A common allele of HLA is associated with asymptomatic SARS-CoV-2 infection.

Studies have demonstrated that at least 20% of individuals infected with SARS-CoV-2 remain asymptomatic1-4. Although most global efforts have focused on severe illness in COVID-19, examining asymptomatic infection provides a unique opportunity to consider early immunological features that promote rapid viral clearance. Here, postulating that variation in the human leukocyte antigen (HLA) loci may underly processes mediating asymptomatic infection, we enrolled 29,947 individuals, for whom high-resolution HLA genotyping data were available, in a smartphone-based study designed to track COVID-19 symptoms and outcomes. Our discovery cohort (n = 1,428) comprised unvaccinated individuals who reported a positive test result for SARS-CoV-2. We tested for association of five HLA loci with disease course and identified a strong association between HLA-B*15:01 and asymptomatic infection, observed in two independent cohorts. Suggesting that this genetic association is due to pre-existing T cell immunity, we show that T cells from pre-pandemic samples from individuals carrying HLA-B*15:01 were reactive to the immunodominant SARS-CoV-2 S-derived peptide NQKLIANQF. The majority of the reactive T cells displayed a memory phenotype, were highly polyfunctional and were cross-reactive to a peptide derived from seasonal coronaviruses. The crystal structure of HLA-B*15:01-peptide complexes demonstrates that the peptides NQKLIANQF and NQKLIANAF (from OC43-CoV and HKU1-CoV) share a similar ability to be stabilized and presented by HLA-B*15:01. Finally, we show that the structural similarity of the peptides underpins T cell cross-reactivity of high-affinity public T cell receptors, providing the molecular basis for HLA-B*15:01-mediated pre-existing immunity.

Development of a liver disease-specific large language model chat interface using retrieval-augmented generation.

BACKGROUND AND AIMS: Large language models (LLMs) have significant capabilities in clinical information processing tasks. Commercially available LLMs, however, are not optimized for clinical uses and are prone to generating hallucinatory information. Retrieval-augmented generation (RAG) is an enterprise architecture that allows the embedding of customized data into LLMs. This approach "specializes" the LLMs and is thought to reduce hallucinations. APPROACH AND RESULTS: We developed "LiVersa," a liver disease-specific LLM, by using our institution's protected health information-complaint text embedding and LLM platform, "Versa." We conducted RAG on 30 publicly available American Association for the Study of Liver Diseases guidance documents to be incorporated into LiVersa. We evaluated LiVersa's performance by conducting 2 rounds of testing. First, we compared LiVersa's outputs versus those of trainees from a previously published knowledge assessment. LiVersa answered all 10 questions correctly. Second, we asked 15 hepatologists to evaluate the outputs of 10 hepatology topic questions generated by LiVersa, OpenAI's ChatGPT 4, and Meta's Large Language Model Meta AI 2. LiVersa's outputs were more accurate but were rated less comprehensive and safe compared to those of ChatGPT 4. RESULTS: We evaluated LiVersa's performance by conducting 2 rounds of testing. First, we compared LiVersa's outputs versus those of trainees from a previously published knowledge assessment. LiVersa answered all 10 questions correctly. Second, we asked 15 hepatologists to evaluate the outputs of 10 hepatology topic questions generated by LiVersa, OpenAI's ChatGPT 4, and Meta's Large Language Model Meta AI 2. LiVersa's outputs were more accurate but were rated less comprehensive and safe compared to those of ChatGPT 4. CONCLUSIONS: In this demonstration, we built disease-specific and protected health information-compliant LLMs using RAG. While LiVersa demonstrated higher accuracy in answering questions related to hepatology, there were some deficiencies due to limitations set by the number of documents used for RAG. LiVersa will likely require further refinement before potential live deployment. The LiVersa prototype, however, is a proof of concept for utilizing RAG to customize LLMs for clinical use cases.

Clinical decision support and electronic interventions to improve care quality in chronic liver diseases and cirrhosis.

Significant quality gaps exist in the management of chronic liver diseases and cirrhosis. Clinical decision support systems-information-driven tools based in and launched from the electronic health record-are attractive and potentially scalable prospective interventions that could help standardize clinical care in hepatology. Yet, clinical decision support systems have had a mixed record in clinical medicine due to issues with interoperability and compatibility with clinical workflows. In this review, we discuss the conceptual origins of clinical decision support systems, existing applications in liver diseases, issues and challenges with implementation, and emerging strategies to improve their integration in hepatology care.

Breakthrough SARS-CoV-2 infection outcomes in vaccinated patients with chronic liver disease and cirrhosis: A National COVID Cohort Collaborative study.

