Assessment of supervised longitudinal learning methods: Insights from predicting low birth weight and very low birth weight using prenatal ultrasound measurements

• Published in: Computers in biology and medicine Vol. 182; p. 109084
• Main Authors: Zhang, Cancan, Yu, Xiufan, Zhang, Bo
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.11.2024; Elsevier Limited
• Subjects: Adult; Algorithms; Babies; Birth weight; Classification; Diabetes; Ensemble learning; Feature extraction; Female; Gestational age; Humans; Infant, Low Birth Weight; Infant, Newborn; Infant, Very Low Birth Weight; Internal Medicine; Learning algorithms; Longitudinal data; Longitudinal Studies; Low birth weight; Machine Learning; Male; Observational learning; Other; Performance evaluation; Predictions; Pregnancy; Public health; Random effects; Risk; Sonographic ultrasound measurements; Statistical methods; Statistical models; Supervised longitudinal learning; Supervised Machine Learning; Ultrasonic imaging; Ultrasonography, Prenatal - methods; Ultrasound; Within-subject dependence; United States > US; Random effects; Sonographic ultrasound measurements; Longitudinal data; Supervised longitudinal learning; Ensemble learning; Within-subject dependence
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.109084

This study aimed to assess the efficacy of various supervised longitudinal learning approaches, comparing traditional statistical models and machine learning algorithms for prediction with longitudinal data. The primary objectives were to evaluate the predictive performance of different supervised longitudinal learning methods for low birth weight (LBW) and very low birth weight (VLBW) based on prenatal ultrasound measurements. Additionally, the study sought to extract interpretable risk features for disease prediction. The evaluation involved benchmarking the performance of longitudinal models against conventional machine learning methods. Classification accuracy for LBW and VLBW at birth, as well as prediction accuracy for birth weight using prenatal sonographic ultrasound measurements, were assessed. Among the learning approaches we investigated in this study, the longitudinal machine learning approach, specifically, the mixed effect random forest (MERF), delivered the overall best performance in predicting birthweights and classifying LBW/VLBW disease status. The MERF combined the power of advanced machine learning algorithms to accommodate the inherent within-individual dependence in the observed data, delivering satisfactory performance in predicting the birthweight and classifying LBW/VLBW disease status. The study emphasized the importance of incorporating previous ultrasound measurements and considering correlations between repeated measurements for accurate prediction. The interpretable trees algorithm used for risk feature extraction proved reliable and applicable to other learning algorithms. These findings underscored the potential of longitudinal learning methods in improving birth weight prediction and highlighted the relevance of consistent risk features in line with established literature. •This study aimed to assess the efficacy of various longitudinal learning approaches, comparing traditional statistical models, longitudinal machine learning algorithms, and conventional machine learning methods.•The evaluation involved benchmarking the performance of longitudinal models against conventional machine learning methods. Classification accuracy for LBW and VLBW at birth, as well as prediction accuracy for birth weight using prenatal sonographic ultrasound measurements, were assessed.•The mixed effect random forest (MERF) delivered the overall best performance in predicting birthweights and classifying LBW/VLBW disease status.•The MERF combined the power of advance machine learning algorithms for longitudinal data to accommodate the inherent within-individual dependence in the observed data, delivering satisfactory performance in predicting the birthweight and classifying LBW/VLBW disease status.