Artificial intelligence-enhanced risk stratification of cancer therapeutics-related cardiac dysfunction using electrocardiographic images.

Background: Risk stratification strategies for cancer therapeutics-related cardiac dysfunction (CTRCD) rely on serial monitoring by specialized imaging, limiting their scalability. Objectives: To examine an artificial intelligence (AI)-enhanced electrocardiographic (AI-ECG) surrogate for imaging risk biomarkers, and its association with CTRCD. Methods: Across a five-hospital U.S.-based health system (2013-2023), we identified patients with breast cancer or non-Hodgkin lymphoma (NHL) who received anthracyclines (AC) and/or trastuzumab (TZM), and a control cohort receiving immune checkpoint inhibitors (ICI). We deployed a validated AI model of left ventricular systolic dysfunction (LVSD) to ECG images (≥0.1, positive screen) and explored its association with i) global longitudinal strain (GLS) measured within 15 days (n=7,271 pairs); ii) future CTRCD (new cardiomyopathy, heart failure, or left ventricular ejection fraction [LVEF]<50%), and LVEF<40%. In the ICI cohort we correlated baseline AI-ECG-LVSD predictions with downstream myocarditis. Results: Higher AI-ECG LVSD predictions were associated with worse GLS (-18% [IQR:-20 to -17%] for predictions<0.1, to -12% [IQR:-15 to -9%] for ≥0.5 (p<0.001)). In 1,308 patients receiving AC/TZM (age 59 [IQR:49-67] years, 999 [76.4%] women, 80 [IQR:42-115] follow-up months) a positive baseline AI-ECG LVSD screen was associated with ~2-fold and ~4.8-fold increase in the incidence of the composite CTRCD endpoint (adj.HR 2.22 [95%CI:1.63-3.02]), and LVEF<40% (adj.HR 4.76 [95%CI:2.62-8.66]), respectively. Among 2,056 patients receiving ICI (age 65 [IQR:57-73] years, 913 [44.4%] women, follow-up 63 [IQR:28-99] months) AI-ECG predictions were not associated with ICI myocarditis (adj.HR 1.36 [95%CI:0.47-3.93]). Conclusion: AI applied to baseline ECG images can stratify the risk of CTRCD associated with anthracycline or trastuzumab exposure.

Use of Open Science Practices in Surgical Journals.

This cross-sectional study assesses the level of adoption of 5 new tools that promote high quality and transparency in surgical research.

Use of Smart Devices to Track Cardiovascular Health Goals in the United States.

BACKGROUND: Smartphone-based health applications are increasingly popular, but their real-world use for cardiovascular risk management remains poorly understood. OBJECTIVES: The purpose of this study was to investigate the patterns of tracking health goals using smart devices, including smartphones and/or tablets, in the United States. METHODS: Using the nationally representative Health Information National Trends Survey for 2017 to 2020, we examined self-reported tracking of health-related goals (optimizing body weight, increasing physical activity, and/or quitting smoking) using smart devices among those with cardiovascular disease (CVD) or cardiovascular risk factors of hypertension, diabetes, obesity, and/or smoking. Survey analyses were used to obtain national estimates of use patterns and identify features associated with the use of these devices for tracking health goals. RESULTS: Of 16,092 Health Information National Trends Survey participants, 10,660 had CVD or cardiovascular risk factors, representing 154.2 million (95% CI: 149.2-159.3 million) U.S. adults. Among the general U.S. adult population, 46% (95% CI: 44%-47%) tracked their health goals using their smart devices, compared with 42% (95% CI: 40%-43%) of those with or at risk of CVD. Younger age, female, Black race, higher educational attainment, and greater income were independently associated with tracking of health goals using smart devices. CONCLUSIONS: Two in 5 U.S. adults with or at risk of CVD use their smart devices to track health goals. While representing a potential avenue to improve care, the lower use of smart devices among older and low-income individuals, who are at higher risk of adverse cardiovascular outcomes, requires that digital health interventions are designed so as not to exacerbate existing disparities.

National Trends in Racial and Ethnic Disparities in Use of Recommended Therapies in Adults with Atherosclerotic Cardiovascular Disease, 1999-2020.

