Multi-feature fusion RFE random forest for schizophrenia classification and treatment response prediction
Abstract Schizophrenia(SZ) classification and treatment response prediction hold substantial clinical application value. However, only a limited number of researchers have exploited the multi-feature information derived from resting-state functional magnetic resonance imaging (rs-fMRI) to achieve sh...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-03-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-89359-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850039638255730688 |
|---|---|
| author | Chang Wang Rui Zhang Jiyuan Zhang Yaning Ren Ting Pang Xiangyu Chen Xiao Li Zongya Zhao Yongfeng Yang Wenjie Ren Yi Yu |
| author_facet | Chang Wang Rui Zhang Jiyuan Zhang Yaning Ren Ting Pang Xiangyu Chen Xiao Li Zongya Zhao Yongfeng Yang Wenjie Ren Yi Yu |
| author_sort | Chang Wang |
| collection | DOAJ |
| description | Abstract Schizophrenia(SZ) classification and treatment response prediction hold substantial clinical application value. However, only a limited number of researchers have exploited the multi-feature information derived from resting-state functional magnetic resonance imaging (rs-fMRI) to achieve short-term drug-treatment SZ classification and treatment response prediction. We developed a multi-feature fusion recursive feature elimination random forest (RFE-RF) approach for SZ classification and treatment response prediction. Initially, we computed multiple features, such as regional homogeneity, fractional amplitude of low-frequency fluctuations, and functional connectivity. Subsequently, the RFE-RF method was employed to conduct SZ classification. Moreover, we utilized the rate of score reduction (RR) of the Positive and Negative Symptom Scale (PANSS) to forecast the treatment response of individual patients. Finally, we identified the neuroimaging biomarkers for SZ classification and drug-treatment response prediction. This method achieved the classification results (accuracy = 91.7%, sensitivity = 90.9%, and specificity = 92.6%), and the abnormalities in the visual and default mode networks emerged as potential neuroimaging biomarkers for differentiating SZ from healthy controls (HC). Additionally, we predicted the drug-treatment response of SZ patients in terms of their total PANSS scores, as well as negative and positive symptom scores after eight weeks of treatment. Specifically, the abnormalities in the visual network, sensorimotor network, and right superior frontal gyrus are crucial biomarkers for the short-term drug-treatment response of negative symptoms in SZ patients. Meanwhile, the abnormalities in the visual and default mode networks serve as important biomarkers of the short-term drug-treatment response of positive symptoms. There findings offer novel insights into the neural mechanisms underlying SZ following eight weeks of short-term drug treatment. With further clinical validation in the future, this research may provide potential biomarkers and intervention targets for personalized treatment of SZ. |
| format | Article |
| id | doaj-art-614162a44f554d87ad41b209a693c364 |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-614162a44f554d87ad41b209a693c3642025-08-20T02:56:16ZengNature PortfolioScientific Reports2045-23222025-03-0115111310.1038/s41598-025-89359-5Multi-feature fusion RFE random forest for schizophrenia classification and treatment response predictionChang Wang0Rui Zhang1Jiyuan Zhang2Yaning Ren3Ting Pang4Xiangyu Chen5Xiao Li6Zongya Zhao7Yongfeng Yang8Wenjie Ren9Yi Yu10School of Medical Engineering, Xinxiang Medical UniversitySchool of Medical Engineering, Xinxiang Medical UniversitySchool of Medical Engineering, Xinxiang Medical UniversitySchool of Medical Engineering, Xinxiang Medical UniversitySchool of Medical Engineering, Xinxiang Medical UniversitySchool of Medical Engineering, Xinxiang Medical UniversityHenan Collaborative Innovation Center of Prevention and treatment of mental disorder, the Second Affiliated Hospital of Xinxiang Medical UniversitySchool of Medical Engineering, Xinxiang Medical UniversityHenan Key Laboratory of Biological PsychiatrySchool of Medical Engineering, Xinxiang Medical UniversitySchool of Medical Engineering, Xinxiang Medical UniversityAbstract Schizophrenia(SZ) classification and treatment response prediction hold substantial clinical application value. However, only a limited number of researchers have exploited the multi-feature information derived from resting-state functional magnetic resonance