Challenges in translational machine learning

Abstract

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.

Emerging applications of artificial intelligence in pathogen genomics

“…Research done to develop explainable AI for transparency of decision-making (Wadden, 2022;Durań and Jongsma, 2021;Minh et al, 2022) and to understand algorithmic discrimination (Obermeyer et al, 2019;Heinrichs, 2022) is underdeveloped in many relevant applications. It remains important to be cognisant of how AI tools are designed so that their outputs are interpreted in the context of their limitations and strengths (Scott et al, 2021;Couckuyt et al, 2022;Sokhansanj and Rosen, 2022). Regulatory frameworks will need to contend with these issues before widespread adoption of AI in clinical diagnostics is appropriate.…”

Severe hematopoietic stem cell inflammation compromises chronic granulomatous disease gene therapy

“…We used an elastic-net logistic regression model 29 , 71 , 72 with the glmnet package in order to predict the HSCs’ ability to engraft or not.…”

Spatial Downscaling of Satellite-Based Soil Moisture Products Using Machine Learning Techniques: A Review

“…This computer-based training is a learning procedure which can be categorised into unsupervised, semi-supervised, supervised, and reinforcement learning. Supervised learning requires the availability of labelled data [70]. ML methods could also be categorised according to the techniques that they utilise.…”