Gradient Boosting Decision Trees on Medical Diagnosis over Tabular Data

TL;DR

This paper demonstrates that Gradient Boosting Decision Trees (GBDT), including XGBoost, CatBoost, and LightGBM, outperform traditional ML and deep learning models in medical diagnosis tasks using tabular data, with higher efficiency and lower computational costs.

Contribution

The study provides a comprehensive evaluation showing GBDT methods outperform other models in medical classification tasks on tabular data, highlighting their efficiency and effectiveness.

Findings

GBDT methods outperform traditional ML and deep learning models.

GBDT models require less computational power.

GBDT achieves the highest average rank on benchmark datasets.

Abstract

Medical diagnosis is a crucial task in the medical field, in terms of providing accurate classification and respective treatments. Having near-precise decisions based on correct diagnosis can affect a patient's life itself, and may extremely result in a catastrophe if not classified correctly. Several traditional machine learning (ML), such as support vector machines (SVMs) and logistic regression, and state-of-the-art tabular deep learning (DL) methods, including TabNet and TabTransformer, have been proposed and used over tabular medical datasets. Additionally, due to the superior performances, lower computational costs, and easier optimization over different tasks, ensemble methods have been used in the field more recently. They offer a powerful alternative in terms of providing successful medical decision-making processes in several diagnosis tasks. In this study, we investigated the benefits of ensemble methods, especially the Gradient Boosting Decision Tree (GBDT) algorithms in medical classification tasks over tabular data, focusing on XGBoost, CatBoost, and LightGBM. The experiments demonstrate that GBDT methods outperform traditional ML and deep neural network architectures and have the highest average rank over several benchmark tabular medical diagnosis datasets. Furthermore, they require much less computational power compared to DL models, creating the optimal methodology in terms of high performance and lower complexity.