Interpretable Machine Learning Model For Heart Disease Prediction

Asih, Putri Sari and Azhar, Yufis and Wicaksono, Galih Wasis and Akbi, Denar Regata (2023) Interpretable Machine Learning Model For Heart Disease Prediction. In: 8th International Conference on Computer Science and Computational Intelligence (ICCSCI 2023). Procedia Computer Science, 227 . Elsevier, Elsevier B.V, pp. 439-445.

[thumbnail of Asih Azhar Wicaksono Akbi - interpretable machine learning SHAP LIME.pdf]
Preview
Text
Asih Azhar Wicaksono Akbi - interpretable machine learning SHAP LIME.pdf

Download (932kB) | Preview
[thumbnail of Similarity - Asih Azhar Wicaksono Akbi - interpretable machine learning SHAP LIME.pdf]
Preview
Text
Similarity - Asih Azhar Wicaksono Akbi - interpretable machine learning SHAP LIME.pdf

Download (1MB) | Preview

Abstract

In the medical industry, accurately predicting a patient’s likelihood of heart disease requires a high-performance model and explaining how the model arrived at its conclusion. To address this, a study has proposed a way to interpret machine learning models using SHAP and LIME. Four models have been created: Vector Machine, Random Forest, XGBoost, and k-Nearest Neighbor. The SVM and XGBoost models exhibit the highest f1-score performance, reaching up to 88%. These models can then be utilized during the interpretation stage with the aid of SHAP and LIME. Based on the SHAP visualization results, it is evident that the predictions made include various significant variables. Meanwhile, LIME explains the classification of each data point. Additionally, it confirms that SHAP and LIME are valuable tools for interpreting models.

Item Type: Book Section / Proceedings
Keywords: : interpretable machine learning; SHAP; LIME.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Engineering > Department of Informatics (55201)
Depositing User: galih.w.w Gali Wasis Wicaksono,S.Kom
Date Deposited: 16 Mar 2024 04:54
Last Modified: 16 Mar 2024 04:54
URI: https://eprints.umm.ac.id/id/eprint/4858

Actions (login required)

View Item
View Item