Citations

Abstract Aims Coronary angiography might contain clinically relevant information, beyond its traditional role in delineating coronary artery disease. We sought to explore the role of deep learning (DL) in detecting right ventricular dysfunction from routinely acquired cine images during coronary angiography. Methods and results 3D-convolutional neural networks (CNN) were trained to identify right ventricle (RV) dysfunction from diagnostic angiography of the right coronary artery (RCA). The model’s input was two cine angiograms from LAO and RAO projections. The model’s output was normal vs. abnormal RV function. Ground truth on RV function was obtained from the nearest transthoracic echocardiogram to the coronary angiogram. Two analyses were performed to identify (i) any RV dysfunction (≥mild) and (ii) significant RV dysfunction (≥mild–moderate). A total of 10 336 coronary angiograms from 9849 patients (mean age 66, 36% women) were included. The cohort was split into training (70%), validation (15%), and testing (15%) sets. In the testing sets, the models attained an area under the ROC curve (AUC), sensitivity, and specificity of 0.82 (95% CI: 0.80–0.84), 0.75, and 0.74, for detecting any RV dysfunction, and 0.83 (95% CI: 0.80–0.86), 0.82, and 0.70 for detecting significant (≥mild–moderate) RV dysfunction. Combining an ECG-driven AI model with the angio-driven model improved the AUC values to 0.83 and 0.87 for detecting any or advanced RV dysfunction, respectively. Conclusion A novel deep learning algorithm yielded acceptable classification accuracy in detecting RV dysfunction from routine cine angiography of the RCA. The model’s performance improved further by adding ECG to its inputs.

High dose chemotherapy followed by autologous hematopoietic cell transplantation (auto HCT) is a standard therapy for patients with plasma cell disorders (PCD). A barrier to improving candidate selection for auto HCT is appraisal of risk for transplant related complications. Electrocardiography (ECG) is a standard pre-HCT test to evaluate the potential for arrhythmia and structural heart disease. We hypothesized that an artificial intelligence (AI) based interpretation of ECG waveform data (AI-ECG) could enhance risk prediction for cardiac-specific and other outcomes following auto HCT for patients with PCD. To test this hypothesis, we used several AI-ECG tools developed using a deep-learning based approach that were trained to predict comorbidity (Attia et al, Lancet 2019 & Grogan et al, Mayo Clin Proc 2021). Model outputs include a scaled prediction value indicating increasing risk for atrial fibrillation/flutter (AF), reduced ejection fraction (EF), or cardiac amyloidosis. We evaluated this tool in 9,225 ECGs obtained from 849 patients (median 6 ECGs/patient, inter-quartile range: 3-12) who underwent first or subsequent auto HCT at Memorial Sloan Kettering Cancer Center between 2016-2022 and who had a diagnosis of multiple myeloma (N = 810), amyloidosis (N = 37), or other PCD (N = 2). The endpoints were to determine whether baseline AI-ECG prediction of AF risk correlated with peri-transplant AF events, and to explore whether model outputs correlated with survival and other cardiac clinical outcomes. The mean age of patients was 61.0 years (range 23.7 - 81.2) and median follow up was 2.7 years post auto HCT. Contributing cardiovascular risk factors included a prior history of AF (N = 101, 11.9%), coronary or cerebrovascular disease (N = 95, 11.2%), and diabetes mellitus (N = 98, 11.5%). Reduced dose melphalan (< 200 mg/m 2) was administered in 26%. The HCT-comorbidity index (HCT-CI) was high risk (≥3) in 52.7%. The one-year overall survival and progression-free survival in the whole cohort was 94% (95% confidence interval (95% CI): 92 - 95%) and 86% (84 - 89%), respectively. Among patients not in AF at pre HCT evaluation, the 90-day cumulative incidence of AF was 5.6% (4.2 - 7.3%). In univariable competing risk regression, baseline pre HCT AI-ECG appraisal of AF risk was strongly correlated with incidence AF in patients who were in sinus rhythm before HCT (hazard ratio (HR): 25.1, 95% CI: 11.7 - 53.7, p < 0.001). In a multivariable model adjusting for patient age and HCT-CI, AI-ECG AF predicted risk remained associated with incidence of post HCT AF (HR: 13.4, 95% CI: 5.9 - 30.4, p < 0.001). Considering a decision threshold identified during original model training, AI-ECG predicted AF events with an accuracy of 75% (Mcnemar's p < 2 x 10 -16). The precision, recall, and F1-score were 0.94, 0.77, and 0.85, respectively. AI-ECG predicted age correlated highly with actual patient age (Spearman rho = 0.59, p < 2 x 10 -16). Amyloid risk scores were highly correlated with a known clinical history of amyloidosis (median 0.45 versus 0.05, Wilcoxon rank-sum p < 0.001). Patients with EF < 50% had greater prediction scores for cardiomyopathy compared to patients with normal EF (median 0.23 versus 0.01, Wilcoxon rank-sum p <0.001). In univariable analysis, increasing AI-ECG predicted age (HR 1.02, CI: 1.003 - 1.04, p = 0.02) and predicted AF risk score (HR: 3.2, CI: 1.4 - 7.2, p = 0.006) were associated with risk for death, whereas predicted amyloid score and predicted low EF were not associated with decreased survival. In multivariable analysis of all patients that considered patient age, hematopoietic comorbidity index, and remission status at HCT, increasing predicted AF score trended towards association with increased risk for death (HR: 2.3, 95%CI: 1.0 - 5.5, p = 0.059). Predicted AF score correlated highly with the HCT-CI and patient age. Finally, we examined whether risk prediction for low EF correlated with peri-HCT fluid overload (FO) defined by absolute weight gain. The incidence of ≥ 10% weight gain (grade 2 FO) and ≥ 20% weight gain (grade 3 FO) at 180 days post HCT was 7.4% (95% CI: 5.8%, 9.3%) and 1.0% (95% CI: 0.5%, 1.8%), respectively. Predicted low EF was not associated with development of either grade 2 or grade 3 FO in this population. In summary, AI-ECG predicts episodes of AF in patients undergoing auto HCT for PCD and may augment transplant risk appraisal when considered in conjunction with other measures of comorbidity.