Importance: Despite efforts to improve the quality of care for patients with atherosclerotic cardiovascular disease (ASCVD), it is unclear whether the US has made progress in reducing racial and ethnic differences in utilization of guideline-recommended therapies for secondary prevention. Objective: To evaluate 21-year trends in racial and ethnic differences in utilization of guideline-recommended pharmacological medications and lifestyle modifications among US adults with ASCVD. Design, Setting, and Participants: This cross-sectional study includes data from the National Health and Nutrition Examination Survey between 1999 and 2020. Eligible participants were adults aged 18 years or older with a history of ASCVD. Data were analyzed between March 2022 and May 2023. Exposure: Self-reported race and ethnicity. Main Outcome and Measures: Rates and racial and ethnic differences in the use of guideline-recommended pharmacological medications and lifestyle modifications. Results: The study included 5218 adults with a history of ASCVD (mean [SD] age, 65.5 [13.2] years, 2148 women [weighted average, 44.2%]), among whom 1170 (11.6%) were Black, 930 (7.7%) were Hispanic or Latino, and 3118 (80.7%) were White in the weighted sample. Between 1999 and 2020, there was a significant increase in total cholesterol control and statin use in all racial and ethnic subgroups, and in angiotensin-converting enzyme inhibitor (ACEI) and angiotensin receptor blocker (ARB) utilization in non-Hispanic White individuals and Hispanic and Latino individuals (Hispanic and Latino individuals: 17.12 percentage points; 95% CI, 0.37-37.88 percentage points; P = .046; non-Hispanic White individuals: 12.14 percentage points; 95% CI, 6.08-18.20 percentage points; P < .001), as well as smoking cessation within the Hispanic and Latino population (-27.13 percentage points; 95% CI, -43.14 to -11.12 percentage points; P = .002). During the same period, the difference in smoking cessation between Hispanic and Latino individuals and White individuals was reduced (-24.85 percentage points; 95% CI, -38.19 to -11.51 percentage points; P < .001), but racial and ethnic differences for other metrics did not change significantly. Notably, substantial gaps persisted between current care and optimal care throughout the 2 decades of data analyzed. In the period of 2017 to 2020, optimal regimens were observed in 47.4% (95% CI, 39.3%-55.4%), 48.7% (95% CI, 36.7%-60.6%), and 53.0% (95% CI, 45.6%-60.4%) of Black, Hispanic and Latino, and White individuals, respectively. Conclusions and Relevance: In this cross-sectional study of US adults with ASCVD, significant disparities persisted between current care and optimal care, surpassing any differences observed among demographic groups. These findings highlight the critical need for sustained efforts to bridge these gaps and achieve better outcomes for all patients, regardless of their racial and ethnic backgrounds.

Distinguishing features of long COVID identified through immune profiling.

Post-acute infection syndromes may develop after acute viral disease1. Infection with SARS-CoV-2 can result in the development of a post-acute infection syndrome known as long COVID. Individuals with long COVID frequently report unremitting fatigue, post-exertional malaise, and a variety of cognitive and autonomic dysfunctions2-4. However, the biological processes that are associated with the development and persistence of these symptoms are unclear. Here 275 individuals with or without long COVID were enrolled in a cross-sectional study that included multidimensional immune phenotyping and unbiased machine learning methods to identify biological features associated with long COVID. Marked differences were noted in circulating myeloid and lymphocyte populations relative to the matched controls, as well as evidence of exaggerated humoral responses directed against SARS-CoV-2 among participants with long COVID. Furthermore, higher antibody responses directed against non-SARS-CoV-2 viral pathogens were observed among individuals with long COVID, particularly Epstein-Barr virus. Levels of soluble immune mediators and hormones varied among groups, with cortisol levels being lower among participants with long COVID. Integration of immune phenotyping data into unbiased machine learning models identified the key features that are most strongly associated with long COVID status. Collectively, these findings may help to guide future studies into the pathobiology of long COVID and help with developing relevant biomarkers.

Clinical trial data sharing: a cross-sectional study of outcomes associated with two U.S. National Institutes of Health models.

The impact and effectiveness of clinical trial data sharing initiatives may differ depending on the data sharing model used. We characterized outcomes associated with models previously used by the U.S. National Institutes of Health (NIH): National Heart, Lung, and Blood Institute's (NHLBI) centralized model and National Cancer Institute's (NCI) decentralized model. We identified trials completed in 2010-2013 that met NIH data sharing criteria and matched studies based on cost and/or size, determining whether trial data were shared, and for those that were, the frequency of secondary internal publications (authored by at least one author from the original research team) and shared data publications (authored by a team external to the original research team). We matched 77 NHLBI-funded trials to 77 NCI-funded trials; among these, 20 NHLBI-sponsored trials (26%) and 4 NCI-sponsored trials (5%) shared data (OR 6.4, 95% CI: 2.1, 19.8). From the 4 NCI-sponsored trials sharing data, we identified 65 secondary internal and 2 shared data publications. From the 20 NHLBI-sponsored trials sharing data, we identified 188 secondary internal and 53 shared data publications. The NHLBI's centralized data sharing model was associated with more trials sharing data and more shared data publications when compared with the NCI's decentralized model.

Use of Wearable Devices in Individuals With or at Risk for Cardiovascular Disease in the US, 2019 to 2020.

