{
  "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 {approx} 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.",
  "abstract_shown": true,
  "affiliations": [
    "Vanderbilt University Medical Center"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "name": "G. Chen"
    },
    {
      "name": "M. Jones"
    },
    {
      "name": "I. Gadiyar"
    },
    {
      "name": "T. D. Satterthwaite"
    },
    {
      "name": "A. Chen"
    },
    {
      "affs": [
        0
      ],
      "name": "S. Vandekar"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cqgpwh4zkpd0z.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.11.01.763540",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.11.01.763540v1.full",
  "id": "cqgpwh4zkpd0z",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.11.01.763540v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "neuroscience"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.11.01.763540v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/cqgpwh4zkpd0z.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T00:21:42Z",
      "native_id": "10.64898/2026.11.01.763540",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.11.01.763540v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:neuroscience",
      "subfield": "neuroscience"
    }
  ],
  "title": "Contributions of Site Heterogeneity in Multi-site Brain-Phenotype Predictions",
  "title_text": "Contributions of Site Heterogeneity in Multi-site Brain-Phenotype Predictions",
  "type": "preprint",
  "updated_at": "2026-11-06T00:21:27Z",
  "url": "https://research.draconitic.com/paper/cqgpwh4zkpd0z",
  "venue": "bioRxiv",
  "versions": []
}