Development and Validation of an Interpretable Machine Learning Model for Predicting Tic Disorders and Severity in Children Based on Electroencephalogram Data

Accurate diagnosis of Tic disorders (TD) and its severity based on electroencephalogram (EEG) data were of great clinical importance. This study analyzed EEG data from 90 children with TD and 88 healthy controls (HC). A two-stage progressive diagnosis framework based on EEG data and machine learning...

Full description

Saved in:
Bibliographic Details
Main Authors: Wanting Xiang, Gang Zhu, Yichong Hou, Zhandong Mei, Lin Wan, Li Zhang, Guang Yang, Jian Zu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Transactions on Neural Systems and Rehabilitation Engineering
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11036828/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850163486474108928
author Wanting Xiang
Gang Zhu
Yichong Hou
Zhandong Mei
Lin Wan
Li Zhang
Guang Yang
Jian Zu
author_facet Wanting Xiang
Gang Zhu
Yichong Hou
Zhandong Mei
Lin Wan
Li Zhang
Guang Yang
Jian Zu
author_sort Wanting Xiang
collection DOAJ
description Accurate diagnosis of Tic disorders (TD) and its severity based on electroencephalogram (EEG) data were of great clinical importance. This study analyzed EEG data from 90 children with TD and 88 healthy controls (HC). A two-stage progressive diagnosis framework based on EEG data and machine learning methods was developed. To achieve individualized prediction and reduce the feature dimension, we proposed a novel individual-based feature-weighted integration method in machine learning, as well as a new SHAP-driven feature selection and weighting (SFSW) strategy to improve the prediction accuracy. Based on 13 weighted features, Logistic Regression model achieved an average accuracy of 94.2% (95% CI, 90.6%-97.9%) in diagnosing TD, with a sensitivity of 92.4% (95% CI, 85.3%-99.5%) and a specificity of 96.1% (95% CI, 92.9%-99.2%). The Decision Tree model attained an average accuracy of 81.5% (95% CI, 68.6%-94.5%) in predicting severity, with a sensitivity of 81.5% (95% CI, 68.6%-94.5%) and a specificity of 89.9% (95% CI, 82.1%-97.6%). In the hold-out set validation, the method demonstrated accuracy rates of 95.7% in diagnosing TD and 83.3% in predicting severity. Interpretability analysis revealed that the top three main features affecting TD diagnosis were the mean frequency (MNF) of P3 channel <inline-formula> <tex-math notation="LaTeX">$\beta $ </tex-math></inline-formula> band, age and MNF of C3 channel <inline-formula> <tex-math notation="LaTeX">$\gamma $ </tex-math></inline-formula> band. This work offered a more efficient approach to individualized diagnosis of TD and had substantial practical value for clinical auxiliary diagnosis and intervention.
format Article
id doaj-art-443ce35eead4436bb750070a0dbad36f
institution OA Journals
issn 1534-4320
1558-0210
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Transactions on Neural Systems and Rehabilitation Engineering
spelling doaj-art-443ce35eead4436bb750070a0dbad36f2025-08-20T02:22:15ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102025-01-01332416242710.1109/TNSRE.2025.357976311036828Development and Validation of an Interpretable Machine Learning Model for Predicting Tic Disorders and Severity in Children Based on Electroencephalogram DataWanting Xiang0Gang Zhu1Yichong Hou2Zhandong Mei3Lin Wan4Li Zhang5Guang Yang6Jian Zu7https://orcid.org/0000-0003-3633-0725School of Mathematics and Statistics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, ChinaDepartment of Pediatrics, The First Medical Center, Chinese PLA General Hospital, Beijing, ChinaSchool of Mathematics and Statistics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, ChinaSchool of Mathematics and Statistics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, ChinaDepartment of Pediatrics, The First Medical Center, Chinese PLA General Hospital, Beijing, ChinaChinese Institute for Brain Research, Beijing, ChinaDepartment of Pediatrics, The First Medical Center, Chinese PLA General Hospital, Beijing, ChinaSchool of Mathematics and Statistics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, ChinaAccurate diagnosis of Tic disorders (TD) and its severity based on electroencephalogram (EEG) data were of great clinical importance. This study analyzed EEG data from 90 children with TD and 88 healthy