Poverty and neighborhood opportunity effects on neonate DNAm developmental age.

BACKGROUND: Children from families with low socioeconomic status (SES), as determined by income, experience several negative outcomes, such as higher rates of newborn mortality and behavioral issues. Moreover, associations between DNA methylation and low income or poverty status are evident beginning at birth, suggesting prenatal influences on offspring development. Recent evidence suggests neighborhood opportunities may protect against some of the health consequences of living in low income households. The goal of this study was to assess whether neighborhood opportunities moderate associations between household income (HI) and neonate developmental maturity as measured with DNA methylation. METHODS: Umbilical cord blood DNA methylation data was available in 198 mother-neonate pairs from the larger CANDLE cohort. Gestational age acceleration was calculated using an epigenetic clock designed for neonates. Prenatal HI and neighborhood opportunities measured with the Childhood Opportunity Index (COI) were regressed on gestational age acceleration controlling for sex, race, and cellular composition. RESULTS: Higher HI was associated with higher gestational age acceleration (B = .145, t = 4.969, p = 1.56x10-6, 95% CI [.087, .202]). Contrary to expectation, an interaction emerged showing higher neighborhood educational opportunity was associated with lower gestational age acceleration at birth for neonates with mothers living in moderate to high HI (B = -.048, t = -2.08, p = .03, 95% CI [-.092, -.002]). Female neonates showed higher gestational age acceleration at birth compared to males. However, within males, being born into neighborhoods with higher social and economic opportunity was associated with higher gestational age acceleration. CONCLUSION: Prenatal HI and neighborhood qualities may affect gestational age acceleration at birth. Therefore, policy makers should consider neighborhood qualities as one opportunity to mitigate prenatal developmental effects of HI.

Ising meson spectroscopy on a noisy digital quantum simulator.

Quantum simulation has the potential to be an indispensable technique for the investigation of non-perturbative phenomena in strongly-interacting quantum field theories (QFTs). In the modern quantum era, with Noisy Intermediate Scale Quantum (NISQ) simulators widely available and larger-scale quantum machines on the horizon, it is natural to ask: what non-perturbative QFT problems can be solved with the existing quantum hardware? We show that existing noisy quantum machines can be used to analyze the energy spectrum of several strongly-interacting 1+1D QFTs, which exhibit non-perturbative effects like 'quark confinement' and 'false vacuum decay'. We perform quench experiments on IBM's quantum simulators to compute the energy spectrum of 1+1D quantum Ising model with a longitudinal field. Our results demonstrate that digital quantum simulation in the NISQ era has the potential to be a viable alternative to numerical techniques such as density matrix renormalization group or the truncated conformal space methods for analyzing QFTs.

Single-stranded DNA binding protein hitches a ride with the Escherichia coli YoaA-χ helicase.

The Escherichia coli XPD/Rad3-like helicase, YoaA, and DNA polymerase III subunit, χ, are involved in E. coli DNA damage tolerance and repair. YoaA and χ promote tolerance to the DNA chain-terminator, 3 -azidothymidine (AZT), and together form the functional helicase complex, YoaA-χ. How YoaA-χ contributes to DNA damage tolerance is not well understood. E. coli single-stranded DNA binding protein (SSB) accumulates at stalled replication forks, and the SSB-χ interaction is required to promote AZT tolerance via an unknown mechanism. YoaA-χ and SSB interactions were investigated in vitro to better understand this DNA damage tolerance mechanism, and we discovered YoaA-χ and SSB have a functional interaction. SSB confers a substrate-specific effect on the helicase activity of YoaA-χ, barely affecting YoaA-χ on an overhang DNA substrate but inhibiting YoaA-χ on forked DNA. A paralog helicase, DinG, unwinds SSB-bound DNA in a similar manner to YoaA-χ on the substrates tested. Through use of ensemble experiments, we believe SSB binds behind YoaA-χ relative to the DNA ds/ss junction and show via single-molecule assays that SSB translocates along ssDNA with YoaA-χ. This is, to our knowledge, the first demonstration of a mechanoenzyme pulling SSB along ssDNA.

Feasibility of remote monitoring for fatal coronary heart disease using Apple Watch ECGs.