Importance: Wearable devices may be able to improve cardiovascular health, but the current adoption of these devices could be skewed in ways that could exacerbate disparities. Objective: To assess sociodemographic patterns of use of wearable devices among adults with or at risk for cardiovascular disease (CVD) in the US population in 2019 to 2020. Design, Setting, and Participants: This population-based cross-sectional study included a nationally representative sample of the US adults from the Health Information National Trends Survey (HINTS). Data were analyzed from June 1 to November 15, 2022. Exposures: Self-reported CVD (history of heart attack, angina, or congestive heart failure) and CVD risk factors (≥1 risk factor among hypertension, diabetes, obesity, or cigarette smoking). Main Outcomes and Measures: Self-reported access to wearable devices, frequency of use, and willingness to share health data with clinicians (referred to as health care providers in the survey). Results: Of the overall 9303 HINTS participants representing 247.3 million US adults (mean [SD] age, 48.8 [17.9] years; 51% [95% CI, 49%-53%] women), 933 (10.0%) representing 20.3 million US adults had CVD (mean [SD] age, 62.2 [17.0] years; 43% [95% CI, 37%-49%] women), and 5185 (55.7%) representing 134.9 million US adults were at risk for CVD (mean [SD] age, 51.4 [16.9] years; 43% [95% CI, 37%-49%] women). In nationally weighted assessments, an estimated 3.6 million US adults with CVD (18% [95% CI, 14%-23%]) and 34.5 million at risk for CVD (26% [95% CI, 24%-28%]) used wearable devices compared with an estimated 29% (95% CI, 27%-30%) of the overall US adult population. After accounting for differences in demographic characteristics, cardiovascular risk factor profile, and socioeconomic features, older age (odds ratio [OR], 0.35 [95% CI, 0.26-0.48]), lower educational attainment (OR, 0.35 [95% CI, 0.24-0.52]), and lower household income (OR, 0.42 [95% CI, 0.29-0.60]) were independently associated with lower use of wearable devices in US adults at risk for CVD. Among wearable device users, a smaller proportion of adults with CVD reported using wearable devices every day (38% [95% CI, 26%-50%]) compared with overall (49% [95% CI, 45%-53%]) and at-risk (48% [95% CI, 43%-53%]) populations. Among wearable device users, an estimated 83% (95% CI, 70%-92%) of US adults with CVD and 81% (95% CI, 76%-85%) at risk for CVD favored sharing wearable device data with their clinicians to improve care. Conclusions and Relevance: Among individuals with or at risk for CVD, fewer than 1 in 4 use wearable devices, with only half of those reporting consistent daily use. As wearable devices emerge as tools that can improve cardiovascular health, the current use patterns could exacerbate disparities unless there are strategies to ensure equitable adoption.

Open science practices in research published in surgical journals: A cross-sectional study.

Open science practices are research tools used to improve research quality and transparency. These practices have been used by researchers in various medical fields, though the usage of these practices in the surgical research ecosystem has not been quantified. In this work, we studied the use of open science practices in general surgery journals. Eight of the highest-ranked general surgery journals by SJR2 were chosen and their author guidelines were reviewed. From each journal, 30 articles published between January 1, 2019 and August 11, 2021 were randomly chosen and analyzed. Five open science practices were measured (preprint publication prior to peer-reviewed publication, use of Equator guidelines, study protocol preregistration prior to peer-reviewed publication, published peer review, and public accessibility of data, methods, and/or code). Across all 240 articles, 82 (34%) used one or more open science practices. Articles in the International Journal of Surgery showed greatest use of open science practices, with a mean of 1.6 open science practices compared to 0.36 across the other journals (p<.001). Adoption of open science practices in surgical research remains low, and further work is needed to increase utilization of these tools.

Sex-Related Differences in Patient Characteristics, Risk Factors, and Symptomatology in Older Adults with Pulmonary Embolism: Findings from the SERIOUS-PE Study.

Sex-specific factors are implicated in pulmonary embolism (PE) presentation in young patients, as indicated by increased risk in pregnancy. Whether sex differences exist in PE presentation, comorbidities, and symptomatology in older adults, the age group in which most PEs occur, remains unknown. We identified older adults (aged ≥65 years) with PE in a large international PE registry replete with information about relevant clinical characteristics (RIETE registry, 2001-2021). To provide national data from the United States, we assessed sex differences in clinical characteristics and risk factors of Medicare beneficiaries with PE (2001-2019). The majority of older adults with PE in RIETE (19,294/33,462, 57.7%) and in the Medicare database (551,492/948,823, 58.7%) were women. Compared with men, women with PE less frequently had atherosclerotic diseases, lung disease, cancer, or unprovoked PE, but more frequently had varicose veins, depression, prolonged immobility, or history of hormonal therapy (p < 0.001 for all). Women less often presented with chest pain (37.3 vs. 40.6%) or hemoptysis (2.4 vs. 5.6%) but more often with dyspnea (84.6 vs. 80.9%) (p < 0.001 for all). Measures of clot burden, PE risk stratification, and use of imaging modalities were comparable between women and men. PE is more common in elderly women than in men. Cancer and cardiovascular disease are more common in men, whereas transient provoking factors including trauma, immobility, or hormone therapy are more common in elderly women with PE. Whether such differences correlate with disparities in treatment or differences in short- or long-term clinical outcomes warrants further investigation.

