABLE IF EXISTS blood_gas_arterial;
+CREATE TABLE blood_gas_arterial (
+    subject_id        INTEGER,
+    hadm_id           INTEGER,
+    icustay_id        INTEGER,
+    charttime         TIMESTAMP(0),
+    specimen          VARCHAR(200),
+    specimen_pred     VARCHAR(200),
+    specimen_prob     DOUBLE PRECISION,
+    so2               DOUBLE PRECISION,
+    spo2              DOUBLE PRECISION,
+    po2               DOUBLE PRECISION,
+    pco2              DOUBLE PRECISION,
+    fio2_chartevents  DOUBLE PRECISION,
+    fio2              DOUBLE PRECISION,
+    aado2             DOUBLE PRECISION,
+    aado2_calc        DOUBLE PRECISION,
+    pao2fio2          DOUBLE PRECISION,
+    ph                DOUBLE PRECISION,
+    baseexcess        DOUBLE PRECISION,
+    bicarbonate       DOUBLE PRECISION,
+    totalco2          DOUBLE PRECISION,
+    hematocrit        DOUBLE PRECISION,
+    hemoglobin        DOUBLE PRECISION,
+    carboxyhemoglobin DOUBLE PRECISION,
+    methemoglobin     DOUBLE PRECISION,
+    chloride          DOUBLE PRECISION,
+    calcium           DOUBLE PRECISION,
+    temperature       DOUBLE PRECISION,
+    potassium         DOUBLE PRECISION,
+    sodium            DOUBLE PRECISION,
+    lactate           DOUBLE PRECISION,
+    glucose           DOUBLE PRECISION,
+    intubated         DOUBLE PRECISION,
+    tidalvolume       DOUBLE PRECISION,
+    ventilationrate   DOUBLE PRECISION,
+    ventilator        DOUBLE PRECISION,
+    peep              DOUBLE PRECISION,
+    o2flow            DOUBLE PRECISION,
+    requiredo2        DOUBLE PRECISION
+);
+
+DROP TABLE IF EXISTS gcs_all;
+CREATE TABLE gcs_all (
+    icustay_id    INTEGER,
+    charttime     TIMESTAMP(0),
+    gcs           DOUBLE PRECISION,
+    endotrachflag INTEGER
+);
+
+-- 5. Hourly SOFA pipeline.  Each measurement class is materialised
+--    into a narrow staging table keyed by (icustay_id, hr); these
+--    are kept (not dropped) so each stage can be inspected with
+--    EXPLAIN ANALYZE.
+
+-- 5a. Hourly grid (one row per ICU hour per stay).
+DROP TABLE IF EXISTS sofa_grid;
+CREATE TABLE sofa_grid (
+    subject_id INTEGER,
+    hadm_id    INTEGER,
+    icustay_id INTEGER,
+    hr         INTEGER,
+    starttime  TIMESTAMP(0),
+    endtime    TIMESTAMP(0)
+);
+
+-- 5b. MAP minimum within each hour.
+DROP TABLE IF EXISTS sofa_vs;
+CREATE TABLE sofa_vs (
+    icustay_id INTEGER,
+    hr         INTEGER,
+    meanbp_min DOUBLE PRECISION
+);
+
+-- 5c. GCS minimum within each hour (from gcs_all, which already has
+--     the carry-forward and ET-trach=15 rules applied).
+DROP TABLE IF EXISTS sofa_gcs;
+CREATE TABLE sofa_gcs (
+    icustay_id INTEGER,
+    hr         INTEGER,
+    gcs_min    DOUBLE PRECISION
+);
+
+-- 5d. Bilirubin maximum within each hour.
+DROP TABLE IF EXISTS sofa_bili;
+CREATE TABLE sofa_bili (
+    icustay_id    INTEGER,
+    hr            INTEGER,
+    bilirubin_max DOUBLE PRECISION
+);
+
+-- 5e. Creatinine maximum within each hour.
+DROP TABLE IF EXISTS sofa_cr;
+CREATE TABLE sofa_cr (
+    icustay_id     INTEGER,
+    hr             INTEGER,
+    creatinine_max DOUBLE PRECISION
+);
+
+-- 5f. Platelet minimum within each hour.
+DROP TABLE IF EXISTS sofa_plt;
+CREATE TABLE sofa_plt (
+    icustay_id   INTEGER,
+    hr           INTEGER,
+    platelet_min DOUBLE PRECISION
+);
+
+-- 5g. PaO2/FiO2: split into vent / no-vent based on whether an
+--     active ventilation episode covered the blood gas.
+DROP TABLE IF EXISTS sofa_pf;
+CREATE TABLE sofa_pf (
+    icustay_id      INTEGER,
+    hr              INTEGER,
+    pao2fio2_novent DOUBLE PRECISION,
+    pao2fio2_vent   DOUBLE PRECISION
+);
+
+-- 5h. Urine output rolling sum + count of distinct charted hours
+--     within the past 24 h.
+DROP TABLE IF EXISTS sofa_uo;
+CREATE TABLE sofa_uo (
+    icustay_id INTEGER,
+    hr         INTEGER,
+    uo_24hr    DOUBLE PRECISION,
+    uo_tm_24hr BIGINT
+);
+
+-- 5i. Vasopressor rate snapshot at the hour boundary.
