Johnson, Patrick W.

Abstract Background Atrial fibrillation (AF) is diagnosed in up to 50% of patients with heart failure. However, the prevalence of AF among patients with peripartum cardiomyopathy (PPCM) ranges from only 2–10%, with the lowest rates in Black women. An artificial intelligence enhanced electrocardiogram (AI-ECG) has previously been shown to be effective in detecting AF while in sinus rhythm, and for AF risk prediction in a population-based study. Purpose Our objective was to evaluate the use of an AI-ECG for AF risk stratification among women of reproductive age (18 to 49 years) with PPCM compared to other forms of cardiomyopathy. Methods We identified 59 reproductive age women with a diagnosis of PPCM between January 2007, and October 2018 and included matched controls in a 3:1 fashion. Matching was performed based on sex, age, race, and left ventricular ejection fraction. We excluded patients with a diagnosis of AF prior to cardiomyopathy diagnosis date. AI-ECG prediction probabilities were generated for ECGs performed within a 30-day window prior to the patient's first cardiomyopathy diagnosis date for the entire study cohort. Results A total of 236 patients were included in the final analysis (59 cases, 177 controls). Overall, the median age at cardiomyopathy diagnosis was 31.7 years (IQR: 18.5, 49.4), 76.3% were White, 8.5% were Black, and 15.3% represented other or unknown race. Over the period studied, 3.4% of women with PPCM developed AF compared to 5.6% of women with other cardiomyopathies. The frequency of positive AI-ECG predictions for AF was more common among women with other cardiomyopathies (40.7%) compared to women with PPCM (20.3%). The predicted odds ratio for AF development following a cardiomyopathy diagnosis based on AI-ECG results was 0.37 (95% CI: 0.18, 0.73) for PPCM compared to other cardiomyopathies (p=0.006). Conclusion We demonstrated that an AI-ECG model for AF prediction may play a potential role in arrhythmia risk stratification/prediction among young women with PPCM who have a demonstrable lower risk for AF compared to women with other cardiomyopathies. Mechanisms for lower AF risk among patients with PPCM remain unknown. Further studies evaluating mechanistic pathways will be essential. Funding Acknowledgement Type of funding sources: None.

Abstract Background Screening for left ventricular (LV) systolic dysfunction (defined as ejection fraction ≤35%) based on data from a standard 12-lead electrocardiogram (ECG) has become well established when standard digital ECGs are available–8 independent leads sampled at least 250 hertz for 10 seconds. As the algorithm has been incorporated into various clinical scenarios and ancillary research projects, a limitation of the binary classification at 35% has become apparent. Purpose The objective of this study was to develop and validate a deep learning-based algorithm that would classify LVEF into three categories based on only the digital ECG input. Methods After IRB approval, native digital resting ECGs acquired between 1/1/2010 and 12/31/2021 on patients seen in Mayo Clinic in Jacksonville were extracted from the institutional electronic ECG database management system (MUSE, GE Healthcare). These ECGs were matched with transthoracic echocardiograms obtained up to four days prior or 30 days after the ECGs acquisition. A convolutional neural network consisting of 8 layers of convolutions, batch normalization and pooling was trained using Keras and Tensorflow with hyper-parameter optimization for L1 and L2 regularization, learning rate adjustments, and class weights to predict three classes of LVEF: ≤35%, 36–51%, and ≥52% based on clinical relevance. The primary measure of overall performance was the detection of LVEF ≤35%; however, the triad of model predictions was also considered in translating the model output to human interpretable findings. Results A total of 30,153 patients (60,169 ECG pairings; mean age 63 years; 48% male) were randomly split at the patient level into training (24,172 patients), validation (2,973 patients) and testing (3,008 patients). The trained model provided robust discrimination in the withheld testing data – AUROC of 0.941 (95% CI: 0.931 to 0.950). Using the optimal model threshold based on Youden's index from the validation data (0.186), sensitivity and specificity were estimated to be 87.9% (95% CI: 83.8% to 91.2%) and 86.3% (95% CI: 85.4% to 87.2%) in the testing data. In instances where discordant predictions were observed, the posterior distribution of model probabilities provide additional insights into the possible underlying value of LVEF (Figure 1). Conclusions The utilization of a multi-category deep learning classification model for the detection of reduced ejection fraction adds new dimensions to the use of AI technologies on digital ECGs. This work shows high discrimination can still be obtained when using three classes of LVEF. Funding Acknowledgement Type of funding sources: None.