Comparing Detection Schemes for Adversarial Images against Deep Learning Models for Cancer Imaging.

Deep learning (DL) models have demonstrated state-of-the-art performance in the classification of diagnostic imaging in oncology. However, DL models for medical images can be compromised by adversarial images, where pixel values of input images are manipulated to deceive the DL model. To address this limitation, our study investigates the detectability of adversarial images in oncology using multiple detection schemes. Experiments were conducted on thoracic computed tomography (CT) scans, mammography, and brain magnetic resonance imaging (MRI). For each dataset we trained a convolutional neural network to classify the presence or absence of malignancy. We trained five DL and machine learning (ML)-based detection models and tested their performance in detecting adversarial images. Adversarial images generated using projected gradient descent (PGD) with a perturbation size of 0.004 were detected by the ResNet detection model with an accuracy of 100% for CT, 100% for mammogram, and 90.0% for MRI. Overall, adversarial images were detected with high accuracy in settings where adversarial perturbation was above set thresholds. Adversarial detection should be considered alongside adversarial training as a defense technique to protect DL models for cancer imaging classification from the threat of adversarial images.

Characterization of multi-domain postoperative recovery trajectories after cardiac surgery using a digital platform.

Understanding postoperative recovery is critical for guiding efforts to improve post-acute phase care. How recovery evolves during the first 30 days after cardiac surgery is not well-understood. A digital platform may enable granular quantification of recovery by frequently capturing patient-reported outcome measures (PROM) that can be clinically implemented to support recovery. We conduct a prospective cohort study using a digital platform to measure recovery after cardiac surgery using a PROM sent every 3 days for 30 days after surgery to characterize recovery in multiple domains (e.g., pain, sleep, activities of daily living, anxiety) and to identify factors related to the patient's perception of overall recovery. We enroll patients who underwent cardiac surgery at a tertiary center between January 2019 and March 2020 and automatically deliver PROMs and reminders electronically. Of the 10 surveys delivered per patient, 8 (IQR 6-10) are completed. Patients who experienced postoperative complications more commonly belong to the worst overall recovery trajectory. Of the 12 domains modeled, only the worst anxiety trajectory is associated with the worse overall recovery trajectory membership, suggesting that even when patients struggle in the recovery of other domains, the patient may still feel progress in their recovery. We demonstrate that using a digital platform, automated PROM data collection, and characterization of multi-domain recovery trajectories is feasible and likely implementable in clinical practice. Overall recovery may be impacted by complications, while slow progress in constituent domains may still allow for the perception of overall recovery progression.

Racial and Ethnic Disparities in Financial Barriers Among Overweight and Obese Adults Eligible for Semaglutide in the United States.

Background Semaglutide holds the promise for weight loss and risk reduction. Less is known about racial and ethnic disparities in financial barriers among the semaglutide-eligible population. Methods and Results We conducted a cross-sectional analysis of adults aged 18 years or older using data from the National Health and Nutrition Examination Survey 2015 to 2020. We analyzed adults eligible for semaglutide based on Food and Drug Administration labeling and assessed financial barriers and social determinants of health among the eligible population overall and by race and ethnicity. A total of 13 711 adults were included in the final analysis. In 2015 to 2020, 51.1% (48.3%-53.2%) of US adults (≈43.3 million) met the Food and Drug Administration eligibility criteria for semaglutide. The percentage of adults eligible for semaglutide was highest among Black adults (56.6% [54.2%-59.1%]), followed by Hispanic adults (55.0% [52.8%-57.3%]). Among adults eligible for semaglutide, 11.9% (10.1%-13.6%) were uninsured, 13.3% (12.1%-14.5%) lacked a usual source of care, 33.6% (30.2%-36.9%) had low family income, and 38.9% (36.5%-41.3%) lacked higher education. Compared with White individuals, significantly larger proportions of Black and Hispanic individuals were uninsured, lacked a usual source of care, had low family income, or lacked higher education (P<0.001 for all). Conclusions Many Americans who were eligible for semaglutide were likely to be unable to afford the medication. Among the eligible population, a larger proportion of Black and Hispanic adults had financial barriers than other subgroups.

