Clustering and prediction of long-term functional recovery patterns in first-time stroke patients
ObjectivesThe purpose of this study was to cluster long-term multifaceted functional recovery patterns and to establish prediction models for functional outcome in first-time stroke patients using unsupervised machine learning.MethodsThis study is an interim analysis of the dataset from the Korean S...
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-03-01
|
| Series: | Frontiers in Neurology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fneur.2023.1130236/full |
| _version_ | 1811158328426889216 |
|---|---|
| author | Seyoung Shin Won Hyuk Chang Deog Young Kim Jongmin Lee Min Kyun Sohn Min-Keun Song Yong-Il Shin Yang-Soo Lee Min Cheol Joo So Young Lee Junhee Han Jeonghoon Ahn Gyung-Jae Oh Young-Taek Kim Kwangsu Kim Yun-Hee Kim Yun-Hee Kim |
| author_facet | Seyoung Shin Won Hyuk Chang Deog Young Kim Jongmin Lee Min Kyun Sohn Min-Keun Song Yong-Il Shin Yang-Soo Lee Min Cheol Joo So Young Lee Junhee Han Jeonghoon Ahn Gyung-Jae Oh Young-Taek Kim Kwangsu Kim Yun-Hee Kim Yun-Hee Kim |
| author_sort | Seyoung Shin |
| collection | DOAJ |
| description | ObjectivesThe purpose of this study was to cluster long-term multifaceted functional recovery patterns and to establish prediction models for functional outcome in first-time stroke patients using unsupervised machine learning.MethodsThis study is an interim analysis of the dataset from the Korean Stroke Cohort for Functioning and Rehabilitation (KOSCO), a long-term, prospective, multicenter cohort study of first-time stroke patients. The KOSCO screened 10,636 first-time stroke patients admitted to nine representative hospitals in Korea during a three-year recruitment period, and 7,858 patients agreed to enroll. Early clinical and demographic features of stroke patients and six multifaceted functional assessment scores measured from 7 days to 24 months after stroke onset were used as input variables. K-means clustering analysis was performed, and prediction models were generated and validated using machine learning.ResultsA total of 5,534 stroke patients (4,388 ischemic and 1,146 hemorrhagic; mean age 63·31 ± 12·86; 3,253 [58.78%] male) completed functional assessments 24 months after stroke onset. Through K-means clustering, ischemic stroke (IS) patients were clustered into five groups and hemorrhagic stroke (HS) patients into four groups. Each cluster had distinct clinical characteristics and functional recovery patterns. The final prediction models for IS and HS patients achieved relatively high prediction accuracies of 0.926 and 0.887, respectively.ConclusionsThe longitudinal, multi-dimensional, functional assessment data of first-time stroke patients were successfully clustered, and the prediction models showed relatively good accuracies. Early identification and prediction of long-term functional outcomes will help clinicians develop customized treatment strategies. |
| first_indexed | 2024-04-10T05:22:39Z |
| format | Article |
| id | doaj.art-9d833dc599234edabcbf65cfb14fe3d3 |
| institution | Directory Open Access Journal |
| issn | 1664-2295 |
| language | English |
| last_indexed | 2024-04-10T05:22:39Z |
| publishDate | 2023-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurology |
| spelling | doaj.art-9d833dc599234edabcbf65cfb14fe3d32023-03-08T06:24:40ZengFrontiers Media S.A.Frontiers in Neurology1664-22952023-03-011410.3389/fneur.2023.11302361130236Clustering and prediction of long-term functional recovery patterns in first-time stroke patientsSeyoung Shin0Won Hyuk Chang1Deog Young Kim2Jongmin Lee3Min Kyun Sohn4Min-Keun Song5Yong-Il Shin6Yang-Soo Lee7Min Cheol Joo8So Young Lee9Junhee Han10Jeonghoon Ahn11Gyung-Jae Oh12Young-Taek Kim13Kwangsu Kim14Yun-Hee Kim15Yun-Hee Kim16Department of Physical and Rehabilitation Medicine, Center for Prevention and Rehabilitation, Heart Vascular Stroke Institute, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of KoreaDepartment of Physical and Rehabilitation Medicine, Center for Prevention and Rehabilitation, Heart Vascular Stroke Institute, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of KoreaDepartment and Research Institute of Rehabilitation Medicine, Yonsei University College of Medicine, Seoul, Republic of KoreaDepartment of Rehabilitation Medicine, Konkuk University School of Medicine, Seoul, Republic of KoreaDepartment of Rehabilitation Medicine, College of Medicine, Chungnam National University, Daejeon, Republic of KoreaDepartment of Physical and Rehabilitation Medicine, Chonnam National University Medical School, Gwangju, Republic of KoreaDepartment of Rehabilitation Medicine, Pusan National University School of Medicine, Pusan National University Yangsan Hospital, Yangsan-si, Republic of KoreaDepartment of Rehabilitation Medicine, School of Medicine, Kyungpook National University, Kyungpook National University Hospital, Daegu, Republic of KoreaDepartment of Rehabilitation Medicine, Wonkwang University School of Medicine, Iksan, Republic of KoreaDepartment of Rehabilitation Medicine, Jeju National University Hospital, Jeju National University School of Medicine, Jeju-si, Republic of Korea0Department of Statistics, Hallym University, Chuncheon-si, Republic of Korea1Department of Health Convergence, Ewha Womans University, Seoul, Republic of Korea2Department of Preventive Medicine, School of Medicine, Wonkwang University, Iksan, Republic of Korea3Department of Preventive Medicine, Chungnam National University