An Interpretable Machine Learning Approach for Hepatitis B Diagnosis
Source abstract
Abstract
Hepatitis B is a potentially deadly liver infection caused by the hepatitis B virus. It is a serious public health problem globally. Substantial efforts have been made to apply machine learning in detecting the virus. However, the application of model interpretability is limited in the existing literature. Model interpretability makes it easier for humans to understand and trust the machine-learning model. Therefore, in this study, we used SHapley Additive exPlanations (SHAP), a game-based theoretical approach to explain and visualize the predictions of machine learning models applied for hepatitis B diagnosis. The algorithms used in building the models include decision tree, logistic regression, support vector machines, random forest, adaptive boosting (AdaBoost), and extreme gradient boosting (XGBoost), and they achieved balanced accuracies of 75%, 82%, 75%, 86%, 92%, and 90%, respectively. Meanwhile, the SHAP values showed that bilirubin is the most significant feature contributing to a higher mortality rate. Consequently, older patients are more likely to die with elevated bilirubin levels. The outcome of this study can aid health practitioners and health policymakers in explaining the result of machine learning models for health-related problems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Artificial Intelligence in Healthcare · Hepatitis B Virus Studies · Machine Learning in Healthcare
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Center for Human-Compatible Artificial Intelligence (CHAI), Berkeley Institute for Data Science (BIDS), University of California, Berkeley, CA 94720, USA
Department of Mathematics and Statistics, York University, Toronto, ON M3J 1P3, Canada
Center for Telecommunications, Department of Electrical and Electronic Engineering Science, University of Johannesburg, Johannesburg 2006, South Africa
Department of Chemistry, Bayelsa Medical University, Yenagoa PMB 178, Nigeria
Department of Industrial Engineering, Faculty of Engineering, Stellenbosch University, Stellenbosch 7600, South Africa
School of Computing and Mathematical Sciences, University of Leicester, Leicester LE1 7RH, UK
Department of Electrical and Electronic Engineering Science, University of Johannesburg, Johannesburg 2006, South Africa
Department of Mathematics, Wake Forest University, Winston-Salem, NC 27109, USA
Department of Mathematics and Computer Science, Alabama State University, Montgomery, AL 36104, USA
Department of Integrative Biology, The University of Texas at Austin, Austin, TX 78712, USA
Department of Mathematics and Applied Mathematics, University of Johannesburg, Doornfontein 2028, South Africa
References (85)
Show source-provided references
1. (2022, May 25). Hepatitis B Foundation: Hepatitis B Facts and Figures. Available online: https://deepai.org/machine-learning-glossary-and-terms/neural-network.
2. Good Practice in using HBsAg in Chronic Hepatitis B Study Group (GPs-CHB Study Group). Repeated Measurements of Hepatitis B Surface Antigen Identify Carriers of Inactive HBV During Long-term Follow-up10.1016/j.cgh.2016.01.019 ↗
3. (2022, April 30). WHO Fact Sheet: Hepatitis B—Symptoms. Available online: https://www.who.int/news-room/fact-sheets/detail/hepatitis-b.
4. (2022, April 30). Mayo Clinic: Hepatitis B—Symptoms. Available online: https://shorturl.at/nuzV7.
5. Cost-effectiveness of universal screening for chronic hepatitis B virus infection in China: An economic evaluation10.1016/S2214-109X(21)00517-9 ↗
6. Tesfa, T., Hawulte, B., Tolera, A., and Abate, D. (2021). Hepatitis B virus infection and associated risk factors among medical students in Eastern Ethiopia. PLoS ONE, 16.10.1371/journal.pone.0247267 ↗
7. Hepatitis B virus: Advances in prevention, diagnosis, and therapy10.1128/CMR.00046-19 ↗
8. Revisiting hepatitis B virus: Challenges of curative therapies10.1128/JVI.01032-19 ↗
9. The hepatitis B epidemic and the urgent need for cure preparedness10.1038/s41575-018-0041-6 ↗
10. Towards curative therapy of chronic viral hepatitis10.1055/a-0824-1576 ↗
11. Machine-learning-based classification of real-time tissue elastography for hepatic fibrosis in patients with chronic hepatitis B10.1016/j.compbiomed.2017.07.012 ↗
12. Characterization of the receptor-binding domain (RBD) of 2019 novel coronavirus: Implication for development of RBD protein as a viral attachment inhibitor and vaccine10.1038/s41423-020-0400-4 ↗
13. Estimation of the probability of an event as a function of several independent variables10.1093/biomet/54.1-2.167 ↗
14. Uttreshwar, G.S., and Ghatol, A. (2009, January 6–7). Hepatitis B Diagnosis Using Logical Inference And Generalized Regression Neural Networks. Proceedings of the 2009 IEEE International Advance Computing Conference, Patiala, India.10.1109/IADCC.2009.4809255 ↗
15. Wang, H., Liu, Y., and Huang, W. (2017, January 29–31). Random forest and Bayesian prediction for Hepatitis B virus reactivation. Proceedings of the 2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), Guilin, China.10.1109/FSKD.2017.8393087 ↗
16. Agbele, K.K., Oriogun, P.K., Seluwa, A.G., and Aruleba, K.D. (2015, January 11–12). Towards a model for enhancing ICT4 development and information security in healthcare system. Proceedings of the 2015 IEEE International Symposium on Technology and Society (ISTAS), Dublin, Ireland.10.1109/ISTAS.2015.7439404 ↗
17. Ho, T.K. (1995, January 14–16). Random decision forests. Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, Canada.