Identifying quality of life outcome patterns to inform treatment choices in ischemic cardiomyopathy.

BACKGROUND: The Surgical Treatment for Ischemic Heart Failure (STICH) trial found that routine use of coronary artery bypass surgery (CABG) improved mean quality of life (QoL) scores relative to guideline-directed medical therapy (GDMT) in patients with ischemic cardiomyopathy. However, mean differences in QoL scores do not provide what patients want to know when facing a high-risk/high-benefit treatment choice. METHODS: We analyzed Kansas City Cardiomyopathy Questionnaire (KCCQ) Overall Summary scores in CABG and GDMT patients over 36 months using a combination of statistical methods to group QoL data into clinically relevant outcome patterns (phenotype trajectories) and to then identify the main baseline predictors of each phenotype. QoL outcome phenotypes were developed using mixture models to define the dominant phenotype trajectories present in STICH QoL data. Logistic regression models were used to predict each patient's probability of achieving each outcome pattern with each treatment. RESULTS: In STICH, 592 patients underwent CABG and 607 were managed with GDMT. Our analyses identified 3 phenotype trajectory patterns in both treatment groups. Two of the 3 trajectories showed improving patterns, and were classified as "good QoL trajectories," seen in 498 (84.1%) CABG and 449 (73.9%) GDMT patients. Defining a consequential CABG-GDMT treatment difference as a >10% higher absolute predicted probability of belonging to good QoL trajectories, 277 (23.5%) patients were more likely to have good outcome with CABG while 45 (3.8%) patients were more likely to have a good outcome with GDMT. For 644 (54.7%) patients, CABG and GDMT probabilities of a good outcome were within 5% of each other. CONCLUSIONS: The pattern of QoL outcomes after CABG compared with GDMT in STICH followed 3 main phenotypic trajectories, which could be predicted based on individual baseline features. Patient-specific predictions about expected QoL outcomes with different treatment choices provide an intuitive framework for personalizing patient decision making.

Clinical Presentation and Short- and Long-term Outcomes in Patients With Isolated Distal Deep Vein Thrombosis vs Proximal Deep Vein Thrombosis in the RIETE Registry.

Importance: Insufficient data exist about the clinical presentation, short-term, and long-term outcomes of patients with isolated distal deep vein thrombosis (IDDVT), that is, thrombosis in infrapopliteal veins without proximal extension or pulmonary embolism (PE). Objective: To determine the clinical characteristics, short-term, and 1-year outcomes in patients with IDDVT and to compare the outcomes in unadjusted and multivariable adjusted analyses with patients who had proximal DVT. Design, Setting, and Participants: This was a multicenter, international cohort study in participating sites of the Registro Informatizado Enfermedad Tromboembólica (RIETE) registry conducted from March 1, 2001, through February 28, 2021. Patients included in this study had IDDVT. Patients with proximal DVT were identified for comparison. Patients were excluded if they had a history of asymptomatic DVT, upper-extremity DVT, coexisting PE, or COVID-19 infection. Main Outcomes and Measures: Primary outcomes were 90-day and 1-year mortality, 1-year major bleeding, and 1-year venous thromboembolism (VTE) deterioration, which was defined as subsequent development of proximal DVT or PE. Results: A total of 33 897 patients were identified with isolated DVT (without concomitant PE); 5938 (17.5%) had IDDVT (mean [SD] age, 61 [17] years; 2975 male patients [50.1%]), and 27 959 (82.5%) had proximal DVT (mean [SD] age, 65 [18] years; 14 315 male patients [51.2%]). Compared with individuals with proximal DVT, those with IDDVT had a lower comorbidity burden but were more likely to have had recent surgery or to have received hormonal therapy. Patients with IDDVT had lower risk of 90-day mortality compared with those with proximal DVT (odds ratio [OR], 0.47; 95% CI, 0.40-0.55). Findings were similar in 1-year unadjusted analyses (hazard ratio [HR], 0.52; 95% CI, 0.46-0.59) and adjusted analyses (HR, 0.72; 95% CI, 0.64-0.82). Patients with IDDVT had a lower 1-year hazard of VTE deterioration (HR, 0.83; 95% CI, 0.69-0.99). In 1-year adjusted analyses of patients without an adverse event within the first 3 months, IDDVT was associated with lower risk of VTE deterioration (adjusted HR, 0.48; 95% CI, 0.24-0.97). By 1-year follow-up, symptoms or signs of postthrombotic syndrome were less common in patients with IDDVT (47.6% vs 60.5%). Conclusions and Relevance: Results of this cohort study suggest that patients with IDDVT had a less ominous prognosis compared with patients with proximal DVT. Such differences were likely multifactorial, including the differences in demographics, risk factors, comorbidities, particularly for all-cause mortality, and a potential association of thrombus location with VTE deterioration and postthrombotic syndrome. Randomized clinical trials are needed to assess the optimal long-term management of IDDVT.

