Literature DB >> 35134568

Predicting physician burnout using clinical activity logs: Model performance and lessons learned.

Sunny S Lou1, Hanyang Liu2, Benjamin C Warner2, Derek Harford1, Chenyang Lu2, Thomas Kannampallil3.   

Abstract

BACKGROUND: Burnout is a significant public health concern affecting more than half of the healthcare workforce; however, passive screening tools to detect burnout are lacking. We investigated the ability of machine learning (ML) techniques to identify burnout using passively collected electronic health record (EHR)-based audit log data.
METHOD: Physician trainees participated in a longitudinal study where they completed monthly burnout surveys and provided access to their EHR-based audit logs. Using the monthly burnout scores as the target outcome, we trained ML models using combinations of features derived from audit log data-aggregate measures of clinical workload, time series-based temporal measures of EHR use, and the baseline burnout score. Five ML models were constructed to predict burnout as a continuous score: penalized linear regression, support vector machine, neural network, random forest, and gradient boosting machine.
RESULTS: 88 trainee physicians participated and completed 416 surveys; greater than10 million audit log actions were collected (Mean [Standard Deviation] = 25,691 [14,331] actions per month, per physician). The workload feature set predicted burnout score with a mean absolute error (MAE) of 0.602 (95% Confidence Interval (CI), 0.412-0.826), and was able to predict burnout status with an average AUROC of 0.595 (95% CI 0.355-0.808) and average accuracy 0.567 (95% CI 0.393-0.742). The temporal feature set had a similar performance, with MAE 0.596 (95% CI 0.391-0.826), and AUROC 0.581 (95% CI 0.343-0.790). The addition of the baseline burnout score to the workload features improved the model performance to a mean AUROC of 0.829 (95% CI 0.607-0.996) and mean accuracy of 0.781 (95% CI 0.587-0.936); however, this performance was not meaningfully different than using the baseline burnout score alone.
CONCLUSIONS: Current findings illustrate the complexities of predicting burnout exclusively based on clinical work activities as captured in the EHR, highlighting its multi-factorial and individualized nature. Future prediction studies of burnout should account for individual factors (e.g., resilience, physiological measurements such as sleep) and associated system-level factors (e.g., leadership).
Copyright © 2022 Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Burnout; Clinical workload; Machine learning; Trainees; Wellness

Mesh:

Year:  2022        PMID: 35134568      PMCID: PMC8901565          DOI: 10.1016/j.jbi.2022.104015

Source DB:  PubMed          Journal:  J Biomed Inform        ISSN: 1532-0464            Impact factor:   6.317


  62 in total

1.  Task switching.

Authors:  Stephen Monsell
Journal:  Trends Cogn Sci       Date:  2003-03       Impact factor: 20.229

2.  Changes in Burnout and Satisfaction With Work-Life Balance in Physicians and the General US Working Population Between 2011 and 2014.

Authors:  Tait D Shanafelt; Omar Hasan; Lotte N Dyrbye; Christine Sinsky; Daniel Satele; Jeff Sloan; Colin P West
Journal:  Mayo Clin Proc       Date:  2015-12       Impact factor: 7.616

3.  Prevalence of burnout in the u.s. Oncology community: results of a 2003 survey.

Authors:  Carmen J Allegra; Ray Hall; Greg Yothers
Journal:  J Oncol Pract       Date:  2005-11       Impact factor: 3.840

4.  Impact of organizational leadership on physician burnout and satisfaction.

Authors:  Tait D Shanafelt; Grace Gorringe; Ronald Menaker; Kristin A Storz; David Reeves; Steven J Buskirk; Jeff A Sloan; Stephen J Swensen
Journal:  Mayo Clin Proc       Date:  2015-03-18       Impact factor: 7.616

5.  Association Between Physician Burnout and Patient Safety, Professionalism, and Patient Satisfaction: A Systematic Review and Meta-analysis.

Authors:  Maria Panagioti; Keith Geraghty; Judith Johnson; Anli Zhou; Efharis Panagopoulou; Carolyn Chew-Graham; David Peters; Alexander Hodkinson; Ruth Riley; Aneez Esmail
Journal:  JAMA Intern Med       Date:  2018-10-01       Impact factor: 21.873

6.  Burnout as a predictor of all-cause mortality among industrial employees: a 10-year prospective register-linkage study.

Authors:  Kirsi Ahola; Ari Väänänen; Aki Koskinen; Anne Kouvonen; Arie Shirom
Journal:  J Psychosom Res       Date:  2010-03-19       Impact factor: 3.006

7.  Measuring Electronic Health Record Use in the Pediatric ICU Using Audit-Logs and Screen Recordings.

Authors:  Amrita Sinha; Lindsay A Stevens; Felice Su; Natalie M Pageler; Daniel S Tawfik
Journal:  Appl Clin Inform       Date:  2021-08-11       Impact factor: 2.762

8.  Association of resident fatigue and distress with perceived medical errors.

Authors:  Colin P West; Angelina D Tan; Thomas M Habermann; Jeff A Sloan; Tait D Shanafelt
Journal:  JAMA       Date:  2009-09-23       Impact factor: 56.272

9.  Behavioral Indicators on a Mobile Sensing Platform Predict Clinically Validated Psychiatric Symptoms of Mood and Anxiety Disorders.

Authors:  Skyler Place; Danielle Blanch-Hartigan; Channah Rubin; Cristina Gorrostieta; Caroline Mead; John Kane; Brian P Marx; Joshua Feast; Thilo Deckersbach; Alex Sandy Pentland; Andrew Nierenberg; Ali Azarbayejani
Journal:  J Med Internet Res       Date:  2017-03-16       Impact factor: 5.428

10.  Clinician Burnout Associated With Sex, Clinician Type, Work Culture, and Use of Electronic Health Records.

Authors:  Eugenia McPeek-Hinz; Mina Boazak; J Bryan Sexton; Kathryn C Adair; Vivian West; Benjamin A Goldstein; Robert S Alphin; Sherif Idris; W Ed Hammond; Shelley E Hwang; Jonathan Bae
Journal:  JAMA Netw Open       Date:  2021-04-01
View more
  2 in total

1.  Perceived Value of the Electronic Health Record and Its Association with Physician Burnout.

Authors:  Maria Livaudais; Derek Deng; Tracy Frederick; Francine Grey-Theriot; Philip J Kroth
Journal:  Appl Clin Inform       Date:  2022-08-18       Impact factor: 2.762

2.  Effect of clinician attention switching on workload and wrong-patient errors.

Authors:  Sunny S Lou; Seunghwan Kim; Derek Harford; Benjamin C Warner; Philip R O Payne; Joanna Abraham; Thomas Kannampallil
Journal:  Br J Anaesth       Date:  2022-05-12       Impact factor: 11.719

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.