BACKGROUND AND AIMS: Outcomes of breakthrough SARS-CoV-2 infections have not been well characterized in non-veteran vaccinated patients with chronic liver diseases (CLD). We used the National COVID Cohort Collaborative (N3C) to describe these outcomes. APPROACH AND RESULTS: We identified all CLD patients with or without cirrhosis who had SARS-CoV-2 testing in the N3C Data Enclave as of January 15, 2022. We used Poisson regression to estimate incidence rates of breakthrough infections and Cox survival analyses to associate vaccination status with all-cause mortality at 30 days among infected CLD patients. We isolated 278,457 total CLD patients: 43,079 (15%) vaccinated and 235,378 (85%) unvaccinated. Of 43,079 vaccinated patients, 32,838 (76%) were without cirrhosis and 10,441 (24%) with cirrhosis. Breakthrough infection incidences were 5.4 and 4.9 per 1000 person-months for fully vaccinated CLD patients without cirrhosis and with cirrhosis, respectively. Of the 68,048 unvaccinated and 10,441 vaccinated CLD patients with cirrhosis, 15% and 3.7%, respectively, developed SARS-CoV-2 infection. The 30-day outcome of mechanical ventilation or death after SARS-CoV-2 infection for unvaccinated and vaccinated CLD patients with cirrhosis were 15.2% and 7.7%, respectively. Compared to unvaccinated patients with cirrhosis, full vaccination was associated with a 0.34-times adjusted hazard of death at 30 days. CONCLUSIONS: In this N3C study, breakthrough infection rates were similar among CLD patients with and without cirrhosis. Full vaccination was associated with a 66% reduction in risk of all-cause mortality for breakthrough infection among CLD patients with cirrhosis. These results provide an additional impetus for increasing vaccination uptake in CLD populations.

Association of nirmatrelvir for acute SARS-CoV-2 infection with subsequent Long COVID symptoms in an observational cohort study.

Oral nirmatrelvir/ritonavir is approved as treatment for acute COVID-19, but the effect of treatment during acute infection on risk of Long COVID is unknown. We hypothesized that nirmatrelvir treatment during acute SARS-CoV-2 infection reduces risk of developing Long COVID and rebound after treatment is associated with Long COVID. We conducted an observational cohort study within the Covid Citizen Science (CCS) study, an online cohort study with over 100 000 participants. We included vaccinated, nonhospitalized, nonpregnant individuals who reported their first SARS-CoV-2 positive test March-August 2022. Oral nirmatrelvir/ritonavir treatment was ascertained during acute SARS-CoV-2 infection. Patient-reported Long COVID symptoms, symptom rebound and test-positivity rebound were asked on subsequent surveys at least 3 months after SARS-CoV-2 infection. A total of 4684 individuals met the eligibility criteria, of whom 988 (21.1%) were treated and 3696 (78.9%) were untreated; 353/988 (35.7%) treated and 1258/3696 (34.0%) untreated responded to the Long COVID survey (n = 1611). Among 1611 participants, median age was 55 years and 66% were female. At 5.4 ± 1.3 months after infection, nirmatrelvir treatment was not associated with subsequent Long COVID symptoms (odds ratio [OR]: 1.15; 95% confidence interval [CI]: 0.80-1.64; p = 0.45). Among 666 treated who answered rebound questions, rebound symptoms or test positivity were not associated with Long COVID symptoms (OR: 1.34; 95% CI: 0.74-2.41; p = 0.33). Within this cohort of vaccinated, nonhospitalized individuals, oral nirmatrelvir treatment during acute SARS-CoV-2 infection and rebound after nirmatrelvir treatment were not associated with Long COVID symptoms more than 90 days after infection.

Predicting post-liver transplant outcomes in patients with acute-on-chronic liver failure using Expert-Augmented Machine Learning.

Liver transplantation (LT) is a treatment for acute-on-chronic liver failure (ACLF), but high post-LT mortality has been reported. Existing post-LT models in ACLF have been limited. We developed an Expert-Augmented Machine Learning (EAML) model to predict post-LT outcomes. We identified ACLF patients who underwent LT in the University of California Health Data Warehouse. We applied the RuleFit machine learning (ML) algorithm to extract rules from decision trees and create intermediate models. We asked human experts to rate the rules generated by RuleFit and incorporated these ratings to generate final EAML models. We identified 1384 ACLF patients. For death at 1 year, areas under the receiver-operating characteristic curve were 0.707 (confidence interval [CI] 0.625-0.793) for EAML and 0.719 (CI 0.640-0.800) for RuleFit. For death at 90 days, areas under the receiver-operating characteristic curve were 0.678 (CI 0.581-0.776) for EAML and 0.707 (CI 0.615-0.800) for RuleFit. In pairwise comparisons, both EAML and RuleFit models outperformed cross-sectional models. Significant discrepancies between experts and ML occurred in rankings of biomarkers used in clinical practice. EAML may serve as a method for ML-guided hypothesis generation in further ACLF research.