18. Aruleba, K., Obaido, G., Ogbuokiri, B., Fadaka, A.O., Klein, A., Adekiya, T.A., and Aruleba, R.T. (2020). Applications of Computational Methods in Biomedical Breast Cancer Imaging Diagnostics: A Review. J. Imaging, 6.10.3390/jimaging6100105 ↗
19. Aruleba, R.T., Adekiya, T.A., Ayawei, N., Obaido, G., Aruleba, K., Mienye, I., Aruleba, I., and Ogbuokiri, B. (2022). COVID-19 Diagnosis: A Review of Rapid Antigen, RT-PCR and Artificial Intelligence Methods. Bioengineering, 3.10.3390/bioengineering9040153 ↗
20. Mienye, I.D., Obaido, G., Aruleba, K., and Dada, O.A. (2022). Enhanced Prediction of Chronic Kidney Disease Using Feature Selection and Boosted Classifiers. International Conference on Intelligent Systems Design and Applications, Springer.10.1007/978-3-030-96308-8_49 ↗
21. Using Machine Learning Algorithms to Predict Hepatitis B Surface Antigen Seroclearance
22. Machine learning in medicine: A primer for physicians10.1038/ajg.2010.173 ↗
23. Artificial intelligence to deep learning: Machine intelligence approach for drug discovery10.1007/s11030-021-10217-3 ↗
24. Predicting hepatitis B virus–positive metastatic hepatocellular carcinomas using gene expression profiling and supervised machine learning10.1038/nm843 ↗
25. Using machine learning algorithms to predict hepatitis B surface antigen seroclearance10.1155/2019/6915850 ↗
26. Pilot study using machine learning to identify immune profiles for the prediction of early virological relapse after stopping nucleos (t) ide analogues in HBeAg-negative CHB10.1002/hep4.1626 ↗
27. Performance of SMOTE in a random forest and naive Bayes classifier for imbalanced Hepatitis-B vaccination status
28. Kamimura, H., Nonaka, H., Mori, M., Kobayashi, T., Setsu, T., Kamimura, K., Tsuchiya, A., and Terai, S. (2022). Use of a Deep Learning Approach for the Sensitive Prediction of Hepatitis B Surface Antigen Levels in Inactive Carrier Patients. J. Clin. Med., 11.10.3390/jcm11020387 ↗
29. Xia, Z., Qin, L., Ning, Z., and Zhang, X. (2022). Deep learning time series prediction models in surveillance data of hepatitis incidence in China. PLoS ONE, 17.10.1371/journal.pone.0265660 ↗
30. Dua, D., Graff, C., and UCI Machine Learning Repository (2022, July 01). University of California, Irvine, School of Information and Computer Sciences. Available online: http://archive.ics.uci.edu/ml.
31. Mgboh, U., Ogbuokiri, B., Obaido, G., and Aruleba, K. (2020). Visual Data Mining: A Comparative Analysis of Selected Datasets. International Conference on Intelligent Systems Design and Applications, Springer.10.1007/978-3-030-71187-0_35 ↗
32. Scheda, R., and Diciotti, S. (2022). Explanations of Machine Learning Models in Repeated Nested Cross-Validation: An Application in Age Prediction Using Brain Complexity Features. Appl. Sci., 12.10.3390/app12136681 ↗
33. Consensus features nested cross-validation10.1093/bioinformatics/btaa046 ↗
34. Jones, I. (2014). Research Methods for Sports Studies, Routledge.
35. Patro, S., and Sahu, K.K. (2015). Normalization: A preprocessing stage. arXiv.10.17148/IARJSET.2015.2305 ↗
36. (2022, October 15). Sklearn Pipeline. Available online: https://scikit-learn.org/stable/modules/generated/sklearn.pipeline.Pipeline.html.