Background: Fatal coronary heart disease (FCHD) is often described as sudden cardiac death (affects >4 million people/year), where coronary artery disease is the only identified condition. Electrocardiographic artificial intelligence (ECG-AI) models for FCHD risk prediction using ECG data from wearable devices could enable wider screening/monitoring efforts. Objectives: To develop a single-lead ECG-based deep learning model for FCHD risk prediction and assess concordance between clinical and Apple Watch ECGs. Methods: An FCHD single-lead ("lead I" from 12-lead ECGs) ECG-AI model was developed using 167,662 ECGs (50,132 patients) from the University of Tennessee Health Sciences Center. Eighty percent of the data (5-fold cross-validation) was used for training and 20% as a holdout. Cox proportional hazards (CPH) models incorporating ECG-AI predictions with age, sex, and race were also developed. The models were tested on paired clinical single-lead and Apple Watch ECGs from 243 St. Jude Lifetime Cohort Study participants. The correlation and concordance of the predictions were assessed using Pearson correlation (R), Spearman correlation (ρ), and Cohen's kappa. Results: The ECG-AI and CPH models resulted in AUC = 0.76 and 0.79, respectively, on the 20% holdout and AUC = 0.85 and 0.87 on the Atrium Health Wake Forest Baptist external validation data. There was moderate-strong positive correlation between predictions (R = 0.74, ρ = 0.67, and κ = 0.58) when tested on the 243 paired ECGs. The clinical (lead I) and Apple Watch predictions led to the same low/high-risk FCHD classification for 99% of the participants. CPH prediction correlation resulted in an R = 0.81, ρ = 0.76, and κ = 0.78. Conclusion: Risk of FCHD can be predicted from single-lead ECGs obtained from wearable devices and are statistically concordant with lead I of a 12-lead ECG.

Structure- and Property-Based Optimization of Efficient Pan-Bromodomain and Extra Terminal Inhibitors to Identify Oral and Intravenous Candidate I-BET787.

The bromodomain and extra terminal (BET) family of bromodomain-containing proteins are important epigenetic regulators that elicit their effect through binding histone tail N-acetyl lysine (KAc) post-translational modifications. Recognition of such markers has been implicated in a range of oncology and immune diseases and, as such, small-molecule inhibition of the BET family bromodomain-KAc protein-protein interaction has received significant interest as a therapeutic strategy, with several potential medicines under clinical evaluation. This work describes the structure- and property-based optimization of a ligand and lipophilic efficient pan-BET bromodomain inhibitor series to deliver candidate I-BET787 (70) that demonstrates efficacy in a mouse model of inflammation and suitable properties for both oral and intravenous (IV) administration. This focused two-phase explore-exploit medicinal chemistry effort delivered the candidate molecule in 3 months with less than 100 final compounds synthesized.

DNA-Templated Nanofabrication of CdS-Au Nanoscale Schottky Contacts and Electrical Characterization.

DNA-templated nanofabrication presents an innovative approach to creating self-assembled nanoscale metal-semiconductor-based Schottky contacts, which can advance nanoelectronics. Herein, we report the successful fabrication of metal-semiconductor Schottky contacts using a DNA origami scaffold. The scaffold, consisting of DNA strands organized into a specific linear architecture, facilitates the competitive arrangement of Au and CdS nanorods, forming heterojunctions, and addresses previous limitations in low electrical conductance making DNA-templated electronics with semiconductor nanomaterials. Electroless gold plating extends the Au nanorods and makes the necessary electrical contacts. Tungsten electrical connection lines are further created by electron beam-induced deposition. Electrical characterization reveals nonlinear Schottky barrier behavior, with electrical conductance ranging from 0.5 × 10-4 to 1.7 × 10-4 S. The conductance of these DNA-templated junctions is several million times higher than with our prior Schottky contacts. Our research establishes an innovative self-assembly approach with applicable metal and semiconductor materials for making highly conductive nanoscale Schottky contacts, paving the way for the future development of DNA-based nanoscale electronics.

Discovery of ITI-333, a Novel Orally Bioavailable Molecule Targeting Multiple Receptors for the Treatment of Pain and Other Disorders.

