Exploring predictors of interaction among low-birth-weight infants and their caregivers: a machine learning-based random forest approach.

BACKGROUND: Quality caregiver-infant interaction is crucial for infant growth, health, and development. Traditional methods for evaluating the quality of caregiver-infant interaction have predominantly relied on rating scales or observational techniques. However, rating scales are prone to inaccuracies, while observational techniques are resource-intensive. The utilization of easily collected medical records in conjunction with machine learning techniques offers a promising and viable strategy for accurate and efficient assessment of caregiver-infant interaction quality. METHODS: This study was conducted at a follow-up outpatient clinic at two tertiary maternal and infant health centers located in Shanghai, China. 68 caregivers and their 3-15-month-old infants were videotaped for 3-5 min during playing interactions in non-threatening environment. Two trained experts utilized the Infant CARE-Index (ICI) procedure to assess whether the caregivers were sensitive or not in a dyadic context. This served as the gold standard. Predictors were collected through Health Information Systems (HIS) and questionnaires, which included accessible features such as demographic information, parental coping ability, infant neuropsychological development, maternal depression, parent-infant interaction, and infant temperament. Four classification models with fivefold cross-validation and grid search hyperparameter tuning techniques were employed to yield prediction metrics. Interpretable analyses were conducted to explain the results. RESULTS: The score of sensitive caregiver-infant interaction was 6.34 ± 2.62. The Random Forest model gave the best accuracy (83.85%±6.93%). Convergent findings identified infant age, care skills of infants, mother age, infant temperament-regulatory capacity, birth weight, positive coping, health-care-knowledge-of-infants, type of caregiver, MABIS-bonding issues, ASQ-Fine Motor as the strongest predictors of interaction sensitivity between infants and their caregiver. CONCLUSIONS: The proposed method presents a promising and efficient approach that synergistically combines rating scales and artificial technology to detect important features of caregiver-infant interactions. This novel approach holds several implications for the development of automatic computational assessment tools in the field of nursing studies.

Predictive role of NICU-related stress, postpartum depression trajectory and family coping on growth trajectory of moderate-to-late preterm infants: A longitudinal study.

AIMS: To describe the changes in moderate-to-late preterm infants' (MLPIs) growth during 12 months of corrected age (CA) and to examine the predictive role of NICU-related stress, postpartum depression trajectory and family coping ability on the physical developmental trajectory of MLPIs. DESIGN: A prospective longitudinal study. METHODS: There were 237 mother-infant dyads with at least two follow-up data records included. General characteristics and NICU-related stress were recorded from medical records at baseline. Infants' physical growth was measured at 40 weeks, 1, 3, 6, 9 and 12 months CA during outpatient follow-up. Maternal postpartum depressive symptoms and family coping ability were assessed by questionnaires at 1, 3, 6, 9 and 12 months CA and 1 month CA respectively. We investigated the modifiable factors inside and outside of NICU on the trajectories of physical growth in the first year in MLPIs, mainly by using latent growth curve models with time-varying covariates. RESULTS: The curved trajectories of weight, length and head circumference in the first year in MLPIs demonstrated gradually slowed growth rates and these infants were above the WHO growth standards for the same age and sex. The latent growth curve models indicated that more NICU-related stress was negatively associated with the weight and length at 40 weeks CA, and family coping ability (parent-child relationship) at 1 month CA was associated with the growth rate of weight. Besides, more NICU-related stress predicted faster length growth rate. The infants of mothers who were in the group of high-level postpartum depression trajectory had a slower growth rate of head circumference. CONCLUSIONS: Our study identified the modifiable factors along the care continuum influencing the trajectory of MLPIs' physical growth. Nurses should receive more training about infant stress measurement and family-centred care to work in partnership with parents so that MLPIs can reach their full developmental potential. Also, multidisciplinary interventions including stress reduction strategies, close psychological monitoring and education improving parent-infant relationships should be further developed to achieve optimizing growth in the first year of MLPIs. IMPLICATIONS FOR THE PROFESSION AND/OR PATIENT CARE: It is recommended that nurses pay attention to the long-term physical growth status of MLPIs, and closely support their families. Quantifying NICU-related stress and developing reduction strategies should be the priority for clinical staff during hospitalization. After discharge, persistent screening of depressive symptoms, psychological intervention and education about the parent-child relationship need to be included in the follow-up visits. PATIENT OR PUBLIC CONTRIBUTION: No patient or public contribution. The study only included patients who were research participants.

Uni- and multimodal sensory-supported interventions for very preterm and extremely preterm infants in the neonatal intensive care unit: An overview of systematic reviews and interventional studies.

BACKGROUND: Very and extremely preterm infants (VEPIs) experience sensory deprivation in the neonatal intensive care unit (NICU). While various sensory-supported interventions might improve immediate physiological response, their impact on long-term development remains unclear. Additionally, these interventions may pose challenges in the NICU environment due to complex treatments and monitoring requirements. AIMS: This review aimed to understand the current evidence on sensory-supported interventions in the NICU, identify the components of these interventions and determine their effects on the VEPIs. STUDY DESIGN: A systematic search across nine electronic databases (PubMed, EBSCO, EMBASE, Web of Science, Scopus, Cochrane, Cochrane trial, IEEE Xplore DL and ACM DL) was conducted in December 2020 and updated in September 2022. The search gathers information on sensory-supported interventions for VEPIs in the NICU. RESULTS: The search yielded 23 systematic reviews and 22 interventional studies, categorized into auditory (19), tactile/kinesthetic (5), positional/movement support (7), visual (1) and multisensory (13) interventions. While unimodal and multimodal interventions showed short-term benefits, their long-term effects on VEPIs are indeterminate. Translating these findings into clinical practice remains a challenge due to identified gaps. CONCLUSION: Our reviews indicate that sensory-supported interventions have a transient impact, with intervention studies reporting positive effects. Future research should develop and test comprehensive, continuous multisensory interventions tailored for the early NICU stage. RELEVANCE TO CLINICAL PRACTICE: Multimodal sensory interventions show promise for VEPIs, but long-term effects need further study. Standardizing protocols for NICU integration and parental involvement is crucial. Ongoing research and collaboration are essential for optimizing interventions and personalized care.