Machine learning and markerless gait analysis show high predictive accuracy for return-to-sport readiness and re-injury riskMachine Learning Helps Predict Return to Sport After ACL Injury

Frontiers in Medicine Published June 17, 2026 Study authors: Rajat Satija, Daphika Dkhar DOI ↗ Editorial oversight: Dr. Lars van Dijk, PhD · Surgical, Procedural & Diagnostic

AI-generated summary of the cited source, checked by automated accuracy review. How we work

Key Takeaway

Note high predictive accuracy for return-to-sport and re-injury risk using wearable sensors, but await external validation.

This meta-analysis evaluates the predictive accuracy of machine learning and markerless gait analysis for assessing return-to-sport readiness and re-injury risk in adults with lower extremity injuries, including those with anterior cruciate ligament injuries. The study synthesizes data from wearable sensor studies and markerless motion analysis to determine diagnostic performance.

Wearable sensor-based machine learning models demonstrated a pooled accuracy of 0.92 for return-to-sport readiness (95% CI: 0.89–0.95) and a pooled accuracy of 0.90 for re-injury risk (95% CI: 0.84–0.95). Additionally, markerless motion analysis for injury risk screening showed a sensitivity of 0.82 and specificity of 0.77.

The authors note several limitations, including significant methodological heterogeneity and a reliance on internal validation rather than external validation. These factors may limit the generalizability of the findings to diverse clinical settings.

While these technologies show high predictive accuracy for clinical decision-making, full clinical implementation requires standardized reporting and more rigorous external validation. The current evidence suggests potential utility but underscores the need for further validation before widespread adoption.

How this fits prior evidence

This meta-analysis addresses a gap in objective assessment tools following previous findings that neuromuscular training reduces ACL injury risk in athletes. While prior evidence established the efficacy of specific rehabilitation protocols, this study evaluates the diagnostic accuracy of machine learning and markerless gait analysis to monitor return-to-sport readiness and re-injury risk.

Researchers looked at how machine learning and markerless gait analysis can help patients with lower extremity injuries, such as ACL tears. They specifically looked at whether these technologies could accurately predict when a person is ready to play sports again and if they are at risk for a new injury.

The study found that wearable sensors combined with machine learning showed high accuracy in predicting both return-to-sport readiness and the risk of re-injury. Additionally, markerless motion analysis showed good results in screening for injury risks. These tools use data from movement to provide a clearer picture of a patient's physical status.

Because these findings come from a meta-analysis with some differences in how studies were conducted, they are not yet ready for widespread clinical use. The current models lack external validation, which means they need more testing in different settings before they can be used as standard tools. For now, these results show promise for the future of sports medicine.

What this means for you:

Machine learning and wearable sensors show high accuracy in predicting recovery progress after lower limb injuries.

Common questions

How accurate is this technology at predicting if I can play sports again?

Studies using wearable sensors and machine learning showed a pooled accuracy of 0.92 for determining return-to-sport readiness. This suggests the technology is very effective at identifying when an athlete might be ready to resume their activities after a lower extremity injury.

Can these tools help predict if I will get injured again?

Yes, wearable sensor studies showed a pooled accuracy of 0.90 for predicting re-injury risk. This helps healthcare providers understand the likelihood of a new injury occurring after an initial ligament injury like an ACL tear.

Is this technology ready to be used in every clinic today?

While the results are promising, the study notes that these models lack external validation and have some methodological differences. Because of this, the technology is not yet a standard replacement for current methods and needs more testing before it can be widely used.

Study Details

Study typeMeta analysis

EvidenceLevel 1

PublishedJun 2026

View Original Abstract ↓

Anterior cruciate ligament and lower extremity injuries impose a substantial burden in sports medicine, yet conventional assessments fail to capture the dynamic nature of injury risk and recovery. Machine learning and markerless gait analysis offer potential improvements in predicting return-to-sport readiness and re-injury risk, but their clinical reliability remains uncertain. This review evaluates the predictive accuracy and clinical applicability of these approaches. A comprehensive search of PubMed, Embase, Scopus, IEEE Xplore, and CINAHL was conducted up to March 2026. Studies involving adults with lower extremity injuries using machine learning or markerless systems and reporting predictive metrics were included. Pooled accuracy estimates were calculated using a fixed-effect model with logit transformation. Heterogeneity was assessed using the I² statistic. Eleven studies met inclusion criteria for quantitative synthesis. For return-to-sport readiness (six wearable sensor studies), pooled accuracy was 0.92 (95% CI: 0.89–0.95; I² = 52.2%). Sensitivity ranged from 0.79 to 0.99, and specificity from 0.75 to 0.99. For re-injury risk (two wearable sensor studies), pooled accuracy was 0.90 (95% CI: 0.84–0.95; I² = 0.0%). Markerless motion analysis demonstrated sensitivity of 0.82 and specificity of 0.77 for injury risk screening. Deep learning and ensemble models outperformed traditional approaches. Wearable sensor-based machine learning models achieve high predictive accuracy for return-to-sport and re-injury risk. However, methodological heterogeneity, reliance on internal validation, and absence of external validation limit generalisability. Standardised reporting and rigorous external validation are urgently needed before clinical implementation. https://www.crd.york.ac.uk/PROSPERO/view/CRD420261352158, identifier CRD420261352158.

Machine learning and markerless gait analysis show high predictive accuracy for return-to-sport readiness and re-injury riskMachine Learning Helps Predict Return to Sport After ACL Injury

How this fits prior evidence

Common questions

Study Details

Low-intensity pulsed ultrasound shows a 0.79 healing rate in nonunion fractures across observational studies

Trial results show mixed success for ultrasound on nonunion fractures

Clinical research that matters. Delivered to your inbox.

Machine learning and markerless gait analysis show high predictive accuracy for return-to-sport readiness and re-injury riskMachine Learning Helps Predict Return to Sport After ACL Injury

How this fits prior evidence

Common questions

More on anterior cruciate ligament injury

Study Details

Low-intensity pulsed ultrasound shows a 0.79 healing rate in nonunion fractures across observational studies

Trial results show mixed success for ultrasound on nonunion fractures

Clinical research that matters. Delivered to your inbox.

Related in Orthopedics & Sports Medicine

From Other Specialties