Development of more efficacious medications with improved safety profiles to manage and treat multiple forms of pain is a critical element of healthcare. To this end, we have designed and synthesized a novel class of tetracyclic pyridopyrroloquinoxalinone derivatives with analgesic properties. The receptor binding profiles and analgesic properties of these tetracyclic compounds were studied. Systematic optimizations of this novel scaffold culminated in the discovery of the clinical candidate, (6bR,10aS)-8-[3-(4-fluorophenoxy)propyl]-6b,7,8,9,10,10a-hexahydro-1H-pyrido[3',4':4,5]pyrrolo[1,2,3-de]quinoxalin-2(3H)-one (compound 5, ITI-333), which exhibited potent binding affinity to serotonin 5-HT2A (Ki = 8.3 nM) and µ-opioid receptors (MOR, Ki = 11 nM) and moderate affinity to adrenergic α1A (Ki = 28 nM) and dopamine D1 (Ki = 50 nM) receptors. ITI-333 acts as a 5-HT2A receptor antagonist, a MOR partial agonist, and an adrenergic α1A receptor antagonist. ITI-333 exhibited dose-dependent analgesic effects in rodent models of acute pain. Currently, this investigational new drug is in phase I clinical development.

Pharmacologic profile of ITI-333: a novel molecule for treatment of substance use disorders.

RATIONALE: Medications are urgently needed to treat symptoms of drug withdrawal and mitigate dysphoria and psychiatric comorbidities that drive opioid abuse and relapse. ITI-333 is a novel molecule in development for treatment of substance use disorders, psychiatric comorbidities, and pain. OBJECTIVE: Characterize the preclinical profile of ITI-333 using pharmacological, behavioral, and physiological assays. METHODS: Cell-based assays were used to measure receptor binding and intrinsic efficacy of ITI-333; animal models were employed to assess effects on opioid reinstatement, precipitated oxycodone withdrawal, and drug abuse liability. RESULTS: In vitro, ITI-333 is a potent 5-HT2A receptor antagonist (Ki = 8 nM) and a biased, partial agonist at µ-opioid (MOP) receptors (Ki = 11 nM; lacking ß-arrestin agonism) with lesser antagonist activity at adrenergic α1A (Ki = 28 nM) and dopamine D1 (Ki = 50 nM) receptors. In vivo, ITI-333 blocks 5-HT2A receptor-mediated head twitch and MOP receptor-mediated effects on motor hyperactivity in mice. ITI-333 alone is a naloxone-sensitive analgesic (mice) which suppresses somatic signs of naloxone-precipitated oxycodone withdrawal (mice) and heroin cue-induced reinstatement responding without apparent tolerance or physical dependence after chronic dosing (rats). ITI-333 did not acutely impair gastrointestinal or pulmonary function (rats) and was not intravenously self-administered by heroin-maintained rats or rhesus monkeys. CONCLUSIONS: ITI-333 acts as a potent 5-HT2A receptor antagonist, as well a biased MOP receptor partial agonist with low intrinsic efficacy. ITI-333 mitigates opioid withdrawal/reinstatement, supporting its potential utility as a treatment for OUD.

Lion lords and sharing hyaenas: Carnivore guild dynamics around elephant carcasses.

Megaherbivore carcasses represent sporadic but energetically rewarding resources for carnivores, offering a unique opportunity to study coexistence dynamics between facultative scavengers. South African fenced protected areas, such as Madikwe Game Reserve (Madikwe hereafter), host viable populations of large carnivores and high densities of elephants, Loxodonta africana. However, high carnivore densities can lead to potentially fatal interspecific encounters and increased competition, particularly around high-quality trophic resources. This study explores the temporal partitioning and co-detection strategies of carnivores at six elephant carcasses in Madikwe, aiming to understand how the increased carrion biomass available at elephant carcasses influences coexistence dynamics. Camera traps were deployed to monitor carcasses during two periods (2019 and 2020), revealing occurrences of six carnivore species. Carnivores, particularly black-backed jackals, Lupulella mesomelas, (hereafter jackal), lions, Panthera leo, and spotted hyaenas, Crocuta crocuta, comprised 56.7% of carcass observations, highlighting their pivotal roles in scavenging dynamics. Pairwise co-detection analysis demonstrated consistent association and shared peak activity periods between jackals and spotted hyaenas, indicating potential resource sharing. However, the minimal co-detection rates between lions and other carnivores highlight their resource domination. There was some evidence of temporal partitioning between carnivores, with most species exhibiting earlier peaks in nocturnal activity to avoid temporal overlap with lions. This study emphasises the importance of elephant carcasses in the diet of multiple species and coexistence techniques utilised to exploit this ephemeral resource. As fenced protected areas become crucial for conserving intact carnivore guilds globally, further research into carnivore behavioural adaptations at carcasses is recommended to shed light on their coexistence strategies.

