Effects of Artificial Intelligence Rehabilitation on Motor ability and Daily living ability of Hemiplegic Patients with Stroke—Meta-Analysis of Randomized Controlled Trials (Preprint) DOI Creative Commons

Ziwen Chen,

Hou Guanhua,

Lili Yang

et al.

Published: Feb. 10, 2025

BACKGROUND A large number of hemiplegic stroke patients worldwide require rehabilitation. Artificial intelligence (AI) has the potential to conserve human resources and offers broad application prospects. With advancements in medicine technology, AI begun integrating into rehabilitation, providing personalized rehabilitation plans. However, effects on motor daily living abilities remain unclear. OBJECTIVE Evaluate patients. METHODS The Cochrane Library, Web Science, PubMed, Embase, CINAHL, CNKI, VIP, Wanfang databases were systematically searched for randomized controlled trials (RCTs) with stroke. search timeframe was from construction database January 1, 2025. literature screened according nerfing criteria, relevant information extracted, Meta-analysis performed using RevMan5.3 software. RESULTS 16 studies involving 565 hemiplegia included. showed that, compared conventional more effective improving ability [MD=3.35, 95%CI (1.39, 5.32), P<0.001], balance [MD=7.26, (6.37, 8.14), muscle strength grip [SMD=0.65, (0.25, 1.04), P=0.001], perform activities [SMD=1.71, (0.73, 2.69), P<0.001]. improvements limb function [MD=0.11, (-0.06, 0.28), P=0.210], tone [MD=-0.28, (-0.57, 0.02), P=0.060], [MD=-0.04, (-0.49, 0.41), P=0.860], hand dexterity [MD=9.31, (-7.48, 26.09), P=0.280] not statistically significant. Subgroup analyses revealed no statistical difference between machines [MD=1.80, (-1.37, 4.97), P=0.270]. In contrast, virtual reality [MD=5.07, (4.23, 5.91), brain-computer interface [MD=6.99, (3.06, 10.92), telerehabilitation [MD=0.96, (0.23, 1.68), P=0.010] all significantly improved performance. Additionally, interventions a total frequency ≥20 [MD=4.29, (2.21, 6.36), P<0.001] duration ≥6 weeks [MD=3.73, (1.22, 6.24), P=0.004] effective. intervention ≥10 hours [MD=5.71, (3.02, 8.40), also had better effect improvement. that >10 [SMD=3.18, (1.44, 4.93), ability. CONCLUSIONS can improve hemiplegia. Using reality, interface, is recommended, ,with interventions, hours. activities, recommended enhance function, strength, strength. it does function. be More high-quality are needed validate these findings further. CLINICALTRIAL PROSPERO CRD42025636225；https://tinyurl.com/2uc3eac2.

Language: Английский

Effects of Artificial Intelligence Rehabilitation on Motor ability and Daily living ability of Hemiplegic Patients with Stroke—Meta-Analysis of Randomized Controlled Trials (Preprint) DOI Creative Commons

Ziwen Chen,

Hou Guanhua,

Lili Yang

et al.

Published: Feb. 10, 2025

BACKGROUND A large number of hemiplegic stroke patients worldwide require rehabilitation. Artificial intelligence (AI) has the potential to conserve human resources and offers broad application prospects. With advancements in medicine technology, AI begun integrating into rehabilitation, providing personalized rehabilitation plans. However, effects on motor daily living abilities remain unclear. OBJECTIVE Evaluate patients. METHODS The Cochrane Library, Web Science, PubMed, Embase, CINAHL, CNKI, VIP, Wanfang databases were systematically searched for randomized controlled trials (RCTs) with stroke. search timeframe was from construction database January 1, 2025. literature screened according nerfing criteria, relevant information extracted, Meta-analysis performed using RevMan5.3 software. RESULTS 16 studies involving 565 hemiplegia included. showed that, compared conventional more effective improving ability [MD=3.35, 95%CI (1.39, 5.32), P<0.001], balance [MD=7.26, (6.37, 8.14), muscle strength grip [SMD=0.65, (0.25, 1.04), P=0.001], perform activities [SMD=1.71, (0.73, 2.69), P<0.001]. improvements limb function [MD=0.11, (-0.06, 0.28), P=0.210], tone [MD=-0.28, (-0.57, 0.02), P=0.060], [MD=-0.04, (-0.49, 0.41), P=0.860], hand dexterity [MD=9.31, (-7.48, 26.09), P=0.280] not statistically significant. Subgroup analyses revealed no statistical difference between machines [MD=1.80, (-1.37, 4.97), P=0.270]. In contrast, virtual reality [MD=5.07, (4.23, 5.91), brain-computer interface [MD=6.99, (3.06, 10.92), telerehabilitation [MD=0.96, (0.23, 1.68), P=0.010] all significantly improved performance. Additionally, interventions a total frequency ≥20 [MD=4.29, (2.21, 6.36), P<0.001] duration ≥6 weeks [MD=3.73, (1.22, 6.24), P=0.004] effective. intervention ≥10 hours [MD=5.71, (3.02, 8.40), also had better effect improvement. that >10 [SMD=3.18, (1.44, 4.93), ability. CONCLUSIONS can improve hemiplegia. Using reality, interface, is recommended, ,with interventions, hours. activities, recommended enhance function, strength, strength. it does function. be More high-quality are needed validate these findings further. CLINICALTRIAL PROSPERO CRD42025636225；https://tinyurl.com/2uc3eac2.

Language: Английский

Citations

0