Machine learning approach effectively discriminates between Parkinson’s disease and progressive supranuclear palsy: Multi-level indices of rs-fMRI
Aim: Parkinson’s disease (PD) and progressive supranuclear palsy (PSP) present similar clinical symptoms, but their treatment options and clinical prognosis differ significantly. Therefore, we aimed to discriminate between PD and PSP based on multi-level indices of resting-state functional magnetic...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-09-01
|
| Series: | Brain Research Bulletin |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0361923025002886 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849686188722487296 |
|---|---|
| author | Weiling Cheng Xiao Liang Wei Zeng Jiali Guo Zhibiao Yin Jiankun Dai Daojun Hong Fuqing Zhou Fangjun Li Xin Fang |
| author_facet | Weiling Cheng Xiao Liang Wei Zeng Jiali Guo Zhibiao Yin Jiankun Dai Daojun Hong Fuqing Zhou Fangjun Li Xin Fang |
| author_sort | Weiling Cheng |
| collection | DOAJ |
| description | Aim: Parkinson’s disease (PD) and progressive supranuclear palsy (PSP) present similar clinical symptoms, but their treatment options and clinical prognosis differ significantly. Therefore, we aimed to discriminate between PD and PSP based on multi-level indices of resting-state functional magnetic resonance imaging (rs-fMRI) via the machine learning approach. Materials and methods: A total of 58 PD and 52 PSP patients were prospectively enrolled in this study. Participants were randomly allocated to a training set and a validation set in a 7:3 ratio. Various rs-fMRI indices were extracted, followed by a comprehensive feature screening for each index. We constructed fifteen distinct combinations of indices and selected four machine learning algorithms for model development. Subsequently, different validation templates were employed to assess the classification results and investigate the relationship between the most significant features and clinical assessment scales. Results: The classification performance of logistic regression (LR) and support vector machine (SVM) models, based on multiple index combinations, was significantly superior to that of other machine learning models and combinations when utilizing automatic anatomical labeling (AAL) templates. This has been verified across different templates. Conclusions: The utilization of multiple rs-fMRI indices significantly enhances the performance of machine learning models and can effectively achieve the automatic identification of PD and PSP at the individual level. |
| format | Article |
| id | doaj-art-a50e79b58c5d4c06a80d5e86e7b47d29 |
| institution | DOAJ |
| issn | 1873-2747 |
| language | English |
| publishDate | 2025-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Brain Research Bulletin |
| spelling | doaj-art-a50e79b58c5d4c06a80d5e86e7b47d292025-08-20T03:22:48ZengElsevierBrain Research Bulletin1873-27472025-09-0122911147610.1016/j.brainresbull.2025.111476Machine learning approach effectively discriminates between Parkinson’s disease and progressive supranuclear palsy: Multi-level indices of rs-fMRIWeiling Cheng0Xiao Liang1Wei Zeng2Jiali Guo3Zhibiao Yin4Jiankun Dai5Daojun Hong6Fuqing Zhou7Fangjun Li8Xin Fang9Jiangxi Provincial Key Laboratory for Precision Pathology and Intelligent Diagnosis, Department of Radiology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, Jiangxi, China; Jiangxi Province Medical Imaging Research Institute, Nanchang, Jiangxi, China; Clinical Research Center For Medical Imaging, Nanchang, Jiangxi, ChinaJiangxi Provincial Key Laboratory for Precision Pathology and Intelligent Diagnosis, Department of Radiology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, Jiangxi, China; Jiangxi Province Medical Imaging Research Institute, Nanchang, Jiangxi, China; Clinical Research Center For Medical Imaging, Nanchang, Jiangxi, ChinaJiangxi Provincial Key Laboratory for Precision Pathology and Intelligent Diagnosis, Department of Radiology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, Jiangxi, China; Jiangxi Province Medical Imaging Research Institute, Nanchang, Jiangxi, China; Clinical Research Center For Medical Imaging, Nanchang, Jiangxi, ChinaDepartment of Neurology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, Jiangxi, ChinaDepartment of Neurology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, Jiangxi, ChinaMRI research, GE Healthcare, Beijing, ChinaDepartment of Neurology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, Jiangxi, ChinaJiangxi Provincial Key Laboratory for Precision Pathology and Intelligent Diagnosis, Department of Radiology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, Jiangxi, China; Jiangxi Province Medical Imaging Research Institute, Nanchang, Jiangxi, China; Clinical Research Center For Medical Imaging, Nanchang, Jiangxi, China; Corresponding author at: Jiangxi Provincial Key Laboratory for Precision Pathology