Trends in Adverse Event Rates in Hospitalized Patients, 2010-2019.

Importance: Patient safety is a US national priority, yet lacks a comprehensive assessment of progress over the past decade. Objective: To determine the change in the rate of adverse events in hospitalized patients. Design, Setting, and Participants: This serial cross-sectional study used data from the Medicare Patient Safety Monitoring System from 2010 to 2019 to assess in-hospital adverse events in patients. The study included 244 542 adult patients hospitalized in 3156 US acute care hospitals across 4 condition groups from 2010 through 2019: acute myocardial infarction (17%), heart failure (17%), pneumonia (21%), and major surgical procedures (22%); and patients hospitalized from 2012 through 2019 for all other conditions (22%). Exposures: Adults aged 18 years or older hospitalized during each included calendar year. Main Outcomes and Measures: Information on adverse events (abstracted from medical records) included 21 measures across 4 adverse event domains: adverse drug events, hospital-acquired infections, adverse events after a procedure, and general adverse events (hospital-acquired pressure ulcers and falls). The outcomes were the total change over time for the observed and risk-adjusted adverse event rates in the subpopulations. Results: The study sample included 190 286 hospital discharges combined in the 4 condition-based groups of acute myocardial infarction, heart failure, pneumonia, and major surgical procedures (mean age, 68.0 [SD, 15.9] years; 52.6% were female) and 54 256 hospital discharges for the group including all other conditions (mean age, 57.7 [SD, 20.7] years; 59.8% were female) from 3156 acute care hospitals across the US. From 2010 to 2019, the total change was from 218 to 139 adverse events per 1000 discharges for acute myocardial infarction, from 168 to 116 adverse events per 1000 discharges for heart failure, from 195 to 119 adverse events per 1000 discharges for pneumonia, and from 204 to 130 adverse events per 1000 discharges for major surgical procedures. From 2012 to 2019, the rate of adverse events for all other conditions remained unchanged at 70 adverse events per 1000 discharges. After adjustment for patient and hospital characteristics, the annual change represented by relative risk in all adverse events per 1000 discharges was 0.94 (95% CI, 0.93-0.94) for acute myocardial infarction, 0.95 (95% CI, 0.94-0.96) for heart failure, 0.94 (95% CI, 0.93-0.95) for pneumonia, 0.93 (95% CI, 0.92-0.94) for major surgical procedures, and 0.97 (95% CI, 0.96-0.99) for all other conditions. The risk-adjusted adverse event rates declined significantly in all patient groups for adverse drug events, hospital-acquired infections, and general adverse events. For patients in the major surgical procedures group, the risk-adjusted rates of events after a procedure declined significantly. Conclusions and Relevance: In the US between 2010 and 2019, there was a significant decrease in the rates of adverse events abstracted from medical records for patients admitted for acute myocardial infarction, heart failure, pneumonia, and major surgical procedures and there was a significant decrease in the adjusted rates of adverse events between 2012 and 2019 for all other conditions. Further research is needed to understand the extent to which these trends represent a change in patient safety.

Efficacy and Safety Considerations With Dose-Reduced Direct Oral Anticoagulants: A Review.

Importance: Dose-reduced regimens of direct oral anticoagulants (DOACs) may be used for 2 main purposes: dose-adjusted treatment intended as full-intensity anticoagulation (eg, for stroke prevention in atrial fibrillation [AF] in patients requiring dose reduction) or low-intensity treatment (eg, extended-duration treatment of venous thromboembolism [VTE]). We reviewed randomized clinical trials (RCTs) to understand the scenarios in which dose-adjusted or low-intensity DOACs were tested and reviewed the labeled indications by regulatory authorities, using data from large registries to assess whether the use of dose-reduced DOACs in routine practice aligned with the findings of RCTs. Observations: Among 4191 screened publications, 35 RCTs that used dose-adjusted DOACs were identified for dabigatran, apixaban, rivaroxaban, and edoxaban. Of these 35 RCTs, 29 were related to stroke prevention in AF. Efficacy and safety results for dose-adjusted DOACs in large RCTs of AF were similar to those found for full-dose DOACs. To our knowledge, dabigatran, apixaban, and rivaroxaban have not been studied as dose-adjusted therapy for acute VTE treatment. Low-intensity DOACs were identified in 37 RCTs. Low-intensity DOACs may be used for extended-duration treatment of VTE (apixaban and rivaroxaban), primary prevention in orthopedic surgeries (dabigatran, apixaban, and rivaroxaban), primary prevention in ambulatory high-risk cancer patients (apixaban and rivaroxaban) or (postdischarge) high-risk medical patients (rivaroxaban), in stable atherosclerotic vascular disease, or after a recent revascularization for peripheral artery disease in conjunction with aspirin (rivaroxaban). Minor variations exist between regulatory authorities in different regions regarding criteria for dose adjustment of DOACs. Data from large registries indicated that dose-reduced DOACs were used occasionally with doses or for clinical scenarios different from those studied in RCTs or recommended by regulatory authorities. Conclusions and Relevance: Dose adjustment and low-intensity treatment are 2 different forms of dose-reduced DOACs. Dose adjustment is mostly relevant for AF and should be done based on the approved criteria. Dose adjustment of DOACs should not be used for acute VTE treatment in most cases. In contrast, low-intensity DOACs may be used for primary or secondary VTE prevention for studied and approved indications. Attention should be given to routine practice patterns to align the daily clinical practice with existing evidence of safety and efficacy.

