Predicting the Neurodevelopmental Outcome in Extremely Preterm Newborns Using a Multimodal Prognostic Model Including Brain Function Information

Abstract

ImportanceEarly assessment of the prognosis of preterm newborns is crucial for accurately informing parents and making treatment decisions. The currently available prognostic models rarely incorporate functional brain information from conventional electroencephalography (cEEG).ObjectiveTo examine the performance of a multimodal model combining (1) brain function information with (2) brain structure information (cranial ultrasonography), and (3) perinatal and (4) postnatal risk factors for the prediction of death or neurodevelopmental impairment (NDI) in extremely preterm infants.Design, Setting, and ParticipantsPreterm newborns (23-28 weeks’ gestational age) admitted to the neonatal intensive care unit at Amiens-Picardie University Hospital were retrospectively included (January 1, 2013, to January 1, 2018). Risk factors from the 4 categories were collected during the first 2 weeks post delivery. Neurodevelopmental impairment was assessed at age 2 years with the Denver Developmental Screening Test II. No or moderate NDI was considered a favorable outcome. Death or severe NDI was considered an adverse outcome. Data analysis was performed from August 26, 2021, to March 31, 2022.Main Outcomes and MeasuresAfter the selection of variables significantly associated with outcome, 4 unimodal prognostic models (considering each category of variable independently) and 1 multimodal model (considering all variables simultaneously) were developed. After a multivariate analysis for models built with several variables, decision-tree algorithms were run on each model. The areas under the curve for decision-tree classifications of adverse vs favorable outcomes were determined for each model, compared using bootstrap tests, and corrected for type I errors.ResultsA total of 109 newborns (58 [53.2% male]) born at a mean (SD) gestational age of 26.3 (1.1) weeks were included. Among them, 52 (47.7%) had a favorable outcome at age 2 years. The multimodal model area under the curve (91.7%; 95% CI, 86.4%-97.0%) was significantly higher than those of the unimodal models (P < .003): perinatal model (80.6%; 95% CI, 72.5%-88.7%), postnatal model (81.0%; 95% CI, 72.6%-89.4%), brain structure model (cranial ultrasonography) (76.6%; 95% CI, 67.8%-85.3%), and brain function model (cEEG) (78.8%; 95% CI, 69.9%-87.7%).Conclusions and RelevanceIn this prognostic study of preterm newborns, the inclusion of brain information in a multimodal model was associated with significant improvement in the outcome prediction, which may have resulted from the complementarity of the risk factors and reflected the complexity of the mechanisms that interfered with brain maturation and led to death or NDI.

Transforming spontaneous premature neonatal EEG to unpaired spontaneous fetal MEG using a CycleGan learning approach

“…Such risks include prematurity, in utero asphyxia, preeclampsia, fetal growth retardation, exposure to neurodevelopmental toxins, fetal cerebral suffering, and other pathologies/causes likely to impact the dynamics of fetal cerebral functioning [47]. The prenatal assessment of neural activity necessitates the identification of fetal neurobiomarkers of neurodevelopment, similar to what is carried out using EEG in premature newborns as part of clinical routine, aimed at evaluating the normality of brain function at different periods of development and predicting neurodevelopmental outcomes [1, 48]. Our proposed approach represents the first steps toward this ambitious goal by transferring the clinical knowledge acquired using EEG in premature neonates to fMEG, before identifying the neurobiomarkers of brain development in the fetus by MEG.…”

Semi-Automatic GUI Platform to Characterize Brain Development in Preterm Children Using Ultrasound Images

“…The reasons for preterm birth are multiple and fetal, maternal, and placental factors interact [2]. Some risk factors for preterm birth include chorioamnionitis (infection), maternal hypertensive disorders, genetic factors, altered nutritional status, multiple gestation, and toxic exposure, among others [3] According to the World Health Organization (WHO), an estimated 13.4 million babies were born too early in 2020; that is more than one in ten babies [4]. Approximately 900,000 children died in 2019 of complications during preterm birth [5].…”

The Persisting Value of Autopsies on Extremely Preterm Infants in the 21st Century

“…According to the World Health Organization, more than 90% of EP babies born in low-income countries die within the first few days of life compared with less than 10% of EP babies in high-income settings 2 . In addition to the high mortality, the EP infants had poor neurodevelopmental outcome 3 . Among the causes of in-hospital mortality, necrotizing enterocolitis (NEC), respiratory distress syndrome, intraventricular hemorrhage (IVH), infections, and gastrointestinal causes are among the top 4 .…”