Prediction of Poststroke Depression Based on the Outcomes of Machine Learning Algorithms
Poststroke depression (PSD) is a major psychiatric disorder that develops after stroke; however, whether PSD treatment improves cognitive and functional impairments is not clearly understood. We reviewed data from 31 subjects with PSD and 34 age-matched controls without PSD; all subjects underwent n...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-04-01
|
Series: | Journal of Clinical Medicine |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-0383/11/8/2264 |
_version_ | 1797410660574822400 |
---|---|
author | Yeong Hwan Ryu Seo Young Kim Tae Uk Kim Seong Jae Lee Soo Jun Park Ho-Youl Jung Jung Keun Hyun |
author_facet | Yeong Hwan Ryu Seo Young Kim Tae Uk Kim Seong Jae Lee Soo Jun Park Ho-Youl Jung Jung Keun Hyun |
author_sort | Yeong Hwan Ryu |
collection | DOAJ |
description | Poststroke depression (PSD) is a major psychiatric disorder that develops after stroke; however, whether PSD treatment improves cognitive and functional impairments is not clearly understood. We reviewed data from 31 subjects with PSD and 34 age-matched controls without PSD; all subjects underwent neurological, cognitive, and functional assessments, including the National Institutes of Health Stroke Scale (NIHSS), the Korean version of the Mini-Mental Status Examination (K-MMSE), computerized neurocognitive test (CNT), the Korean version of the Modified Barthel Index (K-MBI), and functional independence measure (FIM) at admission to the rehabilitation unit in the subacute stage following stroke and 4 weeks after initial assessments. Machine learning methods, such as support vector machine, k-nearest neighbors, random forest, voting ensemble models, and statistical analysis using logistic regression were performed. PSD was successfully predicted using a support vector machine with a radial basis function kernel function (area under curve (AUC) = 0.711, accuracy = 0.700). PSD prognoses could be predicted using a support vector machine linear algorithm (AUC = 0.830, accuracy = 0.771). The statistical method did not have a better AUC than that of machine learning algorithms. We concluded that the occurrence and prognosis of PSD in stroke patients can be predicted effectively based on patients’ cognitive and functional statuses using machine learning algorithms. |
first_indexed | 2024-03-09T04:33:24Z |
format | Article |
id | doaj.art-e0a6e36177514709b6ceb92b86840747 |
institution | Directory Open Access Journal |
issn | 2077-0383 |
language | English |
last_indexed | 2024-03-09T04:33:24Z |
publishDate | 2022-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Journal of Clinical Medicine |
spelling | doaj.art-e0a6e36177514709b6ceb92b868407472023-12-03T13:33:14ZengMDPI AGJournal of Clinical Medicine2077-03832022-04-01118226410.3390/jcm11082264Prediction of Poststroke Depression Based on the Outcomes of Machine Learning AlgorithmsYeong Hwan Ryu0Seo Young Kim1Tae Uk Kim2Seong Jae Lee3Soo Jun Park4Ho-Youl Jung5Jung Keun Hyun6Department of Rehabilitation Medicine, College of Medicine, Dankook University, Cheonan 31116, KoreaDepartment of Rehabilitation Medicine, College of Medicine, Dankook University, Cheonan 31116, KoreaDepartment of Rehabilitation Medicine, College of Medicine, Dankook University, Cheonan 31116, KoreaDepartment of Rehabilitation Medicine, College of Medicine, Dankook University, Cheonan 31116, KoreaWelfare & Medical ICT Research Department, Electronics and Telecommunications Research Institute, Daejeon 34129, KoreaWelfare & Medical ICT Research Department, Electronics and Telecommunications Research Institute, Daejeon 34129, KoreaDepartment of Rehabilitation Medicine, College of Medicine, Dankook University, Cheonan 31116, KoreaPoststroke depression (PSD) is a major psychiatric disorder that develops after stroke; however, whether PSD treatment improves cognitive and functional impairments is not clearly understood. We reviewed data from 31 subjects with PSD and 34 age-matched controls without PSD; all subjects underwent neurological, cognitive, and functional assessments, including the National Institutes of Health Stroke Scale (NIHSS), the Korean version of the Mini-Mental Status Examination (K-MMSE), computerized neurocognitive test (CNT), the Korean version of the Modified Barthel Index (K-MBI), and functional independence measure (FIM) at admission to the rehabilitation unit in the subacute stage following stroke and 4 weeks after initial assessments. Machine learning methods, such as support vector machine, k-nearest neighbors, random forest, voting ensemble models, and statistical analysis using logistic regression were performed. PSD was successfully predicted using a support vector machine with a radial basis function kernel function (area under curve (AUC) = 0.711, accuracy = 0.700). PSD prognoses could be predicted using a support vector machine linear algorithm (AUC = 0.830, accuracy = 0.771). The statistical method did not have a better AUC than that of machine learning algorithms. We concluded that the occurrence and prognosis of PSD in stroke patients can be predicted effectively based on patients’ cognitive and functional statuses using machine learning algorithms.https://www.mdpi.com/2077-0383/11/8/2264poststroke depressionpredictionmachine learningfunctional scalecognitive scale |
spellingShingle | Yeong Hwan Ryu Seo Young Kim Tae Uk Kim Seong Jae Lee Soo Jun Park Ho-Youl Jung Jung Keun Hyun Prediction of Poststroke Depression Based on the Outcomes of Machine Learning Algorithms Journal of Clinical Medicine poststroke depression prediction machine learning functional scale cognitive scale |
title | Prediction of Poststroke Depression Based on the Outcomes of Machine Learning Algorithms |
title_full | Prediction of Poststroke Depression Based on the Outcomes of Machine Learning Algorithms |
title_fullStr | Prediction of Poststroke Depression Based on the Outcomes of Machine Learning Algorithms |
title_full_unstemmed | Prediction of Poststroke Depression Based on the Outcomes of Machine Learning Algorithms |
title_short | Prediction of Poststroke Depression Based on the Outcomes of Machine Learning Algorithms |
title_sort | prediction of poststroke depression based on the outcomes of machine learning algorithms |
topic | poststroke depression prediction machine learning functional scale cognitive scale |
url | https://www.mdpi.com/2077-0383/11/8/2264 |
work_keys_str_mv | AT yeonghwanryu predictionofpoststrokedepressionbasedontheoutcomesofmachinelearningalgorithms AT seoyoungkim predictionofpoststrokedepressionbasedontheoutcomesofmachinelearningalgorithms AT taeukkim predictionofpoststrokedepressionbasedontheoutcomesofmachinelearningalgorithms AT seongjaelee predictionofpoststrokedepressionbasedontheoutcomesofmachinelearningalgorithms AT soojunpark predictionofpoststrokedepressionbasedontheoutcomesofmachinelearningalgorithms AT hoyouljung predictionofpoststrokedepressionbasedontheoutcomesofmachinelearningalgorithms AT jungkeunhyun predictionofpoststrokedepressionbasedontheoutcomesofmachinelearningalgorithms |