Abstract Background Current approaches utilizing non-invasive methods to screen for cardiac allograft rejection (gene expression profiling and cell free DNA) have yet to be broadly integrated into heart transplant management and have shown limited discrimination (AUCs of 0.68 and 0.77, respectively). Changes in the electrocardiogram (ECG) have been reported at the time of severe cardiac rejection, including low voltages and conduction abnormalities. It remains unknown if subtle ECG changes correlating with cardiac allograft rejection can be detected earlier using machine learning methods. Purpose We sought to develop an artificial intelligence (AI) model to detect cardiac allograft rejection based on the 12 lead ECG. Methods We identified all patients who underwent a heart transplant at 3 hospital sites within a single health system from Jan 1998 through Apr 2021 and extracted digital 12-lead ECG data as well as endomyocardial biopsy pathology results from the electronic medical record. We partitioned our data into a training (80%), validation (10%), and test set (10%) based on a group stratification sampling. Each patient was present in only one set and each set had a positivity rate of 2.6% with 6,074/758/758 ECGs belonging to 1,146/140/141 unique patients in each set respectively. Cardiac allograft rejection was defined as moderate or severe acute cellular rejection based on International Society for Heart and Lung Transplantation (ISHLT) guidelines. A convolutional neural network, using the 12-lead ECG data as input, was trained with hyperparameter optimization for regularization, learning rate adjustments, and class weights. Model performance metrics were based on the test data and estimated using the final model architecture. Results 1,587 heart transplant recipients who had at least one endomyocardial biopsy were evaluated for inclusion. We limited our sample to ECGs performed within 30 days of the biopsy date (7,590 ECGs, representing 1,425 unique patients). Our study population had a median age of 55.8 years and 28.7% were female. The median number of ECG-biopsy pairs per patient was 5. The majority of endomyocardial biopsy results were classified as none or mild rejection (97.1%), and 2.9% had moderate/severe rejection. The ECG-based AI model detected cardiac allograft rejection with an area under the receiver operative curve (AUC) of 0.84 in the test set. The sensitivity, specificity, positive and negative predictive values were 95%, 52.6%. 5.2% and 99.7% respectively. Conclusions An AI-ECG model appears to outperform novel non-invasive laboratory tests (gene expression profiling and cell free DNA) for detecting cardiac allograft rejection and does not require a blood draw or the additional complexities surrounding sample processing. This model relies on a readily available and relatively inexpensive test, the ECG. In addition, AI predictions can be made available within a few minutes following ECG acquisition. Funding Acknowledgement Type of funding sources: Private hospital(s). Main funding source(s): Mayo Clinic

Abstract The anti-spike T-cell and antibody responses to SARS-CoV-2 mRNA vaccines in patients with B-cell malignancies were examined in a real-world setting. A next-generation sequencing (NGS)–based molecular assay was used to assess SARS-CoV-2–specific T-cell responses. After the second dose, 58% (166/284) of seropositive and 45% (99/221) of seronegative patients display anti-spike T cells. The percentage of patients who displayed T-cell response was higher among patients receiving mRNA-1273 vaccines compared with those receiving BNT162b2 vaccines. After the third vaccination, 40% (137/342) of patients seroconverted, although only 22% displayed sufficient antibody levels associated with the production of neutralizing antibodies. 97% (717/738) of patients who were seropositive before the third dose had markedly elevated anti-spike antibody levels. Anti-spike antibody levels, but not T-cell responses, were depressed by B cell–directed therapies. Vaccinated patients with B-cell malignancies with a poor response to SARS-CoV-2 vaccines may remain vulnerable to COVID-19 infections. Significance: This study represents the first investigation of SARS-CoV-2–specific immune responses to vaccination in a patient registry using an NGS-based method for T-cell receptor repertoire–based analysis combined with anti-spike antibody assessments. Vaccinated patients with B cell–derived hematologic malignancies are likely at higher risk of infection or severe COVID-19. This article is highlighted in the In This Issue feature, p. 476

