Machine Learning and Health Science Research: Tutorial

Abstract

Machine learning (ML) has seen impressive growth in health science research due to its capacity for handling complex data to perform a range of tasks, including unsupervised learning, supervised learning, and reinforcement learning. To aid health science researchers in understanding the strengths and limitations of ML and to facilitate its integration into their studies, we present here a guideline for integrating ML into an analysis through a structured framework, covering steps from framing a research question to study design and analysis techniques for specialized data types.

Keywords: health science researcher; machine learning; machine learning pipeline; medical machine learning; precision medicine; reproducibility; unsupervised learning.

Figure 1

Machine learning workflow for a health science research question, from research question refinement to results reporting, with additional considerations. The cyclic nature of the process is reflected in the arrows, as several different iterations may be considered before narrowing down to a decisive pipeline, leading to result reporting.

Figure 2

Commonly used algorithms in the supervised setting by algorithm type distinguished between classification and regression problems, as well as methods used in unsupervised learning.