Hospital, Daejeon, Republic of Korea4College of Computing, Sungkyunkwan University, Suwon-si, Republic of KoreaDepartment of Physical and Rehabilitation Medicine, Center for Prevention and Rehabilitation, Heart Vascular Stroke Institute, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea5Department of Health Sciences and Technology, Department of Medical Device Management and Research, Department of Digital Health, Samsung Advanced Institute for Health Sciences & Technology (SAIHST), Sungkyunkwan University, Seoul, Republic of KoreaObjectivesThe purpose of this study was to cluster long-term multifaceted functional recovery patterns and to establish prediction models for functional outcome in first-time stroke patients using unsupervised machine learning.MethodsThis study is an interim analysis of the dataset from the Korean Stroke Cohort for Functioning and Rehabilitation (KOSCO), a long-term, prospective, multicenter cohort study of first-time stroke patients. The KOSCO screened 10,636 first-time stroke patients admitted to nine representative hospitals in Korea during a three-year recruitment period, and 7,858 patients agreed to enroll. Early clinical and demographic features of stroke patients and six multifaceted functional assessment scores measured from 7 days to 24 months after stroke onset were used as input variables. K-means clustering analysis was performed, and prediction models were generated and validated using machine learning.ResultsA total of 5,534 stroke patients (4,388 ischemic and 1,146 hemorrhagic; mean age 63·31 ± 12·86; 3,253 [58.78%] male) completed functional assessments 24 months after stroke onset. Through K-means clustering, ischemic stroke (IS) patients were clustered into five groups and hemorrhagic stroke (HS) patients into four groups. Each cluster had distinct clinical characteristics and functional recovery patterns. The final prediction models for IS and HS patients achieved relatively high prediction accuracies of 0.926 and 0.887, respectively.ConclusionsThe longitudinal, multi-dimensional, functional assessment data of first-time stroke patients were successfully clustered, and the prediction models showed relatively good accuracies. Early identification and prediction of long-term functional outcomes will help clinicians develop customized treatment strategies.https://www.frontiersin.org/articles/10.3389/fneur.2023.1130236/fullstrokefunctional recoveryartificial intelligencemachine learningclusteringprediction |
| spellingShingle | Seyoung Shin Won Hyuk Chang Deog Young Kim Jongmin Lee Min Kyun Sohn Min-Keun Song Yong-Il Shin Yang-Soo Lee Min Cheol Joo So Young Lee Junhee Han Jeonghoon Ahn Gyung-Jae Oh Young-Taek Kim Kwangsu Kim Yun-Hee Kim Yun-Hee Kim Clustering and prediction of long-term functional recovery patterns in first-time stroke patients Frontiers in Neurology stroke functional recovery artificial intelligence machine learning clustering prediction |
| title | Clustering and prediction of long-term functional recovery patterns in first-time stroke patients |
| title_full | Clustering and prediction of long-term functional recovery patterns in first-time stroke patients |
| title_fullStr | Clustering and prediction of long-term functional recovery patterns in first-time stroke patients |
| title_full_unstemmed | Clustering and prediction of long-term functional recovery patterns in first-time stroke patients |
| title_short | Clustering and prediction of long-term functional recovery patterns in first-time stroke patients |
| title_sort | clustering and prediction of long term functional recovery patterns in first time stroke patients |
| topic | stroke functional recovery artificial intelligence machine learning clustering prediction |
| url | https://www.frontiersin.org/articles/10.3389/fneur.2023.1130236/full |
| work_keys_str_mv | AT seyoungshin clusteringandpredictionoflongtermfunctionalrecoverypatternsinfirsttimestrokepatients AT wonhyukchang clusteringandpredictionoflongtermfunctionalrecoverypatternsinfirsttimestrokepatients AT deogyoungkim clusteringandpredictionoflongtermfunctionalrecoverypatternsinfirsttimestrokepatients AT jongminlee clusteringandpredictionoflongtermfunctionalrecoverypatternsinfirsttimestrokepatients AT minkyunsohn clusteringandpredictionoflongtermfunctionalrecoverypatternsinfirsttimestrokepatients AT minkeunsong clusteringandpredictionoflongtermfunctionalrecoverypatternsinfirsttimestrokepatients AT yongilshin clusteringandpredictionoflongtermfunctionalrecoverypatternsinfirsttimestrokepatients AT yangsoolee clusteringandpredictionoflongtermfunctionalrecoverypatternsinfirsttimestrokepatients AT mincheoljoo clusteringandpredictionoflongtermfunctionalrecoverypatternsinfirsttimestrokepatients AT soyounglee clusteringandpredictionoflongtermfunctionalrecoverypatternsinfirsttimestrokepatients AT junheehan clusteringandpredictionoflongtermfunctionalrecoverypatternsinfirsttimestrokepatients AT jeonghoonahn clusteringandpredictionoflongtermfunctionalrecoverypatternsinfirsttimestrokepatients AT gyungjaeoh clusteringandpredictionoflongtermfunctionalrecoverypatternsinfirsttimestrokepatients AT youngtaekkim clusteringandpredictionoflongtermfunctionalrecoverypatternsinfirsttimestrokepatients AT kwangsukim clusteringandpredictionoflongtermfunctionalrecoverypatternsinfirsttimestrokepatients AT yunheekim clusteringandpredictionoflongtermfunctionalrecoverypatternsinfirsttimestrokepatients AT yunheekim clusteringandpredictionoflongtermfunctionalrecoverypatternsinfirsttimestrokepatients |