{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T19:06:32Z","timestamp":1789499192624,"version":"build-2803163510"},"posted":{"date-parts":[[2026,9,11]]},"group-title":"Neuroscience","reference-count":27,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:00:00Z","timestamp":1789084800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Institute of Mental Health","award":["R01MH120482"],"award-info":[{"award-number":["R01MH120482"]}]},{"name":"National Institute of Mental Health","award":["R01MH123550"],"award-info":[{"award-number":["R01MH123550"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,9,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Youth can exhibit signs of delayed or accelerated neurodevelopment, measurable via brain magnetic resonance imaging (MRI). Brain age prediction seeks to estimate brain age at an individual level using machine learning models fitted on healthy individuals. The brain age gap (BAG)\u2013the difference between brain age and chronological age\u2013has been studied as a potential biomarker. However, BAG suffers from known limitations including dependence on chronological age, regression to the mean, and challenges in interpretability. As an alternative framework, we introduce brain age intervals (BAIs) as a normative interval on an individual\u2019s chronological age, based on MRI measures. BAIs can be derived using a recent statistical framework called conformal prediction that yields prediction intervals with guaranteed coverage. We train several brain age prediction models on structural and functional MRI scans from the Reproducible Brain Charts dataset (aged 6-22) and estimated BAIs. The BAIs demonstrated stable empirical coverage close to the nominal 90% level (median coverage=91%, width=7.36 years, root mean square error (RMSE)=2.20 years across 100 repeated train\u2013test splits). Association between interval coverage and clinical measures (p-factor, parental education) were weak, with only a modest directional signal for parental education. Together, these findings demonstrate the feasibility of uncertainty-aware brain age modeling in youth populations while highlighting the need for larger and more diverse samples to detect meaningful clinical and environmental associations.<\/jats:p>","DOI":"10.64898\/2026.09.04.749442","type":"posted-content","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T21:40:16Z","timestamp":1789162816000},"source":"Crossref","is-referenced-by-count":0,"title":["Quantifying Uncertainty in Brain Age Predictions via Conformal Prediction"],"prefix":"10.64898","author":[{"given":"Ujjwal","family":"Samanta","sequence":"first","affiliation":[{"name":"Department of Public Health Sciences, Medical University of South Carolina, Charleston, SC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2036-5571","authenticated-orcid":false,"given":"Golia","family":"Shafiei","sequence":"additional","affiliation":[{"name":"Penn Lifespan Informatics and Neuroimaging Center (PennLINC), Department of Psychiatry, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA"},{"name":"Penn-CHOP Lifespan Brain Institute, Perelman School of Medicine, Children\u2019s Hospital of Philadelphia Research Institute, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9286-0694","authenticated-orcid":false,"given":"Helmet","family":"Karim","sequence":"additional","affiliation":[{"name":"Department of Psychiatry, University of Pittsburgh, Pittsburgh, PA, USA"},{"name":"Department of Bioengineering, University of Pittsburgh, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Theodore D.","family":"Satterthwaite","sequence":"additional","affiliation":[{"name":"Penn Lifespan Informatics and Neuroimaging Center (PennLINC), Department of Psychiatry, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA"},{"name":"Penn-CHOP Lifespan Brain Institute, Perelman School of Medicine, Children\u2019s Hospital of Philadelphia Research Institute, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Public Health Sciences, Medical University of South Carolina, Charleston, SC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"issue":"1","key":"2026091511401816000_2026.09.04.749442v1.1","doi-asserted-by":"crossref","first-page":"3511","DOI":"10.1038\/s41467-024-47748-w","article-title":"Functional connectivity development along the sensorimotor-association axis enhances the cortical hierarchy","volume":"15","year":"2024","journal-title":"Nature communications"},{"key":"2026091511401816000_2026.09.04.749442v1.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2025.08.026"},{"key":"2026091511401816000_2026.09.04.749442v1.3","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-019-0471-7"},{"key":"2026091511401816000_2026.09.04.749442v1.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2010.01.005"},{"key":"2026091511401816000_2026.09.04.749442v1.