Association of daily physical activity with brain volumes and cervical spinal cord areas in multiple sclerosis.

BACKGROUND: Remote activity monitoring has the potential to evaluate real-world, motor function, and disability at home. The relationships of daily physical activity with spinal cord white matter and gray matter (GM) areas, multiple sclerosis (MS) disability and leg function, are unknown. OBJECTIVE: Evaluate the association of structural central nervous system pathology with ambulatory disability. METHODS: Fifty adults with progressive or relapsing MS with motor disability who could walk >2 minutes were assessed using clinician-evaluated, patient-reported outcomes, and quantitative brain and spinal cord magnetic resonance imaging (MRI) measures. Fitbit Flex2, worn on the non-dominant wrist, remotely assessed activity over 30 days. Univariate and multivariate analyses were performed to assess correlations between physical activity and other disability metrics. RESULTS: Mean age was 53.3 years and median Expanded Disability Status Scale (EDSS) was 4.0. Average daily step counts (STEPS) were highly correlated with EDSS and walking measures. Greater STEPS were significantly correlated with greater C2-C3 spinal cord GM areas (ρ = 0.39, p = 0.04), total cord area (TCA; ρ = 0.35, p = 0.04), and cortical GM volume (ρ = 0.32, p = 0.04). CONCLUSION: These results provide preliminary evidence that spinal cord GM area is a neuroanatomical substrate associated with STEPS. STEPS could serve as a proxy to alert clinicians and researchers to possible changes in structural nervous system pathology.

Interindividual Variability in Self-Monitoring of Blood Pressure Using Consumer-Purchased Wireless Devices.

BACKGROUND: Engagement with self-monitoring of blood pressure (BP) declines, on average, over time but may vary substantially by individual. OBJECTIVES: We aimed to describe different 1-year patterns (groups) of self-monitoring of BP behaviors, identify predictors of those groups, and examine the association of self-monitoring of BP groups with BP levels over time. METHODS: We analyzed device-recorded BP measurements collected by the Health eHeart Study-an ongoing prospective eCohort study-from participants with a wireless consumer-purchased device that transmitted date- and time-stamped BP data to the study through a full 12 months of observation starting from the first day they used the device. Participants received no instruction on device use. We applied clustering analysis to identify 1-year self-monitoring, of BP patterns. RESULTS: Participants had a mean age of 52 years and were male and White. Using clustering algorithms, we found that a model with three groups fit the data well: persistent daily use (9.1% of participants), persistent weekly use (21.2%), and sporadic use only (69.7%). Persistent daily use was more common among older participants who had higher Week 1 self-monitoring of BP frequency and was associated with lower BP levels than the persistent weekly use or sporadic use groups throughout the year. CONCLUSION: We identified three distinct self-monitoring of BP groups, with nearly 10% sustaining a daily use pattern associated with lower BP levels.

Email-Based Recruitment Into the Health eHeart Study: Cohort Analysis of Invited Eligible Patients.

BACKGROUND: Web- or app-based digital health studies allow for more efficient collection of health data for research. However, remote recruitment into digital health studies can enroll nonrepresentative study samples, hindering the robustness and generalizability of findings. Through the comprehensive evaluation of an email-based campaign on recruitment into the Health eHeart Study, we aim to uncover key sociodemographic and clinical factors that contribute to enrollment. OBJECTIVE: This study sought to understand the factors related to participation, specifically regarding enrollment, in the Health eHeart Study as a result of a large-scale remote email recruitment campaign. METHODS: We conducted a cohort analysis on all invited University of California, San Francisco (UCSF) patients to identify sociodemographic and clinical predictors of enrollment into the Health eHeart Study. The primary outcome was enrollment, defined by account registration and consent into the Health eHeart Study. The email recruitment campaign was carried out from August 2015 to February 2016, with electronic health record data extracted between September 2019 and December 2019. RESULTS: The email recruitment campaign delivered at least 1 email invitation to 93.5% (193,606/206,983) of all invited patients and yielded a 3.6% (7012/193,606) registration rate among contacted patients and an 84.1% (5899/7012) consent rate among registered patients. Adjusted multivariate logistic regression models analyzed independent sociodemographic and clinical predictors of (1) registration among contacted participants and (2) consent among registered participants. Odds of registration were higher among patients who are older, women, non-Hispanic White, active patients with commercial insurance or Medicare, with a higher comorbidity burden, with congestive heart failure, and randomized to receive up to 2 recruitment emails. The odds of registration were lower among those with medical conditions such as dementia, chronic pulmonary disease, moderate or severe liver disease, paraplegia or hemiplegia, renal disease, or cancer. Odds of subsequent consent after initial registration were different, with an inverse trend of being lower among patients who are older and women. The odds of consent were also lower among those with peripheral vascular disease. However, the odds of consent remained higher among patients who were non-Hispanic White and those with commercial insurance. CONCLUSIONS: This study provides important insights into the potential returns on participant enrollment when digital health study teams invest resources in using email for recruitment. The findings show that participant enrollment was driven more strongly by sociodemographic factors than clinical factors. Overall, email is an extremely efficient means of recruiting participants from a large list into the Health eHeart Study. Despite some improvements in representation, the formulation of truly diverse studies will require additional resources and strategies to overcome persistent participation barriers.