Abstract Aims Cardiotoxicity is a serious side effect of anthracycline treatment, most commonly manifesting as a reduction in left ventricular ejection fraction (EF). Early recognition and treatment have been advocated, but robust, convenient, and cost-effective alternatives to cardiac imaging are missing. Recent developments in artificial intelligence (AI) techniques applied to electrocardiograms (ECGs) may fill this gap, but no study so far has demonstrated its merit for the detection of an abnormal EF after anthracycline therapy. Methods and results Single centre consecutive cohort study of all breast cancer patients with ECG and transthoracic echocardiography (TTE) evaluation before and after (neo)adjuvant anthracycline chemotherapy. Patients with HER2-directed therapy, metastatic disease, second primary malignancy, or pre-existing cardiovascular disease were excluded from the analyses as were patients with EF decline for reasons other than anthracycline-induced cardiotoxicity. Primary readout was the diagnostic performance of AI-ECG by area under the curve (AUC) for EFs < 50%. Of 989 consecutive female breast cancer patients, 22 developed a decline in EF attributed to anthracycline therapy over a follow-up time of 9.8 ± 4.2 years. After exclusion of patients who did not have ECGs within 90 days of a TTE, 20 cases and 683 controls remained. The AI-ECG model detected an EF < 50% and ≤ 35% after anthracycline therapy with an AUC of 0.93 and 0.94, respectively. Conclusion These data support the use of AI-ECG for cardiotoxicity screening after anthracycline-based chemotherapy. This technology could serve as a gatekeeper to more costly cardiac imaging and could enable patients to monitor themselves over long periods of time.

Background: Patients with peripheral artery disease (PAD) are at increased risk for major adverse limb and cardiac events including mortality. Developing screening tools capable of accurate PAD identification is a necessary first step for strategies of adverse outcome prevention. This study aimed to determine whether machine analysis of a resting Doppler waveform using deep neural networks can accurately identify patients with PAD. Methods: Consecutive patients (4/8/2015 – 12/31/2020) undergoing rest and postexercise ankle–brachial index (ABI) testing were included. Patients were randomly allocated to training, validation, and testing subsets (70%/15%/15%). Deep neural networks were trained on resting posterior tibial arterial Doppler waveforms to predict normal (> 0.9) or PAD (⩽ 0.9) using rest and postexercise ABI. A separate dataset of 151 patients who underwent testing during a period after the model had been created and validated (1/1/2021 – 3/31/2021) was used for secondary validation. Area under the receiver operating characteristic curves (AUC) were constructed to evaluate test performance. Results: Among 11,748 total patients, 3432 patients met study criteria: 1941 with PAD (mean age 69 ± 12 years) and 1491 without PAD (64 ± 14 years). The predictive model with highest performance identified PAD with an AUC 0.94 (CI = 0.92–0.96), sensitivity 0.83, specificity 0.88, accuracy 0.85, and positive predictive value (PPV) 0.90. Results were similar for the validation dataset: AUC 0.94 (CI = 0.91–0.98), sensitivity 0.91, specificity 0.85, accuracy 0.89, and PPV 0.89 (postexercise ABI comparison). Conclusion: An artificial intelligence-enabled analysis of a resting Doppler arterial waveform permits identification of PAD at a clinically relevant performance level.

