Antibody response to three-dose anti-SARS-CoV-2 mRNA-vaccination in treated solid cancer patients.

Solid cancer patients are at higher risk of SARS-CoV-2 infection and severe complications. Moreover, vaccine-induced antibody response is impaired in patients on anticancer treatment. In this retrospective, observational, hypothesis-generating, cohort study, we assessed the antibody response to the third dose of mRNA vaccine in a convenience sample of patients on anticancer treatment, comparing it to that of the primary two-dose cycle. Among 99 patients included, 62.6% were ≥60 years old, 32.3% males, 67.7% with advanced disease. Exactly 40.4% were receiving biological therapy, 16.2% chemotherapy only and 7.1% both treatments. After the third dose, seroconversion rate seems to increase significantly, especially in non-responders to two doses. Heterologous vaccine-type regimen (two-dose mRNA-1273 and subsequent tozinameran or vice versa) results in higher antibody levels. This explorative study suggests that repeated doses of mRNA-vaccines could be associated with a better antibody response in this population. Furthermore, heterologous vaccine-type three-dose vaccination seems more effective in this population. Since this is a hypothesis-generating study, adequately statistically powered studies should validate these results.

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.

Correlation between cerebrospinal fluid and plasma neurofilament light protein in treated HIV infection: results from the COBRA study.

Cerebrospinal fluid (CSF) neurofilament light protein (NfL) is a marker of central nervous system neuro-axonal injury. A novel, ultra-sensitive assay can determine plasma NfL. In untreated people-with-HIV (PWH), CSF and plasma NfL are strongly correlated. We aimed to assess this correlation in PWH on suppressive antiretroviral treatment (ART) and lifestyle-similar HIV-negative individuals enrolled into the COmorBidity in Relation to AIDS (COBRA) study. Differences in paired CSF (sandwich ELISA, UmanDiagnostics) and plasma (Simoa digital immunoassay, Quanterix™) NfL between PWH and HIV-negative participants were tested using Wilcoxon's test; associations were assessed using Pearson's correlation. CSF and plasma NfL, standardised to Z-scores, were included as dependent variables in linear regression models to identify factors independently associated with values in PWH and HIV-negative participants. Overall, 132 PWH (all with plasma HIV RNA < 50 copies/mL) and 79 HIV-negative participants were included. Neither CSF (median 570 vs 568 pg/mL, p = 0.37) nor plasma (median 10.7 vs 9.9 pg/mL, p = 0.15) NfL differed significantly between PWH and HIV-negative participants, respectively. CSF and plasma NfL correlated moderately, with no significant difference by HIV status (PWH: rho = 0.52; HIV-negative participants: rho = 0.47, p (interaction) = 0.63). In multivariable regression analysis, higher CSF NfL Z-score was statistically significantly associated with older age and higher CSF protein, and higher plasma NfL Z-score with older age, higher serum creatinine and lower bodyweight. In conclusion, in PWH on ART, the correlation between CSF and plasma NfL is moderate and similar to that observed in lifestyle-similar HIV-negative individuals. Consideration of renal function and bodyweight may be required when utilising plasma NfL.

Screening Accuracy of Mini Addenbrooke's Cognitive Examination Test for HIV-Associated Neurocognitive Disorders in People Ageing with HIV.

Aging and increased cardiovascular risk are major drivers for HIV-associated neurocognitive disorders (HAND), for which accurate screenings are lacking. Mini-Addenbrooke's Cognitive Examination (MACE) reliably detects vascular and neurodegenerative cognitive decline among HIV-negative patients. We evaluated MACE diagnostic accuracy in detecting HAND in people living with HIV (PLWH) and we compared it with the International HIV Dementia Scale (IHDS). A single-centre double-blind study of diagnostic accuracy on adult outpatient PLWH without neurocognitive confounding was performed. MACE and IHDS were administered in 5 and 10 min by clinicians, followed by the reference standard battery (14 tests) by neuropsychologists. HAND diagnosis was based on the modified version of Frascati's criteria by Gisslén to reduce false positives. Exploratory cut-offs were evaluated for MACE. Diagnostic accuracy and clinical utility parameters were assessed. 231 patients were enrolled. 75.7% men with a median age, education, and length of infection of 54 (48-59), 10 (8-13) and 16 (5-25) years. HAND prevalence was 48.5% (38.9% asymptomatic impairment). Compared to IHDS, MACE sensitivity (89.3% vs 70.5%), specificity (94.1% vs 63.0%), correct classification rate (86.5% vs 66.7%), J index (0.83 vs 0.34), AUROC (0.97 vs 0.79), agreement with the gold standard (k 0.84 vs 0.33) and effect size in distinguishing HAND vs non-HAND (d 2.11 vs 1.15) were higher. Among PLWH aged 65 years and above (n = 37) MACE performance was consistently better than IHDS. The quick and easy-to-perform MACE could possess an accurate and useful screening performance for HAND in otherwise neurocognitively healthy cohorts of PLWH.