Digital Tool-Assisted Hospitalization Detection in the Tailored Antiplatelet Initiation to Lessen Outcomes due to Decreased Clopidogrel Response After Percutaneous Coronary Intervention Study Compared to Traditional Site-Coordinator Ascertainment: Intervention Study.

BACKGROUND: Accurate, timely ascertainment of clinical end points, particularly hospitalizations, is crucial for clinical trials. The Tailored Antiplatelet Initiation to Lessen Outcomes Due to Decreased Clopidogrel Response after Percutaneous Coronary Intervention (TAILOR-PCI) Digital Study extended the main TAILOR-PCI trial's follow-up to 2 years, using a smartphone-based research app featuring geofencing-triggered surveys and routine monthly mobile phone surveys to detect cardiovascular (CV) hospitalizations. This pilot study compared these digital tools to conventional site-coordinator ascertainment of CV hospitalizations. OBJECTIVE: The objectives were to evaluate geofencing-triggered notifications and routine monthly mobile phone surveys' performance in detecting CV hospitalizations compared to telephone visits and health record reviews by study coordinators at each site. METHODS: US and Canadian participants from the TAILOR-PCI Digital Follow-Up Study were invited to download the Eureka Research Platform mobile app, opting in for location tracking using geofencing, triggering a smartphone-based survey if near a hospital for ≥4 hours. Participants were sent monthly notifications for CV hospitalization surveys. RESULTS: From 85 participants who consented to the Digital Study, downloaded the mobile app, and had not previously completed their final follow-up visit, 73 (85.8%) initially opted in and consented to geofencing. There were 9 CV hospitalizations ascertained by study coordinators among 5 patients, whereas 8 out of 9 (88.9%) were detected by routine monthly hospitalization surveys. One CV hospitalization went undetected by the survey as it occurred within two weeks of the previous event, and the survey only allowed reporting of a single hospitalization. Among these, 3 were also detected by the geofencing algorithm, but 6 out of 9 (66.7%) were missed by geofencing: 1 occurred in a participant who never consented to geofencing, while 5 hospitalizations occurred among participants who had subsequently turned off geofencing prior to their hospitalization. Geofencing-detected hospitalizations were ascertained within a median of 2 (IQR 1-3) days, monthly surveys within 11 (IQR 6.5-25) days, and site coordinator methods within 38 (IQR 9-105) days. The geofencing algorithm triggered 245 notifications among 39 participants, with 128 (52.2%) from true hospital presence and 117 (47.8%) from nonhospital health care facility visits. Additional geofencing iterative improvements to reduce hospital misidentification were made to the algorithm at months 7 and 12, elevating the rate of true alerts from 35.4% (55 true alerts/155 total alerts before month 7) to 78.7% (59 true alerts/75 total alerts in months 7-12) and ultimately to 93.3% (14 true alerts/5 total alerts in months 13-21), respectively. CONCLUSIONS: The monthly digital survey detected most CV hospitalizations, while the geofencing survey enabled earlier detection but did not offer incremental value beyond traditional tools. Digital tools could potentially reduce the burden on study coordinators in ascertaining CV hospitalizations. The advantages of timely reporting via geofencing should be weighed against the issue of false notifications, which can be mitigated through algorithmic refinements.

Outcomes of SARS-CoV-2 Infection in Patients With Chronic Liver Disease and Cirrhosis: A National COVID Cohort Collaborative Study.

