Alterations in the gut microbiota of toddlers with cow milk protein allergy treated with a partially hydrolyzed formula containing synbiotics: A nonrandomized controlled interventional study.

Formulas containing intact cow milk protein are appropriate alternatives when human milk (HM) is not feasible. However, for babies with a physician-diagnosed cow milk protein allergy (CMPA), hydrolyzed formulas are needed. We conducted a 3-month, open-label, nonrandomized concurrent controlled trial (ChiCTR2100046909) between June 2021 and October 2022 in Qingdao City, China. In this study, CMPA toddlers were fed with a partially hydrolyzed formula containing synbiotics (pHF, n = 43) and compared with healthy toddlers fed a regular intact protein formula (IF, n = 45) or HM (n = 21). The primary endpoint was weight gain; the secondary endpoints were changes in body length and head circumference of both CMPA and healthy toddlers after 3-month feeding; and the exploratory outcomes were changes in gut microbiota composition. After 3 months, there were no significant group differences for length-for-age, weight-for-age, or head circumference-for-age Z scores. In the gut microbiota, pHF feeding increased its richness and diversity, similar to those of IF-fed and HM-fed healthy toddlers. Compared with healthy toddlers, the toddlers with CMPA showed an increased abundance of phylum Bacteroidota, Firmicutes, class Clostridia, and Bacteroidia, and a decreased abundance of class Negativicutes, while pHF feeding partly eliminated these original differences. Moreover, pHF feeding increased the abundance of short-chain fatty acid producers. Our data suggested that this pHF partly simulated the beneficial effects of HM and shifted the gut microbiota of toddlers with CMPA toward that of healthy individuals. In conclusion, this synbiotic-containing pHF might be an appropriate alternative for toddlers with CMPA.

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.