Reassessing acquired neonatal intestinal diseases using unsupervised machine learning.

BACKGROUND: Acquired neonatal intestinal diseases have an array of overlapping presentations and are often labeled under the dichotomous classification of necrotizing enterocolitis (which is poorly defined) or spontaneous intestinal perforation, hindering more precise diagnosis and research. The objective of this study was to take a fresh look at neonatal intestinal disease classification using unsupervised machine learning. METHODS: Patients admitted to the University of Florida Shands Neonatal Intensive Care Unit January 2013-September 2019 diagnosed with an intestinal injury, or had imaging findings of portal venous gas, pneumatosis, abdominal free air, or had an abdominal drain placed or exploratory laparotomy during admission were included. Congenital gastroschisis, omphalocele, intestinal atresia, malrotation were excluded. Data was collected via retrospective chart review with subsequent hierarchal, unsupervised clustering analysis. RESULTS: Five clusters of intestinal injury were identified: Cluster 1 deemed the "Low Mortality" cluster, Cluster 2 deemed the "Mature with Inflammation" cluster, Cluster 3 deemed the "Immature with High Mortality" cluster, Cluster 4 deemed the "Late Injury at Full Feeds" cluster, and Cluster 5 deemed the "Late Injury with High Rate of Intestinal Necrosis" cluster. CONCLUSION: Unsupervised machine learning can be used to cluster acquired neonatal intestinal injuries. Future study with larger multicenter datasets is needed to further refine and classify types of intestinal diseases. IMPACT: Unsupervised machine learning can be used to cluster types of acquired neonatal intestinal injury. Five major clusters of acquired neonatal intestinal injury are described, each with unique features. The clusters herein described deserve future, multicenter study to determine more specific early biomarkers and tailored therapeutic interventions to improve outcomes of often devastating neonatal acquired intestinal injuries.

Objective Activity Parameters Track Patient-specific Physical Recovery Trajectories After Surgery and Link With Individual Preoperative Immune States.

OBJECTIVE: The longitudinal assessment of physical function with high temporal resolution at a scalable and objective level in patients recovering from surgery is highly desirable to understand the biological and clinical factors that drive the clinical outcome. However, physical recovery from surgery itself remains poorly defined and the utility of wearable technologies to study recovery after surgery has not been established. BACKGROUND: Prolonged postoperative recovery is often associated with long-lasting impairment of physical, mental, and social functions. Although phenotypical and clinical patient characteristics account for some variation of individual recovery trajectories, biological differences likely play a major role. Specifically, patient-specific immune states have been linked to prolonged physical impairment after surgery. However, current methods of quantifying physical recovery lack patient specificity and objectivity. METHODS: Here, a combined high-fidelity accelerometry and state-of-the-art deep immune profiling approach was studied in patients undergoing major joint replacement surgery. The aim was to determine whether objective physical parameters derived from accelerometry data can accurately track patient-specific physical recovery profiles (suggestive of a 'clock of postoperative recovery'), compare the performance of derived parameters with benchmark metrics including step count, and link individual recovery profiles with patients' preoperative immune state. RESULTS: The results of our models indicate that patient-specific temporal patterns of physical function can be derived with a precision superior to benchmark metrics. Notably, 6 distinct domains of physical function and sleep are identified to represent the objective temporal patterns: ''activity capacity'' and ''moderate and overall activity (declined immediately after surgery); ''sleep disruption and sedentary activity (increased after surgery); ''overall sleep'', ''sleep onset'', and ''light activity'' (no clear changes were observed after surgery). These patterns can be linked to individual patients preopera-tive immune state using cross-validated canonical-correlation analysis. Importantly, the pSTAT3 signal activity in monocytic myeloid-derived suppressor cells predicted a slower recovery. CONCLUSIONS: Accelerometry-based recovery trajectories are scalable and objective outcomes to study patient-specific factors that drive physical recovery.

In-silico generation of high-dimensional immune response data in patients using a deep neural network.

Technologies for single-cell profiling of the immune system have enabled researchers to extract rich interconnected networks of cellular abundance, phenotypical and functional cellular parameters. These studies can power machine learning approaches to understand the role of the immune system in various diseases. However, the performance of these approaches and the generalizability of the findings have been hindered by limited cohort sizes in translational studies, partially due to logistical demands and costs associated with longitudinal data collection in sufficiently large patient cohorts. An evolving challenge is the requirement for ever-increasing cohort sizes as the dimensionality of datasets grows. We propose a deep learning model derived from a novel pipeline of optimal temporal cell matching and overcomplete autoencoders that uses data from a small subset of patients to learn to forecast an entire patient's immune response in a high dimensional space from one timepoint to another. In our analysis of 1.08 million cells from patients pre- and post-surgical intervention, we demonstrate that the generated patient-specific data are qualitatively and quantitatively similar to real patient data by demonstrating fidelity, diversity, and usefulness.

