An Interpretable and Generalizable Machine Learning Model for Predicting Asthma Outcomes: Integrating AutoML and Explainable AI Techniques
Asthma remains a prevalent chronic condition, impacting millions globally and presenting significant clinical and economic challenges. This study develops a predictive model for asthma outcomes, leveraging automated machine learning (AutoML) and explainable AI (XAI) to balance high predictive accura...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | World |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4060/6/1/15 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850088112660676608 |
|---|---|
| author | Salman Mahmood Raza Hasan Saqib Hussain Rochak Adhikari |
| author_facet | Salman Mahmood Raza Hasan Saqib Hussain Rochak Adhikari |
| author_sort | Salman Mahmood |
| collection | DOAJ |
| description | Asthma remains a prevalent chronic condition, impacting millions globally and presenting significant clinical and economic challenges. This study develops a predictive model for asthma outcomes, leveraging automated machine learning (AutoML) and explainable AI (XAI) to balance high predictive accuracy with interpretability. Using a comprehensive dataset of demographic, clinical, and respiratory function data, we employed AutoGluon to automate model selection, optimization, and ensembling, resulting in a model with 98.99% accuracy and a 0.9996 ROC-AUC score. SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-Agnostic Explanations) were applied to provide both global and local interpretability, ensuring that clinicians can trust and understand model predictions. Additionally, counterfactual analysis enabled hypothetical scenario exploration, supporting personalized asthma management by allowing clinicians to assess potential interventions for individual patient risk profiles. To facilitate clinical adoption, a Streamlit v1.41.0 application was developed for real-time access to predictions and interpretability. This study addresses key gaps in asthma prediction, notably in model transparency and generalizability, while providing a practical tool for enhancing personalized care. Future research could expand the validation across diverse patient populations to reinforce the model’s robustness in broader clinical environments. |
| format | Article |
| id | doaj-art-aee5b7bb2060482a888d1c3c6c28b84c |
| institution | DOAJ |
| issn | 2673-4060 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | World |
| spelling | doaj-art-aee5b7bb2060482a888d1c3c6c28b84c2025-08-20T02:43:05ZengMDPI AGWorld2673-40602025-01-01611510.3390/world6010015An Interpretable and Generalizable Machine Learning Model for Predicting Asthma Outcomes: Integrating AutoML and Explainable AI TechniquesSalman Mahmood0Raza Hasan1Saqib Hussain2Rochak Adhikari3Department of Science and Engineering, Nazeer Hussain University, ST-2, Near Karimabad, Karachi 75950, PakistanDepartment of Computer Science, Solent University, Southampton SO14 0YN, UKComputer and Information Sciences, Northumbria University, Newcastle upon Tyne NE1 8QH, UKDepartment of Computer Science, Solent University, Southampton SO14 0YN, UKAsthma remains a prevalent chronic condition, impacting millions globally and presenting significant clinical and economic challenges. This study develops a predictive model for asthma outcomes, leveraging automated machine learning (AutoML) and explainable AI (XAI) to balance high predictive accuracy with interpretability. Using a comprehensive dataset of demographic, clinical, and respiratory function data, we employed AutoGluon to automate model selection, optimization, and ensembling, resulting in a model with 98.99% accuracy and a 0.9996 ROC-AUC score. SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-Agnostic Explanations) were applied to provide both global and local interpretability, ensuring that clinicians can trust and understand model predictions. Additionally, counterfactual analysis enabled hypothetical scenario exploration, supporting personalized asthma management by allowing clinicians to assess potential interventions for individual patient risk profiles. To facilitate clinical adoption, a Streamlit v1.41.0 application was developed for real-time access to predictions and interpretability. This study addresses key gaps in asthma prediction, notably in model transparency and generalizability, while providing a practical tool for enhancing personalized care. Future research could expand the validation across diverse patient populations to reinforce the model’s robustness in broader clinical environments.https://www.mdpi.com/2673-4060/6/1/15asthma predictionmachine learningAutoMLexplainable AISHAPLIME |
| spellingShingle | Salman Mahmood Raza Hasan Saqib Hussain Rochak Adhikari An Interpretable and Generalizable Machine Learning Model for Predicting Asthma Outcomes: Integrating AutoML and Explainable AI Techniques World asthma prediction machine learning AutoML explainable AI SHAP LIME |
| title | An Interpretable and Generalizable Machine Learning Model for Predicting Asthma Outcomes: Integrating AutoML and Explainable AI Techniques |
| title_full | An Interpretable and Generalizable Machine Learning Model for Predicting Asthma Outcomes: Integrating AutoML and Explainable AI Techniques |
| title_fullStr | An Interpretable and Generalizable Machine Learning Model for Predicting Asthma Outcomes: Integrating AutoML and Explainable AI Techniques |
| title_full_unstemmed | An Interpretable and Generalizable Machine Learning Model for Predicting Asthma Outcomes: Integrating AutoML and Explainable AI Techniques |
| title_short | An Interpretable and Generalizable Machine Learning Model for Predicting Asthma Outcomes: Integrating AutoML and Explainable AI Techniques |
| title_sort | interpretable and generalizable machine learning model for predicting asthma outcomes integrating automl and explainable ai techniques |
| topic | asthma prediction machine learning AutoML explainable AI SHAP LIME |
| url | https://www.mdpi.com/2673-4060/6/1/15 |
| work_keys_str_mv | AT salmanmahmood aninterpretableandgeneralizablemachinelearningmodelforpredictingasthmaoutcomesintegratingautomlandexplainableaitechniques AT razahasan aninterpretableandgeneralizablemachinelearningmodelforpredictingasthmaoutcomesintegratingautomlandexplainableaitechniques AT saqibhussain aninterpretableandgeneralizablemachinelearningmodelforpredictingasthmaoutcomesintegratingautomlandexplainableaitechniques AT rochakadhikari aninterpretableandgeneralizablemachinelearningmodelforpredictingasthmaoutcomesintegratingautomlandexplainableaitechniques AT salmanmahmood interpretableandgeneralizablemachinelearningmodelforpredictingasthmaoutcomesintegratingautomlandexplainableaitechniques AT razahasan interpretableandgeneralizablemachinelearningmodelforpredictingasthmaoutcomesintegratingautomlandexplainableaitechniques AT saqibhussain interpretableandgeneralizablemachinelearningmodelforpredictingasthmaoutcomesintegratingautomlandexplainableaitechniques AT rochakadhikari interpretableandgeneralizablemachinelearningmodelforpredictingasthmaoutcomesintegratingautomlandexplainableaitechniques |