Perceptions of a machine learning-based lower-limb exercise training system among older adults with knee pain

Objective This study aimed to examine the effects of semi-immersive virtual reality (VR)-based exercise on the quality of life of older adults. Methods It used a randomized controlled trial design. Older adults (mean age: 72.16 ± 4.9 years) were randomly assigned to experimental ( n = 48) and control ( n = 50) groups. The experimental group engaged in semi-immersive VR exercise for 75–90 min, twice a week, for 12 weeks and partook in no other intervention between the end of the exercise intervention and follow-up. Control group members did not participate in any similar program during the intervention or follow-up periods. Both groups completed three assessments: at baseline (pre-test), post-intervention (post-test), and 3 months later (follow-up). Quality of life was assessed using the World Health Organization Quality of Life Instrument-Older Adults Module. Results Generalized estimating equation analyses indicated that the experimental group exhibited significant post-intervention improvements in quality of life in terms of sensory ability, autonomy, social participation/isolation, death and dying domain, and overall quality of life scores. However, none of these significant effects were maintained 3 months after exercise intervention cessation. Conclusions Semi-immersive VR exercise may be a feasible strategy toward enhancing the quality of life of older adults. However, the participants’ quality of life was not maintained upon exercise cessation, indicating that older adults need to be encouraged to exercise regularly to maintain a good quality of life. VR may need to be combined with other modes of intervention in the future to facilitate long-term quality-of-life improvement in older adults.

Section: Discussionmentioning

confidence: 99%

Effects of semi-immersive virtual reality exercise on the quality of life of community-dwelling older adults: Three-month follow-up of a randomized controlled trial

Wang

2024

“…Similar to the implementation of other healthcare technologies, their usability, acceptance, and effects on knee health are worth further investigation among the end users. 33 – 39…”

Section: Discussionmentioning

confidence: 99%

Automated machine learning-based prediction of the progression of knee pain, functional decline, and incidence of knee osteoarthritis in individuals at high risk of knee osteoarthritis: Data from the osteoarthritis initiative study

Chen,

2023

Self Cite

Objective This study aimed to examine the performance of machine learning models in predicting the progression of knee pain, functional decline, and incidence of knee osteoarthritis (OA) in high-risk individuals, with automated machine learning (AutoML) being used to automate the prediction process. Design There were four stages in the process of our AutoML-integrated prediction. Stage 1—Data preparation: The data of 3200 eligible individuals in the Osteoarthritis Initiative (OAI) study who were considered at high risk of knee OA at the baseline visit were extracted and used. Specifically, 1094 variables from the OAI study were used to predict the changes in knee pain, physical function, and incidence of knee OA (i.e. the first occurrence of frequent knee symptoms and definite tibial osteophytes (Kellgren and Lawrence grade ≥2)) over a 9-year period. Stage 2—Model training: The AutoML approach was used to automatically train nine widely used machine learning (ML) models. Stage 3—Model testing: The AutoML approach was used to automatically test the performance of the ML models. Stage 4—Selection of important input variables: The AutoML approach automated the process of computing the importance scores of all input variables and identifying the most important ones, using the technique of permutation feature importance. Results Using the AutoML approach, the weighted ensemble model and the CatBoost model showed the best performance among all nine ML models. For the prediction of each outcome in each year, the five most important input variables were identified, most of which were obtained from self-reported questionnaire surveys and radiographic imaging reports. Conclusion The AutoML approach has shown potential in automating the process of using ML models to predict long-term changes in knee OA-related outcomes. Its use could support the deployment of ML solutions, facilitating the provision of personalized interventions to prevent the deterioration of knee health and incident knee OA.

“… 20 – 26 Moreover, users’ perceptions of a technology, such as its ease of use and usefulness, can influence their attitudes toward the technology and ultimately impact their acceptance of the technology. 8 , 27 – 39 In the context of the use of technology in poststroke motor rehabilitation, stroke patients’ perceptions of VR-based rehabilitation programmes can also influence their acceptance of and adherence to the programmes; however, research on this topic has been limited.…”

Section: Introductionmentioning

confidence: 99%

Effectiveness, safety and patients’ perceptions of an immersive virtual reality–based exercise system for poststroke upper limb motor rehabilitation: A proof-of-concept and feasibility randomized controlled trial

Chen,

Or,

et al. 2023

Self Cite

Objective This study aimed to examine the effectiveness, safety and patients’ perceptions of an immersive virtual reality (VR)–based exercise system for poststroke upper limb rehabilitation. Methods A proof-of-concept, 2-week randomized controlled trial was conducted. Fifty stroke patients were randomly assigned to either use the immersive VR-based exercise system to perform upper limb exercises for 2 weeks (intervention) or play commercial games (control). Effectiveness, safety and patients’ perceptions of the exercise system were assessed at baseline and at 1- and 2-week follow-ups. Results Intention-to-treat analysis revealed that after 2 weeks, statistically significant improvements in shoulder flexion active range of motion (AROM), shoulder abduction AROM, perceived upper limb motor function and quality of life (QoL) were observed in one or both groups, but not between the groups. Per-protocol analysis showed that after 2 weeks: (i) statistically significant improvement in shoulder abduction AROM was obtained in the intervention group, and the difference in the mean changes between the groups was statistically significant; (ii) statistically significant improvements in coordination/speed (Fugl–Meyer Assessment for Upper Extremity), shoulder flexion AROM, perceived upper limb motor function and QoL were obtained in one or both groups, but not between the groups. Conclusions The immersive VR-based exercise system is a potentially effective, safe and acceptable approach for supporting poststroke motor rehabilitation. These findings can serve as a basis for larger-scale studies on the application of VR for poststroke exercises.