PD_EBM: An Integrated Boosting Approach Based on Selective Features for Unveiling Parkinson's Disease Diagnosis With Global and Local Explanations
ABSTRACT Early detection and characterization are crucial for treating and managing Parkinson's disease (PD). The increasing prevalence of PD and its significant impact on the motor neurons of the brain impose a substantial burden on the healthcare system. Early‐stage detection is vital for imp...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | Engineering Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/eng2.13091 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576626065408000 |
|---|---|
| author | Fahmida Khanom Mohammad Shorif Uddin Rafid Mostafiz |
| author_facet | Fahmida Khanom Mohammad Shorif Uddin Rafid Mostafiz |
| author_sort | Fahmida Khanom |
| collection | DOAJ |
| description | ABSTRACT Early detection and characterization are crucial for treating and managing Parkinson's disease (PD). The increasing prevalence of PD and its significant impact on the motor neurons of the brain impose a substantial burden on the healthcare system. Early‐stage detection is vital for improving patient outcomes and reducing healthcare costs. This study introduces an ensemble boosting machine, termed PD_EBM, for the detection of PD. PD_EBM leverages machine learning (ML) algorithms and a hybrid feature selection approach to enhance diagnostic accuracy. While ML has shown promise in medical applications for PD detection, the interpretability of these models remains a significant challenge. Explainable machine learning (XML) addresses this by providing transparency and clarity in model predictions. Techniques such as Local Interpretable Model‐agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) have become popular for interpreting these models. Our experiment used a dataset of 195 clinical records of PD patients from the University of California Irvine (UCI) Machine Learning repository. Comprehensive data preparation included encoding categorical features, imputing missing values, removing outliers, addressing data imbalance, scaling data, selecting relevant features, and so on. We propose a hybrid boosting framework that focuses on the most important features for prediction. Our boosting model employs a Decision Tree (DT) classifier with AdaBoost, followed by a linear discriminant analysis (LDA) optimizer, achieving an impressive accuracy of 99.44%, outperforming other boosting models. |
| format | Article |
| id | doaj-art-76209f7076bb4f938bdb9a818fe5c33b |
| institution | Kabale University |
| issn | 2577-8196 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Engineering Reports |
| spelling | doaj-art-76209f7076bb4f938bdb9a818fe5c33b2025-01-31T00:22:49ZengWileyEngineering Reports2577-81962025-01-0171n/an/a10.1002/eng2.13091PD_EBM: An Integrated Boosting Approach Based on Selective Features for Unveiling Parkinson's Disease Diagnosis With Global and Local ExplanationsFahmida Khanom0Mohammad Shorif Uddin1Rafid Mostafiz2Department of Mathematics American International University‐Bangladesh Kuratoli Khilkhet BangladeshDepartment of Computer Science and Engineering Jahangirnagar University Savar Dhaka BangladeshInstitute of Information Technology Noakhali Science and Technology University Noakhali BangladeshABSTRACT Early detection and characterization are crucial for treating and managing Parkinson's disease (PD). The increasing prevalence of PD and its significant impact on the motor neurons of the brain impose a substantial burden on the healthcare system. Early‐stage detection is vital for improving patient outcomes and reducing healthcare costs. This study introduces an ensemble boosting machine, termed PD_EBM, for the detection of PD. PD_EBM leverages machine learning (ML) algorithms and a hybrid feature selection approach to enhance diagnostic accuracy. While ML has shown promise in medical applications for PD detection, the interpretability of these models remains a significant challenge. Explainable machine learning (XML) addresses this by providing transparency and clarity in model predictions. Techniques such as Local Interpretable Model‐agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) have become popular for interpreting these models. Our experiment used a dataset of 195 clinical records of PD patients from the University of California Irvine (UCI) Machine Learning repository. Comprehensive data preparation included encoding categorical features, imputing missing values, removing outliers, addressing data imbalance, scaling data, selecting relevant features, and so on. We propose a hybrid boosting framework that focuses on the most important features for prediction. Our boosting model employs a Decision Tree (DT) classifier with AdaBoost, followed by a linear discriminant analysis (LDA) optimizer, achieving an impressive accuracy of 99.44%, outperforming other boosting models.https://doi.org/10.1002/eng2.13091boosting machineexplainable AILDALIMEParkinson's diseaseSHAP |
| spellingShingle | Fahmida Khanom Mohammad Shorif Uddin Rafid Mostafiz PD_EBM: An Integrated Boosting Approach Based on Selective Features for Unveiling Parkinson's Disease Diagnosis With Global and Local Explanations Engineering Reports boosting machine explainable AI LDA LIME Parkinson's disease SHAP |
| title | PD_EBM: An Integrated Boosting Approach Based on Selective Features for Unveiling Parkinson's Disease Diagnosis With Global and Local Explanations |
| title_full | PD_EBM: An Integrated Boosting Approach Based on Selective Features for Unveiling Parkinson's Disease Diagnosis With Global and Local Explanations |
| title_fullStr | PD_EBM: An Integrated Boosting Approach Based on Selective Features for Unveiling Parkinson's Disease Diagnosis With Global and Local Explanations |
| title_full_unstemmed | PD_EBM: An Integrated Boosting Approach Based on Selective Features for Unveiling Parkinson's Disease Diagnosis With Global and Local Explanations |
| title_short | PD_EBM: An Integrated Boosting Approach Based on Selective Features for Unveiling Parkinson's Disease Diagnosis With Global and Local Explanations |
| title_sort | pd ebm an integrated boosting approach based on selective features for unveiling parkinson s disease diagnosis with global and local explanations |
| topic | boosting machine explainable AI LDA LIME Parkinson's disease SHAP |
| url | https://doi.org/10.1002/eng2.13091 |
| work_keys_str_mv | AT fahmidakhanom pdebmanintegratedboostingapproachbasedonselectivefeaturesforunveilingparkinsonsdiseasediagnosiswithglobalandlocalexplanations AT mohammadshorifuddin pdebmanintegratedboostingapproachbasedonselectivefeaturesforunveilingparkinsonsdiseasediagnosiswithglobalandlocalexplanations AT rafidmostafiz pdebmanintegratedboostingapproachbasedonselectivefeaturesforunveilingparkinsonsdiseasediagnosiswithglobalandlocalexplanations |