An innovative model based on machine learning and fuzzy logic for tracking lower limb exercises in stroke patients
Abstract Rehabilitation after a stroke is vital for regaining functional abilities. However, a shortage of rehabilitation professionals leads to many patients with severe disabilities. Traditional rehabilitation methods can be time-consuming and hard to measure for progress. This study introduces an...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-04-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-90031-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849765522163367936 |
|---|---|
| author | Utpal Chandra Das Ngoc Thien Le Timporn Vitoonpong Chalermdej Prapinpairoj Kawee Anannub Wasan Akarathanawat Aurauma Chutinet Nijasri Charnnarong Suwanwela Pasu Kaewplung Surachai Chaitusaney Watit Benjapolakul |
| author_facet | Utpal Chandra Das Ngoc Thien Le Timporn Vitoonpong Chalermdej Prapinpairoj Kawee Anannub Wasan Akarathanawat Aurauma Chutinet Nijasri Charnnarong Suwanwela Pasu Kaewplung Surachai Chaitusaney Watit Benjapolakul |
| author_sort | Utpal Chandra Das |
| collection | DOAJ |
| description | Abstract Rehabilitation after a stroke is vital for regaining functional abilities. However, a shortage of rehabilitation professionals leads to many patients with severe disabilities. Traditional rehabilitation methods can be time-consuming and hard to measure for progress. This study introduces an innovative machine learning (ML) approach for lower limb rehabilitation in stroke patients. The proposed methodology integrates two models: a fuzzy logic rule-based system and a K-Nearest Neighbor(K-NN) machine learning model. The rule-based model utilizes the Fugl-Meyer Assessment to evaluate lower limb angles during exercises using a camera without human intervention. The hybrid fuzzy logic-based ML model continuously tracks the desired angle, counts exercise repetitions, and provides real-time feedback on patient progress. Furthermore, it measures the Range of Motion (ROM) for each repetition, presenting a graphical visualization of ROMs for ten repetitions simultaneously. The model facilitates real-time evaluation of rehabilitation progress by clinicians, with the lowest observed error rate of $$0.34^\circ$$ of angle measurement. The K-NN model assesses rehabilitation exercise accuracy levels, presenting results graphically, with machine learning accuracy rates of $$97\%$$ , $$92\%$$ , and $$91\%$$ for hip flexion, hip external rotation, and knee extension rehabilitation exercises. Model training utilized data from 30 experienced physical therapists at King Chulalongkorn Memorial Hospital, Bangkok, Thailand, garnering positive evaluations from rehabilitation doctors. The proposed ML-based models offer real-time and prerecorded video capabilities, enabling telerehabilitation applications. This research highlights the potential of ML-based methodologies in stroke rehabilitation to enhance accuracy, efficiency, and patient outcomes. |
| format | Article |
| id | doaj-art-cdec6de27bba4236a3f0dcd24cf6362d |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-cdec6de27bba4236a3f0dcd24cf6362d2025-08-20T03:04:50ZengNature PortfolioScientific Reports2045-23222025-04-0115112010.1038/s41598-025-90031-1An innovative model based on machine learning and fuzzy logic for tracking lower limb exercises in stroke patientsUtpal Chandra Das0Ngoc Thien Le1Timporn Vitoonpong2Chalermdej Prapinpairoj3Kawee Anannub4Wasan Akarathanawat5Aurauma Chutinet6Nijasri Charnnarong Suwanwela7Pasu Kaewplung8Surachai Chaitusaney9Watit Benjapolakul10Center of Excellence in Artificial Intelligence, Machine Learning and Smart Grid Technology, Department of Electrical Engineering, Faculty of Engineering, Chulalongkorn UniversityCenter of Excellence in Artificial Intelligence, Machine Learning and Smart Grid Technology, Department of Electrical Engineering, Faculty of Engineering, Chulalongkorn UniversityDepartment of Rehabilitation Medicine, Faculty of Medicine, Chulalongkorn UniversityDepartment of Rehabilitation Medicine, King Chulalongkorn Memorial Hospital, The Thai Red Cross SocietyHealth Service Center, Chulalongkorn UniversityDivision of Neurology, Department of Medicine, Faculty of Medicine, Chulalongkorn UniversityDivision of Neurology, Department of Medicine, Faculty of Medicine, Chulalongkorn UniversityDivision of Neurology, Department of Medicine, Faculty of Medicine, Chulalongkorn UniversityCenter of Excellence in Artificial Intelligence, Machine Learning and Smart Grid Technology, Department of Electrical Engineering, Faculty of Engineering, Chulalongkorn UniversityCenter of Excellence in Artificial Intelligence, Machine Learning and Smart Grid Technology, Department of Electrical Engineering, Faculty of Engineering, Chulalongkorn UniversityCenter of Excellence in Artificial Intelligence, Machine Learning and Smart Grid Technology, Department of Electrical Engineering, Faculty of Engineering, Chulalongkorn UniversityAbstract Rehabilitation after a stroke is vital for regaining functional