Correlation between computerised and standard cognitive testing in people with HIV and HIV-negative individuals.

We investigated the correlations and agreement between cognitive assessments made using a computerised (CogState™, six domains) and a standard pen-and-paper battery (five domains) in PWH and lifestyle-similar HIV-negative individuals. Demographically adjusted domain and global T-scores were obtained and used to define cognitive impairment according to the multivariate normative comparison (MNC) criteria. Correlations between T-scores and the agreement between the classifications of cognitive impairment obtained from the two batteries were assessed using the Spearman's rank correlation and Cohen's κ, respectively. The correlation between global T-scores from the two batteries was 0.52 (95% CI 0.44-0.60) in PWH and 0.45 (0.29-0.59) in controls (p = 0.38 for their difference). Correlations were generally stronger between domains within the same battery than between those from different batteries. The agreement between the two batteries in classifying individuals as cognitively impaired or not impaired was fair in PWH (κ = 0.24) and poor in HIV-negative individuals (κ = -0.02). The moderate correlation between overall cognitive function and the modest agreement between binary classifications of cognitive impairment obtained from two different batteries indicate the two batteries may assess slightly different components of cognition.

No Evidence for Accelerated Aging-Related Brain Pathology in Treated Human Immunodeficiency Virus: Longitudinal Neuroimaging Results From the Comorbidity in Relation to AIDS (COBRA) Project.

Background: Despite successful antiretroviral therapy, people living with human immunodeficiency virus (PLWH) experience higher rates of age-related morbidity, including abnormal brain structure, brain function, and cognitive impairment. This has raised concerns that PLWH may experience accelerated aging-related brain pathology. Methods: We performed a multicenter longitudinal study of 134 virologically suppressed PLWH (median age, 56.0 years) and 79 demographically similar human immunodeficiency virus (HIV)-negative controls (median age, 57.2 years). To measure cognitive performance and brain pathology, we conducted detailed neuropsychological assessments and multimodality neuroimaging (T1-weighted, T2-weighted, diffusion magnetic resonance imaging [MRI], resting-state functional MRI, spectroscopy, arterial spin labeling) at baseline and at 2 years. Group differences in rates of change were assessed using linear mixed effects models. Results: One hundred twenty-three PLWH and 78 HIV-negative controls completed longitudinal assessments (median interval, 1.97 years). There were no differences between PLWH and HIV-negative controls in age, sex, years of education, smoking or alcohol use. At baseline, PLWH had poorer global cognitive performance (P < .01), lower gray matter volume (P = .04), higher white matter hyperintensity load (P = .02), abnormal white matter microstructure (P < .005), and greater brain-predicted age difference (P = .01). Longitudinally, there were no significant differences in rates of change in any neuroimaging measure between PLWH and HIV-negative controls (P > .1). Cognitive performance was longitudinally stable in both groups. Conclusions: We found no evidence that middle-aged PLWH, when receiving successful treatment, are at increased risk of accelerated aging-related brain changes or cognitive decline over 2 years.

Structural Brain Abnormalities in Successfully Treated HIV Infection: Associations With Disease and Cerebrospinal Fluid Biomarkers.

Background: Brain structural abnormalities have been reported in persons living with human immunodeficiency virus (HIV; PLWH) who are receiving suppressive combination antiretroviral therapy (cART), but their pathophysiology remains unclear. Methods: We investigated factors associated with brain tissue volumes and white matter microstructure (fractional anisotropy) in 134 PLWH receiving suppressive cART and 79 comparable HIV-negative controls, aged ≥45 years, from the Comorbidity in Relation to AIDS cohort, using multimodal neuroimaging and cerebrospinal fluid biomarkers. Results: Compared with controls, PLWH had lower gray matter volumes (-13.7 mL; 95% confidence interval, -25.1 to -2.2) and fractional anisotropy (-0.0073; 95% confidence interval, -.012 to -.0024), with the largest differences observed in those with prior clinical AIDS. Hypertension and the soluble CD14 concentration in cerebrospinal fluid were associated with lower fractional anisotropy. These associations were independent of HIV serostatus (Pinteraction = .32 and Pinteraction = .59, respectively) and did not explain the greater abnormalities in brain structure in relation to HIV infection. Conclusions: The presence of lower gray matter volumes and more white matter microstructural abnormalities in well-treated PLWH partly reflect a combination of historical effects of AIDS, as well as the more general influence of systemic factors, such as hypertension and ongoing neuroinflammation. Additional mechanisms explaining the accentuation of brain structure abnormalities in treated HIV infection remain to be identified.