Background: Transcatheter aortic valve replacement (TAVR) is now an approved alternative to surgical aortic valve replacement for the treatment of severe aortic stenosis. As the clinical adoption of TAVR expands, it remains important to identify predictors of mortality after TAVR. We aimed to evaluate the impact of sex differences in aortic valve calcium score (AVCS) on long-term mortality following TAVR in a large patient sample. Methods: We included consecutive patients who successfully underwent TAVR for treatment of severe native aortic valve stenosis from June 2010 to May 2021 across all US Mayo Clinic sites with follow-up through July 2021. AVCS values were obtained from preoperative computed tomography of the chest. Additional clinical data were abstracted from medical records. Kaplan-Meier curves and Cox-proportional hazard regression models were employed to evaluate the effect of AVCS on long-term mortality. Results: A total of 2543 patients were evaluated in the final analysis. Forty-one percent were women, median age was 82 years (Q1: 76, Q3: 86), 18.4% received a permanent pacemaker following TAVR, and 88.5% received a balloon expandable valve. We demonstrate an increase in mortality risk with higher AVCS after multivariable adjustment ( P <0.001). When stratified by sex, every 500-unit increase in AVCS was associated with a 7% increase in mortality risk among women (adjusted hazard ratio, 1.07 [95% CI, 1.02–1.12]) but not in men. Conclusions: We demonstrate a notable sex difference in the association between AVCS and long-term mortality in a large TAVR patient sample. This study highlights the potential value of AVCS in preprocedural risk stratification, specifically among women undergoing TAVR. Additional studies are needed to validate this finding.

AbstractBackgroundWhile COVID‐19 immunization programs attempted to reach targeted rates, cases rose significantly since the emergence of the delta variant. This retrospective cohort study describes the correlation between antispike antibodies and outcomes of hospitalized, breakthrough cases during the delta variant surge.MethodsAll patients with positive SARS‐CoV‐2 polymerase chain reaction hospitalized at Mayo Clinic Florida from 19 June 2021 to 11 November 2021 were considered for analysis. Cases were analyzed by vaccination status. Breakthrough cases were then analyzed by low and high antibody titers against SARS‐CoV‐2 spike protein, with a cut‐off value of ≥132 U/ml. Outcomes included hospital length of stay (LOS), need for intensive care unit (ICU), mechanical ventilation, and mortality. We used 1:1 nearest neighbor propensity score matching without replacement to assess for confounders.ResultsAmong 627 hospitalized patients with COVID‐19, vaccine breakthrough cases were older with more comorbidities compared to unvaccinated. After propensity score matching, the unvaccinated patients had higher mortality (27 [28.4%] vs. 12 [12.6%], p = 0.002) and LOS (7 [1.0–57.0] vs. 5 [1.0–31.0] days, p = 0.011). In breakthrough cases, low‐titer patients were more likely to be solid organ transplant recipients (16 [34.0%] vs. 9 [12.3%], p = 0.006), with higher need for ICU care (24 [51.1%] vs. 22 [11.0%], p = 0.034), longer hospital LOS (median 6 vs. 5 days, p = 0.013), and higher mortality (10 [21.3%] vs. 5 [6.8%], p = 0.025) than high‐titer patients.ConclusionsHospitalized breakthrough cases were more likely to have underlying risk factors than unvaccinated patients. Low‐spike antibody titers may serve as an indicator for poor prognosis in breakthrough cases admitted to the hospital.

Abstract Background Cardiovascular disease (CVD) has been identified as a major threat to maternal health in the US and UK with cardiomyopathy being one of the most common acquired CVD in the pregnant and postpartum period. Diagnosing cardiomyopathy in pregnancy is challenging due to an overlap of cardiovascular symptoms with normal pregnancy symptoms. Purpose The purpose of this study was to evaluate the effectiveness of an ECG based deep learning model in identifying cardiomyopathy among pregnant and postpartum women. Methods We utilized an ECG based deep learning model to detect cardiomyopathy in a cohort of pregnant or postpartum women seen at multiple hospital sites. Model performance was evaluated using area under the curve (AUC), accuracy, sensitivity, and specificity. We compared the diagnostic probabilities of the deep learning model with natriuretic peptides and a multivariable model consisting of demographic and clinical parameters. Results 1,807 women were included. 7%, 10% and 13% had LVEF ≤35%, &lt;45% and &lt;50% respectively. The ECG based deep learning model identified cardiomyopathy with an AUC of 0.92 for left ventricular ejection fraction (LVEF) ≤35%, 0.89 for LVEF &lt;45% and 0.87 for LVEF &lt;50%. For LVEF ≤35%, AUC was higher in Black (0.95) and Hispanic (0.98) women compared to white (0.91). Natriuretic peptides and the multivariable model had AUCs of 0.85 and 0.72 respectively. Conclusions A deep learning model effectively identifies cardiomyopathy in pregnant or postpartum women, outperforms natriuretic peptides and traditional clinical parameters with the potential to become a powerful initial screening tool for cardiomyopathy in the obstetric care setting. Funding Acknowledgement Type of funding sources: Other. Main funding source(s): This study was made possible using resources supported by the Mayo Clinic Women's Health Research Center and the Mayo Clinic Building Interdisciplinary Research Careers in Women's Health (BIRCWH) Program funded by the National Institutes of Health (NIH), grant number K12 HD065987. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.

