Towards Transparent Diabetes Prediction: Combining AutoML and Explainable AI for Improved Clinical Insights
Diabetes is a global health challenge that requires early detection for effective management. This study integrates Automated Machine Learning (AutoML) with Explainable Artificial Intelligence (XAI) to improve diabetes risk prediction and enhance model interpretability for healthcare professionals....
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/16/1/7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588365825835008 |
|---|---|
| author | Raza Hasan Vishal Dattana Salman Mahmood Saqib Hussain |
| author_facet | Raza Hasan Vishal Dattana Salman Mahmood Saqib Hussain |
| author_sort | Raza Hasan |
| collection | DOAJ |
| description | Diabetes is a global health challenge that requires early detection for effective management. This study integrates Automated Machine Learning (AutoML) with Explainable Artificial Intelligence (XAI) to improve diabetes risk prediction and enhance model interpretability for healthcare professionals. Using the Pima Indian Diabetes dataset, we developed an ensemble model with 85.01% accuracy leveraging AutoGluon’s AutoML framework. To address the “black-box” nature of machine learning, we applied XAI techniques, including SHapley Additive exPlanations (SHAP), Local Interpretable Model-Agnostic Explanations (LIME), Integrated Gradients (IG), Attention Mechanism (AM), and Counterfactual Analysis (CA), providing both global and patient-specific insights into critical risk factors such as glucose and BMI. These methods enable transparent and actionable predictions, supporting clinical decision-making. An interactive Streamlit application was developed to allow clinicians to explore feature importance and test hypothetical scenarios. Cross-validation confirmed the model’s robust performance across diverse datasets. This study demonstrates the integration of AutoML with XAI as a pathway to achieving accurate, interpretable models that foster transparency and trust while supporting actionable clinical decisions. |
| format | Article |
| id | doaj-art-ac784a6b350b42b9a02fb599747a9fcd |
| institution | Kabale University |
| issn | 2078-2489 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj-art-ac784a6b350b42b9a02fb599747a9fcd2025-01-24T13:35:07ZengMDPI AGInformation2078-24892024-12-01161710.3390/info16010007Towards Transparent Diabetes Prediction: Combining AutoML and Explainable AI for Improved Clinical InsightsRaza Hasan0Vishal Dattana1Salman Mahmood2Saqib Hussain3Department of Computer Science, Solent University, Southampton SO14 0YN, UKDigital Transformation, Oman College of Management & Technology, P.O. Box 680, Barka 320, OmanDepartment of Computer Science, Nazeer Hussain University, ST-2, near Karimabad, Karachi 75950, PakistanComputer and Information Sciences, Northumbria University, Newcastle upon Tyne NE1 8QH, UKDiabetes is a global health challenge that requires early detection for effective management. This study integrates Automated Machine Learning (AutoML) with Explainable Artificial Intelligence (XAI) to improve diabetes risk prediction and enhance model interpretability for healthcare professionals. Using the Pima Indian Diabetes dataset, we developed an ensemble model with 85.01% accuracy leveraging AutoGluon’s AutoML framework. To address the “black-box” nature of machine learning, we applied XAI techniques, including SHapley Additive exPlanations (SHAP), Local Interpretable Model-Agnostic Explanations (LIME), Integrated Gradients (IG), Attention Mechanism (AM), and Counterfactual Analysis (CA), providing both global and patient-specific insights into critical risk factors such as glucose and BMI. These methods enable transparent and actionable predictions, supporting clinical decision-making. An interactive Streamlit application was developed to allow clinicians to explore feature importance and test hypothetical scenarios. Cross-validation confirmed the model’s robust performance across diverse datasets. This study demonstrates the integration of AutoML with XAI as a pathway to achieving accurate, interpretable models that foster transparency and trust while supporting actionable clinical decisions.https://www.mdpi.com/2078-2489/16/1/7AutoMLexplainable AI (XAI)diabetes predictionSHAPLIMEcounterfactual analysis |
| spellingShingle | Raza Hasan Vishal Dattana Salman Mahmood Saqib Hussain Towards Transparent Diabetes Prediction: Combining AutoML and Explainable AI for Improved Clinical Insights Information AutoML explainable AI (XAI) diabetes prediction SHAP LIME counterfactual analysis |
| title | Towards Transparent Diabetes Prediction: Combining AutoML and Explainable AI for Improved Clinical Insights |
| title_full | Towards Transparent Diabetes Prediction: Combining AutoML and Explainable AI for Improved Clinical Insights |
| title_fullStr | Towards Transparent Diabetes Prediction: Combining AutoML and Explainable AI for Improved Clinical Insights |
| title_full_unstemmed | Towards Transparent Diabetes Prediction: Combining AutoML and Explainable AI for Improved Clinical Insights |
| title_short | Towards Transparent Diabetes Prediction: Combining AutoML and Explainable AI for Improved Clinical Insights |
| title_sort | towards transparent diabetes prediction combining automl and explainable ai for improved clinical insights |
| topic | AutoML explainable AI (XAI) diabetes prediction SHAP LIME counterfactual analysis |
| url | https://www.mdpi.com/2078-2489/16/1/7 |
| work_keys_str_mv | AT razahasan towardstransparentdiabetespredictioncombiningautomlandexplainableaiforimprovedclinicalinsights AT vishaldattana towardstransparentdiabetespredictioncombiningautomlandexplainableaiforimprovedclinicalinsights AT salmanmahmood towardstransparentdiabetespredictioncombiningautomlandexplainableaiforimprovedclinicalinsights AT saqibhussain towardstransparentdiabetespredictioncombiningautomlandexplainableaiforimprovedclinicalinsights |