Leveraging Explainable AI for Improved Heart Failure Survival Prediction Models
DOI:
https://doi.org/10.63682/jns.v14i32S.7853Keywords:
Artificial Intelligence, Explainable AI, Machine Learning, Heart Failure Prediction, SHAP, LIMEAbstract
Heart failure (HF) is a major cause of illness and death globally, highlighting the need for effective prediction models to identify high-risk patients. Traditional machine learning models are worked as a “black boxes”, offering little understanding of how they make decisions. This study 1) Present a comparative analysis of conventional machine learning models on the HF disease. 2) examines how to incorporate eXplainable Artificial Intelligence (XAI) techniques into heart failure conventional survival prediction models. 3) Analyzes the explainability of heart failure (HF) survival prediction models. This study analyzes a dataset containing 918 patient records with a history of HF. In the first phase of the study, the machine learning model Xtreme Gradient Boosting (XGB) achieves the highest accuracy of 88.59% among all models tested on the HF dataset. The second phase focuses on explainability, emphasizing that cholesterol levels, age, MaxHR, and Oldpeak are crucial features in HF prediction. With the analysis of the experts note that the model performs well because these relevant features significantly contribute to predicting HF and can save the human life.
Downloads
Metrics
References
G. A. Roth, G. A. Mensah, C. O. Johnson, G. Addolorato, E. Ammirati,L. M. Baddour, N. C. Barengo, A. Z. Beaton, E. J. Benjamin, C. P. Ben- ziger et al., “Global burden of cardiovascular diseases and risk factors, 1990–2019: update from the gbd 2019 study,” Journal of the American college of cardiology, vol. 76, no. 25, pp. 2982–3021, 2020.
A. Daza, J. Bobadilla, J. C. Herrera, A. Medina, N. Saboya, K. Zavaleta, and S. Siguenas, “Stacking ensemble based hyperparameters to diagnos- ing of heart disease: Future works,” Results in Engineering, vol. 21, p. 101894, 2024.
A. Gavhane, G. Kokkula, I. Pandya, and K. Devadkar, “Prediction of heart disease using machine learning,” in 2018 second interna- tional conference on electronics, communication and aerospace technol- ogy (ICECA). IEEE, 2018, pp. 1275–1278.
D. Paikaray and A. K. Mehta, “An extensive approach towards heart stroke prediction using machine learning with ensemble classifier,” in Proceedings of the International Conference on Paradigms of Commu- nication, Computing and Data Sciences: PCCDS 2021. Springer, 2022,pp. 767–777.
[P. A. Moreno-Sanchez, “Improvement of a prediction model for heart failure survival through explainable artificial intelligence,” Frontiers in Cardiovascular Medicine, vol. 10, p. 1219586, 2023.
C. W. Tsao, A. W. Aday, Z. I. Almarzooq, C. A. Anderson, P. Arora,C. L. Avery, C. M. Baker-Smith, A. Z. Beaton, A. K. Boehme, A. E. Buxton et al., “Heart disease and stroke statistics—2023 update: a re- port from the american heart association,” Circulation, vol. 147, no. 8,pp. e93–e621, 2023.
A. F. Members, J. J. McMurray, S. Adamopoulos, S. D. Anker, A. Auric- chio, M. B¨ohm, K. Dickstein, V. Falk, G. Filippatos, C. Fonseca et al., “Esc guidelines for the diagnosis and treatment of acute and chronic heart failure 2012: The task force for the diagnosis and treatment of acute and chronic heart failure 2012 of the european society of cardiol- ogy. developed in collaboration with the heart failure association (hfa) of the esc,” European heart journal, vol. 33, no. 14, pp. 1787–1847, 2012.
S. Mohan, C. Thirumalai, and G. Srivastava, “Effective heart disease prediction using hybrid machine learning techniques,” IEEE access, vol. 7, pp. 81 542–81 554, 2019.
M. U. Emon, M. S. Keya, T. I. Meghla, M. M. Rahman, M. S. Al Ma- mun, and M. S. Kaiser, “Performance analysis of machine learning ap- proaches in stroke prediction,” in 2020 4th international conference on electronics, communication and aerospace technology (ICECA). IEEE, 2020, pp. 1464–1469.
M. Zeng, “The prediction of heart failure based on four machine learning algorithms,” Highlights in Science, Engineering and Technology, vol. 39,pp. 1377–1382, 2023.
S. Sharma and S. Jain, “The coronavirus disease ontology (covido),” in Semantic Intelligence: Select Proceedings of ISIC 2022. Springer Nature Singapore Singapore, 2023, pp. 89–103.
F. H. Dahri, A. A. Laghari, D. K. Sajnani, A. Shazia, and T. Kumar, “Heart failure prediction: a comparative analysis of machine learning algorithms,” in International Conference on Optics, Electronics, and Communication Engineering (OECE 2024), vol. 13395. SPIE, 2024,pp. 634–640.
A. Daza Vergaray, J. Bobadilla Cornelio, J. C. Herrera Miranda,A. Medina Ch´avez, N. Saboya Rios, K. Zavaleta Ramos, and S. M.Sigu¨en˜as Gonzales, “Stacking ensemble based hyperparameters for the prediction of heart disease,” Available at SSRN 4553047.
A. Sutradhar, M. Rafi, M. J. Alam, and S. Islam, “An early warning system of heart failure mortality with combined machine learning meth- ods,” Indones. J. Electr. Eng. Comput. Sci, vol. 32, pp. 1115–1122, 2023.
