Patient Risk Stratification

Mortality Prediction

Logistic Regression

APACHE Scoring

import numpy as np

class MortalityPredictor:
    def __init__(self, n_features):
        self.weights = np.random.randn(n_features) * 0.01
        self.bias = 0.0

    def predict_proba(self, X):
        z = X @ self.weights + self.bias
        return 1 / (1 + np.exp(-z))

    def compute_apache(self, phys_vars, age_score, chronic_score):
        phys_score = sum(4 for k, v in phys_vars.items()
                        if k in ('heart_rate', 'respiratory_rate', 'sodium')
                        and (v > 140 or v < 50))
        return phys_score + age_score + chronic_score

Readmission Risk Scoring

LACE Index

class ReadmissionScorer:
    def compute_lace(self, los, acute_discharge, charlson, ed_visits):
        return (1 if los > 4 else 0) + (1 if acute_discharge else 0) +                (1 if charlson > 3 else 0) + min(ed_visits, 5) * 0.5

    def predict(self, lace_score):
        if lace_score >= 10: return 'high_risk'
        elif lace_score >= 7: return 'moderate_risk'
        return 'low_risk'

Early Warning Systems

MEWS (Modified Early Warning Score)

Survival Analysis

Cox Proportional Hazards

Risk Stratification Bands

Evaluation