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

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.

Association of feeding patterns in infancy with later autism symptoms and neurodevelopment: a national multicentre survey.

BACKGROUND: We aimed to compare differences in infant feeding patterns (breastfeeding and complementary food supplementation) between children with the autism spectrum disorder (ASD) and typically developing (TD) children through a multicentre study. The relationship between these patterns and later core symptoms and neurodevelopment in children with ASD was also investigated. METHODS: We analysed breastfeeding and complementary feeding patterns in 1389 children with ASD and 1190 TD children. The Children Neuropsychological and Behavior Scale-Revision 2016 (CNBS-R2016) was used to assess neurodevelopmental levels. The Autism Behavior Checklist (ABC), Social Responsiveness Scale (SRS), Childhood Autism Rating Scale (CARS), and ASD Warning Behavior Subscale of the CNBS-R2016 were used to assess ASD symptoms. RESULTS: Children with ASD had a shorter breastfeeding duration in infancy (8 (3-12) months vs. 10 (6-14) months, P < 0.001), later introduction of complementary foods (P < 0.001), and poorer acceptance of complementary foods (P < 0.001) than TD children. Total ABC and CARS scores were lower in the group of children with ASD who had been breastfed for 12 months or more than in the group who had been breastfed for less than 6 months. Children with ASD who were given complementary food after 6 months had lower general quotient (GQ), adaptive ability, fine motor and language scores than those who were given complementary food within 4-6 months. Children with ASD with poor acceptance of complementary foods had higher ABC and SRS scores and lower gross motor scores than those who had good acceptance. CONCLUSIONS: Children with ASD have a shorter duration of breastfeeding, a later introduction of complementary foods, and poorer acceptance of complementary foods than TD children. These feeding patterns may be related to the symptoms and growth of children with ASD. The research suggests that continued breastfeeding for longer than 12 months may be beneficial in reducing ASD symptoms and that infants who have difficulty introducing complementary foods should be followed up for neurodevelopment. TRIAL REGISTRATION: The ethics committee of the Children's Hospital of Chongqing Medical University approved the study. Approval Number: (2018) IRB (STUDY) NO. 121, and registered in the Chinese Clinical Trial Registry (Registration number: ChiCTR2000031194, registered on 23/03/2020).

Vitamin D status is primarily associated with core symptoms in children with autism spectrum disorder: A multicenter study in China.

OBJECTIVE: We aimed to investigate the relationship between vitamin D status and core symptoms and neurodevelopmental levels in children with ASD with a multicenter survey. METHODS: We enrolled 1321 ASD children and 1279 typically developing (TD) children aged 2-7 years from 13 cities in China. ASD symptoms were assessed with the Autism Behavior Checklist (ABC), Social Responsiveness Scale (SRS) and Childhood Autism Rating Scale (CARS), and neurodevelopmental levels were evaluated with the Children Neuropsychological and Behavior Scale-Revision 2016 (CNBS-R2016). RESULTS: Children with ASD had lower serum 25(OH)D levels than TD children. Serum 25(OH)D levels were negatively associated with CARS and communication warning behavior of CNBS-R2016 scores, and were not associated with the development quotients of ASD children. ASD Children were grouped based on the quartiles for 25(OH)D levels in the controls, and children in the first to third quartiles had higher SRS social communication and/or CARS and communication warning behavior of CNBS-R2016 scores than those in the fourth quartile. CONCLUSIONS: Serum 25(OH)D levels were primarily associated with core symptoms in children with ASD, and individuals with relatively lower 25(OH)D levels displayed worse autistic symptomatology. More research is needed to determine whether vitamin D supplements would be a useful treatment for ASD.

Structural networks in children with autism spectrum disorder with regression: A graph theory study.

