Research published in the Canadian Medical Association Journal highlights the potential of risk prediction tools in identifying patients at high risk of overdose and death after being discharged from hospital against medical advice. Patients who leave hospital early, known as “before medically advised” (BMA) discharges, face significantly elevated risks. They are approximately twice as likely to die and around ten times more likely to experience an illicit drug overdose within the first 30 days following discharge.
Each year, about 500,000 people in the United States and 30,000 people in Canada opt for BMA discharges. According to Dr. Hiten Naik from the University of British Columbia, the development of two risk prediction models could enhance discussions between clinicians and patients regarding the implications of early discharge. These models aim to assess a patient’s risk of death from any cause and their likelihood of experiencing an illicit drug overdose, especially for those with a history of substance use.
Understanding the Risk Factors
The study analyzed data from British Columbia, focusing on two distinct cohorts. The first cohort, comprising 6,440 adults from the general population, revealed that death following a BMA discharge occurred less frequently than expected, with one death for every 63 BMA discharges. Key predictors of mortality included conditions such as multimorbidity, heart disease, and cancer.
The second cohort included 4,466 individuals with a history of substance use. Findings indicated that certain factors such as homelessness, reliance on income assistance, opioid use disorder, and a recent history of drug overdose significantly increased the risk of overdose after discharge. Specifically, the study noted that, among those with a substance use history, there was approximately one illicit drug overdose for every 19 BMA discharges within the same 30-day period.
Dr. Naik and his co-authors emphasize the critical opportunity this timeframe presents for overdose prevention strategies. They advocate for hospitals and healthcare systems to implement these prediction models to systematically identify high-risk patients and automatically enroll them in support programs.
Implications for Healthcare Systems
The authors suggest that by integrating these risk prediction models, healthcare providers can reduce uncertainty surrounding BMA discharges. This could alleviate some of the moral distress faced by clinicians when making decisions about patient discharges. “Calculating a specific patient’s risk, combined with clinical judgment and other risk scores, might help facilitate constructive discussions about the decision to initiate a BMA discharge,” Dr. Naik explains.
The study underscores the need for proactive measures in healthcare settings. By recognizing and addressing the heightened risks associated with early hospital discharge, healthcare systems can not only improve patient outcomes but also enhance the overall quality of care.
For more information, refer to the article titled “Predicting drug overdose and death after ‘before medically advised’ hospital discharge” published in the Canadian Medical Association Journal in 2025.