BACKGROUND & AIMS: In patients with chronic liver disease (CLD) with or without cirrhosis, existing studies on the outcomes with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection have limited generalizability. We used the National COVID Cohort Collaborative (N3C), a harmonized electronic health record dataset of 6.4 million, to describe SARS-CoV-2 outcomes in patients with CLD and cirrhosis. METHODS: We identified all patients with CLD with or without cirrhosis who had SARS-CoV-2 testing in the N3C Data Enclave as of July 1, 2021. We used survival analyses to associate SARS-CoV-2 infection, presence of cirrhosis, and clinical factors with the primary outcome of 30-day mortality. RESULTS: We isolated 220,727 patients with CLD and SARS-CoV-2 test status: 128,864 (58%) were noncirrhosis/negative, 29,446 (13%) were noncirrhosis/positive, 53,476 (24%) were cirrhosis/negative, and 8941 (4%) were cirrhosis/positive patients. Thirty-day all-cause mortality rates were 3.9% in cirrhosis/negative and 8.9% in cirrhosis/positive patients. Compared to cirrhosis/negative patients, cirrhosis/positive patients had 2.38 times adjusted hazard of death at 30 days. Compared to noncirrhosis/positive patients, cirrhosis/positive patients had 3.31 times adjusted hazard of death at 30 days. In stratified analyses among patients with cirrhosis with increased age, obesity, and comorbid conditions (ie, diabetes, heart failure, and pulmonary disease), SARS-CoV-2 infection was associated with increased adjusted hazard of death. CONCLUSIONS: In this study of approximately 221,000 nationally representative, diverse, and sex-balanced patients with CLD; we found SARS-CoV-2 infection in patients with cirrhosis was associated with 2.38 times mortality hazard, and the presence of cirrhosis among patients with CLD infected with SARS-CoV-2 was associated with 3.31 times mortality hazard. These results provide an additional impetus for increasing vaccination uptake and further research regarding immune responses to vaccines in patients with severe liver disease.

The U.S. COVID-19 County Policy Database: a novel resource to support pandemic-related research.

BACKGROUND: It is increasingly recognized that policies have played a role in both alleviating and exacerbating the health and economic consequences of the COVID-19 pandemic. There has been limited systematic evaluation of variation in U.S. local COVID-19-related policies. This study introduces the U.S. COVID-19 County Policy (UCCP) Database, whose objective is to systematically gather, characterize, and assess variation in U.S. county-level COVID-19-related policies. METHODS: In January-March 2021, we collected an initial wave of cross-sectional data from government and media websites for 171 counties in 7 states on 22 county-level COVID-19-related policies within 3 policy domains that are likely to affect health: (1) containment/closure, (2) economic support, and (3) public health. We characterized the presence and comprehensiveness of policies using univariate analyses. We also examined the correlation of policies with one another using bivariate Spearman's correlations. Finally, we examined geographical variation in policies across and within states. RESULTS: There was substantial variation in the presence and comprehensiveness of county policies during January-March 2021. For containment and closure policies, the percent of counties with no restrictions ranged from 0% (for public events) to more than half for public transportation (67.8%), hair salons (52.6%), and religious gatherings (52.0%). For economic policies, 76.6% of counties had housing support, while 64.9% had utility relief. For public health policies, most were comprehensive, with 70.8% of counties having coordinated public information campaigns, and 66.7% requiring masks outside the home at all times. Correlations between containment and closure policies tended to be positive and moderate (i.e., coefficients 0.4-0.59). There was variation within and across states in the number and comprehensiveness of policies. CONCLUSIONS: This study introduces the UCCP Database, presenting granular data on local governments' responses to the COVID-19 pandemic. We documented substantial variation within and across states on a wide range of policies at a single point in time. By making these data publicly available, this study supports future research that can leverage this database to examine how policies contributed to and continue to influence pandemic-related health and socioeconomic outcomes and disparities. The UCCP database is available online and will include additional time points for 2020-2021 and additional counties nationwide.

Web-Based Mindfulness-Based Interventions for Well-being: Randomized Comparative Effectiveness Trial.

