Data-driven longitudinal characterization of neonatal health and morbidity

Abstract

Although prematurity is the single largest cause of death in children under 5 years of age, the current definition of prematurity, based on gestational age, lacks the precision needed for guiding care decisions. Here, we propose a longitudinal risk assessment for adverse neonatal outcomes in newborns based on a deep learning model that uses electronic health records (EHRs) to predict a wide range of outcomes over a period starting shortly before conception and ending months after birth. By linking the EHRs of the Lucile Packard Children’s Hospital and the Stanford Healthcare Adult Hospital, we developed a cohort of 22,104 mother-newborn dyads delivered between 2014 and 2018. Maternal and newborn EHRs were extracted and used to train a multi-input multitask deep learning model, featuring a long short-term memory neural network, to predict 24 different neonatal outcomes. An additional cohort of 10,250 mother-newborn dyads delivered at the same Stanford Hospitals from 2019 to September 2020 was used to validate the model. Areas under the receiver operating characteristic curve at delivery exceeded 0.9 for 10 of the 24 neonatal outcomes considered and were between 0.8 and 0.9 for 7 additional outcomes. Moreover, comprehensive association analysis identified multiple known associations between various maternal and neonatal features and specific neonatal outcomes. This study used linked EHRs from more than 30,000 mother-newborn dyads and would serve as a resource for the investigation and prediction of neonatal outcomes. An interactive website is available for independent investigators to leverage this unique dataset: https://maternal-child-health-associations.shinyapps.io/shiny_app/ .

Challenges to the study of gender dysphoria

“…Using advanced machine-learning methodologies, even electronic health records can be used to identify novel associations between maternal conditions and neonatal outcomes that have clinical plausibility. 5 Importantly, we are not suggesting, however, that the use of such advanced machine-learning approaches should be used for the prediction of gender dysphoria, but instead for informing better, and perhaps earlier, decision-making when such analyses are considered in the context of the current clinical approaches employed to help individuals suffering from gender dysphoria. However, there seems to be a limited literature on the biological contributors to gender dysphoria.…”

“…Whereas many of the individual omics measures have been shown to be predictive biomarkers, their computational integration with the more traditional risk factors has enhanced their predictive power and been helpful in identifying potentially causative biologic pathways as preventive or therapeutic targets. Using advanced machine‐learning methodologies, even electronic health records can be used to identify novel associations between maternal conditions and neonatal outcomes that have clinical plausibility 5 . Importantly, we are not suggesting, however, that the use of such advanced machine‐learning approaches should be used for the prediction of gender dysphoria, but instead for informing better, and perhaps earlier, decision‐making when such analyses are considered in the context of the current clinical approaches employed to help individuals suffering from gender dysphoria.…”

Leveraging electronic health records to identify risk factors for recurrent pregnancy loss across two medical centers: a case-control study

“…Lastly, to ascertain which results validated across medical centers, we compared findings from our UCSF and Stanford studies. This validation work builds on our existing foundation of porting EHR analysis models between medical centers towards generalizability of both methods and results 37 .…”

Large-scale correlation network construction for unraveling the coordination of complex biological systems

“…It features off-the-shelf algorithms suitable for both personal and high-performance computers, enabling workflows and downstream analysis approaches. We illustrate the broad scope and potential of CorALS by exploring perspectives on complex biological processes in large-scale multiomics and single-cell studies.The advancement of modern technologies, including single-cell 1 and multiomics approaches 2 , wearable devices 3 , and integrated electronic health records 4,5 , have enabled an exciting era of precision medicine. These technologies regularly produce datasets with hundreds of thousands of variables (here referred to as features), allowing for unprecedented profiling of complex biological processes such as diseases, pregnancy or healing 2,6,7 .…”

“…The advancement of modern technologies, including single-cell 1 and multiomics approaches 2 , wearable devices 3 , and integrated electronic health records 4,5 , have enabled an exciting era of precision medicine. These technologies regularly produce datasets with hundreds of thousands of variables (here referred to as features), allowing for unprecedented profiling of complex biological processes such as diseases, pregnancy or healing 2,6,7 .…”