1. Development of a Prediction Model to Identify Children at Risk of Future Developmental Delay at Age 4 in a Population-Based Setting
- Author
-
Marlou L. A. de Kroon, Martijn W. Heymans, Sijmen A. Reijneveld, Arend F. Bos, Nienke H van Dokkum, Department of Health and Life Sciences, Public Health Research (PHR), Epidemiology and Data Science, APH - Methodology, and APH - Personalized Medicine
- Subjects
Male ,Developmental Disabilities ,Health, Toxicology and Mutagenesis ,Population ,Psychological intervention ,lcsh:Medicine ,Standard score ,Logistic regression ,developmental surveillance ,Article ,Cohort Studies ,03 medical and health sciences ,0302 clinical medicine ,Discriminative model ,Pregnancy ,Risk Factors ,Surveys and Questionnaires ,030225 pediatrics ,Humans ,Medicine ,Longitudinal Studies ,030212 general & internal medicine ,education ,Selection (genetic algorithm) ,education.field_of_study ,Keywords: prediction model ,business.industry ,lcsh:R ,Public Health, Environmental and Occupational Health ,Area under the curve ,Infant ,Models, Theoretical ,prediction model ,developmental delay ,Logistic Models ,Area Under Curve ,Child, Preschool ,Multivariate Analysis ,Developmental Milestone ,Female ,business ,Demography - Abstract
Our aim was to develop a prediction model for infants from the general population, with easily obtainable predictors, that accurately predicts risk of future developmental delay at age 4 and then assess its performance. Longitudinal cohort data were used (N = 1983), including full-term and preterm children. Development at age 4 was assessed using the Ages and Stages Questionnaire. Candidate predictors included perinatal and parental factors as well as growth and developmental milestones during the first two years. We applied multiple logistic regression with backwards selection and internal validation, and we assessed calibration and discriminative performance (i.e., area under the curve (AUC)). The model was evaluated in terms of sensitivity and specificity at several cut-off values. The final model included sex, maternal educational level, pre-existing maternal obesity, several milestones (smiling, speaking 2&ndash, 3 word sentences, standing) and weight for height z score at age 1. The fit was good, and the discriminative performance was high (AUC: 0.837). Sensitivity and specificity were 73% and 80% at a cut-off probability of 10%. Our model is promising for use as a prediction tool in community-based settings. It could aid to identify infants in early life (age 2) with increased risk of future developmental problems at age 4 that may benefit from early interventions.
- Published
- 2020
- Full Text
- View/download PDF