Machine Science in Biomedicine: Practicalities, Pitfalls and Potential

TL;DR

This paper reviews the application of Machine Science in biomedicine, discussing recent studies, current challenges, and the potential of data-driven research methodologies in advancing biomedical science.

Contribution

It provides an overview of recent biomedical Machine Science studies and critically assesses the practical challenges and opportunities in this emerging field.

Findings

Data mining techniques are central to biomedical Machine Science.

Current limitations include data quality, costs, and skill requirements.

There is significant potential for Machine Science to transform biomedical research.

Abstract

Machine Science, or Data-driven Research, is a new and interesting scientific methodology that uses advanced computational techniques to identify, retrieve, classify and analyse data in order to generate hypotheses and develop models. In this paper we describe three recent biomedical Machine Science studies, and use these to assess the current state of the art with specific emphasis on data mining, data assessment, costs, limitations, skills and tool support.