Meeting Banner
Abstract #4628

A deep transfer learning model for early prediction of cognitive deficits using brain structural connectome data in very preterm infants

Ming Chen1,2, Hailong Li1, Jinghua Wang3, Weihong Yuan3,4, Adebayo Brainmah4, Mekibib Altaye5, Nehal Parikh1,6, and Lili He1,4,6
1The Perinatal Institute and Section of Neonatology, Perinatal and Pulmonary Biology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States, 2Department of Electronic Engineering and Computing Science, University of Cincinnati, Cincinnati, OH, United States, 3Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, OH, United States, 4Imaging Research Center, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States, 5Department of Biostatistics, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, United States, 6Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, OH, United States

The high risk of cognitive deficits is a major concern for parents and clinicians caring for premature babies. Early and accurate identification of children at risk is urgently needed for early treatment decision. We propose a deep transfer learning model to predict cognitive deficits at 2 years corrected age using brain structural connectome data obtained at term. The proposed model was able to identify infants at high-risk of later cognitive deficit with an accuracy of 78.5% and an AUC of 0.75. The predicted cognitive scores were significantly correlated with corresponding Bayley-III cognitive scores, with a Pearson’s correlation coefficient of 0.48.

This abstract and the presentation materials are available to 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here