Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: Journal of Medical Internet Research

Date Submitted: Jul 22, 2020
Date Accepted: Oct 14, 2020

The final, peer-reviewed published version of this preprint can be found here:

Comparing Precision Machine Learning With Consumer, Quality, and Volume Metrics for Ranking Orthopedic Surgery Hospitals: Retrospective Study

Saeed M, Goyal D, Guttag J, Syed Z, Mehta R, Elahi Z

Comparing Precision Machine Learning With Consumer, Quality, and Volume Metrics for Ranking Orthopedic Surgery Hospitals: Retrospective Study

J Med Internet Res 2020;22(12):e22765

DOI: 10.2196/22765

PMID: 33258459

PMCID: 7738251

Recommending Providers for Surgical Care: Comparing Consumer Ratings, Quality Stars, Reputation Rankings, Average Volumes, Average Outcomes and Machine Learning for Recommending Orthopedic Surgery Hospitals in a Metro Region

  • Mohammed Saeed; 
  • Dev Goyal; 
  • John Guttag; 
  • Zeeshan Syed; 
  • Rudra Mehta; 
  • Zahoor Elahi

ABSTRACT

Background:

Patients’ choice of providers when undergoing elective surgeries significantly impacts both peri-operative outcomes and costs. There exist a variety of approaches that are available to patients for evaluating between different hospital choices.

Objective:

To compare differences in outcomes and costs between hospitals recommended using popular internet-based consumer ratings, quality stars, reputation rankings, average volumes, average outcomes and machine learning-based recommendations for hospital settings to perform hip replacements in a large metro area.

Methods:

Retrospective data from 4,192 hip replacement surgeries among Medicare beneficiaries in 2018 in a large metro area were analyzed for variations in outcomes (90-day post-procedure hospitalizations and emergency department visits) and costs (90-day total cost of care) between hospitals recommended by multiple approaches: internet-based consumer ratings, quality stars, reputation rankings, average yearly surgical volume, average outcome rates, and machine learning-based recommendations.The average rates of outcomes and costs were compared between the patients who underwent surgery at a recommended hospital using each recommended approach in unadjusted and propensity-based adjusted comparisons.

Results:

Only a minority of patients (28% to 50%) were found to be matched to recommended hospitals for each of the different approaches. Of the approaches considered, hip replacements at hospitals that were recommended using consumer ratings, quality stars and machine learning were all consistently associated with improvements in outcomes and costs in both adjusted and unadjusted analyses. The improvement was greatest across all metrics and analyses for machine learning-based recommendations.

Conclusions:

There is a substantive opportunity to increase the number of patients matched to appropriate hospitals across a broad variety of recommendation approaches. Machine learning-based recommendations of hospitals for performing elective hip replacement surgeries offers the greatest opportunity to improve outcomes and lower total costs of care by identifying recommended hospitals on a patient-specific basis.


 Citation

Please cite as:

Saeed M, Goyal D, Guttag J, Syed Z, Mehta R, Elahi Z

Comparing Precision Machine Learning With Consumer, Quality, and Volume Metrics for Ranking Orthopedic Surgery Hospitals: Retrospective Study

J Med Internet Res 2020;22(12):e22765

DOI: 10.2196/22765

PMID: 33258459

PMCID: 7738251

Per the author's request the PDF is not available.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.