Predicting mental and psychomotor delay in very pre-term infants using machine learning.

BACKGROUND: Very preterm infants are at elevated risk for neurodevelopmental delays. Earlier prediction of delays allows timelier intervention and improved outcomes. Machine learning (ML) was used to predict mental and psychomotor delay at 25 months. METHODS: We applied RandomForest classifier to data from 1109 very preterm infants recruited over 20 years. ML selected key predictors from 52 perinatal and 16 longitudinal variables (1-22 mo assessments). SHapley Additive exPlanations provided model interpretability. RESULTS: Balanced accuracy with perinatal variables was 62%/61% (mental/psychomotor). Top predictors of mental and psychomotor delay overlapped and included: birth year, days in hospital, antenatal MgSO4, days intubated, birth weight, abnormal cranial ultrasound, gestational age, mom's age and education, and intrauterine growth restriction. Highest balanced accuracy was achieved with 19-month follow-up scores and perinatal variables (72%/73%). CONCLUSIONS: Combining perinatal and longitudinal data, ML modeling predicted 24 month mental/psychomotor delay in very preterm infants ½ year early, allowing intervention to start that much sooner. Modeling using only perinatal features fell short of clinical application. Birth year's importance reflected a linear decline in predicting delay as birth year became more recent. IMPACT: Combining perinatal and longitudinal data, ML modeling was able to predict 24 month mental/psychomotor delay in very preterm infants ½ year early (25% of their lives) potentially advancing implementation of intervention services. Although cognitive/verbal and fine/gross motor delays require separate interventions, in very preterm infants there is substantial overlap in the risk factors that can be used to predict these delays. Birth year has an important effect on ML prediction of delay in very preterm infants, with those born more recently (1989-2009) being increasing less likely to be delayed, perhaps reflecting advances in medical practice.

Superstorm Sandy exposure in utero is associated with neurobehavioral phenotypes and brain structure alterations in childhood: A machine learning approach.

Introduction: Prenatal maternal stress (PNMS), including exposure to natural disasters, has been shown to serve as a risk factor for future child psychopathology and suboptimal brain development, particularly among brain regions shown to be sensitive to stress and trauma exposure. However, statistical approaches deployed in most studies are usually constrained by a limited number of variables for the sake of statistical power. Explainable machine learning, on the other hand, enables the study of high data dimension and offers novel insights into the prominent subset of behavioral phenotypes and brain regions most susceptible to PNMS. In the present study, we aimed to identify the most important child neurobehavioral and brain features associated with in utero exposure to Superstorm Sandy (SS). Methods: By leveraging an explainable machine learning technique, the Shapley additive explanations method, we tested the marginal feature effect on SS exposures and examined the individual variable effects on disaster exposure. Results: Results show that certain brain regions are especially sensitive to in utero exposure to SS. Specifically, in utero SS exposure was associated with larger gray matter volume (GMV) in the right caudate, right hippocampus, and left amygdala and smaller GMV in the right parahippocampal gyrus. Additionally, higher aggression scores at age 5 distinctly correlated with SS exposure. Discussion: These findings suggest in utero SS exposure may be associated with greater aggression and suboptimal developmental alterations among various limbic and basal ganglia brain regions.