A recent study published in the Canadian Medical Association Journal has revealed that risk prediction tools could significantly aid in identifying patients most vulnerable to overdose and death following a “before medically advised” (BMA) discharge from hospitals. The research indicates that individuals who leave a medical facility against physician advice are approximately twice as likely to die and ten times more likely to experience an illicit drug overdose within the first 30 days after discharge.
Every year, around 500,000 patients in the United States and 30,000 in Canada opt for BMA discharges, often leaving healthcare providers concerned about their well-being. Dr. Hiten Naik from the University of British Columbia and co-authors argue that these risk prediction models, when combined with clinical judgment, can foster more informed discussions between healthcare professionals and patients regarding the implications of such decisions.
Understanding the Risk Factors
The study involved two distinct risk prediction models. The first model estimates the overall risk of death from any cause within 30 days after a BMA discharge. The second model specifically targets patients with a history of substance use, estimating their risk of illicit drug overdose during the same timeframe. Researchers evaluated two cohorts: cohort A, consisting of 6,440 adults from the general population, and cohort B, which included 4,466 individuals with a history of substance use.
Findings from cohort A indicated that deaths following BMA discharges were less frequent than anticipated, with a ratio of one death for every 63 discharges. Key predictors of mortality included multimorbidity, heart disease, and cancer. In contrast, cohort B highlighted significant risk factors for drug overdose, such as homelessness, reliance on income assistance, opioid use disorder, and previous overdose incidents within the past year.
Implications for Healthcare Systems
The authors emphasized that the period immediately following a BMA discharge presents a critical opportunity for overdose prevention, especially among patients with substance use histories. They noted that illicit drug overdose was notably prevalent, with approximately one overdose occurring for every 19 BMA discharges in this group.
To enhance patient support and safety, the study suggests that hospitals could incorporate these risk prediction models into their discharge protocols. Automating alerts and enrolling high-risk patients in support programs could be instrumental in mitigating potential risks associated with BMA discharges.
“These models offer a starting point for identifying patients who are high risk and may benefit from greater support,” the authors concluded.
The research underlines the importance of addressing the vulnerabilities faced by patients opting for BMA discharges and calls for systemic changes within healthcare frameworks to improve outcomes and reduce preventable fatalities.
Further details can be found in the study titled “Predicting drug overdose and death after ‘before medically advised’ hospital discharge,” published in the Canadian Medical Association Journal in 2025 (DOI: 10.1503/cmaj.250492).