abilities. However, a shortage of rehabilitation professionals leads to many patients with severe disabilities. Traditional rehabilitation methods can be time-consuming and hard to measure for progress. This study introduces an innovative machine learning (ML) approach for lower limb rehabilitation in stroke patients. The proposed methodology integrates two models: a fuzzy logic rule-based system and a K-Nearest Neighbor(K-NN) machine learning model. The rule-based model utilizes the Fugl-Meyer Assessment to evaluate lower limb angles during exercises using a camera without human intervention. The hybrid fuzzy logic-based ML model continuously tracks the desired angle, counts exercise repetitions, and provides real-time feedback on patient progress. Furthermore, it measures the Range of Motion (ROM) for each repetition, presenting a graphical visualization of ROMs for ten repetitions simultaneously. The model facilitates real-time evaluation of rehabilitation progress by clinicians, with the lowest observed error rate of $$0.34^\circ$$ of angle measurement. The K-NN model assesses rehabilitation exercise accuracy levels, presenting results graphically, with machine learning accuracy rates of $$97\%$$ , $$92\%$$ , and $$91\%$$ for hip flexion, hip external rotation, and knee extension rehabilitation exercises. Model training utilized data from 30 experienced physical therapists at King Chulalongkorn Memorial Hospital, Bangkok, Thailand, garnering positive evaluations from rehabilitation doctors. The proposed ML-based models offer real-time and prerecorded video capabilities, enabling telerehabilitation applications. This research highlights the potential of ML-based methodologies in stroke rehabilitation to enhance accuracy, efficiency, and patient outcomes.https://doi.org/10.1038/s41598-025-90031-1RehabilitationLower limb recoveryFuzzy logicK-NN modelMediaPipe pose |
| spellingShingle | Utpal Chandra Das Ngoc Thien Le Timporn Vitoonpong Chalermdej Prapinpairoj Kawee Anannub Wasan Akarathanawat Aurauma Chutinet Nijasri Charnnarong Suwanwela Pasu Kaewplung Surachai Chaitusaney Watit Benjapolakul An innovative model based on machine learning and fuzzy logic for tracking lower limb exercises in stroke patients Scientific Reports Rehabilitation Lower limb recovery Fuzzy logic K-NN model MediaPipe pose |
| title | An innovative model based on machine learning and fuzzy logic for tracking lower limb exercises in stroke patients |
| title_full | An innovative model based on machine learning and fuzzy logic for tracking lower limb exercises in stroke patients |
| title_fullStr | An innovative model based on machine learning and fuzzy logic for tracking lower limb exercises in stroke patients |
| title_full_unstemmed | An innovative model based on machine learning and fuzzy logic for tracking lower limb exercises in stroke patients |
| title_short | An innovative model based on machine learning and fuzzy logic for tracking lower limb exercises in stroke patients |
| title_sort | innovative model based on machine learning and fuzzy logic for tracking lower limb exercises in stroke patients |
| topic | Rehabilitation Lower limb recovery Fuzzy logic K-NN model MediaPipe pose |
| url | https://doi.org/10.1038/s41598-025-90031-1 |
| work_keys_str_mv | AT utpalchandradas aninnovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT ngocthienle aninnovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT timpornvitoonpong aninnovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT chalermdejprapinpairoj aninnovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT kaweeanannub aninnovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT wasanakarathanawat aninnovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT auraumachutinet aninnovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT nijasricharnnarongsuwanwela aninnovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT pasukaewplung aninnovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT surachaichaitusaney aninnovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT watitbenjapolakul aninnovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT utpalchandradas innovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT ngocthienle innovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT timpornvitoonpong innovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT chalermdejprapinpairoj innovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT kaweeanannub innovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT wasanakarathanawat innovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT auraumachutinet innovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT nijasricharnnarongsuwanwela innovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT pasukaewplung innovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT surachaichaitusaney innovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients AT watitbenjapolakul innovativemodelbasedonmachinelearningandfuzzylogicfortrackinglowerlimbexercisesinstrokepatients |