BackgroundHealthcare is approaching a tipping point as burnout and dissatisfaction with work-life integration (WLI) in healthcare workers continue to increase. A scale evaluating common behaviours as actionable examples of WLI was introduced to measure work-life balance.Objectives(1) Explore differences in WLI behaviours by role, specialty and other respondent demographics in a large healthcare system. (2) Evaluate the psychometric properties of the work-life climate scale, and the extent to which it acts like a climate, or group-level norm when used at the work setting level. (3) Explore associations between work-life climate and other healthcare climates including teamwork, safety and burnout.MethodsCross-sectional survey study completed in 2016 of US healthcare workers within a large academic healthcare system.Results10 627 of 13 040 eligible healthcare workers across 440 work settings within seven entities of a large healthcare system (81% response rate) completed the routine safety culture survey. The overall work-life climate scale internal consistency was α=0.830. WLI varied significantly among healthcare worker role, length of time in specialty and work setting. Random effects analyses of variance for the work-life climate scale revealed significant between-work setting and within-work setting variance and intraclass correlations reflected clustering at the work setting level. T-tests of top versus bottom WLI quartile work settings revealed that positive work-life climate was associated with better teamwork and safety climates, as well as lower personal burnout and burnout climate (p<0.001).ConclusionProblems with WLI are common in healthcare workers and differ significantly based on position and time in specialty. Although typically thought of as an individual difference variable, WLI appears to operate as a climate, and is consistently associated with better safety culture norms.

Background Improving the resiliency of healthcare workers is a national imperative, driven in part by healthcare workers having minimal exposure to the skills and culture to achieve work–life balance (WLB). Regardless of current policies, healthcare workers feel compelled to work more and take less time to recover from work. Satisfaction with WLB has been measured, as has work–life conflict, but how frequently healthcare workers engage in specific WLB behaviours is rarely assessed. Measurement of behaviours may have advantages over measurement of perceptions; behaviours more accurately reflect WLB and can be targeted by leaders for improvement. Objectives To describe a novel survey scale for evaluating work–life climate based on specific behavioural frequencies in healthcare workers. To evaluate the scale’s psychometric properties and provide benchmarking data from a large healthcare system. To investigate associations between work–life climate, teamwork climate and safety climate. Methods Cross-sectional survey study of US healthcare workers within a large healthcare system. Results 7923 of 9199 eligible healthcare workers across 325 work settings within 16 hospitals completed the survey in 2009 (86% response rate). The overall work–life climate scale internal consistency was Cronbach α=0.790. t-Tests of top versus bottom quartile work settings revealed that positive work–life climate was associated with better teamwork climate, safety climate and increased participation in safety leadership WalkRounds with feedback (p<0.001). Univariate analysis of variance demonstrated differences that varied significantly in WLB between healthcare worker role, hospitals and work setting. Conclusions The work–life climate scale exhibits strong psychometric properties, elicits results that vary widely by work setting, discriminates between positive and negative workplace norms, and aligns well with other culture constructs that have been found to correlate with clinical outcomes.

IMPORTANCE The ability to accurately predict in-hospital mortality for patients at the time of admission could improve clinical and operational decision-making and outcomes. Few of the machine learning models that have been developed to predict in-hospital death are both broadly applicable to all adult patients across a health system and readily implementable. Similarly, few have been implemented, and none have been evaluated prospectively and externally validated.OBJECTIVES To prospectively and externally validate a machine learning model that predicts in-hospital mortality for all adult patients at the time of hospital admission and to design the model using commonly available electronic health record data and accessible computational methods. DESIGN, SETTING, AND PARTICIPANTSIn this prognostic study, electronic health record data from a total of 43 180 hospitalizations representing 31 003 unique adult patients admitted to a quaternary academic hospital (hospital A) from October 1, 2014, to December 31, 2015, formed a training and validation cohort. The model was further validated in additional cohorts spanning from March 1, 2018, to August 31, 2018, using 16 122 hospitalizations representing 13 094 unique adult patients admitted to hospital A, 6586 hospitalizations representing 5613 unique adult patients admitted to hospital B, and 4086 hospitalizations representing 3428 unique adult patients admitted to hospital C. The model was integrated into the production electronic health record system and prospectively validated on a cohort of 5273 hospitalizations representing 4525 unique adult patients admitted to hospital A between February 14, 2019, and April 15, 2019. MAIN OUTCOMES AND MEASURES The main outcome was in-hospital mortality. Model performance was quantified using the area under the receiver operating characteristic curve and area under the precision recall curve. RESULTS A total of 75 247 hospital admissions (median [interquartile range] patient age, 59.5 [29.0]years; 45.9% involving male patients) were included in the study. The in-hospital mortality rates for the training validation; retrospective validations at hospitals A, B, and C; and prospective validation cohorts were 3.0%, 2.7%, 1.8%, 2.1%, and 1.6%, respectively. The area under the receiver operating characteristic curves were 0.87 (95% CI, 0.83-0.89), 0.85 (95% CI, 0.83-0.87), 0.89 (95% CI, 0.86-0.92), 0.84 (95% CI, 0.80-0.89), and 0.86 (95% CI, 0.83-0.90), respectively. The area under the precision recall curves were 0.29 (95% CI, 0.25-0.37), 0.17 (95% CI, 0.13-0.22), 0.22 (95% CI, 0.14-0.31), 0.13 (95% CI, 0.08-0.21), and 0.14 (95% CI, 0.09-0.21), respectively. CONCLUSIONS AND RELEVANCEProspective and multisite retrospective evaluations of a machine learning model demonstrated good discrimination of in-hospital mortality for adult patients at the (continued) Key Points Question How accurately can a machine learning model predict risk of in-hospital mortality for adult patients when evaluated prospectively and externally? Findings In this p...

Key Points Question What is the association of clinician sex, use of the electronic health record (EHR), and work culture with clinician burnout? Findings This cross-sectional study of 1310 clinicians found burnout to be more prevalent in women, attending physicians, and advanced practice providers. Multivariate modeling of burnout identified local work culture accounting for 17.6% variance compared with only 1.3% variance for EHR metrics. Female sex independently contributed more to likelihood of clinician burnout and significantly interacted with work culture domains of commitment and work-life balance. Meaning These findings suggest that clinician sex and local work culture may contribute more to burnout than the EHR.