+DROP TABLE IF EXISTS sofa_vaso;
+CREATE TABLE sofa_vaso (
+    icustay_id          INTEGER,
+    hr                  INTEGER,
+    rate_epinephrine    DOUBLE PRECISION,
+    rate_norepinephrine DOUBLE PRECISION,
+    rate_dopamine       DOUBLE PRECISION,
+    rate_dobutamine     DOUBLE PRECISION
+);
+
+-- 5j. Wide assembly: grid LEFT JOINed onto every measurement table.
+DROP TABLE IF EXISTS sofa_wide;
+CREATE TABLE sofa_wide (
+    subject_id          INTEGER,
+    hadm_id             INTEGER,
+    icustay_id          INTEGER,
+    hr                  INTEGER,
+    starttime           TIMESTAMP(0),
+    endtime             TIMESTAMP(0),
+    meanbp_min          DOUBLE PRECISION,
+    gcs_min             DOUBLE PRECISION,
+    bilirubin_max       DOUBLE PRECISION,
+    creatinine_max      DOUBLE PRECISION,
+    platelet_min        DOUBLE PRECISION,
+    pao2fio2_novent     DOUBLE PRECISION,
+    pao2fio2_vent       DOUBLE PRECISION,
+    uo_24hr             DOUBLE PRECISION,
+    uo_tm_24hr          BIGINT,
+    rate_epinephrine    DOUBLE PRECISION,
+    rate_norepinephrine DOUBLE PRECISION,
+    rate_dopamine       DOUBLE PRECISION,
+    rate_dobutamine     DOUBLE PRECISION
+);
+
+-- 5k. Per-hour component scores (no rolling window yet).
+DROP TABLE IF EXISTS sofa_components;
+CREATE TABLE sofa_components (
+    subject_id          INTEGER,
+    hadm_id             INTEGER,
+    icustay_id          INTEGER,
+    hr                  INTEGER,
+    starttime           TIMESTAMP(0),
+    endtime             TIMESTAMP(0),
+    meanbp_min          DOUBLE PRECISION,
+    gcs_min             DOUBLE PRECISION,
+    bilirubin_max       DOUBLE PRECISION,
+    creatinine_max      DOUBLE PRECISION,
+    platelet_min        DOUBLE PRECISION,
+    pao2fio2_novent     DOUBLE PRECISION,
+    pao2fio2_vent       DOUBLE PRECISION,
+    uo_24hr             DOUBLE PRECISION,
+    uo_tm_24hr          BIGINT,
+    rate_epinephrine    DOUBLE PRECISION,
+    rate_norepinephrine DOUBLE PRECISION,
+    rate_dopamine       DOUBLE PRECISION,
+    rate_dobutamine     DOUBLE PRECISION,
+    respiration         INTEGER,
+    coagulation         INTEGER,
+    liver               INTEGER,
+    cardiovascular      INTEGER,
+    cns                 INTEGER,
+    renal               INTEGER
+);
+
+-- 5l. Final hourly SOFA: 24-hour rolling MAX per component, summed.
+DROP TABLE IF EXISTS sofa_hourly;
+CREATE TABLE sofa_hourly (
+    subject_id             INTEGER,
+    hadm_id                INTEGER,
+    icustay_id             INTEGER,
+    hr                     INTEGER,
+    starttime              TIMESTAMP(0),
+    endtime                TIMESTAMP(0),
+    respiration            INTEGER,
+    coagulation            INTEGER,
+    liver                  INTEGER,
+    cardiovascular         INTEGER,
+    cns                    INTEGER,
+    renal                  INTEGER,
+    respiration_24hours    INTEGER,
+    coagulation_24hours    INTEGER,
+    liver_24hours          INTEGER,
+    cardiovascular_24hours INTEGER,
+    cns_24hours            INTEGER,
+    renal_24hours          INTEGER,
+    sofa_24hours           INTEGER
+);
+
+-- 6. Suspicion of infection.
+DROP TABLE IF EXISTS antibiotic;
+CREATE TABLE antibiotic (
+    subject_id INTEGER,
+    hadm_id    INTEGER,
+    icustay_id INTEGER,
+    antibiotic VARCHAR(255),
+    route      VARCHAR(120),
+    -- MIMIC-III prescriptions has DATE-precision startdate / enddate
+    -- (stored as TIMESTAMP(0) but always at 00:00:00).
+    starttime  TIMESTAMP(0),
+    stoptime   TIMESTAMP(0)
+);
+
+DROP TABLE IF EXISTS suspicion_of_infection;
+CREATE TABLE suspicion_of_infection (
+    subject_id               INTEGER,
+    icustay_id               INTEGER,
+    hadm_id                  INTEGER,
+    ab_id                    BIGINT,
+    antibiotic               VARCHAR(255),
+    antibiotic_time          TIMESTAMP,
+    suspected_infection      INTEGER,
+    suspected_infection_time TIMESTAMP,
+    culture_time             TIMESTAMP,
+    specimen                 VARCHAR(100),
+    positive_culture         INTEGER
+);
+
+-- 7. Final Sepsis-3 onset table (one row per ICU stay).
+DROP TABLE IF EXISTS sepsis3;
+CREATE TABLE sepsis3 (
+    subject_id               INTEGER,
+    icustay_id               INTEGER,
+    antibiotic_time          TIMESTAMP,
+    culture_time             TIMESTAMP,
+    suspected_infection_time TIMESTAMP,
+    sofa_time                TIMESTAMP(0),
+    sofa_score               INTEGER,
+    respiration              INTEGER,
+    coagulation              INTEGER,
+    liver                    INTEGER,
+    cardiovascular           INTEGER,
+    cns                      INTEGER,
+    renal                    INTEGER,
+    sepsis3                  BOOLEAN
+);