Cannabis, cocaine, methamphetamine, and opiates increase the risk of incident atrial fibrillation.

AIMS: Atrial fibrillation (AF) is now regarded as a preventable disease, requiring a search for modifiable risk factors. With legalization of cannabis and more lenient laws regarding the use of other illicit substances, investigation into the potential effects of methamphetamine, cocaine, opiate, and cannabis exposure on incident AF is needed. METHODS AND RESULTS: Using Office of Statewide Health Planning and Development databases, a longitudinal analysis was performed of adult Californians ≥18 years of age who received care in an emergency department, outpatient surgery facility, or hospital from 1 January 2005 to 31 December 2015. Associations between healthcare coding for the use of each substance and a new AF diagnosis were assessed. Among 23,561,884 patients, 98 271 used methamphetamine, 48 701 used cocaine, 10 032 used opiates, and 132 834 used cannabis. Of the total population, 998 747 patients (4.2%) developed incident AF during the study period. After adjusting for potential confounders and mediators, use of methamphetamines, cocaine, opiates, and cannabis was each associated with increased incidence of AF: hazard ratios 1.86 [95% confidence interval (CI) 1.81-1.92], 1.61 (95% CI 1.55-1.68), 1.74 (95% CI 1.62-1.87), and 1.35 (95% CI 1.30-1.40), respectively. Negative control analyses in the same cohort failed to reveal similarly consistent positive relationships. CONCLUSION: Methamphetamine, cocaine, opiate, and cannabis uses were each associated with increased risk of developing incident AF. Efforts to mitigate the use of these substances may represent a novel approach to AF prevention.

Integrating a Machine Learning System Into Clinical Workflows: Qualitative Study.

BACKGROUND: Machine learning models have the potential to improve diagnostic accuracy and management of acute conditions. Despite growing efforts to evaluate and validate such models, little is known about how to best translate and implement these products as part of routine clinical care. OBJECTIVE: This study aims to explore the factors influencing the integration of a machine learning sepsis early warning system (Sepsis Watch) into clinical workflows. METHODS: We conducted semistructured interviews with 15 frontline emergency department physicians and rapid response team nurses who participated in the Sepsis Watch quality improvement initiative. Interviews were audio recorded and transcribed. We used a modified grounded theory approach to identify key themes and analyze qualitative data. RESULTS: A total of 3 dominant themes emerged: perceived utility and trust, implementation of Sepsis Watch processes, and workforce considerations. Participants described their unfamiliarity with machine learning models. As a result, clinician trust was influenced by the perceived accuracy and utility of the model from personal program experience. Implementation of Sepsis Watch was facilitated by the easy-to-use tablet application and communication strategies that were developed by nurses to share model outputs with physicians. Barriers included the flow of information among clinicians and gaps in knowledge about the model itself and broader workflow processes. CONCLUSIONS: This study generated insights into how frontline clinicians perceived machine learning models and the barriers to integrating them into clinical workflows. These findings can inform future efforts to implement machine learning interventions in real-world settings and maximize the adoption of these interventions.