Autonomous modeling of repetitive movement for rehabilitation exercise monitoring
Abstract Background Insightful feedback generation for daily home-based stroke rehabilitation is currently unavailable due to the inefficiency of exercise inspection done by therapists. We aim to produce a compact anomaly representation that allows a therapist to pay attention to only a few specific...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-07-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-022-01907-5 |
| _version_ | 1811328531174522880 |
|---|---|
| author | Prayook Jatesiktat Guan Ming Lim Christopher Wee Keong Kuah Dollaporn Anopas Wei Tech Ang |
| author_facet | Prayook Jatesiktat Guan Ming Lim Christopher Wee Keong Kuah Dollaporn Anopas Wei Tech Ang |
| author_sort | Prayook Jatesiktat |
| collection | DOAJ |
| description | Abstract Background Insightful feedback generation for daily home-based stroke rehabilitation is currently unavailable due to the inefficiency of exercise inspection done by therapists. We aim to produce a compact anomaly representation that allows a therapist to pay attention to only a few specific sections in a long exercise session record and boost their efficiency in feedback generation. Methods This study proposes a data-driven technique to model a repetitive exercise using unsupervised phase learning on an artificial neural network and statistical learning on principal component analysis (PCA). After a model is built on a set of normal healthy movements, the model can be used to extract a sequence of anomaly scores from a movement of the same prescription. Results The method not only works on a standard marker-based motion capture system but also performs well on a more compact and affordable motion capture system based-on Kinect V2 and wrist-worn inertial measurement units that can be used at home. An evaluation of four different exercises shows its potential in separating anomalous movements from normal ones with an average area under the curve (AUC) of 0.9872 even on the compact motion capture system. Conclusions The proposed processing technique has the potential to help clinicians in providing high-quality feedback for telerehabilitation in a more scalable way. |
| first_indexed | 2024-04-13T15:27:49Z |
| format | Article |
| id | doaj.art-714df0b985574bd889765d4713cc88df |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-04-13T15:27:49Z |
| publishDate | 2022-07-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-714df0b985574bd889765d4713cc88df2022-12-22T02:41:28ZengBMCBMC Medical Informatics and Decision Making1472-69472022-07-0122111910.1186/s12911-022-01907-5Autonomous modeling of repetitive movement for rehabilitation exercise monitoringPrayook Jatesiktat0Guan Ming Lim1Christopher Wee Keong Kuah2Dollaporn Anopas3Wei Tech Ang4Rehabilitation Research Institute of Singapore, Nanyang Technological UniversitySchool of Mechanical and Aerospace Engineering, Nanyang Technological UniversityRehabilitation Centre, Centre for Advanced Rehabilitation Therapeutics, Tan Tock Seng HospitalBiodesign Innovation Center, Department of Parasitology, Faculty of Medicine Siriraj Hospital, Mahidol UniversityRehabilitation Research Institute of Singapore, Nanyang Technological UniversityAbstract Background Insightful feedback generation for daily home-based stroke rehabilitation is currently unavailable due to the inefficiency of exercise inspection done by therapists. We aim to produce a compact anomaly representation that allows a therapist to pay attention to only a few specific sections in a long exercise session record and boost their efficiency in feedback generation. Methods This study proposes a data-driven technique to model a repetitive exercise using unsupervised phase learning on an artificial neural network and statistical learning on principal component analysis (PCA). After a model is built on a set of normal healthy movements, the model can be used to extract a sequence of anomaly scores from a movement of the same prescription. Results The method not only works on a standard marker-based motion capture system but also performs well on a more compact and affordable motion capture system based-on Kinect V2 and wrist-worn inertial measurement units that can be used at home. An evaluation of four different exercises shows its potential in separating anomalous movements from normal ones with an average area under the curve (AUC) of 0.9872 even on the compact motion capture system. Conclusions The proposed processing technique has the potential to help clinicians in providing high-quality feedback for telerehabilitation in a more scalable way.https://doi.org/10.1186/s12911-022-01907-5Anomaly detectionRehabilitation exerciseRepetitive movementSegmentationTime normalizationUpper limb kinematics |
| spellingShingle | Prayook Jatesiktat Guan Ming Lim Christopher Wee Keong Kuah Dollaporn Anopas Wei Tech Ang Autonomous modeling of repetitive movement for rehabilitation exercise monitoring BMC Medical Informatics and Decision Making Anomaly detection Rehabilitation exercise Repetitive movement Segmentation Time normalization Upper limb kinematics |
| title | Autonomous modeling of repetitive movement for rehabilitation exercise monitoring |
| title_full | Autonomous modeling of repetitive movement for rehabilitation exercise monitoring |
| title_fullStr | Autonomous modeling of repetitive movement for rehabilitation exercise monitoring |
| title_full_unstemmed | Autonomous modeling of repetitive movement for rehabilitation exercise monitoring |
| title_short | Autonomous modeling of repetitive movement for rehabilitation exercise monitoring |
| title_sort | autonomous modeling of repetitive movement for rehabilitation exercise monitoring |
| topic | Anomaly detection Rehabilitation exercise Repetitive movement Segmentation Time normalization Upper limb kinematics |
| url | https://doi.org/10.1186/s12911-022-01907-5 |
| work_keys_str_mv | AT prayookjatesiktat autonomousmodelingofrepetitivemovementforrehabilitationexercisemonitoring AT guanminglim autonomousmodelingofrepetitivemovementforrehabilitationexercisemonitoring AT christopherweekeongkuah autonomousmodelingofrepetitivemovementforrehabilitationexercisemonitoring AT dollapornanopas autonomousmodelingofrepetitivemovementforrehabilitationexercisemonitoring AT weitechang autonomousmodelingofrepetitivemovementforrehabilitationexercisemonitoring |