JMIR Publications

ABSTRACT

Background:

Considering that most patients with low or no significant risk factors can safely undergo noncardiac surgery without additional cardiac evaluation, and given the excessive evaluations often performed in patients undergoing intermediate or higher risk noncardiac surgeries, practical preoperative risk assessment tools are essential to reduce unnecessary delays for urgent outpatient services and manage medical costs more efficiently

Objective:

To utilize the Observational Medical Outcomes Partnership Common Data Model (OMOP CDM) to develop a predictive model by applying machine learning algorithms that can effectively predict major adverse cardiac and cerebrovascular events (MACCE) in patients undergoing noncardiac surgery.

Methods:

This retrospective observational network study collected data by converting electronic health records (EHRs) into a standardized OMOP CDM format. The study was conducted in two tertiary hospitals. Data included demographic information, diagnoses, laboratory results, medications, surgical types, and clinical outcomes. A total of 46,225 patients were recruited from Seoul National University Bundang Hospital and 396,424 from Asan Medical Center. We selected patients aged 65 years or older undergoing noncardiac surgeries, excluding cardiac or emergency surgeries, and those with less than 30 days of observation. Using these observational healthcare data, we developed machine learning-based prediction models employing the observational health data sciences and informatics (OHDSI) open-source patient-level prediction package in R version 4.1.0.

Results:

All machine learning prediction models outperformed the Revised Cardiac Risk Index (RCRI), achieving a higher area under the receiver operating characteristic (AUROC) for MACCE prediction. Among the five predictive models, random forest demonstrated the best performance with an AUROC of 0.817 in external validation with moderate calibration. Moreover, the significance of predictors linked to previous diagnoses and laboratory measurements underscored their critical role in effectively predicting perioperative risk.

Conclusions:

Our prediction models outperformed the widely used RCRI in predicting MACCE within 30 days after noncardiac surgery. We anticipate that applying this model to actual EHRs will benefit clinical practice and reduce medical costs. Clinical Trial: Not applicable.