GSDMB/ORMDL3 Rare/Common Variants Are Associated with Inhaled Corticosteroid Response among Children with Asthma.

Inhaled corticosteroids (ICS) are efficacious in the treatment of asthma, which affects more than 300 million people in the world. While genome-wide association studies have identified genes involved in differential treatment responses to ICS in asthma, few studies have evaluated the effects of combined rare and common variants on ICS response among children with asthma. Among children with asthma treated with ICS with whole exome sequencing (WES) data in the PrecisionLink Biobank (91 White and 20 Black children), we examined the effect and contribution of rare and common variants with hospitalizations or emergency department visits. For 12 regions previously associated with asthma and ICS response (DPP10, FBXL7, NDFIP1, TBXT, GLCCI1, HDAC9, TBXAS1, STAT6, GSDMB/ORMDL3, CRHR1, GNGT2, FCER2), we used the combined sum test for the sequence kernel association test (SKAT) adjusting for age, sex, and BMI and stratified by race. Validation was conducted in the Biorepository and Integrative Genomics (BIG) Initiative (83 White and 134 Black children). Using a Bonferroni threshold for the 12 regions tested (i.e., 0.05/12 = 0.004), GSDMB/ORMDL3 was significantly associated with ICS response for the combined effect of rare and common variants (p-value = 0.003) among White children in the PrecisionLink Biobank and replicated in the BIG Initiative (p-value = 0.02). Using WES data, the combined effect of rare and common variants for GSDMB/ORMDL3 was associated with ICS response among asthmatic children in the PrecisionLink Biobank and replicated in the BIG Initiative. This proof-of-concept study demonstrates the power of biobanks of pediatric real-life populations in asthma genomic investigations.

Co-occurring psychological distress and alcohol or other drug use among Indigenous Australians: Data from the National Aboriginal and Torres Strait Islander Health Survey.

OBJECTIVES: To determine the prevalence and demographic, social and health characteristics associated with co-occurring psychological distress symptoms, risky alcohol and/or substance use among a national sample of Aboriginal and Torres Strait Islander people aged 15 years or older. METHODS: This study uses secondary cross-sectional data from the 2018-19 National Aboriginal and Torres Strait Islander Health Survey (NATSIHS). Data were collected via face-to-face interviews with those living in private dwellings across Australia. Participants were Aboriginal and Torres Strait Islander people (n = 10,579) aged 15 years or older. Data pertaining to psychological distress, alcohol and substance use were obtained and weighted to represent the total population of Aboriginal and Torres Strait Islander people in Australia. RESULTS: A total of 20.3% participants were found to have co-occurring psychological distress, risky alcohol use and/or substance use, and 4.0% reported co-occurrence of all three conditions. Female participants in a registered marriage and fully engaged in study or employment had lower rates of co-occurring conditions. Poorer self-rated health, one or more chronic conditions and increased experiences of unfair treatment and physical harm in the past 12 months were associated with increased rates of co-occurring conditions. CONCLUSION: A range of potential risk and protective factors were identified for co-occurring psychological distress, risky alcohol and/or substance use among Aboriginal and Torres Strait Islander people. This information is critical for planning effective holistic strategies to decrease the burden of suffering imposed upon the individual, family and community members impacted by co-occurring conditions.

First record of Arionvulgaris Moquin-Tandon, 1855 (Arionidae) from Armenia.

Background: Arionvulgaris Moquin-Tandon, 1855 is amongst the fastest-spreading terrestrial slugs Europe-wide. In recent years, it has been recorded in Canada, Mexico and continues to expand eastwards into Eurasia. Renowned for its high invasiveness, combatting its swift spread creates significant challenges in organising effective preventative measures. New information: This study presents the first record of Arionvulgaris from Armenia, which is the second record of this species' invasion of the Caucasus. In 2022, a substantial population of A.vulgaris was observed close to the City of Stepanavan, which is also the first record in Armenia of the family Arionidae. How the species was introduced to Armenia remains unknown. Identification of Arionvulgaris was conducted, based on external and genital morphology and mitochondrial CO1 (cytochrome c oxidase subunit 1) gene sequencing, revealing notable similarities with Central European clades. Our results confirm the introduction and distribution of A.vulgaris to Armenia. Invasion of such species into Armenia will require additional monitoring and would be aided by further research on Armenia's mollusc fauna in the future.

