Unsupervised deep learning of electrocardiograms enables scalable human disease profiling.

The 12-lead electrocardiogram (ECG) is inexpensive and widely available. Whether conditions across the human disease landscape can be detected using the ECG is unclear. We developed a deep learning denoising autoencoder and systematically evaluated associations between ECG encodings and ~1,600 Phecode-based diseases in three datasets separate from model development, and meta-analyzed the results.

PARG inhibition induces nuclear aggregation of PARylated PARP1.

Poly (ADP-ribose) glycohydrolase (PARG) inhibitors are currently under clinical development for the treatment of DNA repair-deficient cancers; however, their precise mechanism of action is still unclear. Here, we report that PARG inhibition leads to excessive PARylated poly (ADP-ribose) polymerase 1 (PARP1) reducing the ability of PARP1 to properly localize to sites of DNA damage. Strikingly, the mis-localized PARP1 accumulates as aggregates throughout the nucleus.

Genetic Architectures of Medical Images Revealed by Registration of Multiple Modalities.

The advent of biobanks with vast quantities of medical imaging and paired genetic measurements creates huge opportunities for a new generation of genotype-phenotype association studies. However, disentangling biological signals from the many sources of bias and artifacts remains difficult. Using diverse medical images and time-series (ie, magnetic resonance imagings [MRIs], electrocardiograms [ECGs], and dual-energy X-ray absorptiometries [DXAs]), we show how registration, both spatial and temporal, guided by domain knowledge or learned , helps uncover biological information.

Consider this a WARNing.

Atrial fibrillation (AF) prediction can be valuable at many timescales and in many populations. In this issue of , Gavidia et al. train a model called WARN for short-term prediction of AF in the timescale of minutes in patients wearing 24-h continuous Holter electrocardiograms.

NAPRT Silencing in FH-Deficient Renal Cell Carcinoma Confers Therapeutic Vulnerabilities via NAD+ Depletion.

Hereditary leiomyomatosis and renal cell carcinoma (HLRCC) is caused by loss of function mutations in fumarate hydratase (FH) and results in an aggressive subtype of renal cell carcinoma with limited treatment options. Loss of FH leads to accumulation of fumarate, an oncometabolite that disrupts multiple cellular processes and drives tumor progression. High levels of fumarate inhibit alpha ketoglutarate-dependent dioxygenases, including the ten-eleven translocation (TET) enzymes, and can lead to global DNA hypermethylation.

Trajectories of sentiment in 11,816 psychoactive narratives.

Objective: Can machine learning (ML) enable data-driven discovery of how changes in sentiment correlate with different psychoactive experiences? We investigate by training models directly on text testimonials from a diverse 52-drug pharmacopeia.

Methods: Using large language models (i.e.

Cross-modal autoencoder framework learns holistic representations of cardiovascular state.

A fundamental challenge in diagnostics is integrating multiple modalities to develop a joint characterization of physiological state. Using the heart as a model system, we develop a cross-modal autoencoder framework for integrating distinct data modalities and constructing a holistic representation of cardiovascular state. In particular, we use our framework to construct such cross-modal representations from cardiac magnetic resonance images (MRIs), containing structural information, and electrocardiograms (ECGs), containing myoelectric information.

Artificial intelligence-enabled classification of hypertrophic heart diseases using electrocardiograms.

Background: Differentiating among cardiac diseases associated with left ventricular hypertrophy (LVH) informs diagnosis and clinical care.

Objective: To evaluate if artificial intelligence-enabled analysis of the 12-lead electrocardiogram (ECG) facilitates automated detection and classification of LVH.

Methods: We used a pretrained convolutional neural network to derive numerical representations of 12-lead ECG waveforms from patients in a multi-institutional healthcare system who had cardiac diseases associated with LVH (n = 50,709), including cardiac amyloidosis (n = 304), hypertrophic cardiomyopathy (n = 1056), hypertension (n = 20,802), aortic stenosis (n = 446), and other causes (n = 4766).

COVID-19-Related Changes to Drug-Selling Networks and Their Effects on People Who Use Illicit Opioids.

Objective: The COVID-19 pandemic has significantly affected people's ability to buy, sell, and obtain items that they use in their daily lives. It may have had a particularly negative effect on the ability of people who use illicit opioids to obtain them because the networks they relied on are illicit and not part of the formal economy. Our objective in this research was to examine if, and how, disruptions related to COVID-19 of illicit opioid markets have affected people who use illicit opioids.

Targeting Krebs-cycle-deficient renal cell carcinoma with Poly ADP-ribose polymerase inhibitors and low-dose alkylating chemotherapy.

Loss-of-function mutations in genes encoding the Krebs cycle enzymes Fumarate Hydratase () and Succinate Dehydrogenase () induce accumulation of fumarate and succinate, respectively and predispose patients to hereditary cancer syndromes including the development of aggressive renal cell carcinoma (RCC). Fumarate and succinate competitively inhibit αKG-dependent dioxygenases, including Lysine-specific demethylase 4A/B (KDM4A/B), leading to suppression of the homologous recombination (HR) DNA repair pathway. In this study, we have developed new syngeneic - and -deficient murine models of RCC, which demonstrate the expected accumulation of fumarate and succinate, alterations in the transcriptomic and methylation profile, and an increase in unresolved DNA double-strand breaks (DSBs).

Application of Distributed Agent-based Modeling to Investigate Opioid Use Outcomes in Justice Involved Populations.

