t2a_v2/t2a_install_rag_cleanup/src/quality/decision_engine.py

"""Moteur de décisions (post-traitement qualité).

But: conserver la proposition du modèle (cim10_suggestion) tout en produisant une
*sortie finale* plus défendable (cim10_final + cim10_decision).

Ce module est déterministe, court, et auditable.
"""

from __future__ import annotations

import re
import unicodedata
from typing import Optional

from ..config import CodeDecision, Diagnostic, DossierMedical


# --- Règles "étiologiques" : ne pas affirmer sans preuve spécifique ---

IRON_MARKERS = (
    "ferrit",  # ferritine
    "transferr",  # transferrine
    "saturation",  # saturation transferrine
    "cst",  # coefficient de saturation
    "carence mart",
    "martiale",
    "ferripr",  # ferriprive
    "fer intraveineux",
    "fer iv",
    "traitement martial",
)


def _norm(s: str) -> str:
    s = s.replace("’", "'")
    s = unicodedata.normalize("NFKD", s)
    s = "".join(ch for ch in s if not unicodedata.combining(ch))
    s = s.lower()
    return re.sub(r"\s+", " ", s).strip()


def _first_float(text: str) -> Optional[float]:
    m = re.search(r"(-?\d+(?:[\.,]\d+)?)", text)
    if not m:
        return None
    return float(m.group(1).replace(",", "."))


def _parse_normal_range(text: str) -> tuple[Optional[float], Optional[float]]:
    # Ex: "[N: 12-17]" / "[N: 12 - 17]"
    m = re.search(r"\[\s*N\s*:\s*([0-9]+(?:[\.,][0-9]+)?)\s*-\s*([0-9]+(?:[\.,][0-9]+)?)\s*\]", text)
    if not m:
        return None, None
    lo = float(m.group(1).replace(",", "."))
    hi = float(m.group(2).replace(",", "."))
    return lo, hi


def _anemia_bio(diag: Diagnostic) -> bool:
    # 1) via preuves_cliniques (souvent déjà interprétées)
    for p in diag.preuves_cliniques or []:
        blob = f"{p.element} {p.interpretation}".lower()
        if "hemoglob" in blob or "hémoglob" in blob or blob.strip().startswith("hb"):
            val = _first_float(p.element) or _first_float(p.interpretation)
            lo, _ = _parse_normal_range(p.element)
            lo = lo if lo is not None else 12.0
            if val is not None and val < lo:
                return True
            if "confirm" in blob and "anemie" in blob:
                return True
    # 2) fallback : le texte mentionne une anémie chiffrée
    ex = _norm(diag.source_excerpt or "")
    if "hemoglob" in ex or "hémoglob" in ex:
        return True
    return False


def _iron_evidence_blob(dossier: DossierMedical, diag: Diagnostic) -> str:
    parts: list[str] = []

    # Preuves patient (extraits + éléments structurés)
    if diag.source_excerpt:
        parts.append(str(diag.source_excerpt))

    for p in diag.preuves_cliniques or []:
        parts.append(f"{p.element} {p.interpretation}")

    # Biologie clé globale (si ferritine/fer a été capté ailleurs)
    for b in dossier.biologie_cle or []:
        parts.append(f"{b.test} {b.valeur or ''}")

    # Traitements (si supplémentation martiale documentée)
    for t in dossier.traitements_sortie or []:
        parts.append(f"{t.medicament} {t.posologie or ''}")

    return _norm("\n".join(parts))


def apply_decisions(dossier: DossierMedical) -> None:
    """Applique des décisions finales sur DP/DAS.

    - Ne supprime pas la suggestion du modèle.
    - Remplit cim10_final systématiquement quand une suggestion existe.
    - Remplit cim10_decision uniquement si action != KEEP (pour garder le JSON lisible).
    """

    def _set_default_final(diag: Diagnostic):
        if diag.cim10_suggestion and diag.cim10_final is None:
            diag.cim10_final = diag.cim10_suggestion

    # DP
    if dossier.diagnostic_principal:
        _set_default_final(dossier.diagnostic_principal)

    # DAS
    for das in dossier.diagnostics_associes or []:
        _set_default_final(das)

    # --- Règle: D50 sans preuve martiale -> downgrade D64.9 + needs_info ---
    for das in dossier.diagnostics_associes or []:
        if das.cim10_suggestion != "D50":
            continue

        blob = _iron_evidence_blob(dossier, das)
        has_iron = any(m in blob for m in IRON_MARKERS)
        has_anemia = _anemia_bio(das)

        # Si on n'a même pas d'anémie biologique, on n'automatise pas.
        if not has_anemia:
            continue

        if not has_iron:
            das.cim10_final = "D64.9"
            das.cim10_decision = CodeDecision(
                action="DOWNGRADE",
                final_code="D64.9",
                downgraded_from="D50",
                reason="Anémie biologique sans preuve d'étiologie ferriprive (bilan martial absent/insuffisant).",
                needs_info=[
                    "Bilan martial disponible ? (ferritine, fer, CST/transferrine)",
                    "Mention explicite 'anémie ferriprive' ou carence martiale ?",
                    "Traitement martial (fer per os/IV) documenté ?",
                ],
                applied_rules=["RULE-D50-NEEDS-IRON"],
            )



def decision_summaries(dossier: DossierMedical) -> list[str]:
    """Retourne une liste de lignes lisibles à injecter dans alertes_codage."""
    lines: list[str] = []

    def _summ(where: str, d: Diagnostic):
        dec = d.cim10_decision
        if not dec or dec.action == "KEEP":
            return
        if dec.action == "DOWNGRADE":
            lines.append(f"DECISION: {where} {dec.downgraded_from}→{dec.final_code} ({', '.join(dec.applied_rules)})")
            for ni in dec.needs_info[:3]:
                lines.append(f"DECISION:   besoin_info: {ni}")
        elif dec.action == "REMOVE":
            lines.append(f"DECISION: {where} {d.cim10_suggestion} supprimé ({', '.join(dec.applied_rules)})")

    if dossier.diagnostic_principal:
        _summ("diagnostic_principal", dossier.diagnostic_principal)

    for i, das in enumerate(dossier.diagnostics_associes or []):
        _summ(f"diagnostics_associes[{i}]", das)

    return lines