Prediction of neuropathologic lesions from clinical data.

INTRODUCTION: Post-mortem analysis provides definitive diagnoses of neurodegenerative diseases; however, only a few can be diagnosed during life. METHODS: This study employed statistical tools and machine learning to predict 17 neuropathologic lesions from a cohort of 6518 individuals using 381 clinical features (Table S1). The multisite data allowed validation of the model's robustness by splitting train/test sets by clinical sites. A similar study was performed for predicting Alzheimer's disease (AD) neuropathologic change without specific comorbidities. RESULTS: Prediction results show high performance for certain lesions that match or exceed that of research annotation. Neurodegenerative comorbidities in addition to AD neuropathologic change resulted in compounded, but disproportionate, effects across cognitive domains as the comorbidity number increased. DISCUSSION: Certain clinical features could be strongly associated with multiple neurodegenerative diseases, others were lesion-specific, and some were divergent between lesions. Our approach could benefit clinical research, and genetic and biomarker research by enriching cohorts for desired lesions.

Newborn screen metabolic panels reflect the impact of common disorders of pregnancy.

BACKGROUND: Hypertensive disorders of pregnancy and maternal diabetes profoundly affect fetal and newborn growth, yet disturbances in intermediate metabolism and relevant mediators of fetal growth alterations remain poorly defined. We sought to determine whether there are distinct newborn screen metabolic patterns among newborns affected by maternal hypertensive disorders or diabetes in utero. METHODS: A retrospective observational study investigating distinct newborn screen metabolites in conjunction with data linked to birth and hospitalization records in the state of California between 2005 and 2010. RESULTS: A total of 41,333 maternal-infant dyads were included. Infants of diabetic mothers demonstrated associations with short-chain acylcarnitines and free carnitine. Infants born to mothers with preeclampsia with severe features and chronic hypertension with superimposed preeclampsia had alterations in acetylcarnitine, free carnitine, and ornithine levels. These results were further accentuated by size for gestational age designations. CONCLUSIONS: Infants of diabetic mothers demonstrate metabolic signs of incomplete beta oxidation and altered lipid metabolism. Infants of mothers with hypertensive disorders of pregnancy carry analyte signals that may reflect oxidative stress via altered nitric oxide signaling. The newborn screen analyte composition is influenced by the presence of these maternal conditions and is further associated with the newborn size designation at birth. IMPACT: Substantial differences in newborn screen analyte profiles were present based on the presence or absence of maternal diabetes or hypertensive disorder of pregnancy and this finding was further influenced by the newborn size designation at birth. The metabolic health of the newborn can be examined using the newborn screen and is heavily impacted by the condition of the mother during pregnancy. Utilizing the newborn screen to identify newborns affected by common conditions of pregnancy may help relate an infant's underlying biological disposition with their clinical phenotype allowing for greater risk stratification and intervention.

Dendritic Cell-Based Vaccines that Utilize Myeloid Rather than Plasmacytoid Cells Offer a Superior Survival Advantage in Malignant Glioma.

Dendritic cells (DCs) are professional APCs that are traditionally divided into two distinct subsets, myeloid DC (mDCs) and plasmacytoid DC (pDCs). pDCs are known for their ability to secrete large amounts of IFN-α. Apart from IFN-α production, pDCs can also process Ag and induce T cell immunity or tolerance. In several solid tumors, pDCs have been shown to play a critical role in promoting tumor immunosuppression. We investigated the role of pDCs in the process of glioma progression in the syngeneic murine model of glioma. We show that glioma-infiltrating pDCs are the major APC in glioma and are deficient in IFN-α secretion (p < 0.05). pDC depletion leads to increased survival of the mice bearing intracranial tumor by decreasing the number of regulatory T cells (Tregs) and by decreasing the suppressive capabilities of Tregs. We subsequently compared the ability of mDCs and pDCs to generate effective antiglioma immunity in a GL261-OVA mouse model of glioma. Our data suggest that mature pDCs and mDCs isolated from naive mice can be effectively activated and loaded with SIINFEKL Ag in vitro. Upon intradermal injection in the hindleg, a fraction of both types of DCs migrate to the brain and lymph nodes. Compared to mice vaccinated with pDC or control mice, mice vaccinated with mDCs generate a robust Th1 type immune response, characterized by high frequency of CD4(+)T-bet(+) T cells and CD8(+)SIINFEKEL(+) T cells. This robust antitumor T cell response results in tumor eradication and long-term survival in 60% of the animals (p < 0.001).

