This algorithm improves feature importance assessment for machine learning models predicting cardiovascular events, indicating reduced resource waste.
In this article, SHAP values are used to give the model a result close to an accurate one. Which factors are good reasons for the SHAP model's result, some factors have no connection at all, and some other factors might be interfering with the model's result. The problem is that in machine learning, we are spending time and resources on training all the data, but the result remains low. Therefore, by finding the values of SHAP and reducing the factors that do not affect the result according to the data provided, we can obtain a higher result. From this, a new method for determining the values of SHAP was proposed. That is, taking into account the dependence of the data, a method is proposed for obtaining a more accurate result for both the SHAP value and the model value.
No takes yet. Share an insight, caveat, or question.
Saidov et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: