Machine learning for medical imaging: methodological failures and recommendations for the future

G Varoquaux, V Cheplygina - NPJ digital medicine, 2022 - nature.com
Research in computer analysis of medical images bears many promises to improve patients'
health. However, a number of systematic challenges are slowing down the progress of the …

Quantitative approaches to guide epilepsy surgery from intracranial EEG

JM Bernabei, A Li, AY Revell, RJ Smith… - Brain, 2023 - academic.oup.com
Over the past 10 years, the drive to improve outcomes from epilepsy surgery has stimulated
widespread interest in methods to quantitatively guide epilepsy surgery from intracranial …

Data leakage inflates prediction performance in connectome-based machine learning models

M Rosenblatt, L Tejavibulya, R Jiang, S Noble… - Nature …, 2024 - nature.com
Predictive modeling is a central technique in neuroimaging to identify brain-behavior
relationships and test their generalizability to unseen data. However, data leakage …

[HTML][HTML] Class imbalance should not throw you off balance: Choosing the right classifiers and performance metrics for brain decoding with imbalanced data

P Thölke, YJ Mantilla-Ramos, H Abdelhedi, C Maschke… - NeuroImage, 2023 - Elsevier
Abstract Machine learning (ML) is increasingly used in cognitive, computational and clinical
neuroscience. The reliable and efficient application of ML requires a sound understanding of …

How to avoid machine learning pitfalls: a guide for academic researchers

MA Lones - arxiv preprint arxiv:2108.02497, 2021 - arxiv.org
Mistakes in machine learning practice are commonplace, and can result in a loss of
confidence in the findings and products of machine learning. This guide outlines common …

A guided multiverse study of neuroimaging analyses

J Dafflon, P F. Da Costa, F Váša, RP Monti… - Nature …, 2022 - nature.com
For most neuroimaging questions the range of possible analytic choices makes it unclear
how to evaluate conclusions from any single analytic method. One possible way to address …

The performance of machine learning models in predicting suicidal ideation, attempts, and deaths: a meta-analysis and systematic review

K Kusuma, M Larsen, JC Quiroz, M Gillies… - Journal of psychiatric …, 2022 - Elsevier
Research has posited that machine learning could improve suicide risk prediction models,
which have traditionally performed poorly. This systematic review and meta-analysis …

Cross-validation strategy impacts the performance and interpretation of machine learning models

L Sweet, C Müller, M Anand… - Artificial Intelligence for …, 2023 - journals.ametsoc.org
Abstract Machine learning algorithms are able to capture complex, nonlinear, interacting
relationships and are increasingly used to predict agricultural yield variability at regional and …

Predicting ACL injury using machine learning on data from an extensive screening test battery of 880 female elite athletes

S Jauhiainen, JP Kauppi, T Krosshaug… - … American Journal of …, 2022 - journals.sagepub.com
Background: Injury risk prediction is an emerging field in which more research is needed to
recognize the best practices for accurate injury risk assessment. Important issues related to …

Dermal features derived from optoacoustic tomograms via machine learning correlate microangiopathy phenotypes with diabetes stage

A Karlas, N Katsouli, NA Fasoula, M Bariotakis… - Nature Biomedical …, 2023 - nature.com
Skin microangiopathy has been associated with diabetes. Here we show that skin-
microangiopathy phenotypes in humans can be correlated with diabetes stage via …