controls (HC). A two-stage progressive diagnosis framework based on EEG data and machine learning methods was developed. To achieve individualized prediction and reduce the feature dimension, we proposed a novel individual-based feature-weighted integration method in machine learning, as well as a new SHAP-driven feature selection and weighting (SFSW) strategy to improve the prediction accuracy. Based on 13 weighted features, Logistic Regression model achieved an average accuracy of 94.2% (95% CI, 90.6%-97.9%) in diagnosing TD, with a sensitivity of 92.4% (95% CI, 85.3%-99.5%) and a specificity of 96.1% (95% CI, 92.9%-99.2%). The Decision Tree model attained an average accuracy of 81.5% (95% CI, 68.6%-94.5%) in predicting severity, with a sensitivity of 81.5% (95% CI, 68.6%-94.5%) and a specificity of 89.9% (95% CI, 82.1%-97.6%). In the hold-out set validation, the method demonstrated accuracy rates of 95.7% in diagnosing TD and 83.3% in predicting severity. Interpretability analysis revealed that the top three main features affecting TD diagnosis were the mean frequency (MNF) of P3 channel <inline-formula> <tex-math notation="LaTeX">$\beta $ </tex-math></inline-formula> band, age and MNF of C3 channel <inline-formula> <tex-math notation="LaTeX">$\gamma $ </tex-math></inline-formula> band. This work offered a more efficient approach to individualized diagnosis of TD and had substantial practical value for clinical auxiliary diagnosis and intervention.https://ieeexplore.ieee.org/document/11036828/Tic disordersseverityelectroencephalogrammachine learninginterpretability
spellingShingle Wanting Xiang
Gang Zhu
Yichong Hou
Zhandong Mei
Lin Wan
Li Zhang
Guang Yang
Jian Zu
Development and Validation of an Interpretable Machine Learning Model for Predicting Tic Disorders and Severity in Children Based on Electroencephalogram Data
IEEE Transactions on Neural Systems and Rehabilitation Engineering
Tic disorders
severity
electroencephalogram
machine learning
interpretability
title Development and Validation of an Interpretable Machine Learning Model for Predicting Tic Disorders and Severity in Children Based on Electroencephalogram Data
title_full Development and Validation of an Interpretable Machine Learning Model for Predicting Tic Disorders and Severity in Children Based on Electroencephalogram Data
title_fullStr Development and Validation of an Interpretable Machine Learning Model for Predicting Tic Disorders and Severity in Children Based on Electroencephalogram Data
title_full_unstemmed Development and Validation of an Interpretable Machine Learning Model for Predicting Tic Disorders and Severity in Children Based on Electroencephalogram Data
title_short Development and Validation of an Interpretable Machine Learning Model for Predicting Tic Disorders and Severity in Children Based on Electroencephalogram Data
title_sort development and validation of an interpretable machine learning model for predicting tic disorders and severity in children based on electroencephalogram data
topic Tic disorders
severity
electroencephalogram
machine learning
interpretability
url https://ieeexplore.ieee.org/document/11036828/
work_keys_str_mv AT wantingxiang developmentandvalidationofaninterpretablemachinelearningmodelforpredictingticdisordersandseverityinchildrenbasedonelectroencephalogramdata
AT gangzhu developmentandvalidationofaninterpretablemachinelearningmodelforpredictingticdisordersandseverityinchildrenbasedonelectroencephalogramdata
AT yichonghou developmentandvalidationofaninterpretablemachinelearningmodelforpredictingticdisordersandseverityinchildrenbasedonelectroencephalogramdata
AT zhandongmei developmentandvalidationofaninterpretablemachinelearningmodelforpredictingticdisordersandseverityinchildrenbasedonelectroencephalogramdata
AT linwan developmentandvalidationofaninterpretablemachinelearningmodelforpredictingticdisordersandseverityinchildrenbasedonelectroencephalogramdata
AT lizhang developmentandvalidationofaninterpretablemachinelearningmodelforpredictingticdisordersandseverityinchildrenbasedonelectroencephalogramdata
AT guangyang developmentandvalidationofaninterpretablemachinelearningmodelforpredictingticdisordersandseverityinchildrenbasedonelectroencephalogramdata
AT jianzu developmentandvalidationofaninterpretablemachinelearningmodelforpredictingticdisordersandseverityinchildrenbasedonelectroencephalogramdata