Criminal justice involved (CJI) individuals with a history of opioid use disorder (OUD) are at high risk of overdose and death in the weeks following release from jail. We developed the Justice-Community Circulation Model (JCCM) to investigate OUD/CJI dynamics post-release and the effects of interventions on overdose deaths. The JCCM uses a synthetic agent-based model population of approximately 150,000 unique individuals that is generated using demographic information collected from multiple Chicago-area studies and data sets.

Utility of Point-of-Care Lung Ultrasonography for Evaluating Acute Chest Syndrome in Young Patients With Sickle Cell Disease.

Study Objective: Acute chest syndrome is a leading cause of mortality in patients with sickle cell disease (SCD). Because early detection of acute chest syndrome is directly tied to prognosis, young patients with SCD undergo countless chest radiography screenings throughout their lifetime for commonly occurring acute chest syndrome risk factors such as fever, chest pain, or cough. Chest radiography is not an ideal screening method because it is associated with radiation exposure, which accumulates with repeated imaging.

Rural risk environments, opioid-related overdose, and infectious diseases: A multidimensional, spatial perspective.

Background: Much remains unknown in rural risk environments, despite a growing crisis in these areas. We adapt a risk environment framework to characterize rural southern Illinois and describe the relations of risk environments, opioid-related overdose, HIV, Hepatitis C, and sexually transmitted infection rates between 2015 and 2017.

Methods: Over two dozen risk environment variables are summarized across zip-code (n = 128) or county levels (n = 16) based on availability and theoretical relevance.

Lean and deep models for more accurate filtering of SNP and INDEL variant calls.

Summary: We investigate convolutional neural networks (CNNs) for filtering small genomic variants in short-read DNA sequence data. Errors created during sequencing and library preparation make variant calling a difficult task. Encoding the reference genome and aligned reads covering sites of genetic variation as numeric tensors allows us to leverage CNNs for variant filtration.

'Like Skydiving without a Parachute': How Class Origin Shapes Occupational Trajectories in British Acting.

There is currently widespread concern that access to, and success within, the British acting profession is increasingly dominated by those from privileged class origins. This article seeks to empirically interrogate this claim using data on actors from the Great British Class Survey ( = 404) and 47 qualitative interviews. First, survey data demonstrate that actors from working-class origins are significantly underrepresented within the profession.

High enhancer, downer, withdrawal helper: Multifunctional nonmedical benzodiazepine use among young adult opioid users in New York City.

Background: Benzodiazepines are a widely prescribed psychoactive drug; in the U.S., both medical and nonmedical use of benzodiazepines has increased markedly in the past 15 years.

Mind the gap: financial London and the regional class pay gap.

The hidden barriers, or 'gender pay gap', preventing women from earning equivalent incomes to men is well documented. Yet recent research has uncovered that, in Britain, there is also a comparable class-origin pay gap in higher professional and managerial occupations. So far this analysis has only been conducted at the national level and it is not known whether there are regional differences within the UK.

Sexual Violence in the Context of Drug Use Among Young Adult Opioid Users in New York City.

Drug and alcohol use have been associated with increased risk for sexual violence, but there is little research on sexual violence within the context of drug use among young adult opioid users. The current mixed-methods study explores young adult opioid users' sexual experiences in the context of their drug use. Forty-six New York City young adults (ages 18-32) who reported lifetime nonmedical use of prescription opioids (POs) completed in-depth, semistructured interviews, and 164 (ages 18-29) who reported heroin and/or nonmedical PO use in the past 30 days completed structured assessments that inquired about their drug use and sexual behavior and included questions specific to sexual violence.

Migration narratives: expanding methods to examine the interaction of person and environment among aging gay men.

As they age, gay and bisexual men are embedded in multiple environments and communities. This article reanalyzes data collected as part of a larger qualitative study of crystal methamphetamine use in New York City. Focusing on the migration narratives of 30 racially/ethnically diverse men, age 40 years old and older, recruited from multiple venues several key areas emerged: ostracization, lack of affirmation as well as movement activities.

Sexual contexts and the process of risk reduction.

Understanding the dynamics of sexual risks for HIV among men who have sex with men has been one of the ongoing challenges of HIV prevention. While the majority of HIV-prevention interventions target individual behaviour and decision making, multiple studies point to the importance of social context in shaping risk behaviour. Analysis of qualitative data from a study of men who have sex with men, drug use and sex found that sexual encounters were made up multiple contextual and interpersonal elements, which interacted to shape sexual practices and risk reduction strategies.

The cultural currency of a 'good' sense of humour: British comedy and new forms of distinction.

Traditionally considered lowbrow art par excellence, British comedy has grown steadily in legitimacy since the 'Alternative Comedy Movement' of the early 1980s. Yet while there might be evidence of a transformation in British comic production, there is little understanding of how this has been reflected in patterns of consumption. Indeed, there is a remarkable absence of studies probing comedy taste in British cultural sociology, most notably in Bennett et al's (2009) recent and otherwise exhaustive mapping of cultural taste and participation.

Drug use, community action, and public health: gay men and crystal meth in NYC.

In 2004, GLBT and HIV/AIDS service providers in NYC mobilized against use of crystal methamphetamine among gay men. Both drug use and mobilization were shaped by the history of HIV, particularly the institutions, action repertoires, and social networks forged in earlier AIDS work. This paper is based on qualitative research conducted from 2007 to 2009 with advocates, service providers, and men who have sex with men recruited from diverse venues in NYC gay communities.