Enhancing Self-Care Prediction in Children with Impairments: A Novel Framework for Addressing Imbalance and High Dimensionality
Addressing the challenges in diagnosing and classifying self-care difficulties in exceptional children’s healthcare systems is crucial. The conventional diagnostic process, reliant on professional healthcare personnel, is time-consuming and costly. This study introduces an intelligent approach emplo...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/1/356 |
| _version_ | 1797359071868747776 |
|---|---|
| author | Eman Ibrahim Alyasin Oguz Ata Hayder Mohammedqasim Roa’a Mohammedqasem |
| author_facet | Eman Ibrahim Alyasin Oguz Ata Hayder Mohammedqasim Roa’a Mohammedqasem |
| author_sort | Eman Ibrahim Alyasin |
| collection | DOAJ |
| description | Addressing the challenges in diagnosing and classifying self-care difficulties in exceptional children’s healthcare systems is crucial. The conventional diagnostic process, reliant on professional healthcare personnel, is time-consuming and costly. This study introduces an intelligent approach employing expert systems built on artificial intelligence technologies, specifically random forest, decision tree, support vector machine, and bagging classifier. The focus is on binary and multi-label SCADI datasets. To enhance model performance, we implemented resampling and data shuffling methods to tackle data imbalance and generalization issues, respectively. Additionally, a hyper framework feature selection strategy was applied, using mutual-information statistics and random forest recursive feature elimination (RF-RFE) based on a forward elimination method. Prediction performance and feature significance experiments, employing Shapley value explanation (SHAP), demonstrated the effectiveness of the proposed model. The framework achieved a remarkable overall accuracy of 99% for both datasets used with the fewest number of unique features reported in contemporary literature. The use of hyperparameter tuning for RF modeling further contributed to this significant improvement, suggesting its potential utility in diagnosing self-care issues within the medical industry. |
| first_indexed | 2024-03-08T15:11:36Z |
| format | Article |
| id | doaj.art-572720657e8949e18ed0bfcf462d5d3d |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-08T15:11:36Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-572720657e8949e18ed0bfcf462d5d3d2024-01-10T14:51:51ZengMDPI AGApplied Sciences2076-34172023-12-0114135610.3390/app14010356Enhancing Self-Care Prediction in Children with Impairments: A Novel Framework for Addressing Imbalance and High DimensionalityEman Ibrahim Alyasin0Oguz Ata1Hayder Mohammedqasim2Roa’a Mohammedqasem3Department of Electrical and Computer Engineering, Institute of Science, Altinbas University, Istanbul 34218, TurkeyDepartment of Electrical and Computer Engineering, Institute of Science, Altinbas University, Istanbul 34218, TurkeyFaculty of Engineering, Istanbul Aydin University, Istanbul 34153, TurkeyFaculty of Engineering, Istanbul Aydin University, Istanbul 34153, TurkeyAddressing the challenges in diagnosing and classifying self-care difficulties in exceptional children’s healthcare systems is crucial. The conventional diagnostic process, reliant on professional healthcare personnel, is time-consuming and costly. This study introduces an intelligent approach employing expert systems built on artificial intelligence technologies, specifically random forest, decision tree, support vector machine, and bagging classifier. The focus is on binary and multi-label SCADI datasets. To enhance model performance, we implemented resampling and data shuffling methods to tackle data imbalance and generalization issues, respectively. Additionally, a hyper framework feature selection strategy was applied, using mutual-information statistics and random forest recursive feature elimination (RF-RFE) based on a forward elimination method. Prediction performance and feature significance experiments, employing Shapley value explanation (SHAP), demonstrated the effectiveness of the proposed model. The framework achieved a remarkable overall accuracy of 99% for both datasets used with the fewest number of unique features reported in contemporary literature. The use of hyperparameter tuning for RF modeling further contributed to this significant improvement, suggesting its potential utility in diagnosing self-care issues within the medical industry.https://www.mdpi.com/2076-3417/14/1/356ICF-CYfeature selectionoversamplingpredictive modelsexpert systemShapley value explanation |
| spellingShingle | Eman Ibrahim Alyasin Oguz Ata Hayder Mohammedqasim Roa’a Mohammedqasem Enhancing Self-Care Prediction in Children with Impairments: A Novel Framework for Addressing Imbalance and High Dimensionality Applied Sciences ICF-CY feature selection oversampling predictive models expert system Shapley value explanation |
| title | Enhancing Self-Care Prediction in Children with Impairments: A Novel Framework for Addressing Imbalance and High Dimensionality |
| title_full | Enhancing Self-Care Prediction in Children with Impairments: A Novel Framework for Addressing Imbalance and High Dimensionality |
| title_fullStr | Enhancing Self-Care Prediction in Children with Impairments: A Novel Framework for Addressing Imbalance and High Dimensionality |
| title_full_unstemmed | Enhancing Self-Care Prediction in Children with Impairments: A Novel Framework for Addressing Imbalance and High Dimensionality |
| title_short | Enhancing Self-Care Prediction in Children with Impairments: A Novel Framework for Addressing Imbalance and High Dimensionality |
| title_sort | enhancing self care prediction in children with impairments a novel framework for addressing imbalance and high dimensionality |
| topic | ICF-CY feature selection oversampling predictive models expert system Shapley value explanation |
| url | https://www.mdpi.com/2076-3417/14/1/356 |
| work_keys_str_mv | AT emanibrahimalyasin enhancingselfcarepredictioninchildrenwithimpairmentsanovelframeworkforaddressingimbalanceandhighdimensionality AT oguzata enhancingselfcarepredictioninchildrenwithimpairmentsanovelframeworkforaddressingimbalanceandhighdimensionality AT haydermohammedqasim enhancingselfcarepredictioninchildrenwithimpairmentsanovelframeworkforaddressingimbalanceandhighdimensionality AT roaamohammedqasem enhancingselfcarepredictioninchildrenwithimpairmentsanovelframeworkforaddressingimbalanceandhighdimensionality |