article · Network Computation in Neural Systems
This study evaluates three feature selection techniques, Boruta, SHAP, and BorutaShap, to improve the accuracy and interpretability of machine learning models used in clinical disease diagnosis. Publicly sourced datasets covering diabetes, cardiovascular disease, statlog, and thyroid disease were preprocessed and applied across several machine learning algorithms. The evaluation focused on accuracy, precision, recall, and F1-score across the models. SHAP emerged as the top-performing feature selection method, delivering average diagnostic accuracies of 80.17 percent for diabetes, 85.13 percent for cardiovascular disease, 90.00 percent for statlog, and 99.55 percent for thyroid conditions. Across the assessed algorithms, LightGBM demonstrated the strongest overall diagnostic capability, reaching an average accuracy of 91.00 percent for most disease states while benefiting from improved model interpretability.
Clinical decision-making increasingly relies on automated tools, but medical professionals require transparent reasoning behind computational predictions. Demonstrating that SHAP offers high diagnostic accuracy alongside clear explanations helps build trust in artificial intelligence systems. Selecting the most informative patient data also streamlines algorithmic performance, assisting healthcare teams in identifying critical indicators for conditions such as diabetes and heart disease.
The findings can inform developers of clinical decision-support software and diagnostic algorithms seeking to optimise feature selection and model explainability. Because the research is an early-stage comparative study conducted entirely on public benchmark datasets, further clinical validation and integration into regulated healthcare workflows would be necessary before real-world deployment in hospitals or diagnostic laboratories.
AI-generated from the published abstract. Always read the original work before citing.
Interpretable machine learning models are instrumental in disease diagnosis and clinical decision-making, shedding light on relevant features. Notably, Boruta, SHAP (SHapley Additive exPlanations), and BorutaShap were employed for feature selection, each contributing to the identification of crucial features. These selected features were then utilized to train six machine learning algorithms, including LR, SVM, ETC, AdaBoost, RF, and LR, using diverse medical datasets obtained from public sources after rigorous preprocessing. The performance of each feature selection technique was evaluated across multiple ML models, assessing accuracy, precision, recall, and F1-score metrics. Among these, SHAP showcased superior performance, achieving average accuracies of 80.17%, 85.13%, 90.00%, and 99.55% across diabetes, cardiovascular, statlog, and thyroid disease datasets, respectively. Notably, the LGBM emerged as the most effective algorithm, boasting an average accuracy of 91.00% for most disease states. Moreover, SHAP enhanced the interpretability of the models, providing valuable insights into the underlying mechanisms driving disease diagnosis. This comprehensive study contributes significant insights into feature selection techniques and machine learning algorithms for disease diagnosis, benefiting researchers and practitioners in the medical field. Further exploration of feature selection methods and algorithms holds promise for advancing disease diagnosis methodologies, paving the way for more accurate and interpretable diagnostic models.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1080/0954898x.2024.2331506
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
