Back to Marketplace
Model
v4.1.0
FHIR R4 Validated
HIPAA Ready

Hospital Readmission Risk Predictor

FHIR-native ML model predicting 30-day readmission risk at discharge

by HealthData Labs
4.8(221 reviews)
3,800 deployments

About

Our Hospital Readmission Risk Predictor uses an ensemble of gradient boosting and transformer models trained on 18.4 million inpatient discharges across 340 US hospitals. The model ingests FHIR R4 resources including Encounter, Condition, MedicationRequest, Procedure, Observation, and Patient demographics to generate a 0–100 risk score at point of discharge. It outperforms LACE+ by 18% AUROC on external validation. The model includes fairness evaluations across race, ethnicity, and insurance status and is deployed as a CDS Hooks service compatible with Epic, Cerner, and athenahealth.

Key Features

  • 30-day all-cause readmission prediction (AUROC 0.84)
  • Natural language explanations for each risk score (SHAP values)
  • CDS Hooks integration for real-time EHR alerts
  • Fairness-audited across race, ethnicity, payer, and age

0.84

Model AUROC

+18%

vs LACE+

18.4M

Training Discharges

< 200ms

Prediction Latency

< 2%

Bias Disparity (race)

340

Hospitals Validated

HIPAA BAA included with all enterprise plans

Compliance

HIPAA BAA
SOC 2 Type II
FDA Pre-Submission Reviewed
ONC Certified

Tags

Readmission
Predictive Analytics
FHIR R4
CDS Hooks
ML Model
Population Health
CategoryPredictive Analytics
Versionv4.1.0
UpdatedDec 1, 2025
FHIR VersionR4