BACKGROUND: Mindfulness can improve overall well-being by training individuals to focus on the present moment without judging their thoughts. However, it is unknown how much mindfulness practice and training are necessary to improve well-being. OBJECTIVE: The primary aim of this study was to determine whether a standard 8-session web-based mindfulness-based cognitive therapy (MBCT) program, compared with a brief 3-session mindfulness intervention, improved overall participant well-being. In addition, we sought to explore whether the treatment effects differed based on the baseline characteristics of the participants (ie, moderators). METHODS: Participants were recruited from 17 patient-powered research networks, web-based communities of stakeholders interested in a common research area. Participants were randomized to either a standard 8-session MBCT or a brief 3-session mindfulness training intervention accessed on the web. The participants were followed for 12 weeks. The primary outcome of the study was well-being, as measured by the World Health Organization-Five Well-Being Index. We hypothesized that MBCT would be superior to a brief mindfulness training. RESULTS: We randomized 4411 participants, 3873 (87.80%) of whom were White and 3547 (80.41%) of female sex assigned at birth. The mean baseline World Health Organization-Five Well-Being Index score was 50.3 (SD 20.7). The average self-reported well-being in each group increased over the intervention period (baseline to 8 weeks; model-based slope for the MBCT group: 0.78, 95% CI 0.63-0.93, and brief mindfulness group: 0.76, 95% CI 0.60-0.91) as well as the full study period (ie, intervention plus follow-up; baseline to 20 weeks; model-based slope for MBCT group: 0.41, 95% CI 0.34-0.48; and brief mindfulness group: 0.33, 95% CI 0.26-0.40). Changes in self-reported well-being were not significantly different between MBCT and brief mindfulness during the intervention period (model-based difference in slopes: -0.02, 95% CI -0.24 to 0.19; P=.80) or during the intervention period plus 12-week follow-up (-0.08, 95% CI -0.18 to 0.02; P=.10). During the intervention period, younger participants (P=.05) and participants who completed a higher percentage of intervention sessions (P=.005) experienced greater improvements in well-being across both interventions, with effects that were stronger for participants in the MBCT condition. Attrition was high (ie, 2142/4411, 48.56%), which is an important limitation of this study. CONCLUSIONS: Standard MBCT improved well-being but was not superior to a brief mindfulness intervention. This finding suggests that shorter mindfulness programs could yield important benefits across the general population of individuals with various medical conditions. Younger people and participants who completed more intervention sessions reported greater improvements in well-being, an effect that was more pronounced for participants in the MBCT condition. This finding suggests that standard MBCT may be a better choice for younger people as well as treatment-adherent individuals. TRIAL REGISTRATION: ClinicalTrials.gov NCT03844321; https://clinicaltrials.gov/ct2/show/NCT03844321.

Opal: an implementation science tool for machine learning clinical decision support in anesthesia.

Opal is the first published example of a full-stack platform infrastructure for an implementation science designed for ML in anesthesia that solves the problem of leveraging ML for clinical decision support. Users interact with a secure online Opal web application to select a desired operating room (OR) case cohort for data extraction, visualize datasets with built-in graphing techniques, and run in-client ML or extract data for external use. Opal was used to obtain data from 29,004 unique OR cases from a single academic institution for pre-operative prediction of post-operative acute kidney injury (AKI) based on creatinine KDIGO criteria using predictors which included pre-operative demographic, past medical history, medications, and flowsheet information. To demonstrate utility with unsupervised learning, Opal was also used to extract intra-operative flowsheet data from 2995 unique OR cases and patients were clustered using PCA analysis and k-means clustering. A gradient boosting machine model was developed using an 80/20 train to test ratio and yielded an area under the receiver operating curve (ROC-AUC) of 0.85 with 95% CI [0.80-0.90]. At the default probability decision threshold of 0.5, the model sensitivity was 0.9 and the specificity was 0.8. K-means clustering was performed to partition the cases into two clusters and for hypothesis generation of potential groups of outcomes related to intraoperative vitals. Opal's design has created streamlined ML functionality for researchers and clinicians in the perioperative setting and opens the door for many future clinical applications, including data mining, clinical simulation, high-frequency prediction, and quality improvement.

Wearable Cardioverter-Defibrillator after Myocardial Infarction.

BACKGROUND: Despite the high rate of sudden death after myocardial infarction among patients with a low ejection fraction, implantable cardioverter-defibrillators are contraindicated until 40 to 90 days after myocardial infarction. Whether a wearable cardioverter-defibrillator would reduce the incidence of sudden death during this high-risk period is unclear. METHODS: We randomly assigned (in a 2:1 ratio) patients with acute myocardial infarction and an ejection fraction of 35% or less to receive a wearable cardioverter-defibrillator plus guideline-directed therapy (the device group) or to receive only guideline-directed therapy (the control group). The primary outcome was the composite of sudden death or death from ventricular tachyarrhythmia at 90 days (arrhythmic death). Secondary outcomes included death from any cause and nonarrhythmic death. RESULTS: Of 2302 participants, 1524 were randomly assigned to the device group and 778 to the control group. Participants in the device group wore the device for a median of 18.0 hours per day (interquartile range, 3.8 to 22.7). Arrhythmic death occurred in 1.6% of the participants in the device group and in 2.4% of those in the control group (relative risk, 0.67; 95% confidence interval [CI], 0.37 to 1.21; P=0.18). Death from any cause occurred in 3.1% of the participants in the device group and in 4.9% of those in the control group (relative risk, 0.64; 95% CI, 0.43 to 0.98; uncorrected P=0.04), and nonarrhythmic death in 1.4% and 2.2%, respectively (relative risk, 0.63; 95% CI, 0.33 to 1.19; uncorrected P=0.15). Of the 48 participants in the device group who died, 12 were wearing the device at the time of death. A total of 20 participants in the device group (1.3%) received an appropriate shock, and 9 (0.6%) received an inappropriate shock. CONCLUSIONS: Among patients with a recent myocardial infarction and an ejection fraction of 35% or less, the wearable cardioverter-defibrillator did not lead to a significantly lower rate of the primary outcome of arrhythmic death than control. (Funded by the National Institutes of Health and Zoll Medical; VEST ClinicalTrials.gov number, NCT01446965 .).

