Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

The Epilepsy-Cog study: Methods to establish a harmonized study of late onset epilepsy in a metacohort of six population-based cohorts in the United States.

Epilepsia·2026

Same author

Early clinical and functional predictors of functional recovery after hemorrhagic stroke: a scoping review.

International journal of rehabilitation research. Internationale Zeitschrift fur Rehabilitationsforschung. Revue internationale de recherches de readaptation·2026

Same author

The past, present and future of control architectures in lower-limb cable-driven robots for gait rehabilitation.

Journal of neuroengineering and rehabilitation·2026

Same author

Return of results is important to heterogeneous research participants: A single-site survey.

Journal of clinical and translational science·2026

Same author

Risk prediction models for incident heart failure: a systematic review and meta-analysis.

Heart (British Cardiac Society)·2026

Same author

Internet-Based Microaggressions, Mental Health, and Stress: Development and Validation of the Internet-based Microagressions Scale.

Journal of racial and ethnic health disparities·2026

Search research articles

Related Experiment Video

Updated: Oct 20, 2025

Quantifying Arms and Legs Contributions during Repetitive Electrically-Assisted Sit-To-Stand Exercise in Paraplegics: A Pilot Study

Quantifying Arms and Legs Contributions during Repetitive Electrically-Assisted Sit-To-Stand Exercise in Paraplegics: A Pilot Study

Published on: November 11, 2022

Artificial intelligence application versus physical therapist for squat evaluation: a randomized controlled trial.

Alessandro Luna¹, Lorenzo Casertano², Jean Timmerberg^1,3

¹Vagelos College of Physicians and Surgeons, Columbia University, New York, NY, USA.

Scientific Reports

|September 14, 2021

Summary

Artificial intelligence (AI) mobile applications show promise in improving squat form, performing comparably to physical therapists. While AI accurately identifies correct squats, its ability to detect incorrect form is limited, impacting diagnostic capabilities.

More Related Videos

Author Spotlight: Rehabilitation of Stroke Patients With a Digital Occupational Training System

Author Spotlight: Rehabilitation of Stroke Patients With a Digital Occupational Training System

Published on: December 29, 2023

Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS

Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS

Published on: June 7, 2024

Related Experiment Videos

Last Updated: Oct 20, 2025

Quantifying Arms and Legs Contributions during Repetitive Electrically-Assisted Sit-To-Stand Exercise in Paraplegics: A Pilot Study

Quantifying Arms and Legs Contributions during Repetitive Electrically-Assisted Sit-To-Stand Exercise in Paraplegics: A Pilot Study

Published on: November 11, 2022

Author Spotlight: Rehabilitation of Stroke Patients With a Digital Occupational Training System

Author Spotlight: Rehabilitation of Stroke Patients With a Digital Occupational Training System

Published on: December 29, 2023

Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS

Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS

Published on: June 7, 2024

Area of Science:

Health technology
Artificial intelligence in healthcare
Biomechanics and exercise science

Background:

Artificial intelligence (AI) is increasingly integrated into healthcare to enhance practice and patient outcomes.
Evaluating AI's efficacy in musculoskeletal assessment and rehabilitation is crucial.

Purpose of the Study:

To assess a commercial AI mobile application's ability to identify and improve bodyweight squat form in adults.
To compare the AI's performance against a physical therapist (PT) in providing feedback on squat technique.

Main Methods:

A randomized study compared an AI group (n=15) with a physical therapist (PT) group (n=15).
Participants performed three sets of squats: unassisted control, feedback-assisted, and unassisted test squats.
The AI's diagnostic capabilities were evaluated using sensitivity, specificity, PPV, NPV, and accuracy metrics.

Main Results:

No statistically significant difference was found between the AI and PT groups in improving squat performance.
The AI demonstrated satisfactory ability in identifying correct squat form (sensitivity 0.840).
The AI showed limited ability in identifying incorrect squat form (specificity 0.276), impacting its diagnostic utility.

Conclusions:

The commercial AI mobile application performed comparably to a physical therapist in improving squat form.
Current AI technology has potential for guiding correct exercise form but requires improvement in detecting deviations for enhanced diagnostic value.