Search

Introduction Early identification and intervention of infants who are at risk for or have developmental disorders is an important global health policy and action. The Global Research on Developmental Disabilities [...], Objective. Preterm infants are at high risk of neuromotor disorders. Recent advances in digital technology and machine learning algorithms have enabled the tracking and recognition of anatomical key points of the human body. It remains unclear whether the proposed pose estimation model and the skeleton-based action recognition model for adult movement classification are applicable and accurate for infant motor assessment. Therefore, this study aimed to develop and validate an artificial intelligence (AI) model framework for movement recognition in full-term and preterm infants. Methods. This observational study prospectively assessed 30 full-term infants and 54 preterm infants using the Alberta Infant Motor Scale (58 movements) from 4 to 18 months of age with their movements recorded by 5 video cameras simultaneously in a standardized clinical setup. The movement videos were annotated for the start/end times and presence of movements by 3 pediatric physical therapists. The annotated videos were used for the development and testing of an AI algorithm that consisted of a 17-point human pose estimation model and a skeleton-based action recognition model. Results. The infants contributed 153 sessions of Alberta Infant Motor Scale assessment that yielded 13,139 videos of movements for data processing. The intra and interrater reliabilities for movement annotation of videos by the therapists showed high agreements (88%-100%). Thirty-one of the 58 movements were selected for machine learning because of sufficient data samples and developmental significance. Using the annotated results as the standards, the AI algorithm showed satisfactory agreement in classifying the 31 movements (accuracy = 0.91, recall = 0.91, precision = 0.91, and F1 score = 0.91). Conclusion. The AI algorithm was accurate in classifying 31 movements in full-term and preterm infants from 4 to 18 months of age in a standardized clinical setup. Impact. The findings provide the basis for future refinement and validation of the algorithm on home videos to be a remote infant movement assessment. Keywords: Artificial Intelligence, Assessment, Machine Learning, Motor Development

The prevalence rate of developmental delays and disabilities has been reported as 5% to 17% in children younger than 17 years. (1,2) One Taiwan study demonstrated that one-third of such [...], Background. Caregiver engagement and collaborative team early childhood intervention (ECI) services are international trends; however, relevant evidence of collaborative home-visiting ECI in rural areas is as yet undetermined. Objective. The study aimed to investigate the effectiveness of a collaborative ECI program in a rural area of Taiwan. Design. The study was a pilot randomized control led trial. Methods. Children aged 6 to 33 months experiencing motor delays and their care-givers were enrolled in Taitung, Taiwan. Using stratified randomization, 24 participants were allocated to either experimental or control groups, and both received 5 home visits within 3 months. The experimental group received ECI services based on the International Classification of Functioning, Disability and Health framework and family-centered approaches. The control group received regular home visits by local social workers. Child outcomes included Pediatric Evaluation of Disability Inventory Chinese Version and Peabody Developmental Motor Scale, 2nd edition. Family outcomes included the Disability-Adapted Infant - Toddler version of Home Observation for Measurement, and Chinese versions of the Knowledge of Infant Development Inventory and Parental Stress Index-Short Form. A tester blinded to the study conducted assessments at baseline, postintervention, and 3-month follow-up. Two-way mixed analysis of variance was used with [alpha] = .05 (2-tailed). Results. The experimental group improved scores on the Disability-Adapted Infant-Toddler version of Home Observation for Measurement significantly more than the control group with an effect size of 0.64 at follow-up. In other outcomes, both groups showed no significant differences. The follow-up rate was 69%, and adherence to the ECI program was acceptable. Limitations. A limitation of the study was the heterogeneity of the sample. Conclusions. This pilot study revealed possible effectiveness in implementing collaborative ECI programs based on family-centered approaches and the International Classification of Functioning, Disability and Health in rural areas. Larger field studies are needed to confirm our findings.

Advancements in perinatal and neonatal care have significantly improved the survival of preterm infants with very low birth weight (VLBW; birth weight of < 1500 g) in the past few [...], Background. Family-centered intervention for preterm infants has shown short- to medium-term developmental benefits; however, the neurological effects of intervention have rarely been explored. Objective. The objectives of this study were to examine the effect of a family-centered intervention program (FCIP) on neurophysiological functions in preterm infants with very low birth weight (VLBW; birth weight of < 1500 g) in Taiwan, to compare the effect of the FCIP with that of a usual-care program (UCP), and to explore the FCIP-induced changes in neurobehavioral and neurophysiological functions. Design. This was a multicenter, single-blind randomized controlled trial. Setting. The study took place in 3 medical centers in northern and southern Taiwan. Participants. Two hundred fifty-one preterm infants with VLBW were included. Intervention. The FCIP group received a family-centered intervention and the UCP group received standard care during hospitalization. Measurements. Infants were assessed in terms of neurobehavioral performance using the Neonatal Neurobehavioral Examination-Chinese version, and their neurophysiological function was assessed using electroencephalography/event-related potentials during sleep and during an auditory oddball task during the neonatal period. Results. The FCIP promoted more mature neurophysiological function than the UCP, including greater negative mean amplitudes of mismatch negativities in the left frontal region in the oddball task in all infants, lower intrahemispheric prefrontal-central coherence during sleep in infants who were small for gestational age, and higher interhemispheric frontal coherence during sleep in those who were appropriate for gestational age. Furthermore, interhemispheric coherence was positively associated with the total neurobehavioral score in preterm infants who were appropriate for gestational age (r = 0.20). Limitations. The fact that more parental adherence strategies were used in the FCIP group than in the UCP group might have favored the intervention effect in this study. Conclusions. Family-centered intervention facilitates short-term neurophysiological maturation in preterm infants with VLBW in Taiwan.

Autism spectrum disorder (ASD) is a lifelong neurodevelopmental disorder that occurs in approximately 1 in 68 children aged 8 years. (1) It is primarily characterized by limited social interaction and [...], Background. Increasing evidence shows common motor deficits associated with autism spectrum disorder (ASD) that can relate to impaired planning and control processes of the sensorimotor system. Catching is a fundamental motor skill that requires coordination between vision, posture, and arm movements. Although postural control and ball catching have been shown to be impaired in children with ASD, previous studies have not investigated how these components are integrated. Objective. The objective of this study was to investigate the sensorimotor control of arm movements and postural adjustments during ball catching in children with and without ASD. Design. This study employed a cross-sectional design. Methods. Fifteen children with ASD (mean [SD] age = 8.8 [1.2] years; 12 boys) and 15 age- and sex-matched typically developing children participated in this study. Children were asked to catch a ball rolling down a ramp in 6 test conditions in which visual inputs and ramp direction were manipulated to provide different sensory conditions and postural demands. Results. Compared with their typically developing peers, children with ASD had increased difficulties catching balls, especially those from lateral directions. They less often used visual information to plan for catching motion, demonstrated fewer and delayed anticipatory postural adjustments, and exhibited increased corrective control. Limitations. The sample excluded children with intellectual disability and attention deficit and hyperactivity disorders that might reduce the generalizability to the whole ASD population. Conclusions. Our results suggest that motor difficulties present in children with ASD can result from compromised sensorimotor integration in planning and control of movements.

Background. Family-centered care for preterm infants in Western societies has yielded short- to medium-term benefits. However, the intervention effects have rarely been validated in Eastern societies. Objective. The aim of [...]

Background. Early identification of motor dysfunction in preterm infants with very low birth weight (VLBW) is important in order to provide early intervention. Objective. This study was to examine the [...]