imaging (rs-fMRI) to achieve short-term drug-treatment SZ classification and treatment response prediction. We developed a multi-feature fusion recursive feature elimination random forest (RFE-RF) approach for SZ classification and treatment response prediction. Initially, we computed multiple features, such as regional homogeneity, fractional amplitude of low-frequency fluctuations, and functional connectivity. Subsequently, the RFE-RF method was employed to conduct SZ classification. Moreover, we utilized the rate of score reduction (RR) of the Positive and Negative Symptom Scale (PANSS) to forecast the treatment response of individual patients. Finally, we identified the neuroimaging biomarkers for SZ classification and drug-treatment response prediction. This method achieved the classification results (accuracy = 91.7%, sensitivity = 90.9%, and specificity = 92.6%), and the abnormalities in the visual and default mode networks emerged as potential neuroimaging biomarkers for differentiating SZ from healthy controls (HC). Additionally, we predicted the drug-treatment response of SZ patients in terms of their total PANSS scores, as well as negative and positive symptom scores after eight weeks of treatment. Specifically, the abnormalities in the visual network, sensorimotor network, and right superior frontal gyrus are crucial biomarkers for the short-term drug-treatment response of negative symptoms in SZ patients. Meanwhile, the abnormalities in the visual and default mode networks serve as important biomarkers of the short-term drug-treatment response of positive symptoms. There findings offer novel insights into the neural mechanisms underlying SZ following eight weeks of short-term drug treatment. With further clinical validation in the future, this research may provide potential biomarkers and intervention targets for personalized treatment of SZ.https://doi.org/10.1038/s41598-025-89359-5Schizophrenia classificationTreatment response predictionMulti-feature FusionRecursive feature eliminationRandom Forest |
| spellingShingle | Chang Wang Rui Zhang Jiyuan Zhang Yaning Ren Ting Pang Xiangyu Chen Xiao Li Zongya Zhao Yongfeng Yang Wenjie Ren Yi Yu Multi-feature fusion RFE random forest for schizophrenia classification and treatment response prediction Scientific Reports Schizophrenia classification Treatment response prediction Multi-feature Fusion Recursive feature elimination Random Forest |
| title | Multi-feature fusion RFE random forest for schizophrenia classification and treatment response prediction |
| title_full | Multi-feature fusion RFE random forest for schizophrenia classification and treatment response prediction |
| title_fullStr | Multi-feature fusion RFE random forest for schizophrenia classification and treatment response prediction |
| title_full_unstemmed | Multi-feature fusion RFE random forest for schizophrenia classification and treatment response prediction |
| title_short | Multi-feature fusion RFE random forest for schizophrenia classification and treatment response prediction |
| title_sort | multi feature fusion rfe random forest for schizophrenia classification and treatment response prediction |
| topic | Schizophrenia classification Treatment response prediction Multi-feature Fusion Recursive feature elimination Random Forest |
| url | https://doi.org/10.1038/s41598-025-89359-5 |
| work_keys_str_mv | AT changwang multifeaturefusionrferandomforestforschizophreniaclassificationandtreatmentresponseprediction AT ruizhang multifeaturefusionrferandomforestforschizophreniaclassificationandtreatmentresponseprediction AT jiyuanzhang multifeaturefusionrferandomforestforschizophreniaclassificationandtreatmentresponseprediction AT yaningren multifeaturefusionrferandomforestforschizophreniaclassificationandtreatmentresponseprediction AT tingpang multifeaturefusionrferandomforestforschizophreniaclassificationandtreatmentresponseprediction AT xiangyuchen multifeaturefusionrferandomforestforschizophreniaclassificationandtreatmentresponseprediction AT xiaoli multifeaturefusionrferandomforestforschizophreniaclassificationandtreatmentresponseprediction AT zongyazhao multifeaturefusionrferandomforestforschizophreniaclassificationandtreatmentresponseprediction AT yongfengyang multifeaturefusionrferandomforestforschizophreniaclassificationandtreatmentresponseprediction AT wenjieren multifeaturefusionrferandomforestforschizophreniaclassificationandtreatmentresponseprediction AT yiyu multifeaturefusionrferandomforestforschizophreniaclassificationandtreatmentresponseprediction |