Search engine for discovering works of Art, research articles, and books related to Art and Culture
ShareThis
Javascript must be enabled to continue!

Contributions of Site Heterogeneity in Multi-site Brain-Phenotype Predictions

View through CrossRef
Abstract Machine learning studies of brain–phenotype associations typically summarize accuracy with a single Pearson correlation, yet in harmonized multi-site data this metric is shaped by training-set size, feature and outcome variability, and true effect heterogeneity. We analyzed structural MRI data from the Reproducible Brain Charts consortium. After preprocessing and quality control, 3486 participants from 9 sites were retained. Three training set compositions were used to understand contributions of site heterogeneity after harmonization: within-site (Local), size-downsampled multi-site (Multi-Down), and full multi-site (Multi-Full). Another site-agnostic strategy (Overall) pooled all sites into a single dataset. All strategies included the target site in the training and testing samples. These analyses separate the contribution of the site effect from that of sample size. Between-site heterogeneity was extensive (age I ² ≈ 95%). The overall correlation of age prediction ( r = 0.73) exceeded the within-site meta-analytic estimate (Multi-Full r = 0.63). The improvement of correlation in the pooled dataset was driven by a mechanical inflation from the larger outcome variance. At matched sample size, within-site training outperformed harmonized multi-site training. Increasing the multi-site training sample size did not yield a significant advantage over within-site training. The apparent advantage of cross-dataset training thus appears to reflect training-set size rather than a benefit of multi-site composition per se. The same pattern generally held for the weaker brain-p-factor signals. Together, these results indicate that between-site heterogeneity in machine learning brain– phenotype prediction persists after harmonization. We recommend reporting site-level prediction accuracy and feature dispersion and standard deviation of the outcome variable alongside any pooled estimate to improve inter-site and inter-study comparison of machine learning prediction accuracy. Key points Between-site heterogeneity in machine-learning brain–phenotype prediction persists after harmonization: across nine CovBat-harmonized sites ( N = 3,486), within-site models outperformed multi-site models at matched training size, and enlarging the multi-site training set did not consistently surpass within-site training. A single pooled correlation masks this heterogeneity: pooling sites overstated within-site accuracy for age ( r = 0.73 vs. 0.63), largely because pooling widens the outcome’s range. Site-level accuracy tracked imaging-feature variance and outcome variability; we recommend reporting site-level accuracy, feature variance, and outcome standard deviation alongside any pooled estimate.
Title: Contributions of Site Heterogeneity in Multi-site Brain-Phenotype Predictions
Description:
Abstract Machine learning studies of brain–phenotype associations typically summarize accuracy with a single Pearson correlation, yet in harmonized multi-site data this metric is shaped by training-set size, feature and outcome variability, and true effect heterogeneity.
We analyzed structural MRI data from the Reproducible Brain Charts consortium.
After preprocessing and quality control, 3486 participants from 9 sites were retained.
Three training set compositions were used to understand contributions of site heterogeneity after harmonization: within-site (Local), size-downsampled multi-site (Multi-Down), and full multi-site (Multi-Full).
Another site-agnostic strategy (Overall) pooled all sites into a single dataset.
All strategies included the target site in the training and testing samples.
These analyses separate the contribution of the site effect from that of sample size.
Between-site heterogeneity was extensive (age I ² ≈ 95%).
The overall correlation of age prediction ( r = 0.
73) exceeded the within-site meta-analytic estimate (Multi-Full r = 0.
63).
The improvement of correlation in the pooled dataset was driven by a mechanical inflation from the larger outcome variance.
At matched sample size, within-site training outperformed harmonized multi-site training.
Increasing the multi-site training sample size did not yield a significant advantage over within-site training.
The apparent advantage of cross-dataset training thus appears to reflect training-set size rather than a benefit of multi-site composition per se.
The same pattern generally held for the weaker brain-p-factor signals.
Together, these results indicate that between-site heterogeneity in machine learning brain– phenotype prediction persists after harmonization.
We recommend reporting site-level prediction accuracy and feature dispersion and standard deviation of the outcome variable alongside any pooled estimate to improve inter-site and inter-study comparison of machine learning prediction accuracy.
Key points Between-site heterogeneity in machine-learning brain–phenotype prediction persists after harmonization: across nine CovBat-harmonized sites ( N = 3,486), within-site models outperformed multi-site models at matched training size, and enlarging the multi-site training set did not consistently surpass within-site training.
A single pooled correlation masks this heterogeneity: pooling sites overstated within-site accuracy for age ( r = 0.
73 vs.
0.
63), largely because pooling widens the outcome’s range.
Site-level accuracy tracked imaging-feature variance and outcome variability; we recommend reporting site-level accuracy, feature variance, and outcome standard deviation alongside any pooled estimate.

Related Results

Brain Organoids, the Path Forward?
Brain Organoids, the Path Forward?
Photo by Maxim Berg on Unsplash INTRODUCTION The brain is one of the most foundational parts of being human, and we are still learning about what makes humans unique. Advancements ...
[RETRACTED] Gro-X Brain Reviews - Is Gro-X Brain A Scam? v1
[RETRACTED] Gro-X Brain Reviews - Is Gro-X Brain A Scam? v1
[RETRACTED]➢Item Name - Gro-X Brain➢ Creation - Natural Organic Compound➢ Incidental Effects - NA➢ Accessibility - Online➢ Rating - ⭐⭐⭐⭐⭐➢ Click Here To Visit - Official Website - ...
Hydatid Disease of The Brain Parenchyma: A Systematic Review
Hydatid Disease of The Brain Parenchyma: A Systematic Review
Abstarct Introduction Isolated brain hydatid disease (BHD) is an extremely rare form of echinococcosis. A prompt and timely diagnosis is a crucial step in disease management. This ...
Brain Anatomy
Brain Anatomy
The human brain is one of the important organs in the human body. It is the most complex of all organs. The brain is an organ composed of billions of nerve cells. It has parts of t...
Brain Biochemistry and Its Disease
Brain Biochemistry and Its Disease
The human brain is one of the important organs in the human body. It is the most complex of all organs. The brain is an organ composed of billions of nerve cells. It has parts of t...
Brain volume abnormalities and clinical outcomes following paediatric traumatic brain injury
Brain volume abnormalities and clinical outcomes following paediatric traumatic brain injury
Abstract Long-term outcomes are difficult to predict after paediatric traumatic brain injury. The presence or absence of focal brain injuries often do not explain co...
“What” and “when” predictions modulate auditory processing in a contextually specific manner
“What” and “when” predictions modulate auditory processing in a contextually specific manner
Abstract Extracting regularities from ongoing stimulus streams to form predictions is crucial for adaptive behavior. Such regularities exist in terms of the content...

Back to Top