Rationale and design of the TAILOR-PCI digital study: Transitioning a randomized controlled trial to a digital registry.

BACKGROUND: Tailored Antiplatelet Initiation to Lessen Outcomes Due to Decreased Clopidogrel Response after Percutaneous Coronary Intervention (TAILOR-PCI) is the largest cardiovascular genotype-based randomized pragmatic trial (NCT#01742117) to evaluate the role of genotype-guided selection of oral P2Y12 inhibitor therapy in improving ischemic outcomes after PCI. The trial has been extended from the original 12- to 24-month follow-up, using study coordinator-initiated telephone visits. TAILOR-PCI Digital Study tests the feasibility of extending the trial follow-up in a subset of patients for up to 24 months using state-of-the-art digital solutions. The rationale, design, and approach of extended digital study of patients recruited into a large, international, multi-center clinical trial has not been previously described. METHODS: A total of 930 patients from U.S. and Canadian sites previously enrolled in the 5,302 patient TAILOR-PCI trial within 23 months of randomization are invited by mail to the Digital Study website (http://tailorpci.eurekaplatform.org) and by up to 2 recruiting telephone calls. Eureka, a direct-to-participant digital research platform, is used to consent and collect prospective data on patients for the digital study. Patients are asked to answer health-related surveys at fixed intervals using the Eureka mobile app and or desktop platform. The likelihood of patients enrolled in a randomized clinical trial transitioning to a registry using digital technology, the reasons for nonparticipation and engagement rates are evaluated. To capture hospitalizations, patients may optionally enable geofencing, a process that allows background location tracking and triggering of surveys if a hospital visit greater than 4 hours is detected. In addition, patients answer digital hospitalization surveys every month. Hospitalization data received from the Digital Study will be compared to data collected from study coordinator telephone visits during the same time frame. CONCLUSIONS: The TAILOR-PCI Digital Study evaluates the feasibility of transitioning a large multicenter randomized clinical trial to a digital registry. The study could provide evidence for the ability of digital technology to follow clinical trial patients and to ascertain trial-related events thus also building the foundation for conducting digital clinical trials. Such a digital approach may be especially pertinent in the era of COVID-19.

Medicaid Policy and Liver Transplant for Alcohol-Associated Liver Disease.

BACKGROUND AND AIMS: In some states, liver transplantation (LT) for alcohol-associated liver disease (ALD) is covered by Medicaid only with documentation of abstinence and/or alcohol rehabilitation. Different Medicaid policies may affect the distribution of LT for ALD, particularly post-2011, as centers have adopted early (i.e., specific abstinence period not required) LT practices. APPROACH AND RESULTS: We surveyed Medicaid policies in all states actively performing LT and linked state policies to prospectively collected national registry data on LT recipients from 2002 to 2017 with ALD as the primary listing diagnosis. We categorized Medicaid policies for states as "restrictive" (requiring documentation of a specific abstinence period and/or rehabilitation) versus "unrestrictive" (deferring to center eligibility policies). Difference-of-differences analysis, comparing 2002-2011 versus 2012-2017, evaluated whether restrictive policies were associated with decreased proportion of LTs paid by Medicaid among patients with ALD post-2011. We performed sensitivity analyses to account for any differences by diagnosis of hepatocellular carcinoma, hepatitis C virus, nonalcoholic steatohepatitis, or Medicare insurance. We also performed a sensitivity analysis to account for any difference by prevalence of ALD among restrictive versus unrestrictive states. Of 10,836 LT recipients in 2002-2017, 7,091 were from 24 states in the restrictive group and 3,745 from 14 states in the unrestrictive group. The adjusted proportion (95% confidence interval) of LTs paid by Medicaid among restrictive versus unrestrictive states between 2002 and 2011 was 17.6% (15.4%-19.8%) versus 18.9% (15.4%-22.3%) (P = 0.54) and between 2012 and 2017, 17.2% (14.7%-19.7%) versus 23.2% (19.8%-26.6%) (P = 0.005). In difference-of-differences analysis, restrictive (versus unrestrictive) policies were associated with a 4.7% (0.8%-8.6%) (P = 0.02) absolute lower adjusted proportion of LTs for ALD paid by Medicaid post-2011. CONCLUSIONS: Restrictive Medicaid policies are present in most states with active LT centers and are associated with lower proportions of LTs for ALD paid by Medicaid post-2011 compared to states with unrestrictive Medicaid policies. Reevaluation of Medicaid alcohol use policies may be warranted, to align more closely with contemporary center-level practices.

