Dataset Information

A multi-task, multi-stage deep transfer learning model for early prediction of neurodevelopment in very preterm infants.

ABSTRACT: Survivors following very premature birth (i.e., ??32 weeks gestational age) remain at high risk for neurodevelopmental impairments. Recent advances in deep learning techniques have made it possible to aid the early diagnosis and prognosis of neurodevelopmental deficits. Deep learning models typically require training on large datasets, and unfortunately, large neuroimaging datasets with clinical outcome annotations are typically limited, especially in neonates. Transfer learning represents an important step to solve the fundamental problem of insufficient training data in deep learning. In this work, we developed a multi-task, multi-stage deep transfer learning framework using the fusion of brain connectome and clinical data for early joint prediction of multiple abnormal neurodevelopmental (cognitive, language and motor) outcomes at 2 years corrected age in very preterm infants. The proposed framework maximizes the value of both available annotated and non-annotated data in model training by performing both supervised and unsupervised learning. We first pre-trained a deep neural network prototype in a supervised fashion using 884 older children and adult subjects, and then re-trained this prototype using 291 neonatal subjects without supervision. Finally, we fine-tuned and validated the pre-trained model using 33 preterm infants. Our proposed model identified very preterm infants at high-risk for cognitive, language, and motor deficits at 2 years corrected age with an area under the receiver operating characteristic curve of 0.86, 0.66 and 0.84, respectively. Employing such a deep learning model, once externally validated, may facilitate risk stratification at term-equivalent age for early identification of long-term neurodevelopmental deficits and targeted early interventions to improve clinical outcomes in very preterm infants.

SUBMITTER: He L

PROVIDER: S-EPMC7492237 | biostudies-literature | 2020 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A multi-task, multi-stage deep transfer learning model for early prediction of neurodevelopment in very preterm infants.

He Lili L Li Hailong H Wang Jinghua J Chen Ming M Gozdas Elveda E Dillman Jonathan R JR Parikh Nehal A NA

Scientific reports 20200915 1

Survivors following very premature birth (i.e., ≤ 32 weeks gestational age) remain at high risk for neurodevelopmental impairments. Recent advances in deep learning techniques have made it possible to aid the early diagnosis and prognosis of neurodevelopmental deficits. Deep learning models typically require training on large datasets, and unfortunately, large neuroimaging datasets with clinical outcome annotations are typically limited, especially in neonates. Transfer learning represents an im ...[more]

PMID: 32934282

Similar Datasets

Project description:Up to 40% of very preterm infants (≤32 weeks' gestational age) were identified with a cognitive deficit at 2 years of age. Yet, accurate clinical diagnosis of cognitive deficit cannot be made until early childhood around 3-5 years of age. Recently, brain structural connectome that was constructed by advanced diffusion tensor imaging (DTI) technique has been playing an important role in understanding human cognitive functions. However, available annotated neuroimaging datasets with clinical and outcome information are usually limited and expensive to enlarge in the very preterm infants' studies. These challenges hinder the development of neonatal prognostic tools for early prediction of cognitive deficit in very preterm infants. In this study, we considered the brain structural connectome as a 2D image and applied established deep convolutional neural networks to learn the spatial and topological information of the brain connectome. Furthermore, the transfer learning technique was utilized to mitigate the issue of insufficient training data. As such, we developed a transfer learning enhanced convolutional neural network (TL-CNN) model for early prediction of cognitive assessment at 2 years of age in very preterm infants using brain structural connectome. A total of 110 very preterm infants were enrolled in this work. Brain structural connectome was constructed using DTI images scanned at term-equivalent age. Bayley III cognitive assessments were conducted at 2 years of corrected age. We applied the proposed model to both cognitive deficit classification and continuous cognitive score prediction tasks. The results demonstrated that TL-CNN achieved improved performance compared to multiple peer models. Finally, we identified the brain regions most discriminative to the cognitive deficit. The results suggest that deep learning models may facilitate early prediction of later neurodevelopmental outcomes in very preterm infants at term-equivalent age.

Project description:ObjectiveTo analyze survival and morbidity among very preterm infants (VPIs) in Shenzhen and explore factors associated with survival without major morbidity.MethodsBetween January 2022 and December 2022, 797 infants were admitted to 25 neonatal intensive care units in Shenzhen with gestational age (GA) < 32 weeks, excluded discharged against medical advice, insufficient information, and congenital malformation, 742 VPIs were included. Comparison of maternal and neonate characteristics, morbidities, survival, and survival without major morbidities between groups used Mann Whitney U test and X2 test, multivariate logistic regression was used to analyze of risk factors of survival without major morbidities.ResultsThe median GA was 29.86 weeks (interquartile range [IQR], 28.0-31.04), and the median birth weight was 1,250 g (IQR, 900-1,500). Of the 797 VPIs, 721 (90.46%) survived, 53.52% (38 of 71) at 25 weeks' or less GA, 86.78% (105 of 121) at 26 to 27 weeks' GA, 91.34% (211 of 230) at 28 to 29 weeks' GA, 97.86% (367 of 375) at 30 to 31 weeks' GA. The incidences of the major morbidities were moderate-to-severe bronchopulmonary dysplasia,16.52% (113 of 671); severe intraventricular hemorrhage and/or periventricular leukomalacia, 2.49% (17 of 671); severe necrotizing enterocolitis, 2.63% (18 of 671); sepsis, 2.34% (16 of 671); and severe retinopathy of prematurity, 4.55% (27 of 593), 65.79% (450 of 671) survived without major morbidities. After adjustment for GA, birth weight, and 5-min Apgar score, antenatal steroid administration (OR = 2.397), antenatal magnesium sulfate administration (OR = 1.554) were the positivity factors to survival without major morbidity of VPIs, however, surfactant therapy (OR = 0.684,), and delivery room resuscitation (OR = 0.626) that were the negativity factors.ConclusionsThe present results indicate that survival and the incidence of survival without major morbidities increased with GA. Further, antenatal administration of steroids and magnesium sulfate, surfactant therapy, and delivery room resuscitation were pronounced determinants of survival without morbidities.

Dataset Information

A multi-task, multi-stage deep transfer learning model for early prediction of neurodevelopment in very preterm infants.

Publications

A multi-task, multi-stage deep transfer learning model for early prediction of neurodevelopment in very preterm infants.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets