Using deep learning-based natural language processing to identify reasons for statin nonuse in patients with atherosclerotic cardiovascular disease.
2022; 2: 88
Background: Statins conclusively decrease mortality in atherosclerotic cardiovascular disease (ASCVD), the leading cause of death worldwide, and are strongly recommended by guidelines. However, real-world statin utilization and persistence are low, resulting in excess mortality. Identifying reasons for statin nonuse at scale across health systems is crucial to developing targeted interventions to improve statin use.Methods: We developed and validated deep learning-based natural language processing (NLP) approaches (Clinical Bidirectional Encoder Representations from Transformers [BERT]) to classify statin nonuse and reasons for statin nonuse using unstructured electronic health records (EHRs) from a diverse healthcare system.Results: We present data from a cohort of 56,530 ASCVD patients, among whom 21,508 (38%) lack guideline-directed statin prescriptions and statins listed as allergies in structured EHR portions. Of these 21,508 patients without prescriptions, only 3,929 (18%) have any discussion of statin use or nonuse in EHR documentation. The NLP classifiers identify statin nonuse with an area under the curve (AUC) of 0.94 (95% CI 0.93-0.96) and reasons for nonuse with a weighted-average AUC of 0.88 (95% CI 0.86-0.91) when evaluated against manual expert chart review in a held-out test set. Clinical BERT identifies key patient-level reasons (side-effects, patient preference) and clinician-level reasons (guideline-discordant practices) for statin nonuse, including differences by type of ASCVD and patient race/ethnicity.Conclusions: Our deep learning NLP classifiers can identify crucial gaps in statin nonuse and reasons for nonuse in high-risk populations to support education, clinical decision support, and potential pathways for health systems to address ASCVD treatment gaps.
View details for DOI 10.1038/s43856-022-00157-w
View details for PubMedID 35856080
IDENTIFYING REASONS FOR STATIN NONADHERENCE IN A DIVERSE, REAL-WORLD POPULATION USING ELECTRONIC HEALTH RECORDS AND NATURAL LANGUAGE PROCESSING
ELSEVIER SCIENCE INC. 2021: 1665
View details for Web of Science ID 000647487501671
Medical Student Values Inform Career Plans in Service & Surgery-A Qualitative Focus Group Analysis.
The Journal of surgical research
2020; 256: 636–44
Diversifying the surgical workforce is a critical component of improving care for underserved patients. To recruit surgeons from diverse backgrounds, we must understand how medical students choose their specialty. We investigate how preclinical students contemplate entering a surgical field.We conducted semistructured focus groups during two iterations of a seminar class called Service Through Surgery. Discussion goals included identifying student values and assessing how they inform early career decisions. We used a systematic, collaborative, and iterative process for transcript analysis, including developing a codebook, assessing inter-rater reliability, and analyzing themes.Twenty-four preclinical medical students from diverse backgrounds participated in seven focus groups; most were women (16; 67%), in their first year of medical school (19; 79%), and interested in surgery (17; 71%). Participants ranked professional fulfillment, spending time with family, and serving their communities and/or underserved populations among their most important values and agreed that conducting groundbreaking research, working long hours, and finding time for leisure activities were the least important. We constructed a framework to describe student responses surrounding their diverse visions for service in future surgical careers through individual doctoring interactions, roles in academia, and broader public service.Our framework provides a basis for greater understanding and study of the ways in which preclinical medical students think about their personal values and visions for service in potential future surgical careers. This research can guide early interventions in medical education to promote diversity and care for the underserved in surgery.
View details for DOI 10.1016/j.jss.2020.07.030
View details for PubMedID 32810664