TY - JOUR
T1 - The Link Between Autism and Sex-Related Neuroanatomy, and Associated Cognition and Gene Expression
AU - APEX Group
AU - EU-AIMS LEAP group
AU - Floris, Dorothea L.
AU - Peng, Han
AU - Warrier, Varun
AU - Lombardo, Michael V.
AU - Pretzsch, Charlotte M.
AU - Moreau, Clara
AU - Tsompanidis, Alex
AU - Gong, Weikang
AU - Mennes, Maarten
AU - Llera, Alberto
AU - van Rooij, Daan
AU - Oldehinkel, Marianne
AU - Forde, Natalie J.
AU - Charman, Tony
AU - Tillmann, Julian
AU - Banaschewski, Tobias
AU - Moessnang, Carolin
AU - Durston, Sarah
AU - Holt, Rosemary J.
AU - Ecker, Christine
AU - Dell'Acqua, Flavio
AU - Loth, Eva
AU - Bourgeron, Thomas
AU - Murphy, Declan G.M.
AU - Marquand, Andre F.
AU - Lai, Meng Chuan
AU - Buitelaar, Jan K.
AU - Baron-Cohen, Simon
AU - Beckmann, Christian F.
PY - 2023/1/1
Y1 - 2023/1/1
N2 - OBJECTIVE: The male preponderance in prevalence of autism is among the most pronounced sex ratios across neurodevelopmental conditions. The authors sought to elucidate the relationship between autism and typical sex-differential neuroanatomy, cognition, and related gene expression. METHODS: Using a novel deep learning framework trained to predict biological sex based on T1-weighted structural brain images, the authors compared sex prediction model performance across neurotypical and autistic males and females. Multiple large-scale data sets comprising T1-weighted MRI data were employed at four stages of the analysis pipeline: 1) pretraining, with the UK Biobank sample (>10,000 individuals); 2) transfer learning and validation, with the ABIDE data sets (1,412 individuals, 5-56 years of age); 3) test and discovery, with the EU-AIMS/AIMS-2-TRIALS LEAP data set (681 individuals, 6-30 years of age); and 4) specificity, with the NeuroIMAGE and ADHD200 data sets (887 individuals, 7-26 years of age). RESULTS: Across both ABIDE and LEAP, features positively predictive of neurotypical males were on average significantly more predictive of autistic males (ABIDE: Cohen's d=0.48; LEAP: Cohen's d=1.34). Features positively predictive of neurotypical females were on average significantly less predictive of autistic females (ABIDE: Cohen's d=1.25; LEAP: Cohen's d=1.29). These differences in sex prediction accuracy in autism were not observed in individuals with ADHD. In autistic females, the male-shifted neurophenotype was further associated with poorer social sensitivity and emotional face processing while also associated with gene expression patterns of midgestational cell types. CONCLUSIONS: The results demonstrate an increased resemblance in both autistic male and female individuals' neuroanatomy with male-characteristic patterns associated with typically sex-differential social cognitive features and related gene expression patterns. The findings hold promise for future research aimed at refining the quest for biological mechanisms underpinning the etiology of autism.
AB - OBJECTIVE: The male preponderance in prevalence of autism is among the most pronounced sex ratios across neurodevelopmental conditions. The authors sought to elucidate the relationship between autism and typical sex-differential neuroanatomy, cognition, and related gene expression. METHODS: Using a novel deep learning framework trained to predict biological sex based on T1-weighted structural brain images, the authors compared sex prediction model performance across neurotypical and autistic males and females. Multiple large-scale data sets comprising T1-weighted MRI data were employed at four stages of the analysis pipeline: 1) pretraining, with the UK Biobank sample (>10,000 individuals); 2) transfer learning and validation, with the ABIDE data sets (1,412 individuals, 5-56 years of age); 3) test and discovery, with the EU-AIMS/AIMS-2-TRIALS LEAP data set (681 individuals, 6-30 years of age); and 4) specificity, with the NeuroIMAGE and ADHD200 data sets (887 individuals, 7-26 years of age). RESULTS: Across both ABIDE and LEAP, features positively predictive of neurotypical males were on average significantly more predictive of autistic males (ABIDE: Cohen's d=0.48; LEAP: Cohen's d=1.34). Features positively predictive of neurotypical females were on average significantly less predictive of autistic females (ABIDE: Cohen's d=1.25; LEAP: Cohen's d=1.29). These differences in sex prediction accuracy in autism were not observed in individuals with ADHD. In autistic females, the male-shifted neurophenotype was further associated with poorer social sensitivity and emotional face processing while also associated with gene expression patterns of midgestational cell types. CONCLUSIONS: The results demonstrate an increased resemblance in both autistic male and female individuals' neuroanatomy with male-characteristic patterns associated with typically sex-differential social cognitive features and related gene expression patterns. The findings hold promise for future research aimed at refining the quest for biological mechanisms underpinning the etiology of autism.
KW - Autism Spectrum Disorder
KW - Brain Imaging Techniques
KW - Gender Differences
KW - Machine Learning
KW - Neuroanatomy
KW - Neurodevelopmental Disorders
UR - http://www.scopus.com/inward/record.url?scp=85145344406&partnerID=8YFLogxK
U2 - 10.1176/appi.ajp.20220194
DO - 10.1176/appi.ajp.20220194
M3 - Article
C2 - 36415971
AN - SCOPUS:85145344406
SN - 0002-953X
VL - 180
SP - 50
EP - 64
JO - The American Journal of Psychiatry
JF - The American Journal of Psychiatry
IS - 1
ER -