Polynomial-SHAP analysis of liver disease markers for capturing of complex feature interactions in machine learning models

• Published in: Computers in biology and medicine Vol. 182; p. 109168
• Main Authors: Ejiyi, Chukwuebuka Joseph, Cai, Dongsheng, Ejiyi, Makuachukwu B., Chikwendu, Ijeoma A., Coker, Kenneth, Oluwasanmi, Ariyo, Bamisile, Oluwatoyosi F., Ejiyi, Thomas U., Qin, Zhen
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.11.2024; Elsevier Limited
• Subjects: Accuracy; Algorithms; Biomarkers - metabolism; Blood; Clinical decision making; Correlation coefficients; Data rebalancing; Datasets; Decision making; Diagnosis; Diagnosis, Computer-Assisted - methods; Diagnostic systems; Empowerment; Feature selection; Hepatitis; Humans; Impact analysis; Internal Medicine; Learning algorithms; Liver; Liver cirrhosis; Liver diseases; Liver Diseases - diagnosis; Machine Learning; Metabolism; Missing data; Observational learning; Other; Performance enhancement; Phosphatase; Physiology; Polynomial features; Polynomials; Protein synthesis; Proteins; SHapley additive exPlanations; Support vector machines; SHapley additive exPlanations; Liver diseases; Polynomial features; Data rebalancing; Machine learning
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.109168

Liver disease diagnosis is pivotal for effective patient management, and machine learning techniques have shown promise in this domain. In this study, we investigate the impact of Polynomial-SHapley Additive exPlanations analysis on enhancing the performance and interpretability of machine learning models for liver disease classification. Our results demonstrate significant improvements in accuracy, precision, recall, F1_score, and Matthews correlation coefficient across various algorithms when polynomial- SHapley Additive exPlanations analysis is applied. Specifically, the Light Gradient Boosting Machine model achieves exceptional performance with 100 % accuracy in both scenarios. Furthermore, by comparing the results obtained with and without the approach, we observe substantial differences in the performance, highlighting the importance of incorporating Polynomial-SHapley Additive exPlanations analysis for improved model performance. The Polynomial features and SHapley Additive exPlanations values also enhance the interpretability of machine learning models by capturing complex feature interactions, enabling users to gain deeper insights into the underlying mechanisms driving the diagnosis. Moreover, data rebalancing using Synthetic Minority Over-sampling Technique and parameter tuning were employed to optimize the performance of the models. These findings underscore the significance of employing this analytical approach in machine-learning-based diagnostic systems for liver diseases, offering superior performance and enhanced interpretability for informed decision-making in clinical practice. •The polynomial-SHAP approach shows exceptional effectiveness in capturing feature importance and interactions.•The proposed approach provides outstanding diagnostic support and enables a personalized management strategy.•Effective handling of missing data, addressing data imbalance, and managing noise, tailored to the complexities of medical data.•The proposed approach outperformed traditional and ensemble classifiers while also providing enhanced interpretability.