Sex-Specific Risk Factors Associated With First Acute Myocardial Infarction in Young Adults.

Importance: An increasing proportion of people in the US hospitalized for acute myocardial infarction (AMI) are younger than 55 years, with the largest increase in young women. Effective prevention requires an understanding of risk factors associated with risk of AMI in young women compared with men. Objectives: To assess the sex-specific associations of demographic, clinical, and psychosocial risk factors with first AMI among adults younger than 55 years, overall, and by AMI subtype. Design, Setting, and Participants: This study used a case-control design with 2264 patients with AMI, aged 18 to 55 years, from the VIRGO (Variation in Recovery: Role of Gender on Outcomes of Young AMI Patients) study and 2264 population-based controls matched for age, sex, and race and ethnicity from the National Health and Nutrition Examination Survey from 2008 to 2012. Data were analyzed from April 2020 to November 2021. Exposures: A wide range of demographic, clinical, and psychosocial risk factors. Main Outcomes and Measures: Odds ratios (ORs) and population attributable fractions (PAF) for first AMI associated with demographic, clinical, and psychosocial risk factors. Results: Of the 4528 case patients and matched controls, 3122 (68.9%) were women, and the median (IQR) age was 48 (44-52) years. Seven risk factors (diabetes [OR, 3.59 (95% CI, 2.72-4.74) in women vs 1.76 (1.19-2.60) in men], depression [OR, 3.09 (95% CI, 2.37-4.04) in women vs 1.77 (1.15-2.73) in men], hypertension [OR, 2.87 (95% CI, 2.31-3.57) in women vs 2.19 (1.65-2.90) in men], current smoking [OR, 3.28 (95% CI, 2.65-4.07) in women vs 3.28 (2.65-4.07) in men], family history of premature myocardial infarction [OR, 1.48 (95% CI, 1.17-1.88) in women vs 2.42 (1.71-3.41) in men], low household income [OR, 1.79 (95% CI, 1.28-2.50) in women vs 1.35 (0.82-2.23) in men], hypercholesterolemia [OR, 1.02 (95% CI, 0.81-1.29) in women vs 2.16 (1.49-3.15) in men]) collectively accounted for the majority of the total risk of AMI in women (83.9%) and men (85.1%). There were significant sex differences in risk factor associations: hypertension, depression, diabetes, current smoking, and family history of diabetes had stronger associations with AMI in young women, whereas hypercholesterolemia had a stronger association in young men. Risk factor profiles varied by AMI subtype, and traditional cardiovascular risk factors had higher prevalence and stronger ORs for type 1 AMI compared with other AMI subtypes. Conclusions and Relevance: In this case-control study, 7 risk factors, many potentially modifiable, accounted for 85% of the risk of first AMI in young women and men. Significant differences in risk factor profiles and risk factor associations existed by sex and by AMI subtype. These findings suggest the need for sex-specific strategies in risk factor modification and prevention of AMI in young adults. Further research is needed to improve risk assessment of AMI subtypes.

Study protocol for the Innovative Support for Patients with SARS-COV-2 Infections Registry (INSPIRE): A longitudinal study of the medium and long-term sequelae of SARS-CoV-2 infection.

