Dataset Information

Using Consistently Low Performance to Identify Low-Quality Physician Groups.

ABSTRACT:

Importance

There has been a growth in the use of performance-based payment models in the past decade, but inherently noisy and stochastic quality measures complicate the assessment of the quality of physician groups. Examining consistently low performance across multiple measures or multiple years could potentially identify a subset of low-quality physician groups.

Objective

To identify low-performing physician groups based on consistently low performance after adjusting for patient characteristics across multiple measures or multiple years for 10 commonly used quality measures for diabetes and cardiovascular disease (CVD).

Design, setting, and participants

This cross-sectional study used medical and pharmacy claims and laboratory data for enrollees ages 18 to 65 years with diabetes or CVD in an Aetna health insurance plan between 2016 and 2019. Each physician group's risk-adjusted performance for a given year was estimated using mixed-effects linear probability regression models. Performance was correlated across measures and time, and the proportion of physician groups that performed in the bottom quartile was examined across multiple measures or multiple years. Data analysis was conducted between September 2020 and May 2021.

Exposures

Primary care physician groups.

Main outcomes and measures

Performance scores of 6 quality measures for diabetes and 4 for CVD, including hemoglobin A1c (HbA1c) testing, low-density lipoprotein testing, statin use, HbA1c control, low-density lipoprotein control, and hospital-based utilization.

Results

A total of 786 641 unique enrollees treated by 890 physician groups were included; 414 655 (52.7%) of the enrollees were men and the mean (SD) age was 53 (9.5) years. After adjusting for age, sex, and clinical and social risk variables, correlations among individual measures were weak (eg, performance-adjusted correlation between any statin use and LDL testing for patients with diabetes, r = -0.10) to moderate (correlation between LDL testing for diabetes and LDL testing for CVD, r = .43), but year-to-year correlations for all measures were moderate to strong. One percent or fewer of physician groups performed in the bottom quartile for all 6 diabetes measures or all 4 cardiovascular disease measures in any given year, while 14 (4.0%) to 39 groups (11.1%) were in the bottom quartile in all 4 years for any given measure other than hospital-based utilization for CVD (1.1%).

Conclusions and relevance

A subset of physician groups that was consistently low performing could be identified by considering performance measures across multiple years. Considering the consistency of group performance could contribute a novel method to identify physician groups most likely to benefit from limited resources.

SUBMITTER: Nguyen CA

PROVIDER: S-EPMC8319756 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ImportanceHospital participation in bundled payment initiatives has been associated with financial savings and stable quality of care. However, how physician group practices (PGPs) perform in bundled payments compared with hospitals remains unknown.ObjectivesTo evaluate the association of PGP participation in the Bundled Payments for Care Improvement (BPCI) initiative with episode outcomes and to compare these with outcomes for participating hospitals.Design, settings, and participantsThis cohort study with a difference-in-differences analysis used 2011 to 2018 Medicare claims data to compare the association of BPCI participation with episode outcomes for PGPs vs hospitals providing medical and surgical care to Medicare beneficiaries. Data analyses were conducted from January 1, 2020, to May 31, 2022.ExposuresHospitalization for any of the 10 highest-volume episodes (5 medical and 5 surgical) included in the BPCI initiative for Medicare patients of participating PGPs and hospitals.Main outcomes and measuresThe primary outcome was 90-day total episode spending. Secondary outcomes were 90-day readmissions and mortality.ResultsThe total sample comprised data from 1 288 781 Medicare beneficiaries, of whom 696 710 (mean [SD] age, 76.2 [10.8] years; 432 429 [59.7%] women; 619 655 [85.5%] White individuals) received care through 379 BPCI-participating hospitals and 1441 propensity-matched non-BPCI-participating hospitals, and 592 071 (mean [SD] age, 75.4 [10.9] years; 527 574 [86.6%] women; 360 835 [59.3%] White individuals) received care from 6405 physicians in BPCI-participating PGPs and 24 758 propensity-matched physicians in non-BPCI-participating PGPs. For PGPs, BPCI participation was associated with greater reductions in episode spending for surgical (difference, -$1368; 95% CI, -$1648 to -$1088) but not for medical episodes (difference, -$101; 95% CI, -$410 to $206). Hospital participation in BPCI was associated with greater reductions in episode spending for both surgical (-$1010; 95% CI, -$1345 to -$675) and medical (-$763; 95% CI, -$1139 to -$386) episodes.Conclusions and relevanceThis cohort study and difference-in-differences analysis of PGPs and hospital participation in BPCI found that bundled payments were associated with cost savings for surgical episodes for PGPs, and savings for both surgical and medical episodes for hospitals. Policy makers should consider the comparative performance of participant types when designing and evaluating bundled payment models.

Project description:BackgroundBurnout 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.MethodPhysician 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.Results88 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.ConclusionsCurrent 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).