BACKGROUND: Regression is frequently described in Autism spectrum disorder (ASD). Limited comprehensive studies have been conducted in patients with ASD with regression. PURPOSE: To explore the network topological properties in ASD children with (ASD-R) and without (ASD-NR) regression. METHODS: In this study, 29 ASD-R, 68 ASD-NR, and 40 children with developmental delay (DD) were recruited. We utilized graph theory to characterize the white matter structure networks by using diffusion tensor imaging and T1-weighted imaging on a 3-T magnetic resonance system. Statistical analyses were performed using IBM SPSS (version 23). RESULTS: ANCOVA showed significant differences in global efficiency, characteristic path length and sigma among the ASD-R, ASD-NR and DD groups, but the difference was not significant between the ASD-R and ASD-NR groups. There were 10 common hubs based on regional degree and regional efficiency in all groups. The hubness of the left superior frontal gyrus-dorsolateral, left middle occipital gyrus and right precuneus were enhanced (by regional degree) and that of the right thalamus was reduced (by regional efficiency) in the ASD-R relative to the ASD-NR group. After controlling for the course of regression, the CARS scores were significantly correlated with the regional efficiency of the right precuneus in the ASD-R group. CONCLUSIONS: The ASD-R children were different from the ASD-NR children in the distribution of hub regions, although there were no global network property differences between them. In ASD-R children, the right precuneus (PCUN.R) might play an important role and relate to autism symptom severity.

WDL-RF: predicting bioactivities of ligand molecules acting with G protein-coupled receptors by combining weighted deep learning and random forest.

Motivation: Precise assessment of ligand bioactivities (including IC50, EC50, Ki, Kd, etc.) is essential for virtual screening and lead compound identification. However, not all ligands have experimentally determined activities. In particular, many G protein-coupled receptors (GPCRs), which are the largest integral membrane protein family and represent targets of nearly 40% drugs on the market, lack published experimental data about ligand interactions. Computational methods with the ability to accurately predict the bioactivity of ligands can help efficiently address this problem. Results: We proposed a new method, WDL-RF, using weighted deep learning and random forest, to model the bioactivity of GPCR-associated ligand molecules. The pipeline of our algorithm consists of two consecutive stages: (i) molecular fingerprint generation through a new weighted deep learning method, and (ii) bioactivity calculations with a random forest model; where one uniqueness of the approach is that the model allows end-to-end learning of prediction pipelines with input ligands being of arbitrary size. The method was tested on a set of twenty-six non-redundant GPCRs that have a high number of active ligands, each with 200-4000 ligand associations. The results from our benchmark show that WDL-RF can generate bioactivity predictions with an average root-mean square error 1.33 and correlation coefficient (r2) 0.80 compared to the experimental measurements, which are significantly more accurate than the control predictors with different molecular fingerprints and descriptors. In particular, data-driven molecular fingerprint features, as extracted from the weighted deep learning models, can help solve deficiencies stemming from the use of traditional hand-crafted features and significantly increase the efficiency of short molecular fingerprints in virtual screening. Availability and implementation: The WDL-RF web server, as well as source codes and datasets of WDL-RF, is freely available at https://zhanglab.ccmb.med.umich.edu/WDL-RF/ for academic purposes. Supplementary information: Supplementary data are available at Bioinformatics online.

[Clinical study of Jiawei Bazhen decoction combined with oxytocin for cervical ripening of qi and blood deficiency type of pregnant women].

To study preliminarily the effect of Jiawei Bazhen decoction combined with oxytocin in promoting cervical ripening of full-term pregnancy women who were in the deficiency of qi and blood type through the syndrome differentiation of traditional Chinese medicine (TCM). 180 patients that met the inclusion criteria of the study were randomly divided into three groups: the control group(oxytocin group), the treatment group (Jiawei Bazhen decoction combined with oxytocin group), the blank control group (expected and observation group). Cervical maturity score (Bishop score), vaginal and cervical secretions fetal fibronectin (FFN), the result of induced labor, the result of mother and baby were observed in each group before and after treatment. The result comes out that the cervical Bishop score of pregnant women for treatment group were significantly higher than the control group and blank control group after treatment (P < 0.05). The FFN of pregnant women for the treatment group were significantly different from the control group and blank control group after treatment (P < 0.05). The pregnancy outcome of the three groups: the labor rate and rate of vaginal delivery of the treatment group were higher than the other two groups, and the difference was statistically significant (P < 0.05). The cesarean section rate of the treatment group was significantly lower than the other two groups, the difference was also statistically significant (P < 0.05). The three groups did not appear the phenomenon of neonatal asphyxia. Jiawei Bazhen decoction combined with oxytocin is effective in producing cervical ripening and induce labor. It is convenient, safe and reliable, for it is no obvious adverse effects on mother and fetus, but effective in reducing the rate of cesarean section, and playing a positive role in promoting natural delivery.