ARTIFICIAL INTELLIGENCE IN POSTOPERATIVE REHABILITATION PLANNING: A SYSTEMATIC REVIEW

Abstract

Background: Artificial intelligence (AI) is increasingly being adopted in postoperative rehabilitation to enhance personalization, efficiency, and patient outcomes. Despite its growing use, evidence regarding the clinical effectiveness of AI-assisted rehabilitation protocols remains fragmented, with limited synthesis of outcome-based data across surgical populations. This systematic review was conducted to address this gap and evaluate the potential of AI in improving rehabilitation outcomes following surgery.

Objective: This systematic review aims to assess the effectiveness and clinical outcomes of AI-assisted rehabilitation protocols compared to conventional rehabilitation methods in postoperative physical therapy.

Methods: A systematic review was conducted following PRISMA guidelines. Four databases—PubMed, Scopus, Web of Science, and the Cochrane Library—were searched for studies published between January 2019 and March 2024. Eligible studies included randomized controlled trials and observational studies evaluating AI interventions in adult postoperative patients. Data extraction was performed using a standardized form, and study quality was assessed using the Cochrane Risk of Bias Tool and Newcastle-Ottawa Scale.

Results: Eight studies met the inclusion criteria, encompassing a total of 1,021 patients undergoing various surgeries such as joint replacement, spinal, and abdominal procedures. AI interventions included predictive models, motion sensors, wearable devices, and virtual coaching platforms. Most studies reported significant improvements in functional recovery, pain reduction, and patient adherence in the AI-assisted groups (p < 0.05). However, heterogeneity in study designs and short follow-up durations limited data synthesis.

Conclusion: AI-assisted rehabilitation shows promising benefits in enhancing postoperative outcomes compared to standard care. Although current findings support its clinical relevance, further large-scale, high-quality trials with long-term follow-up are necessary to establish reliability, cost-effectiveness, and implementation strategies.