Year: 2026
Type: article
Abstract: Diagnosis of an ACL injury is followed by a personalized rehabilitation program and subsequent decisions regarding sport resumption. AI algorithms may be used in assessing such patients and readiness for sports participation using imaging and biomechanical parameters. This review summarizes the current status of AI-supported ACL diagnosis via clinical examination and MRI, rehabilitation and return-to-sport assessment. Using wearable sensors with machine learning, clinicians can quantify movement during the clinical examination of knee joint. Furthermore, deep-learning models showed promise in detection of ACL tears via MRI imaging. During the rehabilitation process, AI can help quantify movement-related load, detect strength asymmetries and predict functional recovery afterwards. Return-to-sport models can integrate physical and psychologic patient's data to predict readiness to resume training and the risk of re-injury. Nevertheless, all these applications answer different clinical questions and good performance in research datasets does not ensure the effectiveness of these tools in clinical practice. The limitations in the patient populations, measurement approaches and definitions of outcome, as well as a lack of external validation, decrease the generalizability of results. Thus, AI models should give clear and verifiable information which clinicians can apply in clinical practice.
Source: Theoretical and Natural Science
Author: Nixuan Ou
Language: English
Subfield: Surgery
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W7224012486