Abstract Aims Cardiovascular disease is a major threat to maternal health, with cardiomyopathy being among the most common acquired cardiovascular diseases during pregnancy and the postpartum period. The aim of our study was to evaluate the effectiveness of an electrocardiogram (ECG)-based deep learning model in identifying cardiomyopathy during pregnancy and the postpartum period. Methods and results We used an ECG-based deep learning model to detect cardiomyopathy in a cohort of women who were pregnant or in the postpartum period seen at Mayo Clinic. Model performance was evaluated using the area under the receiver operating characteristic 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. The study cohort included 1807 women; 7%, 10%, and 13% had left ventricular ejection fraction (LVEF) of 35% or less, <45%, and <50%, respectively. The ECG-based deep learning model identified cardiomyopathy with AUCs of 0.92 (LVEF ≤ 35%), 0.89 (LVEF < 45%), and 0.87 (LVEF < 50%). For LVEF of 35% or less, 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 to 0.86 and 0.72, respectively. Conclusions An ECG-based deep learning model effectively identifies cardiomyopathy during pregnancy and the postpartum period and outperforms natriuretic peptides and traditional clinical parameters with the potential to become a powerful initial screening tool for cardiomyopathy in the obstetric care setting.

Abstract Aims Spectrum bias can arise when a diagnostic test is derived from study populations with different disease spectra than the target population, resulting in poor generalizability. We used a real-world artificial intelligence (AI)-derived algorithm to detect severe aortic stenosis (AS) to experimentally assess the effect of spectrum bias on test performance. Methods and results All adult patients at the Mayo Clinic between 1 January 1989 and 30 September 2019 with transthoracic echocardiograms within 180 days after electrocardiogram (ECG) were identified. Two models were developed from two distinct patient cohorts: a whole-spectrum cohort comparing severe AS to any non-severe AS and an extreme-spectrum cohort comparing severe AS to no AS at all. Model performance was assessed. Overall, 258 607 patients had valid ECG and echocardiograms pairs. The area under the receiver operator curve was 0.87 and 0.91 for the whole-spectrum and extreme-spectrum models, respectively. Sensitivity and specificity for the whole-spectrum model was 80% and 81%, respectively, while for the extreme-spectrum model it was 84% and 84%, respectively. When applying the AI-ECG derived from the extreme-spectrum cohort to patients in the whole-spectrum cohort, the sensitivity, specificity, and area under the curve dropped to 83%, 73%, and 0.86, respectively. Conclusion While the algorithm performed robustly in identifying severe AS, this study shows that limiting datasets to clearly positive or negative labels leads to overestimation of test performance when testing an AI algorithm in the setting of classifying severe AS using ECG data. While the effect of the bias may be modest in this example, clinicians should be aware of the existence of such a bias in AI-derived algorithms.

Echocardiography (Echo), a widely available, noninvasive, and portable bedside imaging tool, is the most frequently used imaging modality in assessing cardiac anatomy and function in clinical practice. On the other hand, its operator dependability introduces variability in image acquisition, measurements, and interpretation. To reduce these variabilities, there is an increasing demand for an operator- and interpreter-independent Echo system empowered with artificial intelligence (AI), which has been incorporated into diverse areas of clinical medicine. Recent advances in AI applications in computer vision have enabled us to identify conceptual and complex imaging features with the self-learning ability of AI models and efficient parallel computing power. This has resulted in vast opportunities such as providing AI models that are robust to variations with generalizability for instantaneous image quality control, aiding in the acquisition of optimal images and diagnosis of complex diseases, and improving the clinical workflow of cardiac ultrasound. In this review, we provide a state-of-the art overview of AI-empowered Echo applications in cardiology and future trends for AI-powered Echo technology that standardize measurements, aid physicians in diagnosing cardiac diseases, optimize Echo workflow in clinics, and ultimately, reduce healthcare costs.