Gray and White Matter Abnormalities in Treated Human Immunodeficiency Virus Disease and Their Relationship to Cognitive Function.

BACKGROUND: Long-term comorbidities such as cognitive impairment remain prevalent in otherwise effectively treated people living with human immunodeficiency virus (HIV). We investigate the relationship between cognitive impairment and brain structure in successfully treated patients using multimodal neuroimaging from the Comorbidity in Relation to AIDS (COBRA) cohort. METHODS: Cognitive function, brain tissue volumes, and white matter microstructure were assessed in 134 HIV-infected patients and 79 controls. All patients had suppressed plasma HIV RNA at cohort entry. In addition to comprehensive voxelwise analyses of volumetric and diffusion tensor imaging, we used an unsupervised machine learning approach to combine cognitive, diffusion, and volumetric data, taking advantage of the complementary information they provide. RESULTS: Compared to the highly comparable control group, cognitive function was impaired in 4 of the 6 cognitive domains tested (median global T-scores: 50.8 vs 54.2; P < .001). Patients had lower gray but not white matter volumes, observed principally in regions where structure generally did not correlate with cognitive function. Widespread abnormalities in white matter microstructure were also seen, including reduced fractional anisotropy with increased mean and radial diffusivity. In contrast to the gray matter, these diffusion abnormalities correlated with cognitive function. Multivariate neuroimaging analysis identified a neuroimaging phenotype associated with poorer cognitive function, HIV infection, and systemic immune activation. CONCLUSIONS: Cognitive impairment, lower gray matter volume, and white matter microstructural abnormalities were evident in HIV-infected individuals despite fully suppressive antiretroviral therapy. White matter abnormalities appear to be a particularly important determinant of cognitive dysfunction seen in well-treated HIV-infected individuals.

Goal formulation and tracking in child mental health settings: when is it more likely and is it associated with satisfaction with care?

Goal formulation and tracking may support preference-based care. Little is known about the likelihood of goal formulation and tracking and associations with care satisfaction. Logistic and Poisson stepwise regressions were performed on clinical data for N = 3757 children from 32 services in the UK (M age = 11; SDage = 3.75; most common clinician-reported presenting problem was emotional problems = 55.6%). Regarding the likelihood of goal formulation, it was more likely for pre-schoolers, those with learning difficulties or those with both hyperactivity disorder and conduct disorder. Regarding the association between goal formulation and tracking and satisfaction with care, parents of children with goals information were more likely to report complete satisfaction by scoring at the maximum of the scale. Findings of the present research suggest that goal formulation and tracking may be an important part of patient satisfaction with care. Clinicians should be encouraged to consider goal formulation and tracking when it is clinically meaningful as a means of promoting collaborative practice.

Prediction of hard cardiovascular events in HIV patients.

OBJECTIVES: To assess the accuracy of risk prediction algorithms used in the general population and an HIV-specific algorithm to predict hard cardiovascular events. METHODS: We compared the pooled equation algorithm (PE) proposed by the American Heart Association with the Framingham risk score (FRS) and the HIV-specific DAD (Data Collection on Adverse Effects of Anti-HIV Drugs) algorithm in a cohort of 2550 HIV+ patients followed for 17 337 patient-years. RESULTS: During follow-up we recorded 67 myocardial infarctions and 2 cardiovascular deaths. PE and FRS identified and missed the same number of events (44 of 69 identified by PE and 49 of 69 by FRS). Similarly, DAD and FRS predicted and missed the same number of events (38 of 64 and 44 of 64 identified, respectively). All algorithms showed moderate sensitivity, specificity and positive predictive values, but high negative predictive values. However, PE and DAD identified more patients with no events than FRS (13.8% and 9.3% net reclassification improvement, respectively). CONCLUSIONS: All algorithms showed a modest predictive ability, although the PE and DAD algorithms identified more patients at low risk.

Defining cognitive impairment in people-living-with-HIV: the POPPY study.

