Machine learning (ML) algorithms are increasingly being used to help implement clinical decision support systems. In this new field, we define as “translational machine learning”, joint efforts and strong communication between data scientists and clinicians help to span the gap between ML and its adoption in the clinic. These collaborations also improve interpretability and trust in translational ML methods and ultimately aim to result in generalizable and reproducible models. To help clinicians and bioinformaticians refine their translational ML pipelines, we review the steps from model building to the use of ML in the clinic. We discuss experimental setup, computational analysis, interpretability and reproducibility, and emphasize the challenges involved. We highly advise collaboration and data sharing between consortia and institutes to build multi-centric cohorts that facilitate ML methodologies that generalize across centers. In the end, we hope that this review provides a way to streamline translational ML and helps to tackle the challenges that come with it.
Bibliographical noteFunding Information:
The research leading to these results has received funding from the Flemish Government under the “Onderzoeksprogramma Artificiële Intelligentie (AI) Vlaanderen” and from the FWO-TBM program (FWOTBM20190001). This project has received funding within the Grand Challenges Program of VIB. This VIB Program received support from the Flemish Government under the Management Agreement 2017–2021 (VR 2016 2312 Doc.1521/4). SVG is an ISAC Marylou Ingram Scholar and supported by an FWO postdoctoral research grant (Research Foundation—Flanders).
© 2022, The Author(s).