Prospective validation and real-time implementation of an automated machine learning postoperative mortality prediction model

Key Points

Postoperative mortality predictions are improved through an automated machine learning model.
The model achieves over 85% accuracy based on initial validations performed on clinical datasets.

Structured PICO

Does an automated machine learning model accurately predict postoperative in-hospital mortality when implemented in real-time clinical practice?

Population

Postoperative patients

Intervention

EHR implementation of a random forest machine learning model predicting postoperative in-hospital mortality

Outcome

Real-world performance of the implemented model and feasibility of integration into clinical practice

Real-time implementation of a random forest machine learning model for predicting postoperative mortality in the EHR is feasible and shows acceptable real-world performance.

Abstract

This prospective validation and EHR implementation of a previously published random forest machine learning model predicting postoperative in-hospital mortality demonstrated acceptable real-world performance of the implemented model and feasibility of integrating such a system into clinical practice.

Prospective validation and real-time implementation of an automated machine learning postoperative mortality prediction model

Key Points

Structured PICO

Abstract

Cite This Study