Minimum Required Distance for Clinically Significant Measurement of Habitual Gait Speed DOI Creative Commons
Myung Woo Park, Sun Gun Chung, Jaewon Beom

и другие.

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Дек. 12, 2024

Abstract Background: Gait speed indicates morbidity and life expectancy in older adults, but the minimum walking distance for measurement remains unclear. This study aimed to determine required measure clinically reliable gait using a smartphone camera pose estimation, whether is influenced by subject characteristics or methods. Methods: Twenty-four healthy volunteers (> 65 years old) performed video-recorded 10-m test, excluding acceleration deceleration. Fourteen body points were derived pose-estimation algorithm. Speed was calculated based on center of mass leading foot which simulates condition with walkway sensor validated against manual measurements. Multiple videos over varying distances obtained cropping video frames at 0.1-meter intervals. Variance specific ANOVA. “Minimum distance” defined as shortest where confidence interval did not exceed minimal important difference (0.1 m/sec). We also investigated clinical, anthropometric, epidemiological variables might influence it assessing their association variance mean squared error from linear regression. Results: measured estimation (1.55 ± 0.18 m/s) highly corresponded (1.56 0.14 (r = 0.866, p < 0.001). 2.1 meter when 95% while “minimun 4.7 90% interval. Gait itself muscle strength positively correlated 0.250, 0.036 speed; r 0.312, 0.008 knee extensor strength; 0.230, 0.053 grip strength) other epidemiologic clinical parameters including age physical performance scales not. Conclusions: Clinically could be achieved inducing level. The weaker slower speed, shorter required.

Язык: Английский

Artificial Intelligence and Its Revolutionary Role in Physical and Mental Rehabilitation: A Review of Recent Advancements DOI Creative Commons
Amir Rahmani Rasa

BioMed Research International, Год журнала: 2024, Номер 2024(1)

Опубликована: Янв. 1, 2024

The integration of artificial intelligence (AI) technologies into physical and mental rehabilitation has the potential to significantly transform these fields. AI innovations, including machine learning algorithms, natural language processing, computer vision, offer occupational therapists advanced tools improve care quality. These facilitate more precise assessments, development tailored intervention plans, efficient treatment delivery, enhanced outcome evaluation. This review explores across various aspects rehabilitation, providing a thorough examination recent advancements current applications. It highlights how applications, such as virtual reality, learning, robotics, are shaping future recovery in therapy.

Язык: Английский

Процитировано

12
From screens to scenes: A survey of embodied AI in healthcare DOI
Yihao Liu, Xu Cao, Tingting Chen

и другие.

Information Fusion, Год журнала: 2025, Номер unknown, С. 103033 - 103033

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

2
Harnessing Generative Artificial Intelligence for Exercise and Training Prescription: Applications and Implications in Sports and Physical Activity—A Systematic Literature Review DOI Creative Commons
Luca Puce, Nicola Luigi Bragazzi, Antonio Currà

и другие.

Applied Sciences, Год журнала: 2025, Номер 15(7), С. 3497 - 3497

Опубликована: Март 22, 2025

Regular physical activity plays a critical role in health promotion and athletic performance, necessitating personalized exercise training prescriptions. While traditional methods rely on expert assessments, artificial intelligence (AI), particularly generative AI models such as ChatGPT Google Gemini, has emerged potential tool for enhancing personalization scalability recommendations. However, the applicability, reliability, adaptability of AI-generated prescriptions remain underexplored. A comprehensive search was performed using UnoPerTutto metadatabase, identifying 2891 records. After duplicate removal (1619 records) screening, 61 full-text reports were assessed eligibility, resulting inclusion 10 studies. The studies varied methodology, including qualitative mixed-methods approaches, quasi-experimental designs, randomized controlled trial (RCT). ChatGPT-4, ChatGPT-3.5, Gemini evaluated across different contexts, strength training, rehabilitation, cardiovascular exercise, general fitness programs. Findings indicate that programs generally adhere to established guidelines but often lack specificity, progression, real-time physiological feedback. recommendations found emphasize safety broad making them useful guidance less effective high-performance training. GPT-4 demonstrated superior performance generating structured resistance compared older models, yet limitations individualization contextual adaptation persisted. appraisal METRICS checklist revealed inconsistencies study quality, regarding prompt model transparency, evaluation frameworks. holds promise democratizing access prescriptions, its remains complementary rather than substitutive guidance. Future research should prioritize adaptability, integration with monitoring, improved AI-human collaboration enhance precision effectiveness AI-driven

Язык: Английский

Процитировано

2
Estimation of elbow flexion torque using equilibrium optimizer on feature selection of NMES MMG signals and hyperparameter tuning of random forest regression DOI Creative Commons
Raphael Uwamahoro, Kenneth Sundaraj, Farah Shahnaz Feroz

и другие.

