ArticleNeuroImage2023
Relationship between prediction accuracy and feature importance reliability: An empirical and theoretical study.
Article in NeuroImage, 2023. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 36 papers, 1 of them a synthesis that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
36 citing papers in PubMed, 1 synthesis or guideline pooled it.
- Beyond binary comparisons: a Bayesian dose-response meta-analysis of exercise on executive function in children and adolescents with ADHD.Pediatric research · 2026Pooled it
- Trial
- Role of surgeon seniority in predicting surgically induced astigmatism after phacoemulsification surgery: a machine learning study.BMC ophthalmology · 2026Article
- Neuroanatomy reflects individual variability in impulsivity in youth.Molecular psychiatry · 2026Article
- Exploring the link between body physiology and cognition: the role of the brain and aging.npj aging · 2026Article
- Feature selection leads to divergent neurobiological interpretations of brain-based machine learning biomarkers.Nature human behaviour · 2026Article
- Convergent and divergent brain-cognition development in early adolescence.Nature communications · 2026Article
- Latent neural architecture organising shared aesthetic evaluations of visual artworks.Nature communications · 2026Article
- Investigating the impact of stressful life events on neuroanatomy across adolescence.bioRxiv : the preprint server for biology · 2026Article
- Common and distinct neurofunctional signatures of dynamic naturalistic emotion regulation strategies.Nature communications · 2026Article
- Development and evaluation of a 15-item health literacy classification model using integrated psychometric approaches in China.BMC public health · 2026Article
- Cognition, but not affect, rests upon a segregated intrinsic network architecture.bioRxiv : the preprint server for biology · 2026Article
- Letter to the Editor: Navigating bias in machine learning-reevaluating feature importances through robust statistical analysis.European radiology · 2026Article
- Overlooked features lead to divergent neurobiological interpretations of brain-based machine learning biomarkers.bioRxiv : the preprint server for biology · 2025Article
- Oxytocin and vasopressin enhance social pain empathy via common and distinct of neural expressions, genetic pathways, and networks.Proceedings of the National Academy of Sciences of the United States of America · 2025Article
- Effective workflow from multimodal MRI data to model-based prediction.Scientific reports · 2025Article
- Sample size matters when estimating test-retest reliability of behaviour.Behavior research methods · 2025Article
- Longer scans boost prediction and cut costs in brain-wide association studies.bioRxiv : the preprint server for biology · 2025Article
- Bias in data-driven replicability analysis of univariate brain-wide association studies.Scientific reports · 2025Article
- Enhancing task fMRI individual difference research with neural signatures.medRxiv : the preprint server for health sciences · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
10 authors.
Funding
Abstract
There is significant interest in using neuroimaging data to predict behavior. The predictive models are often interpreted by the computation of feature importance, which quantifies the predictive relevance of an imaging feature. Tian and Zalesky (2021) suggest that feature importance estimates exhibit low split-half reliability, as well as a trade-off between prediction accuracy and feature importance reliability across parcellation resolutions. However, it is unclear whether the trade-off between prediction accuracy and feature importance reliability is universal. Here, we demonstrate that, with a sufficient sample size, feature importance (operationalized as Haufe-transformed weights) can achieve fair to excellent split-half reliability. With a sample size of 2600 participants, Haufe-transformed weights achieve average intra-class correlation coefficients of 0.75, 0.57 and 0.53 for cognitive, personality and mental health measures respectively. Haufe-transformed weights are much more reliable than original regression weights and univariate FC-behavior correlations. Original regression weights are not reliable even with 2600 participants. Intriguingly, feature importance reliability is strongly positively correlated with prediction accuracy across phenotypes. Within a particular behavioral domain, there is no clear relationship between prediction performance and feature importance reliability across regression models. Furthermore, we show mathematically that feature importance reliability is necessary, but not sufficient, for low feature importance error. In the case of linear models, lower feature importance error is mathematically related to lower prediction error. Therefore, higher feature importance reliability might yield lower feature importance error and higher prediction accuracy. Finally, we discuss how our theoretical results relate with the reliability of imaging features and behavioral measures. Overall, the current study provides empirical and theoretical insights into the relationship between prediction accuracy and feature importance reliability.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.