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.tins.2017.10.001"},{"key":"2026091511401816000_2026.09.04.749442v1.6","doi-asserted-by":"publisher","DOI":"10.1038\/mp.2017.62"},{"key":"2026091511401816000_2026.09.04.749442v1.7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2019.06.017"},{"key":"2026091511401816000_2026.09.04.749442v1.8","doi-asserted-by":"publisher","DOI":"10.1093\/schbul\/sbt142"},{"key":"2026091511401816000_2026.09.04.749442v1.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2012.07.002"},{"key":"2026091511401816000_2026.09.04.749442v1.10","doi-asserted-by":"publisher","DOI":"10.1126\/science.1194144"},{"issue":"1","key":"2026091511401816000_2026.09.04.749442v1.11","doi-asserted-by":"crossref","first-page":"5409","DOI":"10.1038\/s41467-019-13163-9","article-title":"Brain age prediction using deep learning uncovers associated sequence variants","volume":"10","year":"2019","journal-title":"Nature communications"},{"key":"2026091511401816000_2026.09.04.749442v1.12","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.26502"},{"key":"2026091511401816000_2026.09.04.749442v1.13","doi-asserted-by":"crossref","first-page":"102229","DOI":"10.1016\/j.nicl.2020.102229","article-title":"Commentary: Correction procedures in brain-age prediction","volume":"26","year":"2020","journal-title":"NeuroImage: Clinical"},{"key":"2026091511401816000_2026.09.04.749442v1.14","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.70276"},{"issue":"4","key":"2026091511401816000_2026.09.04.749442v1.15","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1561\/2200000101","article-title":"Conformal prediction: A gentle introduction","volume":"16","year":"2023","journal-title":"Foundations and Trends in Machine Learning"},{"issue":"1","key":"2026091511401816000_2026.09.04.749442v1.16","doi-asserted-by":"crossref","first-page":"170181","DOI":"10.1038\/sdata.2017.181","article-title":"An open resource for transdiagnostic research in pediatric mental health and learning disorders","volume":"4","year":"2017","journal-title":"Scientific data"},{"key":"2026091511401816000_2026.09.04.749442v1.17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.07.064"},{"key":"2026091511401816000_2026.09.04.749442v1.18","doi-asserted-by":"publisher","DOI":"10.1002\/mpr.1459"},{"key":"2026091511401816000_2026.09.04.749442v1.19","first-page":"152","article-title":"The NKI-Rockland sample: a model for accelerating the pace of discovery science in psychiatry","volume":"6","year":"2012","journal-title":"Frontiers in neuroscience"},{"key":"2026091511401816000_2026.09.04.749442v1.20","doi-asserted-by":"crossref","first-page":"101020","DOI":"10.1016\/j.dcn.2021.101020","article-title":"Chinese Color Nest Project: An accelerated longitudinal brain-mind cohort","volume":"52","year":"2021","journal-title":"Developmental cognitive neuroscience"},{"key":"2026091511401816000_2026.09.04.749442v1.21","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C , editors. Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining; 2016.","DOI":"10.1145\/2939672.2939785"},{"key":"2026091511401816000_2026.09.04.749442v1.22","unstructured":"Romano Y , Patterson E , Candes E. Conformalized quantile regression. Advances in neural information processing systems. 2019;32."},{"key":"2026091511401816000_2026.09.04.749442v1.23","doi-asserted-by":"crossref","unstructured":"Sarica A , Camastra C , Pelagi A , Arcuri F , Quattrone A , editors. Conformal prediction for uncertainty quantification in brain age estimation using random forests quantile regression on MRI features of the HCP young adult. International Conference on Machine Learning, Optimization, and Data Science; 2024: Springer.","DOI":"10.1007\/978-3-031-82487-6_10"},{"key":"2026091511401816000_2026.09.04.749442v1.24","doi-asserted-by":"crossref","unstructured":"Sarica A , Camastra C , Pelagi A , Arcuri F , Novellino F , Quattrone A , et al. The ICeX framework: Brain age estimation from thalamic nuclei with conformalized and eXplainable random forest regression. Computer Methods and Programs in Biomedicine. 2025:109140.","DOI":"10.1016\/j.cmpb.2025.109140"},{"key":"2026091511401816000_2026.09.04.749442v1.25","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0067346"},{"key":"2026091511401816000_2026.09.04.749442v1.26","doi-asserted-by":"publisher","DOI":"10.1038\/s41380-020-0754-0"},{"key":"2026091511401816000_2026.09.04.749442v1.27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2016.11.005"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.09.04.749442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T18:40:24Z","timestamp":1789497624000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.09.04.749442"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,11]]},"references-count":27,"URL":"https:\/\/doi.org\/10.64898\/2026.09.04.749442","relation":{},"subject":[],"published":{"date-parts":[[2026,9,11]]},"subtype":"preprint"}}