Treffer: dGAMLSS: an exact, distributed algorithm to fit Generalized Additive Models for Location, Scale, and Shape for privacy-preserving population reference charts.
Title:
dGAMLSS: an exact, distributed algorithm to fit Generalized Additive Models for Location, Scale, and Shape for privacy-preserving population reference charts.
Authors:
Hu F; Penn Statistics in Imaging and Visualization Endeavor (PennSIVE), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, United States., Tong J; Center for Health AI and Synthesis of Evidence (CHASE), Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, United States.; Department of Biostatistics, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD 21205, United States., Gardner M; Brain-Gene-Development Lab, The Children's Hospital of Philadelphia, Philadelphia, PA 19104, United States., Chen AA; Department of Public Health Sciences, Medical University of South Carolina, Charleston, SC 29425, United States., Bethlehem RAI; Department of Psychology, University of Cambridge, Cambridge, United Kingdom., Seidlitz J; Brain-Gene-Development Lab, The Children's Hospital of Philadelphia, Philadelphia, PA 19104, United States.; Lifespan Brain Institute, The Children's Hospital of Philadelphia, Philadelphia, PA 19104, United States.; Department of Psychiatry, University of Pennsylvania, Philadelphia, PA 19104, United States.; Department of Child and Adolescent Psychiatry and Behavioral Science, The Children's Hospital of Philadelphia, Philadelphia, PA 19104, United States., Li H; Center for Statistical Methods for Big Data, Department of Biostatistics, and Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, United States., Alexander-Bloch A; Brain-Gene-Development Lab, The Children's Hospital of Philadelphia, Philadelphia, PA 19104, United States.; Lifespan Brain Institute, The Children's Hospital of Philadelphia, Philadelphia, PA 19104, United States.; Department of Psychiatry, University of Pennsylvania, Philadelphia, PA 19104, United States.; Department of Child and Adolescent Psychiatry and Behavioral Science, The Children's Hospital of Philadelphia, Philadelphia, PA 19104, United States., Chen Y; Center for Health AI and Synthesis of Evidence (CHASE), Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, United States., Shinohara RT; Penn Statistics in Imaging and Visualization Endeavor (PennSIVE), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, United States.; Center for Biomedical Image Computing and Analytics (CBICA), Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, United States.
Corporate Authors:
Source:
Bioinformatics (Oxford, England) [Bioinformatics] 2026 Jan 02; Vol. 42 (1).
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Oxford University Press Country of Publication: England NLM ID: 9808944 Publication Model: Print Cited Medium: Internet ISSN: 1367-4811 (Electronic) Linking ISSN: 13674803 NLM ISO Abbreviation: Bioinformatics Subsets: MEDLINE
Imprint Name(s):
Original Publication: Oxford : Oxford University Press, c1998-
MeSH Terms:
References:
Circulation. 2000 Jun 13;101(23):E215-20. (PMID: 10851218)
Acta Paediatr Suppl. 2006 Apr;450:76-85. (PMID: 16817681)
Nature. 2022 Apr;604(7906):525-533. (PMID: 35388223)
Arch Dis Child. 1995 Jul;73(1):25-9. (PMID: 7639544)
Stud Health Technol Inform. 2015;216:574-8. (PMID: 26262116)
J Am Med Inform Assoc. 2014 Jul-Aug;21(4):576-7. (PMID: 24821744)
N Engl J Med. 2018 Nov 29;379(22):2091-2093. (PMID: 30485777)
Stat Methods Med Res. 1995 Sep;4(3):187-96. (PMID: 8548102)
Pac Symp Biocomput. 2019;24:30-41. (PMID: 30864308)
