Burnout in Pediatric Emergency Medicine Physicians: A Predictive Model.

OBJECTIVES: This study aims to determine the prevalence of and identify predictors associated with burnout in pediatric emergency medicine (PEM) physicians and to construct a predictive model for burnout in this population to stratify risk. METHODS: We conducted a cross-sectional electronic survey study among a random sample of board-certified or board-eligible PEM physicians throughout the United States and Canada. Our primary outcome was burnout assessed using the Maslach Burnout Inventory on 3 subscales: emotional exhaustion, depersonalization, and personal accomplishment. We defined burnout as scoring in the high-degree range on any 1 of the 3 subscales. The Maslach Burnout Inventory was followed by questions on personal demographics and work environment. We compared PEM physicians with and without burnout using multivariable logistic regression. RESULTS: We studied a total of 416 PEM board-certified/eligible physicians (61.3% women; mean age, 45.3 ± 8.8 years). Surveys were initiated by 445 of 749 survey recipients (59.4% response rate). Burnout prevalence measured 49.5% (206/416) in the study cohort, with 34.9% (145/416) of participants scoring in the high-degree range for emotional exhaustion, 33.9% (141/416) for depersonalization, and 20% (83/416) for personal accomplishment. A multivariable model identified 6 independent predictors associated with burnout: 1) lack of appreciation from patients, 2) lack of appreciation from supervisors, 3) perception of an unfair clinical work schedule, 4) dissatisfaction with promotion opportunities, 5) feeling that the electronic medical record detracts from patient care, and 6) working in a nonacademic setting (area under the receiver operating characteristic curve, 0.77). A predictive model demonstrated that physicians with 5 or 6 predictors had an 81% probability of having burnout, whereas those with zero predictors had a 28% probability of burnout. CONCLUSIONS: Burnout is prevalent in PEM physicians. We identified 6 independent predictors for burnout and constructed a scoring system that stratifies probability of burnout. This predictive model may be used to guide organizational strategies that mitigate burnout and improve physician well-being.

Predicting frequent emergency department visits among children with asthma using EHR data.

OBJECTIVE: For children with asthma, emergency department (ED) visits are common, expensive, and often avoidable. Though several factors are associated with ED use (demographics, comorbidities, insurance, medications), its predictability using electronic health record (EHR) data is understudied. METHODS: We used a retrospective cohort study design and EHR data from one center to examine the relationship of patient factors in 1 year (2013) and the likelihood of frequent ED use (≥2 visits) in the following year (2014), using bivariate and multivariable statistics. We applied and compared several machine-learning algorithms to predict frequent ED use, then selected a model based on accuracy, parsimony, and interpretability. RESULTS: We identified 2691 children. In bivariate analyses, future frequent ED use was associated with demographics, co-morbidities, insurance status, medication history, and use of healthcare resources. Machine learning algorithms had very good AUC (area under the curve) values [0.66-0.87], though fair PPV (positive predictive value) [48-70%] and poor sensitivity [16-27%]. Our final multivariable logistic regression model contained two variables: insurance status and prior ED use. For publicly insured patients, the odds of frequent ED use were 3.1 [2.2-4.5] times that of privately insured patients. Publicly insured patients with 4+ ED visits and privately insured patients with 6+ ED visits in a year had ≥50% probability of frequent ED use the following year. The model had an AUC of 0.86, PPV of 56%, and sensitivity of 23%. CONCLUSION: Among children with asthma, prior frequent ED use and insurance status strongly predict future ED use.