The Demands of Surgery Residency: More Than Just Duty Hours?

INTRODUCTION: Efforts to improve surgical resident well-being could be accelerated with an improved understanding of resident job demands and resources. In this study, we sought to obtain a clearer picture of surgery resident job demands by assessing how residents distribute their time both inside and outside of the hospital. Furthermore, we aimed to elucidate residents' perceptions about current duty hour regulations. METHODS: A cross-sectional survey was sent to 1098 surgical residents at 27 US programs. Responses regarding work hours, demographics, well-being (utilizing the physician well-being index), and perceptions of duty hours in relation to education and rest, were collected. Data were evaluated using descriptive statistics and content analysis. RESULTS: A total of 163 residents (14.8% response rate) were included in the study. Residents reported a median total patient care hours per week of 78.0 h. Trainees spent 12.5 h on other professional activities. Greater than 40% of residents were "at risk" for depression and suicide based on physician well-being index scores. Four major themes associated with education and rest were identified: 1) duty hour definitions and reporting mechanisms do not completely reflect the amount of work residents perform, 2) quality patient care and educational opportunities do not fit neatly within the duty hour framework, 3) resident perceptions of duty hours are impacted the educational environment, and 4) long work hours and lack of adequate rest negatively affect well-being. CONCLUSIONS: The breadth and depth of trainee job demands are not accurately captured by current duty hour reporting mechanisms, and residents do not believe that their current work hours allow for adequate rest or even completion of other clinical or academic tasks outside of the hospital. Many residents are unwell. Duty hour policies and resident well-being may be improved with a more holistic accounting of resident job demands and greater attention to the resources that residents have to offset those demands.

Natural Language Processing to Estimate Clinical Competency Committee Ratings.

OBJECTIVE: Residency program faculty participate in clinical competency committee (CCC) meetings, which are designed to evaluate residents' performance and aid in the development of individualized learning plans. In preparation for the CCC meetings, faculty members synthesize performance information from a variety of sources. Natural language processing (NLP), a form of artificial intelligence, might facilitate these complex holistic reviews. However, there is little research involving the application of this technology to resident performance assessments. With this study, we examine whether NLP can be used to estimate CCC ratings. DESIGN: We analyzed end-of-rotation assessments and CCC assessments for all surgical residents who trained at one institution between 2014 and 2018. We created models of end-of-rotation assessment ratings and text to predict dichotomized CCC assessment ratings for 16 Accreditation Council for Graduate Medical Education (ACGME) Milestones. We compared the performance of models with and without predictors derived from NLP of end-of-rotation assessment text. RESULTS: We analyzed 594 end-of-rotation assessments and 97 CCC assessments for 24 general surgery residents. The mean (standard deviation) for area under the receiver operating characteristic curve (AUC) was 0.84 (0.05) for models with only non-NLP predictors, 0.83 (0.06) for models with only NLP predictors, and 0.87 (0.05) for models with both NLP and non-NLP predictors. CONCLUSIONS: NLP can identify language correlated with specific ACGME Milestone ratings. In preparation for CCC meetings, faculty could use information automatically extracted from text to focus attention on residents who might benefit from additional support and guide the development of educational interventions.