BACKGROUND: The reported prevalence of cognitive impairment (CI) varies widely in cohorts of people living with HIV (PLWH); this may partly be due to the use of different diagnostic criteria. Agreement between diagnostic criteria of CI, the optimal definition to use, and associations with patient-reported cognitive symptoms have not been fully investigated. METHODS: Two hundred ninety PLWH aged >50 years and 97 matched negative controls completed a detailed assessment of cognitive function and three questions regarding cognitive symptoms. Age- and education-adjusted test scores (T-scores) determined if subjects met the following definitions of CI: Frascati, global deficit score (GDS) and the multivariate normative comparison (MNC) method. RESULTS: PLWH were more likely than controls to meet each definition of CI (ORs were 2.17, 3.12 and 3.64 for Frascati, GDS and MNC, respectively). Agreement of MNC with Frascati and GDS was moderate (Cohen's k = 0.42 and 0.48, respectively), whereas that between Frascati and GDS was good (k = 0.74). A significant association was found between all the three criteria and reporting of memory loss but not with attention and reasoning problems. The 41 (14 %) PLWH meeting all the three criteria had the lowest median global T-score (36.9) and highest rate of symptom reporting (42 %). CONCLUSIONS: Different CI criteria show fair diagnostic agreement, likely reflecting their ability to exclude CI in the same group of individuals. Given the lower overall cognitive performance and higher rates of symptom reporting in those meeting all three criteria of CI, further work assessing this as a definition of CI in PLWH is justified.

Hospital-Based Influenza and Pneumococcal Vaccination for Cancer Patients on Active Treatment and Their Family Members during the COVID-19 Pandemic in Italy: A Single-Center Experience.

In patients with cancer, tumor- and treatment-induced immunosuppression are responsible for a four-fold increase in morbidity and mortality caused by influenza and invasive Streptococcus pneumoniae infections compared to the general population. The main oncology societies strongly recommend vaccination in patients with cancer to prevent these infections. However, vaccine hesitancy is a main concern in this population. The aim of this study was to assess the feasibility of in-hospital vaccination for patients under anticancer treatment and their family members (FMs) against influenza and pneumococcal infections during the COVID-19 pandemic in order to increase vaccine coverage. This was a single-center, prospective, observational study conducted at the Department of Oncology of Luigi Sacco University Hospital (Milan, Italy) between October 2020 and April 2021. The main primary outcome was the incidence of influenza-like illness (ILI) and pneumococcal infections. The main secondary outcome was safety. A total of 341 subjects were enrolled, including 194 patients with cancer and 147 FMs. The incidence of ILI was higher among patients than among FMs (9% vs. 2.7%, OR 3.92, p = 0.02). Moreover, two subjects were diagnosed with pneumococcal pneumonia. The most frequent vaccine-related AEs were pain in the injection site (31%) and fatigue (8.7%). In conclusion, this hospital-based vaccination strategy was feasible during the COVID-19 pandemic, representing a potential model to maximize vaccine coverage during a public health emergency.

Percutaneous Vertebral Reconstruction (PVR) Technique of Pathological Compression Fractures: An Innovative Combined Treatment of Microwave Ablation, Bilateral Expandable Titanium SpineJack Implants Followed by Vertebroplasty.

(1) Background: to retrospectively evaluate safety and efficacy of combined microwave ablation (MWA) and bilateral expandable titanium SpineJack (SJ) implants followed by vertebroplasty (VP) for the treatment of painful thoracolumbar pathological vertebral compression fracture. (2) Methods: from July 2017 to October 2022, twenty-eight patients (13 women and 15 men; mean age 68 ± 11 years) with a history of primary neoplasm and thirty-six painful vertebral metastases with vertebral compression fracture underwent combined MWA and bilateral expandable titanium SpineJack implants with vertebroplasty. We analyzed safety through complications rate, and efficacy through vertebral height restoration and pain decrease, evaluated using a visual analogue scale (VAS), and Functional Mobility Scale (FMS), and local tumor control. Contrast-enhanced CT scans were performed at 1, 3, and 6 months and a contrast-enhanced spine MRI at 6 months after the procedure. (3) Results: Technical success rate was 100%. No procedure-related major complications or death occurred. Vertebral height restoration was observed in 22 levels (58%), with a mean anterior height restoration of 2.6 mm ± 0.6 and a mean middle height restoration of 4.4 mm ± 0.6 (p < 0.001). Mean VAS score of pain evaluation on the day before treatment was 6.3 ± 1.5 (range 4-9). At the 6-month evaluation, the median VAS score for pain was 0.4 ± 0.6 (range 0-2) with a mean reduction of 93.65% (6.8 ± 0.7 vs. 0.4 ± 0.6; p < 0.000) compared with baseline evaluation. Contrast-enhanced CT scans were performed at 1, 3, and 6 months and a contrast-enhanced spine MRI was performed at 6 months after the procedure, showing no local recurrence, implant displacement, or new fractures in the treated site. (4) Conclusions: combined microwave ablation and bilateral expandable titanium SpineJack implants with vertebroplasty is a safe and effective procedure for the treatment of pathological compressive vertebral fractures. The vertebral stabilization achieved early and persistent pain relief, increasing patient mobility, improving recovery of walking capacity, and providing local tumor control.

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.

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.

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.