Sci Data. 2023 Jan 3;10(1):1. (PMID: 36596836)
Stat Med. 2004 Oct 15;23(19):3053-76. (PMID: 15351960)
Fam Med. 1990 Jul-Aug;22(4):307-11. (PMID: 2200734)
Pac Symp Biocomput. 2020;25:695-706. (PMID: 31797639)
Neuroinformatics. 2022 Apr;20(2):377-390. (PMID: 34807353)
Clin Biochem Rev. 2008 Aug;29 Suppl 1:S93-7. (PMID: 18852866)
NPJ Biofilms Microbiomes. 2022 Oct 15;8(1):79. (PMID: 36243731)
Stat Med. 2009 Feb 28;28(5):880-98. (PMID: 19065626)
BMC Med Inform Decis Mak. 2022 Oct 16;22(1):269. (PMID: 36244993)
Stat Med. 2006 Jan 30;25(2):247-65. (PMID: 16143968)
Hum Brain Mapp. 2025 Jun 1;46(8):e70197. (PMID: 40497521)
J Am Med Inform Assoc. 2022 Jul 12;29(8):1366-1371. (PMID: 35579348)
Sci Rep. 2022 Apr 22;12(1):6627. (PMID: 35459767)
BMC Bioinformatics. 2019 Apr 16;20(1):188. (PMID: 30991942)
Acta Paediatr Suppl. 2006 Apr;450:76-85. (PMID: 16817681)
Nature. 2022 Apr;604(7906):525-533. (PMID: 35388223)
Arch Dis Child. 1995 Jul;73(1):25-9. (PMID: 7639544)
Stud Health Technol Inform. 2015;216:574-8. (PMID: 26262116)
J Am Med Inform Assoc. 2014 Jul-Aug;21(4):576-7. (PMID: 24821744)
N Engl J Med. 2018 Nov 29;379(22):2091-2093. (PMID: 30485777)
Stat Methods Med Res. 1995 Sep;4(3):187-96. (PMID: 8548102)
Pac Symp Biocomput. 2019;24:30-41. (PMID: 30864308)
Sci Data. 2023 Jan 3;10(1):1. (PMID: 36596836)
Stat Med. 2004 Oct 15;23(19):3053-76. (PMID: 15351960)
Fam Med. 1990 Jul-Aug;22(4):307-11. (PMID: 2200734)
Pac Symp Biocomput. 2020;25:695-706. (PMID: 31797639)
Neuroinformatics. 2022 Apr;20(2):377-390. (PMID: 34807353)
Clin Biochem Rev. 2008 Aug;29 Suppl 1:S93-7. (PMID: 18852866)
NPJ Biofilms Microbiomes. 2022 Oct 15;8(1):79. (PMID: 36243731)
Stat Med. 2009 Feb 28;28(5):880-98. (PMID: 19065626)
BMC Med Inform Decis Mak. 2022 Oct 16;22(1):269. (PMID: 36244993)
Stat Med. 2006 Jan 30;25(2):247-65. (PMID: 16143968)
Hum Brain Mapp. 2025 Jun 1;46(8):e70197. (PMID: 40497521)
J Am Med Inform Assoc. 2022 Jul 12;29(8):1366-1371. (PMID: 35579348)
Sci Rep. 2022 Apr 22;12(1):6627. (PMID: 35459767)
BMC Bioinformatics. 2019 Apr 16;20(1):188. (PMID: 30991942)
Grant Information:
FOCUS on Health and Leadership for Women and Penn PROMOTES Research on Sex and Gender in Health; R01 MH132934 United States MH NIMH NIH HHS; R01NS112274 United States NH NIH HHS; American Medical Association; United States NH NIH HHS; R01MH123563 United States NH NIH HHS; R01MH112847 United States NH NIH HHS; T32 GM07170 National Institutes of Health Medical Scientist Training; R01 MH112847 United States MH NIMH NIH HHS; R01MH132934 National Institutes of Health Medical Scientist Training; R01 NS112274 United States NS NINDS NIH HHS; R01 MH123550 United States MH NIMH NIH HHS; R01 MH123563 United States MH NIMH NIH HHS; R01NS060910 United States NH NIH HHS; R01MH134896 National Institutes of Health Medical Scientist Training; R01MH133843 National Institutes of Health Medical Scientist Training; U24 NS130411 United States NS NINDS NIH HHS; R01 MH133843 United States MH NIMH NIH HHS; R01MH123550 United States NH NIH HHS; T32 GM007170 United States GM NIGMS NIH HHS; R01 MH134896 United States MH NIMH NIH HHS; R01 NS060910 United States NS NINDS NIH HHS
Contributed Indexing:
Investigator: C Adamson; S Adler; AF Alexander-Bloch; E Anagnostou; KM Anderson; A Areces-Gonzalez; DE Astle; B Auyeung; M Ayub; JB Bae; G Ball; S Baron-Cohen; R Beare; SA Bedford; V Benegal; RAI Bethlehem; F Beyer; J Blangero; MB Cábez; JP Boardman; M Borzage; JF Bosch-Bayard; N Bourke; ET Bullmore; VD Calhoun; MM Chakravarty; C Chen; C Chertavian; G Chetelat; YS Chong; A Corvin; M Costantino; E Courchesne; F Crivello; VL Cropley; J Crosbie; N Crossley; M Delarue; R Delorme; S Desrivieres; GA Devenyi; MAD Biase; R Dolan; KA Donald; G Donohoe; L Dorfschmidt; K Dunlop; AD Edwards; JT Elison; CT Ellis; JA Elman; L Eyler; DA Fair; PC Fletcher; P Fonagy; CE Franz; L Galan-Garcia; A Gholipour; J Giedd; JH Gilmore; DC Glahn; IM Goodyer; PE Grant; NA Groenewold; FM Gunning; RE Gur; RC Gur; CF Hammill; O Hansson; T Hedden; A Heinz; RN Henson; K Heuer; J Hoare; B Holla; AJ Holmes; H Huang; J Ipser; CR Jack; AP Jackowski; T Jia; DT Jones; PB Jones; RS Kahn; H Karlsson; L Karlsson; R Kawashima; EA Kelley; S Kern; KW Kim; MG Kitzbichler; WS Kremen; F Lalonde; B Landeau; J Lerch; JD Lewis; J Li; W Liao; C Liston; MV Lombardo; J Lv; TT Mallard; M Marcelis; SR Mathias; B Mazoyer; P McGuire; MJ Meaney; A Mechelli; B Misic; SE Morgan; D Mothersill; C Ortinau; R Ossenkoppele; M Ouyang; L Palaniyappan; L Paly; PM Pan; C Pantelis; MTM Park; T Paus; Z Pausova; D Paz-Linares; AP Binette; K Pierce; X Qian; A Qiu; A Raznahan; T Rittman; A Rodrigue; CK Rollins; R Romero-Garcia; L Ronan; MD Rosenberg; DH Rowitch; GA Salum; TD Satterthwaite; HL Schaare; RJ Schachar; M Schöll; AP Schultz; J Seidlitz; D Sharp; RT Shinohara; I Skoog; CD Smyser; RA Sperling; DJ Stein; A Stolicyn; J Suckling; G Sullivan; K Sun; B Thyreau; R Toro; N Traut; KA Tsvetanov; NB Turk-Browne; JJ Tuulari; C Tzourio; É Vachon-Presseau; MJ Valdes-Sosa; PA Valdes-Sosa; SL Valk; T van Amelsvoort; SN Vandekar; L Vasung; PE Vértes; LW Victoria; S Villeneuve; A Villringer; JW Vogel; K Wagstyl; YS Wang; SK Warfield; V Warrier; E Westman; ML Westwater; HC Whalley; SR White; AV Witte; N Yang; BTT Yeo; HJ Yun; A Zalesky; HJ Zar; A Zettergren; JH Zhou; H Ziauddeen; D Zimmerman; A Zugman; XN Zuo
Entry Date(s):
Date Created: 20260108 Date Completed: 20260114 Latest Revision: 20260307
Update Code:
20260307
PubMed Central ID:
PMC12802883
DOI:
10.1093/bioinformatics/btaf625
PMID:
41507058
Database:
MEDLINE
Weitere Informationen
Motivation: There is growing interest in estimating population reference ranges across age and sex to better identify atypical clinically-relevant measurements throughout the lifespan. For this task, the World Health Organization recommends using Generalized Additive Models for Location, Scale, and Shape (GAMLSS), which can model non-linear growth trajectories under complex distributions that address the heterogeneity in human populations.Fitting GAMLSS models requires large, generalizable sample sizes, especially for accurate estimation of extreme quantiles, but obtaining such multi-site data can be challenging due to privacy concerns and practical considerations. In settings where patient data cannot be shared, privacy-preserving distributed algorithms for federated learning can be used, but no such algorithm exists for GAMLSS.
Results: We propose distributed GAMLSS (dGAMLSS), a distributed algorithm that can fit GAMLSS models across multiple sites without sharing patient-level data. This includes specific considerations for the fitting of smooth functions at varying levels of communication efficiency. We demonstrate the effectiveness of dGAMLSS in constructing population reference charts across clinical, genomics, and neuroimaging settings and show that dGAMLSS is able to reproduce pooled reference charts and inference down to numerical differences.
Availability and Implementation: An R package providing examples of the dGAMLSS algorithm, as well as functions for sharing and aggregating site-specific parameters, is available at https://github.com/hufengling/dGAMLSS.
(© The Author(s) 2026. Published by Oxford University Press.)