37. An empowered AdaBoost algorithm implementation: A COVID-19 dataset study10.1016/j.cie.2021.107912 ↗
38. Public sentiments toward COVID-19 vaccines in South African cities: An analysis of Twitter posts10.3389/fpubh.2022.987376 ↗
39. Prediction performance of improved decision tree-based algorithms: A review10.1016/j.promfg.2019.06.011 ↗
40. Lee, S.J., Tseng, C.H., Yang, H.Y., Jin, X., Jiang, Q., Pu, B., Hu, W.H., Liu, D.R., Huang, Y., and Zhao, N. (2022). Random RotBoost: An Ensemble Classification Method Based on Rotation Forest and AdaBoost in Random Subsets and Its Application to Clinical Decision Support. Entropy, 24.10.3390/e24050617 ↗
41. Novel binary logistic regression model based on feature transformation of XGBoost for type 2 Diabetes Mellitus prediction in healthcare systems10.1016/j.future.2021.11.003 ↗
42. Ogbuokiri, B., Ahmadi, A., Nia, Z.M., Mellado, B., Wu, J., Orbinski, J., Ali, A., and Jude, K. (2022). Vaccine Hesitancy Hotspots in Africa: An Insight from Geotagged Twitter Posts. TechRxiv.10.36227/techrxiv.20720740.v1 ↗
43. Bokaba, T., Doorsamy, W., and Paul, B.S. (2022). Comparative study of machine learning classifiers for modelling road traffic accidents. Appl. Sci., 12.10.3390/app12020828 ↗
44. An ensemble approach to stabilize the features for multi-domain sentiment analysis using supervised machine learning10.1186/s40537-018-0152-5 ↗
45. Huang, M.W., Chen, C.W., Lin, W.C., Ke, S.W., and Tsai, C.F. (2017). SVM and SVM ensembles in breast cancer prediction. PLoS ONE, 12.10.1371/journal.pone.0161501 ↗
46. A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects10.1109/ACCESS.2022.3207287 ↗
47. An improved ensemble learning approach for the prediction of heart disease risk10.1016/j.imu.2020.100402 ↗
48. The random forest algorithm for statistical learning10.1177/1536867X20909688 ↗
49. An ensemble random forest algorithm for insurance big data analysis10.1109/ACCESS.2017.2738069 ↗
50. Zheng, H., Yuan, J., and Chen, L. (2017). Short-term load forecasting using EMD-LSTM neural networks with a Xgboost algorithm for feature importance evaluation. Energies, 10.10.3390/en10081168 ↗
51. He, J., Hao, Y., and Wang, X. (2021). An interpretable aid decision-making model for flag state control ship detention based on SMOTE and XGBoost. J. Mar. Sci. Eng., 9.10.3390/jmse9020156 ↗
52. Predictive Modeling of Vaccination Uptake in US Counties: A Machine Learning–Based Approach10.2196/33231 ↗
53. Dhaliwal, S. (2018). Effective intrusion detection system using XGBoost. Information, 9.10.3390/info9070149 ↗
54. Li, Y., and Chen, W. (2020). A comparative performance assessment of ensemble learning for credit scoring. Mathematics, 8.10.3390/math8101756 ↗
55. Zheng, H., Xiao, F., Sun, S., and Qin, Y. (2022). Brillouin Frequency Shift Extraction Based on AdaBoost Algorithm. Sensors, 22.10.3390/s22093354 ↗
56. Fair-AdaBoost: Extending AdaBoost method to achieve fair classification10.1016/j.eswa.2022.117240 ↗
57. Ding, Y., Zhu, H., Chen, R., and Li, R. (2022). An Efficient AdaBoost Algorithm with the Multiple Thresholds Classification. Appl. Sci., 12.10.2139/ssrn.4092341 ↗
58. Nohara, Y., Matsumoto, K., Soejima, H., and Nakashima, N. (2019, January 7–10). Explanation of machine learning models using improved Shapley Additive Explanation. Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, Niagara Falls, NY, USA.10.1145/3307339.3343255 ↗
59. Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations (SHAP) approach10.1016/j.engstruct.2020.110927 ↗
60. Shapley additive explanations for NO2 forecasting10.1016/j.ecoinf.2019.101039 ↗
61. An efficient explanation of individual classifications using game theory
62. Explanation of machine learning models using shapley additive explanation and application for real data in hospital10.1016/j.cmpb.2021.106584 ↗