Stigma Related to the Non-Medical Use and Diversion of Prescription Stimulant Drugs: Should We Care.

BACKGROUND: Non-medical use (NMU) and diversion of prescription stimulants are prevalent on college campuses. Diversion represents a primary source of acquisition for NMU among young adults. This study examined relationships between stigmatizing beliefs related to NMU and diversion of stimulant medications and engagement in these behaviors, as well as how such perceptions are associated with indicators of psychological distress among those who engage in these behaviors. METHODS: Young adults (N = 384) were recruited from a large US university to participate in this cross-sectional electronic survey-based study. Relationships between stigma variables and NMU and diversion were assessed. Among those who engage in NMU and diversion, we tested relationships between stigma variables and indicators of psychological distress, using validated instruments. RESULTS: Perceived social and personal stigmatic beliefs did not significantly predict NMU. However, perceived social and personal stigma of diversion significantly reduced diversion likelihood. For NMU, associations were found between stigma variables and indicators of psychological distress. Markedly, we found that as stigmatic perceptions of NMU increased, so did depressive, anxiolytic, and suicidal symptomatology among those who engage in NMU. CONCLUSIONS: Stigmatization does not deter NMU; however, stigmatization is positively associated with psychological harm among those who engage in NMU. Interventions should be developed to reduce stigmatization in order to improve psychological health among those who engage in NMU. Stigmatic perceptions of diversion were not predictive of psychological harm, though they are negatively associated with diversion behavior.

Evolution of wing shape in geometrid moths: phylogenetic effects dominate over ecology.

Locomotory performance is an important determinant of fitness in most animals, including flying insects. Strong selective pressures on wing morphology are therefore expected. Previous studies on wing shape in Lepidoptera have found some support for hypotheses relating wing shape to environment-specific selective pressures on aerodynamic performance. Here, we present a phylogenetic comparative study on wing shape in the lepidopteran family Geometridae, covering 374 species of the northern European fauna. We focused on 11 wing traits including aspect ratio, wing roundness, and the pointedness of the apex, as well as the ratio of forewing and hindwing areas. All measures were taken from images available on the internet, using a combination of tools available in Fiji software and R. We found that wing shape demonstrates a phylogenetically conservative pattern of evolution in Geometridae, showing similar or stronger phylogenetic signal than many of its potential predictors. Several wing traits showed statistically significant associations with predictors such as body size, phenology, and preference for forest habitats. Overall, however, all of these associations remained notably weak, with no wing shape being excluded for any value of the predictors, including body size. We conclude that, in geometrids, wing traits do not readily respond to selective pressures optimizing aerodynamic performance of the moths in different environments. Selection on wing shape may nevertheless operate through other functions of the wings, with the effectiveness of crypsis at rest being a promising candidate for further studies.

Ex vivo lung perfusion in donation after circulatory death: A post hoc analysis of the Normothermic Ex Vivo Lung Perfusion as an Assessment of Extended/Marginal Donors Lungs trial.

OBJECTIVE: Donation after circulatory death (DCD) donors offer the ability to expand the lung donor pool and ex vivo lung perfusion (EVLP) further contributes to this ability by allowing for additional evaluation and resuscitation of these extended criteria donors. We sought to determine the outcomes of recipients receiving organs from DCD EVLP donors in a multicenter setting. METHODS: This was an unplanned post hoc analysis of a multicenter, prospective, nonrandomized trial that took place during 2011 to 2017 with 3 years of follow-up. Patients were placed into 3 groups based off procurement strategy: brain-dead donor (control), brain-dead donor evaluated by EVLP, and DCD donors evaluated by EVLP. The primary outcomes were severe primary graft dysfunction at 72 hours and survival. Secondary outcomes included select perioperative outcomes, and 1-year and 3-years allograft function and quality of life measures. RESULTS: The DCD EVLP group had significantly higher incidence of severe primary graft dysfunction at 72 hours (P = .03), longer days on mechanical ventilation (P < .001) and in-hospital length of stay (P = .045). Survival at 3 years was 76.5% (95% CI, 69.2%-84.7%) for the control group, 68.3% (95% CI, 58.9%-79.1%) for the brain-dead donor group, and 60.7% (95% CI, 45.1%-81.8%) for the DCD group (P = .36). At 3-year follow-up, presence observed bronchiolitis obliterans syndrome or quality of life metrics did not differ among the groups. CONCLUSIONS: Although DCD EVLP allografts might not be appropriate to transplant in every candidate recipient, the expansion of their use might afford recipients stagnant on the waitlist a viable therapy.