M. M. Hassan, M. Raihan, M. H. B. Khan, T. Dhali, M. M. Rahman, andZ. H. Sneha, “A hybrid machine learning approach to predict the risk of having stroke,” in Proceedings of the 2nd International Conference on Computing Advancements, 2022, pp. 460–465.
M. M. Yaqoob, M. Nazir, M. A. Khan, S. Qureshi, and A. Al-Rasheed, “Hybrid classifier-based federated learning in health service providers for cardiovascular disease prediction,” Applied Sciences, vol. 13, no. 3,p. 1911, 2023.
S. Cyriac, R. Sivakumar, N. Raju, and Y. W. Kim, “Heart disease prediction using ensemble voting methods in machine learning,” in 2022 13th International Conference on Information and Communica- tion Technology Convergence (ICTC). IEEE, 2022, pp. 1326–1331.
A. Abbas, A. Imran, A. A. N. Al-Aloosy, S. Fahim, A. Alzahrani, andS. K. Muzaffar, “Heart failure prediction using machine learning ap- proaches,” in 2022 Mohammad Ali Jinnah University International Con- ference on Computing (MAJICC). IEEE, 2022, pp. 1–7.
P. M. Tambe and M. Shrivastava, “Hybrid brave-hunting optimisation for heart disease detection model with svm coupled deep cnn,” Interna- tional Journal of Intelligent Information and Database Systems, vol. 17, no. 1, pp. 92–123, 2025.
Z. Y. Acar and U¨ . Tok, “Combining lstm-enhanced features with ma- chine learning algorithms for improved heart failure prediction,” Selcuk University Journal of Engineering Sciences, vol. 23, no. 2, pp. 48–53, 2024.
S. Basak and K. Chatterjee, “Smart healthcare surveillance system using iot and machine learning approaches for heart disease,” in International Conference on Advancements in Smart Computing and Information Se- curity. Springer, 2022, pp. 304–313.
S. A. Almutairi, “An optimized feature selection and hyperparameter tuning framework for automated heart disease diagnosis.” Computer Systems Science & Engineering, vol. 47, no. 2, 2023.
N. Afiatuddin, R. Rahmaddeni, F. Pratiwi, R. Septia, and H. Hen- drawan, “Evaluation of data mining in heart failure disease classfica- tion,” CogITo Smart Journal, vol. 10, no. 2, pp. 460–473, 2024.
J. Barzola-Monteses, R. Caicedo-Quiroz, F. Parrales-Bravo, C. Medina- Suarez, and W. Yanez-Pazmino, “Convolutional neural networks applied to the diagnosis of cardiovascular disease,” in 2024 43rd International Conference of the Chilean Computer Science Society (SCCC). IEEE, 2024, pp. 1–8.
S. Sharma and S. Jain, “Comprehensive study of semantic annotation: Variant and praxis,” Advances in Computational Intelligence, its Con- cepts Applications (ACI 2021), vol. 2823, pp. 102–116, 2021.
S. Sharma and S. Jain “Ontoxai: a semantic web rule language approach for dengue fever classification using explainable ai and ontology,” Available at SSRN 4726837, 2024.
S. Jain, S. Sharma, J. M. Natterbrede, and M. Hamada, “Rule-based actionable intelligence for disaster situation management,” International Journal of Knowledge and Systems Science (IJKSS), vol. 11, no. 3, pp. 17–32, 2020.
S. Sharma, S. Jain, M. K. Tiwari, and S. lal, “Classifying the state of knowledge-based question answering: patterns, progress, and prospects,” International Journal of Computers and Applications, vol. 47, no. 1, pp. 93–105, 2025.
Fedesoriano: Heart failure prediction dataset, kaggle, sept. 2021. [On- line]. Available: https://www.kaggle.com/datasets/fedesoriano/heart- failure-prediction.
H.-A. Park, “An introduction to logistic regression: from basic concepts to interpretation with particular attention to nursing domain,” Journal of Korean academy of nursing, vol. 43, no. 2, pp. 154–164, 2013.
N. Friedman, D. Geiger, and M. Goldszmidt, “Bayesian network classi- fiers,” Machine learning, vol. 29, pp. 131–163, 1997.
Y. Liao and V. R. Vemuri, “Use of k-nearest neighbor classifier for in- trusion detection,” Computers & security, vol. 21, no. 5, pp. 439–448, 2002.
L. E. Peterson, “K-nearest neighbor,” Scholarpedia, vol. 4, no. 2, p. 1883, 2009.
D. A. Pisner and D. M. Schnyer, “Support vector machine,” in Machine learning. Elsevier, 2020, pp. 101–121.
V. N. Vapnik, “Pattern recognition using generalized portrait method,”Automation and remote control, vol. 24, no. 6, pp. 774–780, 1963.
A. J. Albert, R. Murugan, and T. Sripriya, “Diagnosis of heart disease using oversampling methods and decision tree classifier in cardiology,” Research on Biomedical Engineering, vol. 39, no. 1, pp. 99–113, 2023.
U. Raghavan, R. Albert, and S. Kumara, “Near linear time algorithm to detect community structures in large-scale networks,” Phys. Rev E., vol. 76, p. 036106, 2007.
D. Garreau and U. Luxburg, “Explaining the explainer: A first theoreti- cal analysis of lime,” in International conference on artificial intelligence and statistics. PMLR, 2020, pp. 1287–1296.
C. Biffi, J. J. Cerrolaza, G. Tarroni, W. Bai, A. De Marvao, O. Oktay,C. Ledig, L. Le Folgoc, K. Kamnitsas, G. Doumou et al., “Explainable anatomical shape analysis through deep hierarchical generative models,” IEEE transactions on medical imaging, vol. 39, no. 6, pp. 2088–2099, 2020.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