BACKGROUND: Reports on medium and long-term sequelae of SARS-CoV-2 infections largely lack quantification of incidence and relative risk. We describe the rationale and methods of the Innovative Support for Patients with SARS-CoV-2 Registry (INSPIRE) that combines patient-reported outcomes with data from digital health records to understand predictors and impacts of SARS-CoV-2 infection. METHODS: INSPIRE is a prospective, multicenter, longitudinal study of individuals with symptoms of SARS-CoV-2 infection in eight regions across the US. Adults are eligible for enrollment if they are fluent in English or Spanish, reported symptoms suggestive of acute SARS-CoV-2 infection, and if they are within 42 days of having a SARS-CoV-2 viral test (i.e., nucleic acid amplification test or antigen test), regardless of test results. Recruitment occurs in-person, by phone or email, and through online advertisement. A secure online platform is used to facilitate the collation of consent-related materials, digital health records, and responses to self-administered surveys. Participants are followed for up to 18 months, with patient-reported outcomes collected every three months via survey and linked to concurrent digital health data; follow-up includes no in-person involvement. Our planned enrollment is 4,800 participants, including 2,400 SARS-CoV-2 positive and 2,400 SARS-CoV-2 negative participants (as a concurrent comparison group). These data will allow assessment of longitudinal outcomes from SARS-CoV-2 infection and comparison of the relative risk of outcomes in individuals with and without infection. Patient-reported outcomes include self-reported health function and status, as well as clinical outcomes including health system encounters and new diagnoses. RESULTS: Participating sites obtained institutional review board approval. Enrollment and follow-up are ongoing. CONCLUSIONS: This study will characterize medium and long-term sequelae of SARS-CoV-2 infection among a diverse population, predictors of sequelae, and their relative risk compared to persons with similar symptomatology but without SARS-CoV-2 infection. These data may inform clinical interventions for individuals with sequelae of SARS-CoV-2 infection.

Using Adversarial Images to Assess the Robustness of Deep Learning Models Trained on Diagnostic Images in Oncology.

PURPOSE: Deep learning (DL) models have rapidly become a popular and cost-effective tool for image classification within oncology. A major limitation of DL models is their vulnerability to adversarial images, manipulated input images designed to cause misclassifications by DL models. The purpose of the study is to investigate the robustness of DL models trained on diagnostic images using adversarial images and explore the utility of an iterative adversarial training approach to improve the robustness of DL models against adversarial images. METHODS: We examined the impact of adversarial images on the classification accuracies of DL models trained to classify cancerous lesions across three common oncologic imaging modalities. The computed tomography (CT) model was trained to classify malignant lung nodules. The mammogram model was trained to classify malignant breast lesions. The magnetic resonance imaging (MRI) model was trained to classify brain metastases. RESULTS: Oncologic images showed instability to small pixel-level changes. A pixel-level perturbation of 0.004 (for pixels normalized to the range between 0 and 1) resulted in most oncologic images to be misclassified (CT 25.6%, mammogram 23.9%, and MRI 6.4% accuracy). Adversarial training improved the stability and robustness of DL models trained on oncologic images compared with naive models ([CT 67.7% v 26.9%], mammogram [63.4% vs 27.7%], and MRI [87.2% vs 24.3%]). CONCLUSION: DL models naively trained on oncologic images exhibited dramatic instability to small pixel-level changes resulting in substantial decreases in accuracy. Adversarial training techniques improved the stability and robustness of DL models to such pixel-level changes. Before clinical implementation, adversarial training should be considered to proposed DL models to improve overall performance and safety.

A prospective cohort study examining exposure to incarceration and cardiovascular disease (Justice-Involved Individuals Cardiovascular Disease Epidemiology - JUSTICE study): a protocol paper.

BACKGROUND: People who have been incarcerated have high rates of cardiovascular risk factors, such as hypertension and smoking, and cardiovascular disease (CVD) is a leading cause of hospitalizations and mortality in this population. Despite this, little is known regarding what pathways mediate the association between incarceration exposure and increased rates of CVD morbidity and especially what incarceration specific factors are associated with this risk. The objective of this study is to better understand CVD risk in people exposed to incarceration and the pathways by which accumulate cardiovascular risk over time. METHODS AND ANALYSIS: The Justice-Involved Individuals Cardiovascular Disease Epidemiology (JUSTICE) study is a prospective cohort study of individuals released from incarceration with known cardiovascular risk factors. We are recruiting 500 individuals within three months after release from jail/prison. At baseline we are assessing traditional risk factors for CVD, including diet, exercise, and smoking, and exposure to incarceration-related policies, psychosocial stress, and self-efficacy. Cardiovascular risk factors are measured at baseline through point of care testing. We are following these individuals for the 12 months following the index release from incarceration with re-evaluation of psychosocial factors and clinical risk factors every 6 months. Using these data, we will estimate the direct and indirect latent effects of incarceration on cardiovascular risk factors and the paths via which these effects are mediated. We will also model the anticipated 10-year burden of CVD incidence, health care use, and mortality associated with incarceration. DISCUSSION: Our study will identify factors associated with CVD risk factor control among people released from incarceration. Our measurement of incarceration-related exposures, psychosocial factors, and clinical measures of cardiovascular risk will allow for identification of unique targets for intervention to modify CVD risk in this vulnerable population.