Anti-GITR therapy promotes immunity against malignant glioma in a murine model.

Regulatory T cells (Tregs) are potently immunosuppressive cells that accumulate within the glioma microenvironment. The reduction in their function and/or trafficking has been previously shown to enhance survival in preclinical models of glioma. Glucocorticoid-induced TNFR-related protein (GITR) is a tumor necrosis factor superfamily receptor enriched on Tregs that has shown promise as a target for immunotherapy. An agonistic antibody against GITR has been demonstrated to inhibit Tregs in a number of models and has only been recently addressed in glioma. In this study, we examined the modality of the antibody function at the tumor site as opposed to the periphery as the blood-brain barrier prevents efficient antibody delivery to brain tumors. Mice harboring established GL261 tumors were treated with anti-GITR monotherapy and were shown to have a significant increase in overall survival (p < 0.01) when antibodies were injected directly into the glioma core, whereas peripheral antibody treatment only had a modest effect. Peripheral treatment resulted in a significant decrease in granzyme B (GrB) expression by Tregs, whereas intratumoral treatment resulted in both a decrease in GrB expression by Tregs and their selective depletion, which was largely mediated by FcγR-mediated destruction. We also discovered that anti-GITR treatment results in the enhanced survival and functionality of dendritic cells (DCs)-a previously unreported effect of this immunotherapy. In effect, this study demonstrates that the targeting of GITR is a feasible and noteworthy treatment option for glioma, but is largely dependent on the anatomical location in which the antibodies are delivered.

Single dose GLP toxicity and biodistribution study of a conditionally replicative adenovirus vector, CRAd-S-pk7, administered by intracerebral injection to Syrian hamsters.

BACKGROUND: CRAd-S-pk7 is a conditionally replicative oncolytic adenoviral vector that contains a survivin promoter and a pk7 fiber modification that confer tumor-specific transcriptional targeting and preferential replication in glioma while sparing the surrounding normal brain parenchyma. METHODS: This IND-enabling study performed under GLP conditions evaluated the toxicity and biodistribution of CRAd-S-pk7 administered as a single intracerebral dose to Syrian hamsters, a permissive model of adenoviral replication. Two hundred and forty animals were stereotactically administered either vehicle (n = 60) or CRAd-S-pk7 at 2.5 × 10(7), 2.5 × 10(8), or 2.5 × 10(9) viral particles (vp)/animal (each n = 60) on day 1. The animals were closely monitored for toxicology evaluation, assessment of viral distribution, and immunogenicity of CRAd-S-pk7. RESULTS: Changes in hematology, clinical chemistry, and coagulation parameters were minor and transient, and consistent with the inflammatory changes observed microscopically. These changes were considered to be of little toxicological significance. The vector remained localized primarily in the brain and to some degree in the tissues at the incision site. Low levels of vector DNA were detected in other tissues in a few animals suggesting systemic circulation of the virus. Viral DNA was detected in brains of hamsters for up to 62 days. However, microscopic changes and virus-related toxicity to the central nervous system were considered minor and decreased in incidence and severity over time. Such changes are not uncommon in studies using adenoviral vectors. CONCLUSION: This study provides safety and toxicology data justifying a clinical trial of CRAd-S-pk7 loaded in FDA-approved HB1.F3.CD neural stem cell carriers administered at the tumor resection bed in humans with recurrent malignant glioma.

The role of IDO in brain tumor immunotherapy.

Malignant glioma comprises the majority of primary brain tumors. Coincidently, most of those malignancies express an inducible tryptophan catabolic enzyme, indoleamine 2,3 dioxygenase 1 (IDO1). While IDO1 is not normally expressed at appreciable levels in the adult central nervous system, it's rapidly induced and/or upregulated upon inflammatory stimulus. The primary function of IDO1 is associated with conversion of the essential amino acid, tryptophan, into downstream catabolites known as kynurenines. The depletion of tryptophan and/or accumulation of kynurenine has been shown to induce T cell deactivation, apoptosis and/or the induction of immunosuppressive programming via the expression of FoxP3. This understanding has informed immunotherapeutic design for the strategic development of targeted molecular therapeutics that inhibit IDO1 activity. Here, we review the current knowledge of IDO1 in brain tumors, pre-clinical studies targeting this enzymatic pathway, alternative tryptophan catabolic mediators that compensate for IDO1 loss and/or inhibition, as well as proposed clinical strategies and questions that are critical to address for increasing future immunotherapeutic effectiveness in patients with incurable brain cancer.