Control of cell proliferation by memories of mitosis.

Mitotic duration is tightly constrained, and extended mitosis is characteristic of problematic cells prone to chromosome missegregation and genomic instability. We show here that mitotic extension leads to the formation of p53-binding protein 1 (53BP1)-ubiquitin-specific protease 28 (USP28)-p53 protein complexes that are transmitted to, and stably retained by, daughter cells. Complexes assembled through a Polo-like kinase 1-dependent mechanism during extended mitosis and elicited a p53 response in G1 that prevented the proliferation of the progeny of cells that experienced an approximately threefold extended mitosis or successive less extended mitoses. The ability to monitor mitotic extension was lost in p53-mutant cancers and some p53-wild-type (p53-WT) cancers, consistent with classification of TP53BP1 and USP28 as tumor suppressors. Cancers retaining the ability to monitor mitotic extension exhibited sensitivity to antimitotic agents.

Demographic patterns of walleye (Sander vitreus) reproductive success in a Wisconsin population.

Harvest in walleye Sander vitreus fisheries is size-selective and could influence phenotypic traits of spawners; however, contributions of individual spawners to recruitment are unknown. We used parentage analyses using single nucleotide polymorphisms to test whether parental traits were related to the probability of offspring survival in Escanaba Lake, Wisconsin. From 2017 to 2020, 1339 adults and 1138 juveniles were genotyped and 66% of the offspring were assigned to at least one parent. Logistic regression indicated the probability of reproductive success (survival of age-0 to first fall) was positively (but weakly) related to total length and growth rate in females, but not age. No traits analyzed were related to reproductive success for males. Our analysis identified the model with the predictors' growth rate and year for females and the models with year and age and year for males as the most likely models to explain variation in reproductive success. Our findings indicate that interannual variation (i.e., environmental conditions) likely plays a key role in determining the probability of reproductive success in this population and provide limited support that female age, length, and growth rate influence recruitment.

Advancing the care of individuals with cancer through innovation & technology: Proceedings from the cardiology oncology innovation summit 2020 and 2021.

As cancer therapies increase in effectiveness and patients' life expectancies improve, balancing oncologic efficacy while reducing acute and long-term cardiovascular toxicities has become of paramount importance. To address this pressing need, the Cardiology Oncology Innovation Network (COIN) was formed to bring together domain experts with the overarching goal of collaboratively investigating, applying, and educating widely on various forms of innovation to improve the quality of life and cardiovascular healthcare of patients undergoing and surviving cancer therapies. The COIN mission pillars of innovation, collaboration, and education have been implemented with cross-collaboration among academic institutions, private and public establishments, and industry and technology companies. In this report, we summarize proceedings from the first two annual COIN summits (inaugural in 2020 and subsequent in 2021) including educational sessions on technological innovations for establishing best practices and aligning resources. Herein, we highlight emerging areas for innovation and defining unmet needs to further improve the outcome for cancer patients and survivors of all ages. Additionally, we provide actionable suggestions for advancing innovation, collaboration, and education in cardio-oncology in the digital era.

AI-based preeclampsia detection and prediction with electrocardiogram data.