Abstract Although SARS-CoV-2 vaccines induce a robust immune response in healthy individuals, limited reports indicate that some immunocompromised patients may not produce anti-spike antibodies after vaccination. In this report, we assessed anti-spike antibody levels among 2200 patients with hematologic malignancies after SARS-CoV-2 mRNA vaccination (NCT04794387). Diagnoses and treatments were self-reported using a national online registry. The side-effects profile of the vaccines was not different compared to previous studies in healthy individuals. The serological response &gt;14 days after full vaccination was evaluated using the Roche Elecsys total immunoglobulin anti-spike assay (range: 0-250 U/ml; positive cutoff of &gt; 0.8 U/mL). Approximately 40% and 60% were male and females, respectively, 96% were white or Caucasian, and the median age was 67 (range, 21 to 92 years). Patients received the BNT162b (Pfizer/BioNtech: 55%) or mRNA1246 (Moderna: 45%) vaccines. The largest patient populations had chronic lymphocytic leukemia (CLL: N = 978, 44%), multiple myeloma (MM: 253, 11.4%), follicular lymphoma (FL: 147, 6.6%), Waldenstrom’s macroglobulinemia (WM: 115, 5.9%), Hodgkin lymphoma (HL: 79, 3.5%), diffuse large B-cell lymphoma (DLBCL: 83, 3.7%), mantle cell lymphoma (MCL: 58, 2.6%), or marginal zone lymphomas (MZL: 52, 2.3%). Ninety-one patients (3.8%) were positive for the nucleocapsid antibodies and deleted from the initial analysis. Overall, 564 patients (25%) were seronegative after full vaccination. The largest percentages of seronegative patients had B-cell derived hematologic malignancies: MCL (50%), MZL (37%), DLBCL (34%), CLL (32%), FL (28%), and WM (25%). Seronegative rates of 5.9% and 14% were found in patients with multiple myeloma and acute lymphoblastic leukemia, respectively. All but one HL patient and no patients with smoldering multiple myeloma, myeloproliferative neoplasms, myelodysplastic syndrome were seronegative. Anti-spike antibody levels did not markedly change within 35 individual patients &gt;45 days after the initial vaccine assessment except for one patient who seroconverted after a third vaccine dose. High seronegative rates correlated with treatment regimens that contained anti-CD20 mAbs, any Bruton tyrosine kinase inhibitor, and CD19-directed CAR T-therapy. Seronegative rates were higher with the BioNTech/Pfizer vs. Moderna vaccines in an unadjusted analysis (odds ratio, 1.5; 95% confidence interval, 1.05-1.55; p= 0.015). The overall seronegative rate was ~1% among nucleocapsid-positive patients. Among CLL patients, the seronegative rate was lower among nucleocapsid-positive patients compared to nucleocapsid-negative patients (0% vs. 32%, p&lt;0.001). Providers should be aware that a substantial subset of vaccinated blood cancer patients may be at high risk of breakthrough COVID-19 infections. Alternate therapies with monoclonal antibodies or booster vaccination including those that would allow exposure to more than the spike protein, may offer additional protection for this vulnerable population. Citation Format: Lee M. Greenberger, Larry A. Saltzman, Jonathon W. Senefeld, Patrick W. Johnson, Louis J. DeGennaro, Gwen L. Nichols. Impaired serological response to SARS-CoV-2 mRNA vaccination in patients with hematologic malignancies [abstract]. In: Proceedings of the AACR-NCI-EORTC Virtual International Conference on Molecular Targets and Cancer Therapeutics; 2021 Oct 7-10. Philadelphia (PA): AACR; Mol Cancer Ther 2021;20(12 Suppl):Abstract nr P161.