Development of a novel preclinical model of pneumococcal pneumonia in nonhuman primates.

Pneumococcal pneumonia is a leading cause of bacterial infection and death worldwide. Current diagnostic tests for detecting Streptococcus pneumoniae can be unreliable and can mislead clinical decision-making and treatment. To address this concern, we developed a preclinical model of pneumococcal pneumonia in nonhuman primates useful for identifying novel biomarkers, diagnostic tests, and therapies for human S. pneumoniae infection. Adult colony-bred baboons (n = 15) were infected with escalating doses of S. pneumoniae (Serotype 19A-7). We characterized the pathophysiological and serological profiles of healthy and infected animals over 7 days. Pneumonia was prospectively defined by the presence of three criteria: (1) change in white blood cell count, (2) isolation of S. pneumoniae from bronchoalveolar lavage fluid (BALF) or blood, and (3) concurrent signs/symptoms of infection. Animals given 10(9) CFU consistently met our definition and developed a phenotype of tachypnea, tachycardia, fever, hypoxemia, and radiographic lobar infiltrates at 48 hours. BALF and plasma cytokines, including granulocyte colony-stimulating factor, IL-6, IL-10, and IL-1ra, peaked at 24 to 48 hours. At necropsy, there was lobar consolidation with frequent pleural involvement. Lung histopathology showed alveolar edema and macrophage influx in areas of organizing pneumonia. Hierarchical clustering of peripheral blood RNA data at 48 hours correctly identified animals with and without pneumonia. Dose-dependent inoculation of baboons with S. pneumoniae produces a host response ranging from spontaneous clearance (10(6) CFU) to severe pneumonia (10(9) CFU). Selected BALF and plasma cytokine levels and RNA profiles were associated with severe pneumonia and may provide clinically useful parameters after validation.

Comprehensive overview of the anesthesiology research landscape: A machine Learning Analysis of 737 NIH-funded anesthesiology primary Investigator's publication trends.

Background: Anesthesiology plays a crucial role in perioperative care, critical care, and pain management, impacting patient experiences and clinical outcomes. However, our understanding of the anesthesiology research landscape is limited. Accordingly, we initiated a data-driven analysis through topic modeling to uncover research trends, enabling informed decision-making and fostering progress within the field. Methods: The easyPubMed R package was used to collect 32,300 PubMed abstracts spanning from 2000 to 2022. These abstracts were authored by 737 Anesthesiology Principal Investigators (PIs) who were recipients of National Institute of Health (NIH) funding from 2010 to 2022. Abstracts were preprocessed, vectorized, and analyzed with the state-of-the-art BERTopic algorithm to identify pillar topics and trending subtopics within anesthesiology research. Temporal trends were assessed using the Mann-Kendall test. Results: The publishing journals with most abstracts in this dataset were Anesthesia & Analgesia 1133, Anesthesiology 992, and Pain 671. Eight pillar topics were identified and categorized as basic or clinical sciences based on a hierarchical clustering analysis. Amongst the pillar topics, "Cells & Proteomics" had both the highest annual and total number of abstracts. Interestingly, there was an overall upward trend for all topics spanning the years 2000-2022. However, when focusing on the period from 2015 to 2022, topics "Cells & Proteomics" and "Pulmonology" exhibit a downward trajectory. Additionally, various subtopics were identified, with notable increasing trends in "Aneurysms", "Covid 19 Pandemic", and "Artificial intelligence & Machine Learning". Conclusion: Our work offers a comprehensive analysis of the anesthesiology research landscape by providing insights into pillar topics, and trending subtopics. These findings contribute to a better understanding of anesthesiology research and can guide future directions.

Whole genome deconvolution unveils Alzheimer's resilient epigenetic signature.

