Predicting autism spectrum disorder using maternal risk factors: A multi-center machine learning study

作者全名："Wei, Qiuhong; Xiao, Yuanjie; Yang, Ting; Chen, Jie; Chen, Li; Wang, Ke; Zhang, Jie; Li, Ling; Jia, Feiyong; Wu, Lijie; Hao, Yan; Ke, Xiaoyan; Yi, Mingji; Hong, Qi; Chen, Jinjin; Fang, Shuanfeng; Wang, Yichao; Wang, Qi; Jin, Chunhua; Xu, Ximing; Li, Tingyu"

作者地址："[Wei, Qiuhong; Xiao, Yuanjie; Yang, Ting; Chen, Jie; Wang, Ke; Li, Tingyu] Chongqing Med Univ, Children Nutr Res Ctr,Chongqing Key Lab Child Neur, Natl Clin Res Ctr Child Hlth & Disorders,Minist Ed, Key Lab Child Dev & Disorders,Childrens Hosp, Chongqing, Peoples R China; [Chen, Li] Chongqing Med Univ, Dept Childrens Healthcare, Childrens Hosp, Chongqing, Peoples R China; [Wang, Ke; Xu, Ximing] Chongqing Med Univ, Big Data Ctr Childrens Med Care, Childrens Hosp, 136 Zhongshan Er Rd, Chongqing 400014, Peoples R China; [Zhang, Jie] Xian Childrens Hosp, Xian, Peoples R China; [Li, Ling] Hainan Women & Childrens Med Ctr, Dept Children Rehabil, Haikou, Peoples R China; [Jia, Feiyong] Jilin Univ, Dept Dev & Behav Pediat, Hosp 1, Changchun, Peoples R China; [Wu, Lijie] Harbin Med Univ, Dept Childrens & Adolescent Hlth, Publ Hlth Coll, Harbin, Peoples R China; [Hao, Yan] Huazhong Univ Sci & Technol, Tongji Hosp, Tongji Med Coll, Dept Pediat, Wuhan, Peoples R China; [Ke, Xiaoyan] Nanjing Brain Hosp, Child Mental Hlth Res Ctr, Nanjing, Peoples R China; [Yi, Mingji] Qingdao Univ, Dept Child Hlth Care, Affiliated Hosp, Qingdao, Peoples R China; [Hong, Qi] Maternal & Child Hlth Hosp Baoan, Shenzhen, Peoples R China; [Chen, Jinjin] Shanghai Jiao Tong Univ, Shanghai Childrens Hosp, Dept Child Healthcare, Shanghai, Peoples R China; [Fang, Shuanfeng] Zhengzhou Univ, Childrens Hosp, Zhengzhou, Peoples R China; [Wang, Yichao] Hunan Prov Maternal & Child Hlth Care Hosp, NHC Key Lab Birth Defect Res & Prevent, Changsha, Peoples R China; [Wang, Qi] Deyang Matern & Child Healthcare Hosp, Deyang, Peoples R China; [Jin, Chunhua] Capital Inst Pediat, Dept Children Hlth Care, Beijing, Peoples R China; [Li, Tingyu] Chongqing Med Univ, Children Nutr Res Ctr, Childrens Hosp, 136 Zhongshan Er Rd, Chongqing 400014, Peoples R China"

通信作者："Xu, XM (通讯作者)，Chongqing Med Univ, Big Data Ctr Childrens Med Care, Childrens Hosp, 136 Zhongshan Er Rd, Chongqing 400014, Peoples R China.; Li, TY (通讯作者)，Chongqing Med Univ, Children Nutr Res Ctr, Childrens Hosp, 136 Zhongshan Er Rd, Chongqing 400014, Peoples R China."

来源：PSYCHIATRY RESEARCH

ESI学科分类：PSYCHIATRY/PSYCHOLOGY

WOS号：WOS:001202814100001

JCR分区：Q1

影响因子：4.2

年份：2024

卷号：334

期号：　

开始页：　

结束页：　

文献类型：Article

关键词：Machine learning; Autism spectrum disorder; Maternal risk factor

摘要："Autism spectrum disorder (ASD) is a neurodevelopmental disorder with a complex environmental etiology involving maternal risk factors, which have been combined with machine learning to predict ASD. However, limited studies have considered the factors throughout preconception, perinatal, and postnatal periods, and even fewer have been conducted in multi-center. In this study, five predictive models were developed using 57 maternal risk factors from a cohort across ten cities (ASD:1232, typically developing[TD]: 1090). The extreme gradient boosting model performed best, achieving an accuracy of 66.2 % on the external cohort from three cities (ASD:266, TD:353). The most important risk factors were identified as unstable emotions and lack of multivitamin supplementation using Shapley values. ASD risk scores were calculated based on predicted probabilities from the optimal model and divided into low, medium, and high-risk groups. The logistic analysis indicated that the high-risk group had a significantly increased risk of ASD compared to the low-risk group. Our study demonstrated the potential of machine learning models in predicting the risk for ASD based on maternal factors. The developed model provided insights into the maternal emotion and nutrition factors associated with ASD and highlighted the potential clinical applicability of the developed model in identifying high-risk populations."

基金机构：National Natural Science Foundation of China [81771223]; Chief Medical Expert Studio of Chongqing [YWBF [2018] 263]

基金资助正文：We would like to thank the National Natural Science Foundation of China (No. 81771223) and the Chief Medical Expert Studio of Chongqing (No. YWBF [2018] 263) for providing financial support for this research. We are also grateful to the leaders of the participating centers for their invaluable contribution to this multi -center study. We would also like to extend our thanks to all the staff and participants and their caregivers who gave their time and efforts to participate in this research.