Frontiers in Rehabilitation Sciences, Год журнала: 2025, Номер 6

Опубликована: Фев. 19, 2025

The assessment of limb joint torque is essential for understanding musculoskeletal system dynamics. Yet, the lack direct muscle strength measurement techniques has prompted previous research to deploy estimation using machine learning models. These models often suffer from reduced accuracies due presence redundant and irrelevant information within rapidly expanding complex biomedical datasets as well suboptimal hyperparameters configurations. This study utilized a random forest regression (RFR) model estimate elbow flexion mechanomyography (MMG) signals recorded during electrical stimulation biceps brachii (BB) in 36 right-handed healthy subjects. Given significance both feature engineering hyperparameter tuning optimizing RFR performance, this proposes hybrid method leveraging General Learning Equilibrium Optimizer (GLEO) identify most informative MMG features tune hyperparameters. performance GLEO-coupled with was compared standard (EO) other state-of-the-art algorithms physical physiological function biological signals. Experimental results showed that selected tuned demonstrated significant improvement root mean square error (RMSE), coefficient determination (R2) slope values improving 0.1330 0.1174, 0.7228 0.7853 0.6946 0.7414, respectively test dataset. Convergence analysis further revealed GLEO algorithm exhibited superior capability EO. underscores potential approach selecting highly advancements are evaluating represent advancement biomechanics research.

Язык: Английский

Процитировано

1
AI-Driven Telerehabilitation: Benefits and Challenges of a Transformative Healthcare Approach DOI Creative Commons
Rocco Salvatore Calabrò,

Sepehr Mojdehdehbaher

AI, Год журнала: 2025, Номер 6(3), С. 62 - 62

Опубликована: Март 17, 2025

Artificial intelligence (AI) has revolutionized telerehabilitation by integrating machine learning (ML), big data analytics, and real-time feedback to create adaptive, patient-centered care. AI-driven systems enhance analyzing patient personalize therapy, monitor progress, suggest adjustments, eliminating the need for constant clinician oversight. The benefits of AI-powered include increased accessibility, especially remote or mobility-limited patients, greater convenience, allowing patients perform therapies at home. However, challenges persist, such as privacy risks, digital divide, algorithmic bias. Robust encryption protocols, equitable access technology, diverse training datasets are critical addressing these issues. Ethical considerations also arise, emphasizing human oversight maintaining therapeutic relationship. AI aids clinicians automating administrative tasks facilitating interdisciplinary collaboration. Innovations like 5G networks, Internet Medical Things (IoMT), robotics further telerehabilitation’s potential. By transforming rehabilitation into a dynamic, engaging, personalized process, together represent paradigm shift in healthcare, promising improved outcomes broader worldwide.

Язык: Английский

Процитировано

1
Artificial Intelligence in Medical Education and Mentoring in Rehabilitation Medicine DOI
Julie K. Silver, Mustafa Reha Dodurgali, Nara Gavini

и другие.

American Journal of Physical Medicine & Rehabilitation, Год журнала: 2024, Номер 103(11), С. 1039 - 1044

Опубликована: Июль 15, 2024

Artificial intelligence emerges as a transformative force, offering novel solutions to enhance medical education and mentorship in the specialty of physical medicine rehabilitation. is technology that being adopted nearly every industry. In medicine, use artificial growing. may also assist with some challenges mentorship, including limited availability experienced mentors, logistical difficulties time geography are constraints traditional mentorship. this commentary, we discuss various models mentoring, expert systems, conversational agents, hybrid models. These enable tailored guidance, broaden outreach within rehabilitation community, support continuous learning development. Balancing intelligence's technical advantages essential human elements while addressing ethical considerations, integration into presents paradigm shift toward more accessible, responsive, enriched experience medicine.

Язык: Английский

Процитировано

4
Impact of Artificial Intelligence on Healthcare and Its Challenges in the MENA Region DOI
Walid Hleihel,

Najib Najjar

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
Artificial intelligence in stroke rehabilitation: From acute care to long-term recovery DOI
Spandana Rajendra Kopalli, Madhu Shukla,

B Jayaprakash

и другие.

Neuroscience, Год журнала: 2025, Номер unknown

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0
Deep Learning for Predicting Rehabilitation Success: Advancing Clinical and Patient-Reported Outcome Modeling DOI Open Access

Yasser Mahmoud,

Kaleb Horvath, Yi Zhou

и другие.

Electronics, Год журнала: 2025, Номер 14(6), С. 1082 - 1082

Опубликована: Март 9, 2025

Predicting rehabilitation outcomes is essential for guiding clinical decisions and improving patient care. Traditional machine learning methods, while effective, are often limited in their ability to capture complex, nonlinear relationships data. This study investigates the application of deep techniques, including hybrid Convolutional Neural Networks (CNNs) Recurrent (RNNs), predict success based on patient-reported outcome measures (CROMs PROMs). Using a dataset 1047 patients encompassing diverse musculoskeletal conditions treatment protocols, we compare performance models with previously established approaches such as Random Forest Extra Trees classifiers. Our findings reveal that significantly enhances predictive performance. The weighted F1-score direct classification improved from 65% 74% using CNN-RNN architecture, mean absolute error (MAE) regression-based metrics decreased by 12%, translating more precise estimations functional recovery. These improvements hold significance they enhance tailor interventions individual needs, potentially optimizing recovery timelines resource allocation. Moreover, attention mechanisms integrated into provided interpretability, highlighting key predictors age, range motion, PROM indices. underscores potential advance prediction rehabilitation, offering interpretable tools decision-making. Future work will explore real-time applications integration multimodal data further refine these models.

Язык: Английский

Процитировано

0
Functional and Motoric Outcome of AI-Assisted Stroke Rehabilitation: A Meta-analysis of Randomized Controlled Trials DOI Creative Commons

Tivano Antoni,

Benedictus Benedictus,

Stefanus Erdana Putra

и другие.

Brain Disorders, Год журнала: 2025, Номер unknown, С. 100224 - 100224

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0