Assay for Transposase Accessible Chromatin by sequencing (ATAC-seq) accurately depicts the chromatin regulatory state and altered mechanisms guiding gene expression in disease. However, bulk sequencing entangles information from different cell types and obscures cellular heterogeneity. To address this, we developed Cellformer, a deep learning method that deconvolutes bulk ATAC-seq into cell type-specific expression across the whole genome. Cellformer enables cost-effective cell type-specific open chromatin profiling in large cohorts. Applied to 191 bulk samples from 3 brain regions, Cellformer identifies cell type-specific gene regulatory mechanisms involved in resilience to Alzheimer's disease, an uncommon group of cognitively healthy individuals that harbor a high pathological load of Alzheimer's disease. Cell type-resolved chromatin profiling unveils cell type-specific pathways and nominates potential epigenetic mediators underlying resilience that may illuminate therapeutic opportunities to limit the cognitive impact of the disease. Cellformer is freely available to facilitate future investigations using high-throughput bulk ATAC-seq data.

Quantitative estimate of cognitive resilience and its medical and genetic associations.

BACKGROUND: We have proposed that cognitive resilience (CR) counteracts brain damage from Alzheimer's disease (AD) or AD-related dementias such that older individuals who harbor neurodegenerative disease burden sufficient to cause dementia remain cognitively normal. However, CR traditionally is considered a binary trait, capturing only the most extreme examples, and is often inconsistently defined. METHODS: This study addressed existing discrepancies and shortcomings of the current CR definition by proposing a framework for defining CR as a continuous variable for each neuropsychological test. The linear equations clarified CR's relationship to closely related terms, including cognitive function, reserve, compensation, and damage. Primarily, resilience is defined as a function of cognitive performance and damage from neuropathologic damage. As such, the study utilized data from 844 individuals (age = 79 ± 12, 44% female) in the National Alzheimer's Coordinating Center cohort that met our inclusion criteria of comprehensive lesion rankings for 17 neuropathologic features and complete neuropsychological test results. Machine learning models and GWAS then were used to identify medical and genetic factors that are associated with CR. RESULTS: CR varied across five cognitive assessments and was greater in female participants, associated with longer survival, and weakly associated with educational attainment or APOE ε4 allele. In contrast, damage was strongly associated with APOE ε4 allele (P value < 0.0001). Major predictors of CR were cardiovascular health and social interactions, as well as the absence of behavioral symptoms. CONCLUSIONS: Our framework explicitly decoupled the effects of CR from neuropathologic damage. Characterizations and genetic association study of these two components suggest that the underlying CR mechanism has minimal overlap with the disease mechanism. Moreover, the identified medical features associated with CR suggest modifiable features to counteract clinical expression of damage and maintain cognitive function in older individuals.

Cross-species comparative analysis of single presynapses.

Comparing brain structure across species and regions enables key functional insights. Leveraging publicly available data from a novel mass cytometry-based method, synaptometry by time of flight (SynTOF), we applied an unsupervised machine learning approach to conduct a comparative study of presynapse molecular abundance across three species and three brain regions. We used neural networks and their attractive properties to model complex relationships among high dimensional data to develop a unified, unsupervised framework for comparing the profile of more than 4.5 million single presynapses among normal human, macaque, and mouse samples. An extensive validation showed the feasibility of performing cross-species comparison using SynTOF profiling. Integrative analysis of the abundance of 20 presynaptic proteins revealed near-complete separation between primates and mice involving synaptic pruning, cellular energy, lipid metabolism, and neurotransmission. In addition, our analysis revealed a strong overlap between the presynaptic composition of human and macaque in the cerebral cortex and neostriatum. Our unique approach illuminates species- and region-specific variation in presynapse molecular composition.

Deep representation learning identifies associations between physical activity and sleep patterns during pregnancy and prematurity.

Preterm birth (PTB) is the leading cause of infant mortality globally. Research has focused on developing predictive models for PTB without prioritizing cost-effective interventions. Physical activity and sleep present unique opportunities for interventions in low- and middle-income populations (LMICs). However, objective measurement of physical activity and sleep remains challenging and self-reported metrics suffer from low-resolution and accuracy. In this study, we use physical activity data collected using a wearable device comprising over 181,944 h of data across N = 1083 patients. Using a new state-of-the art deep learning time-series classification architecture, we develop a 'clock' of healthy dynamics during pregnancy by using gestational age (GA) as a surrogate for progression of pregnancy. We also develop novel interpretability algorithms that integrate unsupervised clustering, model error analysis, feature attribution, and automated actigraphy analysis, allowing for model interpretation with respect to sleep, activity, and clinical variables. Our model performs significantly better than 7 other machine learning and AI methods for modeling the progression of pregnancy. We found that deviations from a normal 'clock' of physical activity and sleep changes during pregnancy are strongly associated with pregnancy outcomes. When our model underestimates GA, there are 0.52 fewer preterm births than expected (P = 1.01e - 67, permutation test) and when our model overestimates GA, there are 1.44 times (P = 2.82e - 39, permutation test) more preterm births than expected. Model error is negatively correlated with interdaily stability (P = 0.043, Spearman's), indicating that our model assigns a more advanced GA when an individual's daily rhythms are less precise. Supporting this, our model attributes higher importance to sleep periods in predicting higher-than-actual GA, relative to lower-than-actual GA (P = 1.01e - 21, Mann-Whitney U). Combining prediction and interpretability allows us to signal when activity behaviors alter the likelihood of preterm birth and advocates for the development of clinical decision support through passive monitoring and exercise habit and sleep recommendations, which can be easily implemented in LMICs.

