Model Predicts Poor Outcomes Within 30 Days of a Before Medically Advised Discharge

THURSDAY, Nov. 20, 2025 (HealthDay News) -- A model may predict death or illicit drug overdose within 30 days of a before medically advised (BMA) discharge, according to a study published online Nov. 11 in CMAJ, the journal of the Canadian Medical Association.Hiten Naik, M.D., from the University of British Columbia in Vancouver, Canada, and colleagues used retrospective population-based administrative health data from a random sample of all British Columbia residents to derive and internally validate regression models to estimate the risks for death for 30-day post-BMA discharge (2015 to 2019) after 6,440 nonelective, nonobstetrical adult hospitalizations (model A) and illicit drug overdose for 4,466 hospitalizations in those with evidence of prior substance use (model B).The researchers found that in model A, 1.6 percent of discharges were associated with the death of a patient within 30 days of BMA discharge, which was predicted by a Charlson Comorbidity Index of 2 or higher, cancer, and heart disease. There was good discrimination (C-statistic = 0.78) and excellent calibration. In model B, 5.2 percent of hospitalizations were associated with a patient subsequently overdosing within 30 days of BMA discharge, which was predicted by homelessness, receipt of social income assistance, opioid use disorder, nonalcohol substance use disorder, overdose in the past year, and discharge from a surgical service. Model B also showed good discrimination (C-statistic = 0.79) and excellent calibration."By reducing uncertainty, risk estimates might also reduce clinician moral distress when faced with a BMA discharge," Naik said in a statement.Abstract/Full Text.Sign up for our weekly HealthDay newsletter

Model Predicts Poor Outcomes Within 30 Days of a Before Medically Advised Discharge

Related Stories

Endometriosis Linked to Increased Risk for Congenital Anomalies

AI Model IDs Pancreatic Ductal Adenocarcinoma at Prediagnostic Stage

Model Provides Well-Calibrated Risk Estimates for First Metachronous cSCC

AI Model of Retinal Age Can Predict Clinical Aging