Harnessing Patient Life Stories to Engage Medical Trainees in Strengthening Veteran-Provider Relationships
Abstract: Medical trainees do not have many opportunities to develop communication skills with patients. We established the voluntary “My Life, My Story” (MLMS) program at the Clement J. Zablocki VAMC in Milwaukee, WI, to determine if this pilot narrative medicine program enhanced trainee interpersonal skills and improved patient-centered care. Trainees at the Medical College of Wisconsin conducted in-person or virtual interviews of Veterans receiving care at the Milwaukee VAMC about their meaningful life experiences. Post-interview, trainees wrote a short first-person narrative in the Veteran’s voice, which, after the Veteran’s approval, was added to the electronic medical record and made available to the patient’s care team. Trainees, Veterans, and health professionals completed post-interview surveys, from which we conducted descriptive statistics and qualitatively analyzed the text-based feedback. Between 2020 and 2021, 24 medical trainees participated in our pilot implementation of the MLMS program, conducting a total of 32 interviews. All trainees reported a meaningful personal impact and found the pilot to be “valuable” and “rewarding.” Both trainees and health professionals believed that the MLMS program improved “rapport building” with Veterans. Nearly all Veterans (n = 25, 93%) believed that their medical care team would be able to provide better care after reading their life story. Narrative medicine initiatives like the MLMS program may enable value-added education for trainees. Future research will allow us to better understand and maximize specific educational gains, while further enhancing patient care.
Abstract: Novel and automated means of opioid use and relapse risk detection are needed. Unstructured electronic medical record data, including written progress notes, can be mined for clinically relevant information, including the presence of substance use and relapse-critical markers of risk and recovery from opioid use disorder (OUD). In this study, we used natural language processing (NLP) to automate the extraction of opioid relapses, and the timing of these occurrences, from veteran patients' electronic medical record. We then demonstrated the utility of our NLP tool via analysis of pre-/post-COVID-19 opioid relapse trends among veterans with OUD. For this demonstration, we analyzed data from 107,606 veterans OUD enrolled in Veterans Health Administration, comparing a pandemic-exposed cohort (n = 53,803; January 2019-March 2021) to a matched prepandemic cohort (n = 53,803; October 2017-December 2019). The recall of our NLP tool was 75% and our precision was 94%, demonstrating moderate sensitivity and excellent specificity. Using the NLP tool, we found that the odds of opioid relapse postpandemic onset were proportionally higher compared to prepandemic trends, despite patients having fewer mental health encounters from which to derive instances of relapse postpandemic onset. In this research application of the tool, and as hypothesized, we found that opioid relapse risk was elevated postpandemic. The application of NLP Methods: to identify and monitor relapse risk holds promise for future surveillance, risk prevention, and clinical outcome research.