Prediction of Autism Risk From Family Medical History Data Using Machine Learning: A National Cohort Study From Denmark.
Autism
Epidemiology
Family history
Machine learning
Population based
Risk score
Journal
Biological psychiatry global open science
ISSN: 2667-1743
Titre abrégé: Biol Psychiatry Glob Open Sci
Pays: United States
ID NLM: 9918227369306676
Informations de publication
Date de publication:
Aug 2021
Aug 2021
Historique:
received:
03
02
2021
revised:
09
03
2021
accepted:
18
04
2021
entrez:
3
11
2022
pubmed:
5
5
2021
medline:
5
5
2021
Statut:
epublish
Résumé
A family history of specific disorders (e.g., autism, depression, epilepsy) has been linked to risk for autism spectrum disorder (ASD). This study examines whether family history data could be used for ASD risk prediction. We followed all Danish live births, from 1980 to 2012, of Denmark-born parents for an ASD diagnosis through April 10, 2017 ( The best-performing model comprised 41 indicators: eight mental conditions (e.g., ASD, attention-deficit/hyperactivity disorder, neurotic/stress disorders) and nine nonmental conditions (e.g., obesity, hypertension, asthma) across six family member types; model performance was similar in training and test subsamples. The highest risk score group had 17.0% ASD prevalence and a 15.3-fold (95% confidence interval, 14.0-17.1) increased ASD risk compared with the lowest score group, which had 0.6% ASD prevalence. In contrast, individuals with a full sibling with ASD had 9.5% ASD prevalence and a 6.1-fold (95% confidence interval, 5.9-6.4) higher risk than individuals without an affected sibling. Family history of multiple mental and nonmental conditions can identify more individuals at highest risk for ASD than only considering the immediate family history of ASD. A comprehensive family history may be critical for a clinically relevant ASD risk prediction framework in the future.
Sections du résumé
Background
UNASSIGNED
A family history of specific disorders (e.g., autism, depression, epilepsy) has been linked to risk for autism spectrum disorder (ASD). This study examines whether family history data could be used for ASD risk prediction.
Methods
UNASSIGNED
We followed all Danish live births, from 1980 to 2012, of Denmark-born parents for an ASD diagnosis through April 10, 2017 (
Results
UNASSIGNED
The best-performing model comprised 41 indicators: eight mental conditions (e.g., ASD, attention-deficit/hyperactivity disorder, neurotic/stress disorders) and nine nonmental conditions (e.g., obesity, hypertension, asthma) across six family member types; model performance was similar in training and test subsamples. The highest risk score group had 17.0% ASD prevalence and a 15.3-fold (95% confidence interval, 14.0-17.1) increased ASD risk compared with the lowest score group, which had 0.6% ASD prevalence. In contrast, individuals with a full sibling with ASD had 9.5% ASD prevalence and a 6.1-fold (95% confidence interval, 5.9-6.4) higher risk than individuals without an affected sibling.
Conclusions
UNASSIGNED
Family history of multiple mental and nonmental conditions can identify more individuals at highest risk for ASD than only considering the immediate family history of ASD. A comprehensive family history may be critical for a clinically relevant ASD risk prediction framework in the future.
Identifiants
pubmed: 36324994
doi: 10.1016/j.bpsgos.2021.04.007
pii: S2667-1743(21)00013-6
pmc: PMC9616292
doi:
Types de publication
Journal Article
Langues
eng
Pagination
156-164Informations de copyright
© 2021 The Authors.
Références
Epilepsia. 2016 Dec;57(12):2011-2018
pubmed: 27861783
JAMA Netw Open. 2019 Mar 1;2(3):e190154
pubmed: 30821823
Arch Pediatr Adolesc Med. 2005 Feb;159(2):151-7
pubmed: 15699309
JAMA Psychiatry. 2019 Apr 1;76(4):391-398
pubmed: 30810722
JAMA Psychiatry. 2014 May;71(5):573-81
pubmed: 24806211
Am J Psychiatry. 2013 Apr;170(4):391-8
pubmed: 23545793
Nat Genet. 2019 Mar;51(3):431-444
pubmed: 30804558
Eur Psychiatry. 2020 Feb 26;63(1):e22
pubmed: 32100657
Neurosci Biobehav Rev. 2015 Aug;55:322-32
pubmed: 25981892
Dev Med Child Neurol. 2009 Oct;51(10):779-86
pubmed: 19416313
Autism. 2020 Jan;24(1):26-40
pubmed: 31070044
Eur J Epidemiol. 2018 Jan;33(1):27-36
pubmed: 29349587
Arch Gen Psychiatry. 2012 Nov;69(11):1099-1103
pubmed: 22752149
JAMA. 2018 Jan 2;319(1):81-82
pubmed: 29297068
Obes Rev. 2018 Apr;19(4):464-484
pubmed: 29164765
J Autism Dev Disord. 2015 Dec;45(12):4135-9
pubmed: 26183723
Pediatrics. 2009 Aug;124(2):687-94
pubmed: 19581261
Scand J Public Health. 2011 Jul;39(7 Suppl):54-7
pubmed: 21775352
J Am Acad Child Adolesc Psychiatry. 2019 Sep;58(9):866-875
pubmed: 30851399
JAMA Pediatr. 2014 Aug;168(8):721-8
pubmed: 24911948
Dev Med Child Neurol. 2014 Jan;56(1):59-65
pubmed: 24117446
JAMA. 2018 Nov 6;320(17):1811-1813
pubmed: 30398592
Scand J Public Health. 2011 Jul;39(7 Suppl):22-5
pubmed: 21775345
Pediatrics. 2018 Sep;142(3):
pubmed: 30093539
Psychiatry Res. 2013 May 30;207(3):203-11
pubmed: 23391634
Autism. 2015 Feb;19(2):158-67
pubmed: 24443331
Scand J Public Health. 2011 Jul;39(7 Suppl):30-3
pubmed: 21775347
Pediatrics. 2008 May;121(5):e1357-62
pubmed: 18450879
JAMA Psychiatry. 2019 Oct 1;76(10):1035-1043
pubmed: 31314057
Pediatrics. 2016 Feb;137(2):e20152206
pubmed: 26826214
JAMA Psychiatry. 2020 May 1;77(5):534-540
pubmed: 31774490
JAMA. 2015 Apr 14;313(14):1425-34
pubmed: 25871668
Annu Rev Public Health. 2017 Mar 20;38:81-102
pubmed: 28068486
Dev Med Child Neurol. 2006 Jun;48(6):500-7
pubmed: 16700944
JAMA. 2014 May 7;311(17):1770-7
pubmed: 24794370