Key result
An artificial intelligence mobile application did not significantly differ from a physical therapist in improving bodyweight squat performance, with 27% of the AI group and 60% of the PT group showing improvement (OR 4.125, p=0.072).
Why the study?
AI technology is becoming increasingly prevalent in health care, but its ability compared to a physical therapist to identify and improve bodyweight squat form required evaluation.
Does an artificial intelligence mobile application improve bodyweight squat form in healthy adults compared to a physical therapist?
RCT (n=30)
Single-blind
1:1 ratio using Excel random choice selection
No
Does an artificial intelligence mobile application improve bodyweight squat form in healthy adults compared to a physical therapist?
Effect estimate: OR 4.125 (95% CI 0.883-19.273)
Absolute Event Rate: 27% vs 60%
p-value: p=0.072
An AI mobile application had satisfactory ability to identify correct squat form but limited ability to identify incorrect form, and did not significantly differ from a physical therapist in improving squat performance in healthy adults.
AI apps performed similarly to PT for squat form; leaves open questions on scalability and accuracy in larger or clinical populations.
Artificial intelligence technology is becoming more prevalent in health care as a tool to improve practice patterns and patient outcomes. This study assessed ability of a commercialized artificial intelligence (AI) mobile application to identify and improve bodyweight squat form in adult participants when compared to a physical therapist (PT). Participants randomized to AI group (n = 15) performed 3 squat sets: 10 unassisted control squats, 10 squats with performance feedback from AI, and 10 additional unassisted test squats. Participants randomized to PT group (n = 15) also performed 3 identical sets, but instead received performance feedback from PT. AI group intervention did not differ from PT group (log ratio of two odds ratios = - 0.462, 95% confidence interval (CI) (- 1.394, 0.471), p = 0.332). AI ability to identify a correct squat generated sensitivity 0.840 (95% CI (0.753, 0.901)), specificity 0.276 (95% CI (0.191, 0.382)), PPV 0.549 (95% CI (0.423, 0.669)), NPV 0.623 (95% CI (0.436, 0.780)), and accuracy 0.565 95% CI (0.477, 0.649)). There was no statistically significant association between group allocation and improved squat performance. Current AI had satisfactory ability to identify correct squat form and limited ability to identify incorrect squat form, which reduced diagnostic capabilities.Trial Registration NCT04624594, 12/11/2020, retrospectively registered.
No takes yet. Share an insight, caveat, or question.
Luna et al. (2021) conducted an RCT in Healthy adults (n=30). Artificial intelligence (AI) mobile application vs. Physical therapist (PT) was evaluated on Proportion of participants with more correct squats after intervention (OR 4.125, 95% CI 0.883-19.273, p=0.072). An artificial intelligence mobile application did not significantly differ from a physical therapist in improving bodyweight squat performance, with 27% of the AI group and 60% of the PT group showing improvement (OR 4.125, p=0.072).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: