[Differential diagnosis of autism spectrum disorder and global developmental delay based on machine learning and Children Neuropsychological and Behavioral Scale]. / åŸºäºŽæœºå™¨å­¦ä¹ å’Œå„¿ç«¥ç¥žç»å¿ƒç†è¡Œä¸ºæ£€æŸ¥é‡è¡¨é‰´åˆ«å­¤ç‹¬ç—‡è°±ç³»éšœç¢å’Œå ¨é¢å‘è‚²è¿Ÿç¼“å„¿ç«¥çš„ç ”ç©¶.

OBJECTIVES: To investigate the efficacy and required indicators of Children Neuropsychological and Behavioral Scale-Revision 2016 (CNBS-R2016) in the differential diagnosis of autism spectrum disorder (ASD) and global developmental delay (GDD). METHODS: A total of 277 children with ASD and 415 children with GDD, aged 18-48 months, were enrolled as subjects. CNBS-R2016 was used to assess the developmental levels of six domains, i.e., gross motor, fine motor, adaptive ability, language, social behavior, and warning behavior, and a total of 13 indicators on intelligence age and developmental quotient (DQ) were obtained as the input features. Five commonly used machine learning classifiers were used for training to calculate the classification accuracy, sensitivity, and specificity of each classifier. RESULTS: DQ of warning behavior was selected as the first feature in all five classifiers, and the use of this indicator alone had a classification accuracy of 78.90%. When the DQ of warning behavior was used in combination with the intelligence age of warning behavior, gross motor, and language, it had the highest classification accuracy of 86.71%. CONCLUSIONS: Machine learning combined with CNBS-R2016 can effectively distinguish children with ASD from those with GDD. The DQ of warning behavior plays an important role in machine learning, and its combination with other features can improve classification accuracy, providing a basis for the efficient and accurate differential diagnosis of ASD and GDD in clinical practice.

Assessment of growth pattern of preterm infants up to a corrected age of 24 months. / æ—©äº§å„¿æ ¡æ­£24æœˆé¾„å† ç”Ÿé•¿è½¨è¿¹ç ”ç©¶.

OBJECTIVES: To assess the growth of preterm infants up to a corrected age of 24 months, and to understand the growth trend and pattern of preterm infants. METHODS: A preterm infant follow-up database was established based on the Internet Plus follow-up system. A total of 3 188 preterm infants who were born from April 2018 to April 2021 were enrolled. Their length, weight, and head circumference were recorded at birth and at the corrected ages of 1, 3, 6, 12, 18, and 24 months. The preterm infants were grouped by perinatal factors. The growth curves of these infants were plotted and compared with the International Fetal and Newborn Growth Consortium for the 21st Century (INTERGROWTH-21st) standard and World Health Organization (WHO) standard. RESULTS: The weight, length, and head circumference curves of each group of preterm infants grouped by various perinatal factors all rose rapidly within the corrected age of 6 months, but the growth rate slowed down after the corrected age of 6 months. Based on the actual age for the groups of preterm infants with different gestational ages (<28 weeks, 28-31+6 weeks, 32-33+6 weeks, and 34-36+6 weeks), the length curve gradually coincided with the WHO curve after the actual age of 9 months (P=0.082), while for the preterm infants with a gestational age of <32 weeks, the weight and head circumference curves were significantly lower than the WHO curves (P<0.001). Based on the corrected age, the physical growth curve of preterm infants with different gestational ages (<28 weeks, 28-31+6 weeks, 32-33+6 weeks, and 34-36+6 weeks) basically coincided with each other (P>0.05). For the infants with extremely low birth weight and the small-for-gestational-age infants, the length, weight, and head circumference curves were significantly lower than those of the INTERGROWTH-21st standard and the WHO standard (P<0.05). CONCLUSIONS: The physical growth rate of preterm infants is faster within the corrected age of 6 months, and the growth rate slows down after the corrected age of 6 months. Preterm infants with a smaller gestational age need longer time to catch up in weight and head circumference. More attention should be paid to the physical growth of extremely preterm infants, extremely low birth weight infants, and small-for-gestational-age infants.

[Application of the Children Neuropsychological and Behavioral Scale-Revision 2016 in young children with autism spectrum disorder].

OBJECTIVE: To compare the assessment results of the Children Neuropsychological and Behavioral Scale-Revision 2016 (CNBS-R2016) between young children with autism spectrum disorder (ASD) and global developmental delay (GDD, without ASD) and to explore whether CNBS-R2016 could be helpful to early identification of ASD. METHODS: A total of 260 ASD and 371 GDD children aged 18-30 months were enrolled to finish the assessment of CNBS-R2016. The development quotients (DQs) of the five domains of CNBS-R2016 including gross motor, fine motor, adaptability, language and social behavior were compared between the two groups. The receiver operating characteristic (ROC) curve was used to evaluate the value of the autism-predicted domain in identifying ASD and GDD. RESULTS: The DQs of all the five domains in the ASD group were lower than those in the GDD group (P<0.05). The language DQ and total DQ of the ASD group had a negative correlation with the score of the autism-predicted domain (rs=-0.566, -0.552 respectively, P<0.01). When the cut-off value of the autism-predicted domain was 10.5, the largest area under the ROC curve was 0.835, and the sensitivity and specificity for the diagnosis of ASD were 0.750 and 0.798 respectively. CONCLUSIONS: The development of ASD children aged 18-30 months is worse than that of GDD children. CNBS-R2016 may be helpful to distinguish ASD from children with developmental delay.

Elevated levels of cerebrospinal fluid S100B are associated with brain injury and unfavorable outcomes in children with central nervous system infections.

PURPOSE: This work aimed to assess whether elevated levels of cerebrospinal fluid (CSF) S100B are associated with brain injury and unfavorable outcomes at discharge in children with central nervous system (CNS) infections. METHODS: CSF S100B and associated clinical parameters were retrospectively analyzed in 83 children with CNS infections and 88 children without neurological pathology served as controls. Children with CNS infections were divided into an infectious encephalitis group and an infectious meningitis group based on whether cerebral parenchyma was involved, and CSF S100B levels in different age subgroups between the two groups were compared. The predictive value of CSF S100B in children with infectious encephalitis was evaluated by multivariate logistic regression analysis, and the discriminative power was investigated by receiver operating characteristic (ROC) analysis. RESULTS: CSF S100B levels in the infectious encephalitis group were significantly higher than the infectious meningitis and the control group at each age range. CSF S100B ≥ 0.96 µg/L had 62.9% sensitivity and 76.2% specificity for diagnosing cerebral parenchyma injury in children with CNS infections. Increased CSF S100B levels were proven to be an independent predictor of unfavorable outcomes in children with infectious encephalitis and the optimal cut-off value (1.77 µg/L of CSF S100B) for predicting unfavorable outcomes in children with infectious encephalitis showed 61.1% sensitivity and 96.2% specificity. CONCLUSIONS: This study has demonstrated that elevated levels of CSF S100B are associated with brain injury and could be used as an independent predictor of clinically unfavorable outcomes at discharge in children with CNS infections.