Introduction: More than 76,000 women die yearly from preeclampsia and hypertensive disorders of pregnancy. Early diagnosis and management of preeclampsia can improve outcomes for both mother and baby. In this study, we developed artificial intelligence models to detect and predict preeclampsia from electrocardiograms (ECGs) in point-of-care settings. Methods: Ten-second 12-lead ECG data was obtained from two large health care settings: University of Tennessee Health Science Center (UTHSC) and Atrium Health Wake Forest Baptist (AHWFB). UTHSC data was split into 80% training and 20% holdout data. The model used a modified ResNet convolutional neural network, taking one-dimensional raw ECG signals comprising 12 channels as an input, to predict risk of preeclampsia. Sub-analyses were performed to assess the predictive accuracy for preeclampsia prediction within 30, 60, or 90 days before diagnosis. Results: The UTHSC cohort included 904 ECGs from 759 females (78.8% African American) with a mean ± sd age of 27.3 ± 5.0 years. The AHWFB cohort included 817 ECGs from 141 females (45.4 African American) with a mean ± sd age of 27.4 ± 5.9 years. The cross-validated ECG-AI model yielded an AUC (95% CI) of 0.85 (0.77-0.93) on UTHSC holdout data, and an AUC (95% CI) of 0.81 (0.77-0.84) on AHWFB data. The sub-analysis of different time windows before preeclampsia prediction resulted in AUCs (95% CI) of 0.92 (0.84-1.00), 0.89 (0.81-0.98) and 0.90 (0.81-0.98) when tested on ECGs 30 days, 60 days and 90 days, respectively, before diagnosis. When assessed on early onset preeclampsia (preeclampsia diagnosed at <34 weeks of pregnancy), the model's AUC (95% CI) was 0.98 (0.89-1.00). Discussion: We conclude that preeclampsia can be identified with high accuracy via application of AI models to ECG data.

Development and validation of an electrocardiographic artificial intelligence model for detection of peripartum cardiomyopathy.

BACKGROUND: This study used electrocardiogram data in conjunction with artificial intelligence methods as a noninvasive tool for detecting peripartum cardiomyopathy. OBJECTIVE: This study aimed to assess the efficacy of an artificial intelligence-based heart failure detection model for peripartum cardiomyopathy detection. STUDY DESIGN: We first built a deep-learning model for heart failure detection using retrospective data at the University of Tennessee Health Science Center. Cases were adult and nonpregnant female patients with a heart failure diagnosis; controls were adult nonpregnant female patients without heart failure. The model was then tested on an independent cohort of pregnant women at the University of Tennessee Health Science Center with or without peripartum cardiomyopathy. We also tested the model in an external cohort of pregnant women at Atrium Health Wake Forest Baptist. Key outcomes were assessed using the area under the receiver operating characteristic curve. We also repeated our analysis using only lead I electrocardiogram as an input to assess the feasibility of remote monitoring via wearables that can capture single-lead electrocardiogram data. RESULTS: The University of Tennessee Health Science Center heart failure cohort comprised 346,339 electrocardiograms from 142,601 patients. In this cohort, 60% of participants were Black and 37% were White, with an average age (standard deviation) of 53 (19) years. The heart failure detection model achieved an area under the curve of 0.92 on the holdout set. We then tested the ability of the heart failure model to detect peripartum cardiomyopathy in an independent University of Tennessee Health Science Center cohort of pregnant women and an external Atrium Health Wake Forest Baptist cohort of pregnant women. The independent University of Tennessee Health Science Center cohort included 158 electrocardiograms from 115 patients; our deep-learning model achieved an area under the curve of 0.83 (0.77-0.89) for this data set. The external Atrium Health Wake Forest Baptist cohort involved 80 electrocardiograms from 43 patients; our deep-learning model achieved an area under the curve of 0.94 (0.91-0.98) for this data set. For identifying peripartum cardiomyopathy diagnosed ≥10 days after delivery, the model achieved an area under the curve of 0.88 (0.81-0.94) for the University of Tennessee Health Science Center cohort and of 0.96 (0.93-0.99) for the Atrium Health Wake Forest Baptist cohort. When we repeated our analysis by building a heart failure detection model using only lead-I electrocardiograms, we obtained similarly high detection accuracies, with areas under the curve of 0.73 and 0.93 for the University of Tennessee Health Science Center and Atrium Health Wake Forest Baptist cohorts, respectively. CONCLUSION: Artificial intelligence can accurately detect peripartum cardiomyopathy from electrocardiograms alone. A simple electrocardiographic artificial intelligence-based peripartum screening could result in a timelier diagnosis. Given that results with 1-lead electrocardiogram data were similar to those obtained using all 12 leads, future studies will focus on remote screening for peripartum cardiomyopathy using smartwatches that can capture single-lead electrocardiogram data.