Understanding physicians' work via text analytics on EHR inbox messages.

OBJECTIVES: To develop a text analytics methodology to analyze in a refined manner the drivers of primary care physicians' (PCPs') electronic health record (EHR) inbox work. STUDY DESIGN: This study used 1 year (2018) of EHR inbox messages obtained from the Epic system for 184 PCPs from 18 practices. METHODS: An advanced text analytics latent Dirichlet allocation model was trained on physicians' inbox message texts to identify the different work themes managed by physicians and their relative share of workload across physicians and clinics. RESULTS: The text analytics model identified 30 different work themes rolled up into 2 categories of medical and administrative tasks. We found that 50.8% (range across physicians, 34.5%-61.9%) of the messages were concerned with medical issues and 34.1% (range, 23.0%-48.9%) focused on administrative matters. More specifically, 13.6% (range, 7.1%-22.6%) of the messages involved ambiguous diagnosis issues, 13.2% (range, 6.9%-18.8%) involved condition management issues, 6.7% (range, 1.9%-13.4%) involved identified symptoms issues, 9.5% (range, 5.2%-28.9%) involved paperwork issues, and 17.6% (range, 9.3%-27.1%) involved scheduling issues. Additionally, there was significant variability among physicians and practices. CONCLUSIONS: This study demonstrated that advanced text analytics provide a reliable data-driven methodology to understand the individual physician's EHR inbox management work with a significantly greater level of detail than previous approaches. This methodology can inform decision makers on appropriate workflow redesign to eliminate unnecessary workload on PCPs and to improve cost and quality of care, as well as staff work satisfaction.

Understanding Physician Work and Well-being Through Social Network Modeling Using Electronic Health Record Data: a Cohort Study.

BACKGROUND: Understanding association between factors related to clinical work environment and well-being can inform strategies to improve physicians' work experience. OBJECTIVE: To model and quantify what drivers of work composition, team structure, and dynamics are associated with well-being. DESIGN: Utilizing social network modeling, this cohort study of physicians in an academic health center examined inbasket messaging data from 2018 to 2019 to identify work composition, team structure, and dynamics features. Indicators from a survey in 2019 were used as dependent variables to identify factors predictive of well-being. PARTICIPANTS: EHR data available for 188 physicians and their care teams from 18 primary care practices; survey data available for 163/188 physicians. MAIN MEASURES: Area under the receiver operating characteristic curve (AUC) of logistic regression models to predict well-being dependent variables was assessed out-of-sample. KEY RESULTS: The mean AUC of the model for the dependent variables of emotional exhaustion, vigor, and professional fulfillment was, respectively, 0.665 (SD 0.085), 0.700 (SD 0.082), and 0.669 (SD 0.082). Predictors associated with decreased well-being included physician centrality within support team (OR 3.90, 95% CI 1.28-11.97, P=0.01) and share of messages related to scheduling (OR 1.10, 95% CI 1.03-1.17, P=0.003). Predictors associated with increased well-being included higher number of medical assistants within close support team (OR 0.91, 95% CI 0.83-0.99, P=0.05), nurse-centered message writing practices (OR 0.89, 95% CI 0.83-0.95, P=0.001), and share of messages related to ambiguous diagnosis (OR 0.92, 95% CI 0.87-0.98, P=0.01). CONCLUSIONS: Through integration of EHR data with social network modeling, the analysis highlights new characteristics of care team structure and dynamics that are associated with physician well-being. This quantitative methodology can be utilized to assess in a refined data-driven way the impact of organizational changes to improve well-being through optimizing team dynamics and work composition.

Block coordinate descent algorithm improves variable selection and estimation in error-in-variables regression.

Medical research increasingly includes high-dimensional regression modeling with a need for error-in-variables methods. The Convex Conditioned Lasso (CoCoLasso) utilizes a reformulated Lasso objective function and an error-corrected cross-validation to enable error-in-variables regression, but requires heavy computations. Here, we develop a Block coordinate Descent Convex Conditioned Lasso (BDCoCoLasso) algorithm for modeling high-dimensional data that are only partially corrupted by measurement error. This algorithm separately optimizes the estimation of the uncorrupted and corrupted features in an iterative manner to reduce computational cost, with a specially calibrated formulation of cross-validation error. Through simulations, we show that the BDCoCoLasso algorithm successfully copes with much larger feature sets than CoCoLasso, and as expected, outperforms the naïve Lasso with enhanced estimation accuracy and consistency, as the intensity and complexity of measurement errors increase. Also, a new smoothly clipped absolute deviation penalization option is added that may be appropriate for some data sets. We apply the BDCoCoLasso algorithm to data selected from the UK Biobank. We develop and showcase the utility of covariate-adjusted genetic risk scores for body mass index, bone mineral density, and lifespan. We demonstrate that by leveraging more information than the naïve Lasso in partially corrupted data, the BDCoCoLasso may achieve higher prediction accuracy. These innovations, together with an R package, BDCoCoLasso, make error-in-variables adjustments more accessible for high-dimensional data sets. We posit the BDCoCoLasso algorithm has the potential to be widely applied in various fields, including genomics-facilitated personalized medicine research.