Transforming Healthcare Predictions and Decision-Making: New Model

10 December, 2024
Adam Rose - healthcare predictions

Researchers at the Hebrew University enhanced the Elixhauser Comorbidity Model, improving predictions for length of hospital stay, mortality, readmission, and escalated care. The study outperformed the standard Elixhauser model, offering a comprehensive view of patient complexity. These findings benefit healthcare decisions and patient outcomes, with broad implications for the field.

Risk adjustment models play a critical role in guiding clinical care, adjusting case mix in research, and supporting health services planning and financing, including payment adjustments based on patient complexity. However, these models, such as the Elixhauser Comorbidity Measure, often focus solely on comorbid illnesses and may not fully capture a patient’s medical complexity. This is especially pertinent in Israel, where hospitals are reimbursed a fixed fee per day, irrespective of patient complexity.

Researchers at The Hebrew University have enhanced and externally validated the Elixhauser Comorbidity Model to improve its accuracy. The lead author was Dr. Gidon Liebner, a resident in orthopedics at Hadassah hospital and a graduate of the Hebrew University School of Medicine. The senior authors are Drs. Shuli Brammli-Greenberg and Adam Rose, professors at the Hebrew University School of Public Health.

The study, published in BMC Health Services Research,  incorporated additional clinical and demographic data into the Elixhauser model. By incorporating additional clinical and demographic data, the study has improved the model's accuracy in predicting key outcomes such as length of stay, in-hospital mortality, readmission within 30 days, and escalated care, meaning the intensive care unit or similar sorts of care.

This improved model not only aids healthcare professionals in making more informed clinical decisions but also enables more efficient resource allocation within healthcare facilities. The refined model enhances the overall quality of patient care, potentially leading to cost savings and contributing to advancements in healthcare research.

Leveraging Israel's unique centralized health data repository, the study conducted a retrospective observational cohort analysis of 55,946 admissions to the internal medicine service of the Shaare Zedek Medical Center (Jerusalem). It   found that the enhanced model outperformed the standard Elixhauser Model. By including variables such as laboratory test results, vital signs, and demographic information, the new model achieved significant improvements in prediction accuracy over the basic Elixhauser model, which has itself been in use for decades for this purpose.

The study showed that the upgraded model was better in predicting certain health outcomes. For example, when it came to estimating how long someone would stay in the hospital, the improved model increased its predictiveness from an R2 of 10.1% to 28.1%. Additionally, in predicting whether someone might pass away during their hospital stay, the model's c-statistic, a measure of model predictiveness, went up from 71.1% to 87.9%. These improvements show that the enhanced model is better at figuring out and predicting how long someone will be in the hospital and the risk of in-hospital mortality compared to the standard model.

"Our enhanced model fills a crucial gap in the original Elixhauser Model by providing a more comprehensive assessment of patient complexity," said Prof. Adam J. Rose. "This model has broad applicability to other healthcare settings, both within and beyond internal medicine, and could support decisions regarding admission and care settings, home hospitalization suitability, and payment adjustments based on patient complexity."

The research paper titled “Incorporating Clinical and Demographic Data into the Elixhauser Comorbidity Model: Validation and Impact on Outcome Predictions in a Tertiary Hospital's Internal Medicine Department” is now available in BMC Health Services Research and can be accessed at https://rdcu.be/d2umv

DOI 10.1186/s12913-024-11663-z

Researchers:

Gideon Leibner1, David E. Katz1,2, Yaakov Esayag2, Nechama Kaufman3,4, Shuli Brammli-Greenberg1, Adam J. Rose1

Institutions:

  1. Faculty of Medicine, Hebrew University of Jerusalem, Jerusalem Israel
  2. Department of Internal Medicine, Shaare Zedek Medical Center, Jerusalem Israel
  3. Department of Quality and Patient Safety, Shaare Zedek Medical Center, Jerusalem Israel
  4. Department of Emergency Medicine, Shaare Zedek Medical Center, Jerusalem Israel