63. Pokharel, S., Sah, P., and Ganta, D. (2021). Improved prediction of total energy consumption and feature analysis in electric vehicles using machine learning and shapley additive explanations method. World Electr. Veh. J., 12.10.3390/wevj12030094 ↗
64. Gradient boosting and Shapley additive explanations for fraud detection in electricity distribution grids10.1002/2050-7038.13046 ↗
65. Meddage, P., Ekanayake, I., Perera, U.S., Azamathulla, H.M., Md Said, M.A., and Rathnayake, U. (2022). Interpretation of Machine-Learning-Based (Black-box) Wind Pressure Predictions for Low-Rise Gable-Roofed Buildings Using Shapley Additive Explanations (SHAP). Buildings, 12.10.3390/buildings12060734 ↗
66. Scikit-learn: Machine learning in Python
67. Elgeldawi, E., Sayed, A., Galal, A.R., and Zaki, A.M. (2021). Hyperparameter tuning for machine learning algorithms used for arabic sentiment analysis. Informatics, 8.10.3390/informatics8040079 ↗
68. Chicco, D., and Jurman, G. (2020). The advantages of the Matthews correlation 609 coefficient (MCC) over F1 score and accuracy in binary classification 610 evaluation. BMC Genom., 21.10.1186/s12864-019-6413-7 ↗
69. Performance analysis of cost-sensitive learning methods with application to imbalanced medical data10.1016/j.imu.2021.100690 ↗
70. Sensitivity, specificity, and predictive values: Foundations, pliabilities, and pitfalls in research and practice10.3389/fpubh.2017.00307 ↗
71. Mienye, I.D., and Sun, Y. (2021). Improved heart disease prediction using particle swarm optimization based stacked sparse autoencoder. Electronics, 10.10.3390/electronics10192347 ↗
72. A Modified AUC for Training Convolutional Neural Networks: Taking Confidence into Account10.3389/frai.2021.582928 ↗
73. Luo, J., Liang, X., Xin, J., Li, J., Li, P., Zhou, Q., Hao, S., Zhang, H., Lu, Y., and Wu, T. (Clin. Gastroenterol. Hepatol., 2022). Predicting the Onset of Hepatitis B Virus–Related Acute-on-Chronic Liver Failure, Clin. Gastroenterol. Hepatol., in press.
74. Yarasuri, V.K., Indukuri, G.K., and Nair, A.K. (2019, January 12–14). Prediction of Hepatitis Disease Using Machine Learning Technique. Proceedings of the 2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC), Palladam, India.10.1109/I-SMAC47947.2019.9032585 ↗
75. Survey of Machine Learning Algorithms for Disease Diagnostic
76. Ali, N., Srivastava, D., Tiwari, A., Pandey, A., Pandey, A.K., and Sahu, A. (2022, January 23–24). Predicting Life Expectancy of Hepatitis B Patients using Machine Learning. Proceedings of the 2022 IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE), Ballari, India.10.1109/ICDCECE53908.2022.9793025 ↗
77. Interpretability of Machine Learning Solutions in Public Healthcare: The CRISP-ML Approach10.3389/fdata.2021.660206 ↗
78. An artificial intelligence model to predict hepatocellular carcinoma risk in Korean and Caucasian patients with chronic hepatitis B10.1016/j.jhep.2021.09.025 ↗
79. Analysis of hepatitis B virus infection in blood sera using Raman spectroscopy and machine learning10.1016/j.pdpdt.2018.05.010 ↗
80. Predicting Hepatitis B to be acute or chronic in an infected person using machine learning algorithm10.1016/j.advengsoft.2022.103179 ↗
81. Using quasispecies patterns of hepatitis B virus to predict hepatocellular carcinoma with deep sequencing and machine learning10.1093/infdis/jiaa647 ↗
82. Prediction of vaccine hesitancy based on social media traffic among Israeli parents using machine learning strategies
83. Decision Support System for Predicting Survivability of Hepatitis Patients10.3389/fpubh.2022.862497 ↗
84. Clinical prediction of HBV and HCV related hepatic fibrosis using machine learning10.1016/j.ebiom.2018.07.041 ↗
85. Increased accuracy of prediction hepatitis disease using the application of principal component analysis on a support vector machine10.1088/1742-6596/1968/1/012016 ↗