Risk stratification in hip and knee replacement using artificial intelligence: a dual centre study to support the utility of high-volume low-complexity hubs and ambulatory surgery centres

Abstract

The COVID-19 pandemic has resulted in a significant backlog of hip and knee replacement surgeries in the United Kingdom (UK). 1,2 To address this, surgical hubs have been proposed to enhance efficiency, particularly for high-volume, low-complexity cases. 3,4 These hubs and Ambulatory Surgery Centres often lack higher level care support such as intensive care facilities and are thus suited to patients with less co-morbidity and systemic illness. Pre-operative risk assessment is required to enable correct patient allocation to the appropriate site and reduce unwarranted risk. This study explores the use of artificial intelligence (AI) for risk stratification in hip and knee arthroplasty. A polynomial regression model was developed using patient demographics, blood results, and comorbidities to assign risk scores for postoperative complications. The model was generated from 29,658 patient records from two UK National Health Service (NHS) healthcare organisations. It demonstrated an area under the receiver operating characteristic curve (AUROC) as the evaluation metric and was capable of categorising patients into high and low risk. Validation was performed using a retrospective analysis of 445 patients. Predicted versus actual complications and need for further care were used to examine agreement. The model’s sensitivity was 70% for identifying high-risk patients and had a negative predictive value of 96%. This AI risk prediction was comparable to consultant-led care in risk stratification. These findings suggest that AI can support more streamlined and efficient preoperative risk stratification, potentially reducing the burden on preoperative assessment teams and optimising resource allocation. While not without limitations, the AI model offers a sophisticated adjunct to clinical decision-making around determining risk. This can support facilities like hubs in the UK NHS or Ambulatory Surgery Centres in the United States. • OpenPredictor used 29,658 NHS cases to predict risk postoperative risk in elective arthroplasty. • Polynomial logistic regression modelling using 23 patient and medical variables. • Dual site clinical validation demonstrated sensitivity of 70% and negative predictive value 96%. • Risk assessments were comparable to consultant-led pre-operative assessment.

Ähnliche Arbeiten