Association of Midlife Cardiovascular Risk Factors With the Risk of Heart Failure Subtypes Later in Life.

BACKGROUND: Independent associations between cardiovascular risk factor exposures during midlife and later life development of heart failure (HF) with preserved ejection fraction (HFpEF) versus reduced EF (HFrEF) have not been previously studied. METHODS: We pooled data from 4 US cohort studies (Atherosclerosis Risk in Communities, Cardiovascular Health, Health , Aging and Body Composition, and Multi-Ethnic Study of Atherosclerosis) and imputed annual risk factor trajectories for body mass index, systolic and diastolic blood pressure, low-density lipoprotein and high-density lipoprotein cholesterol, and glucose starting from age 40 years. Time-weighted average exposures to each risk factor during midlife and later life were calculated and analyzed for associations with the development of HFpEF or HFrEF. RESULTS: A total of 23,861 participants were included (mean age at first in-person visit, 61.8 ±1 0.2 years; 56.6% female). During a median follow-up of 12 years, there were 3666 incident HF events, of which 51% had EF measured, including 934 with HFpEF and 739 with HFrEF. A high midlife systolic blood pressure and low midlife high-density lipoprotein cholesterol were associated with HFrEF, and a high midlife body mass index, systolic blood pressure, pulse pressure, and glucose were associated with HFpEF. After adjusting for later life exposures, only midlife pulse pressure remained independently associated with HFpEF. CONCLUSIONS: Midlife exposure to cardiovascular risk factors are differentially associated with HFrEF and HFpEF later in life. Having a higher pulse pressure during midlife is associated with a greater risk for HFpEF but not HFrEF, independent of later life exposures.

Randomized Controlled Trials of Electronic Health Record Interventions: Design, Conduct, and Reporting Considerations.

Electronic health record (EHR) systems can be configured to deliver novel EHR interventions that influence clinical decision making and to support efficient randomized controlled trials (RCTs) designed to evaluate the effectiveness, safety, and costs of those interventions. In designing RCTs of EHR interventions, one should carefully consider the unit of randomization (for example, patient, encounter, clinician, or clinical unit), balancing concerns about contamination of an intervention across randomization units within clusters (for example, patients within clinical units) against the superior control of measured and unmeasured confounders that comes with randomizing a larger number of units. One should also consider whether the key computational assessment components of the EHR intervention, such as a predictive algorithm used to target a subgroup for decision support, should occur before randomization (so that only 1 subgroup is randomized) or after randomization (including all subgroups). When these components are applied after randomization, one must consider expected heterogeneity in the effect of the differential decision support across subgroups, which has implications for overall impact potential, analytic approach, and sample size planning. Trials of EHR interventions should be reviewed by an institutional review board, but may not require patient-level informed consent when the interventions being tested can be considered minimal risk or quality improvement, and when clinical decision making is supported, rather than controlled, by an EHR intervention. Data and safety monitoring for RCTs of EHR interventions should be conducted to guide institutional pragmatic decision making about implementation and ensure that continuing randomization remains justified. Reporting should follow the CONSORT (Consolidated Standards of Reporting Trials) Statement, with extensions for pragmatic trials and cluster RCTs when applicable, and should include detailed materials to enhance reproducibility.

Identifying Potential Intervention Points for Acute Hypoglycemic Events in Patients With Type 2 Diabetes Using Retrospective Clinical Data.

This retrospective study examined changes in medication orders as a risk factor for future acute hypoglycemic events. The investigators identified factors associated with acute hypoglycemic events resulting in emergency department visits or inpatient admissions. Non-Hispanic Black race, chronic kidney disease, insulin at baseline, and nonprivate insurance were associated with higher risk of an acute hypoglycemic event, whereas age, sex, and A1C were not. After adjustment for other risk factors, changes in insulin orders after A1C measurement were associated with a 1.5 times higher risk of an acute hypoglycemia (adjusted hazard ratio 1.48, 95% CI 1.08-2.03). These results further understanding of risk factors and clinical processes relevant to predicting and preventing acute hypoglycemia.