AutoML-Med: A Framework for Automated Machine Learning in Medical Tabular Data

TL;DR

AutoML-Med is a specialized automated machine learning framework designed to handle complex medical tabular data issues, improving predictive accuracy and sensitivity in clinical tasks with minimal user intervention.

Contribution

It introduces a novel AutoML architecture tailored for medical data challenges, integrating Latin Hypercube Sampling and PRCC for optimized preprocessing and model selection.

Findings

Outperforms existing tools in balanced accuracy and sensitivity.

Effectively handles missing data, class imbalance, and heterogeneous features.

Demonstrates significant improvements in clinical prediction tasks.

Abstract

Medical datasets are typically affected by issues such as missing values, class imbalance, a heterogeneous feature types, and a high number of features versus a relatively small number of samples, preventing machine learning models from obtaining proper results in classification and regression tasks. This paper introduces AutoML-Med, an Automated Machine Learning tool specifically designed to address these challenges, minimizing user intervention and identifying the optimal combination of preprocessing techniques and predictive models. AutoML-Med's architecture incorporates Latin Hypercube Sampling (LHS) for exploring preprocessing methods, trains models using selected metrics, and utilizes Partial Rank Correlation Coefficient (PRCC) for fine-tuned optimization of the most influential preprocessing steps. Experimental results demonstrate AutoML-Med's effectiveness in two different clinical settings, achieving higher balanced accuracy and sensitivity, which are crucial for identifying at-risk patients, compared to other state-of-the-art tools. AutoML-Med's ability to improve prediction results, especially in medical datasets with sparse data and class imbalance, highlights its potential to streamline Machine Learning applications in healthcare.