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 …

Establishment of best practices for evidence for prediction: a review

RA Poldrack, G Huckins, G Varoquaux - JAMA psychiatry, 2020 - jamanetwork.com
Importance Great interest exists in identifying methods to predict neuropsychiatric disease
states and treatment outcomes from high-dimensional data, including neuroimaging and …

The promise of machine learning in predicting treatment outcomes in psychiatry

AM Chekroud, J Bondar, J Delgadillo… - World …, 2021 - Wiley Online Library
For many years, psychiatrists have tried to understand factors involved in response to
medications or psychotherapies, in order to personalize their treatment choices. There is …

What is the test-retest reliability of common task-functional MRI measures? New empirical evidence and a meta-analysis

ML Elliott, AR Knodt, D Ireland, ML Morris… - Psychological …, 2020 - journals.sagepub.com
Identifying brain biomarkers of disease risk is a growing priority in neuroscience. The ability
to identify meaningful biomarkers is limited by measurement reliability; unreliable measures …

Imaging structural and functional brain development in early childhood

JH Gilmore, RC Knickmeyer, W Gao - Nature Reviews Neuroscience, 2018 - nature.com
In humans, the period from term birth to∼ 2 years of age is characterized by rapid and
dynamic brain development and plays an important role in cognitive development and risk of …

How to establish robust brain–behavior relationships without thousands of individuals

MD Rosenberg, ES Finn - Nature Neuroscience, 2022 - nature.com
Can studying individual differences in brain structure and function reveal individual
differences in behavior? Analyses of MRI data from nearly 50,000 individuals may suggest …

Machine learning for precision psychiatry: opportunities and challenges

D Bzdok, A Meyer-Lindenberg - Biological Psychiatry: Cognitive …, 2018 - Elsevier
The nature of mental illness remains a conundrum. Traditional disease categories are
increasingly suspected to misrepresent the causes underlying mental disturbance. Yet …

A distributed fMRI-based signature for the subjective experience of fear

F Zhou, W Zhao, Z Qi, Y Geng, S Yao… - Nature …, 2021 - nature.com
The specific neural systems underlying the subjective feeling of fear are debated in affective
neuroscience. Here, we combine functional MRI with machine learning to identify and …

Cross-validation failure: Small sample sizes lead to large error bars

G Varoquaux - Neuroimage, 2018 - Elsevier
Predictive models ground many state-of-the-art developments in statistical brain image
analysis: decoding, MVPA, searchlight, or extraction of biomarkers. The principled approach …

Discovery and validation of biomarkers to aid the development of safe and effective pain therapeutics: challenges and opportunities

KD Davis, N Aghaeepour, AH Ahn, MS Angst… - Nature Reviews …, 2020 - nature.com
Pain medication plays an important role in the treatment of acute and chronic pain
conditions, but some drugs, opioids in particular, have been overprescribed or prescribed …