Data-driven longitudinal characterization of neonatal health and morbidity.

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/.

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

Advanced measurement and data storage technologies have enabled high-dimensional profiling of complex biological systems. For this, modern multiomics studies regularly produce datasets with hundreds of thousands of measurements per sample, enabling a new era of precision medicine. Correlation analysis is an important first step to gain deeper insights into the coordination and underlying processes of such complex systems. However, the construction of large correlation networks in modern high-dimensional datasets remains a major computational challenge owing to rapidly growing runtime and memory requirements. Here we address this challenge by introducing CorALS (Correlation Analysis of Large-scale (biological) Systems), an open-source framework for the construction and analysis of large-scale parametric as well as non-parametric correlation networks for high-dimensional biological data. 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.

Multiomic signals associated with maternal epidemiological factors contributing to preterm birth in low- and middle-income countries.

Preterm birth (PTB) is the leading cause of death in children under five, yet comprehensive studies are hindered by its multiple complex etiologies. Epidemiological associations between PTB and maternal characteristics have been previously described. This work used multiomic profiling and multivariate modeling to investigate the biological signatures of these characteristics. Maternal covariates were collected during pregnancy from 13,841 pregnant women across five sites. Plasma samples from 231 participants were analyzed to generate proteomic, metabolomic, and lipidomic datasets. Machine learning models showed robust performance for the prediction of PTB (AUROC = 0.70), time-to-delivery (r = 0.65), maternal age (r = 0.59), gravidity (r = 0.56), and BMI (r = 0.81). Time-to-delivery biological correlates included fetal-associated proteins (e.g., ALPP, AFP, and PGF) and immune proteins (e.g., PD-L1, CCL28, and LIFR). Maternal age negatively correlated with collagen COL9A1, gravidity with endothelial NOS and inflammatory chemokine CXCL13, and BMI with leptin and structural protein FABP4. These results provide an integrated view of epidemiological factors associated with PTB and identify biological signatures of clinical covariates affecting this disease.

Perinatal infection, inflammation, preterm birth, and brain injury: A review with proposals for future investigations.

Preterm newborns are exposed to several risk factors for developing brain injury. Clinical studies have suggested that the presence of intrauterine infection is a consistent risk factor for preterm birth and white matter injury. Animal models have confirmed these associations by identifying inflammatory cascades originating at the maternofetal interface that penetrate the fetal blood-brain barrier and result in brain injury. Acquired diseases of prematurity further potentiate the risk for cerebral injury. Systems biology approaches incorporating ante- and post-natal risk factors and analyzing omic and multiomic data using machine learning are promising methodologies for further elucidating biologic mechanisms of fetal and neonatal brain injury.

A data-driven health index for neonatal morbidities.

Whereas prematurity is a major cause of neonatal mortality, morbidity, and lifelong impairment, the degree of prematurity is usually defined by the gestational age (GA) at delivery rather than by neonatal morbidity. Here we propose a multi-task deep neural network model that simultaneously predicts twelve neonatal morbidities, as the basis for a new data-driven approach to define prematurity. Maternal demographics, medical history, obstetrical complications, and prenatal fetal findings were obtained from linked birth certificates and maternal/infant hospitalization records for 11,594,786 livebirths in California from 1991 to 2012. Overall, our model outperformed traditional models to assess prematurity which are based on GA and/or birthweight (area under the precision-recall curve was 0.326 for our model, 0.229 for GA, and 0.156 for small for GA). These findings highlight the potential of using machine learning techniques to predict multiple prematurity phenotypes and inform clinical decisions to prevent, diagnose and treat neonatal morbidities.