and Intelligent Diagnosis, Department of Radiology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, Jiangxi, China.Department of Neurology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, Jiangxi, China; Corresponding authors.Department of Neurology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, Jiangxi, China; Corresponding authors.Aim: Parkinson’s disease (PD) and progressive supranuclear palsy (PSP) present similar clinical symptoms, but their treatment options and clinical prognosis differ significantly. Therefore, we aimed to discriminate between PD and PSP based on multi-level indices of resting-state functional magnetic resonance imaging (rs-fMRI) via the machine learning approach. Materials and methods: A total of 58 PD and 52 PSP patients were prospectively enrolled in this study. Participants were randomly allocated to a training set and a validation set in a 7:3 ratio. Various rs-fMRI indices were extracted, followed by a comprehensive feature screening for each index. We constructed fifteen distinct combinations of indices and selected four machine learning algorithms for model development. Subsequently, different validation templates were employed to assess the classification results and investigate the relationship between the most significant features and clinical assessment scales. Results: The classification performance of logistic regression (LR) and support vector machine (SVM) models, based on multiple index combinations, was significantly superior to that of other machine learning models and combinations when utilizing automatic anatomical labeling (AAL) templates. This has been verified across different templates. Conclusions: The utilization of multiple rs-fMRI indices significantly enhances the performance of machine learning models and can effectively achieve the automatic identification of PD and PSP at the individual level.http://www.sciencedirect.com/science/article/pii/S0361923025002886Parkinson’s diseaseProgressive supranuclear palsyRs-fMRI |
| spellingShingle | Weiling Cheng Xiao Liang Wei Zeng Jiali Guo Zhibiao Yin Jiankun Dai Daojun Hong Fuqing Zhou Fangjun Li Xin Fang Machine learning approach effectively discriminates between Parkinson’s disease and progressive supranuclear palsy: Multi-level indices of rs-fMRI Brain Research Bulletin Parkinson’s disease Progressive supranuclear palsy Rs-fMRI |
| title | Machine learning approach effectively discriminates between Parkinson’s disease and progressive supranuclear palsy: Multi-level indices of rs-fMRI |
| title_full | Machine learning approach effectively discriminates between Parkinson’s disease and progressive supranuclear palsy: Multi-level indices of rs-fMRI |
| title_fullStr | Machine learning approach effectively discriminates between Parkinson’s disease and progressive supranuclear palsy: Multi-level indices of rs-fMRI |
| title_full_unstemmed | Machine learning approach effectively discriminates between Parkinson’s disease and progressive supranuclear palsy: Multi-level indices of rs-fMRI |
| title_short | Machine learning approach effectively discriminates between Parkinson’s disease and progressive supranuclear palsy: Multi-level indices of rs-fMRI |
| title_sort | machine learning approach effectively discriminates between parkinson s disease and progressive supranuclear palsy multi level indices of rs fmri |
| topic | Parkinson’s disease Progressive supranuclear palsy Rs-fMRI |
| url | http://www.sciencedirect.com/science/article/pii/S0361923025002886 |
| work_keys_str_mv | AT weilingcheng machinelearningapproacheffectivelydiscriminatesbetweenparkinsonsdiseaseandprogressivesupranuclearpalsymultilevelindicesofrsfmri AT xiaoliang machinelearningapproacheffectivelydiscriminatesbetweenparkinsonsdiseaseandprogressivesupranuclearpalsymultilevelindicesofrsfmri AT weizeng machinelearningapproacheffectivelydiscriminatesbetweenparkinsonsdiseaseandprogressivesupranuclearpalsymultilevelindicesofrsfmri AT jialiguo machinelearningapproacheffectivelydiscriminatesbetweenparkinsonsdiseaseandprogressivesupranuclearpalsymultilevelindicesofrsfmri AT zhibiaoyin machinelearningapproacheffectivelydiscriminatesbetweenparkinsonsdiseaseandprogressivesupranuclearpalsymultilevelindicesofrsfmri AT jiankundai machinelearningapproacheffectivelydiscriminatesbetweenparkinsonsdiseaseandprogressivesupranuclearpalsymultilevelindicesofrsfmri AT daojunhong machinelearningapproacheffectivelydiscriminatesbetweenparkinsonsdiseaseandprogressivesupranuclearpalsymultilevelindicesofrsfmri AT fuqingzhou machinelearningapproacheffectivelydiscriminatesbetweenparkinsonsdiseaseandprogressivesupranuclearpalsymultilevelindicesofrsfmri AT fangjunli machinelearningapproacheffectivelydiscriminatesbetweenparkinsonsdiseaseandprogressivesupranuclearpalsymultilevelindicesofrsfmri AT xinfang machinelearningapproacheffectivelydiscriminatesbetweenparkinsonsdiseaseandprogressivesupranuclearpalsymultilevelindicesofrsfmri |