Abstract
OpenPredictor, a machine learning-enabled clinical decision aid, has been developed to manage backlogs in elective surgeries. It aims to optimise the use of high volume, low complexity surgical pathways by accurately stratifying patient risk, thereby facilitating the allocation of patients to the most suitable surgical sites. The tool augments elective surgical pathways by providing automated secondary opinions for perioperative risk assessments, enhancing decision-making. Its primary application is in elective sites utilising lighter pre-assessment methods, identifying patients with minimal complication risks and those high-risk individuals who may benefit from early pre-assessment.
The Phase 1 clinical evaluation of OpenPredictor entailed a prospective analysis of 156 patient records from elective hip and knee joint replacement surgeries. Using a polynomial logistic regression model, patients were categorised into high, moderate, and low-risk groups. This categorisation incorporated data from various sources, including patient demographics, co-morbidities, blood tests, and overall health status.
In identifying patients at risk of postoperative complications, OpenPredictor demonstrated parity with consultant-led preoperative assessments. It accurately flagged 70% of patients who later experienced complications as moderate or high risk. The tool's efficiency in risk prediction was evidenced by its balanced accuracy (75.6%), sensitivity (70% with a 95% confidence interval of 62.05% to 76.91%), and a high negative predictive value (96.7%).
OpenPredictor presents a scalable and consistent solution for managing elective surgery pathways, comparable in performance to secondary consultant opinions. Its integration into pre-assessment workflows assists in efficient patient categorisation, reduces late surgery cancellations, and optimises resource allocation. The Phase 1 evaluation of OpenPredictor underscores its potential for broader clinical application and highlights the need for ongoing data refinement and system integration to enhance its performance.
