Maximising Large Language Model Utility in Cardiovascular Care: A Practical Guide.

Large language models (LLMs) have emerged as powerful tools in artificial intelligence, demonstrating remarkable capabilities in natural language processing and generation. In this article, we explore the potential applications of LLMs in enhancing cardiovascular care and research. We discuss how LLMs can be used to simplify complex medical information, improve patient-physician communication, and automate tasks such as summarising medical articles and extracting key information. In addition, we highlight the role of LLMs in categorising and analysing unstructured data, such as medical notes and test results, which could revolutionise data handling and interpretation in cardiovascular research. However, we also emphasise the limitations and challenges associated with LLMs, including potential biases, reasoning opacity, and the need for rigourous validation in medical contexts. This review provides a practical guide for cardiovascular professionals to understand and harness the power of LLMs while navigating their limitations. We conclude by discussing the future directions and implications of LLMs in transforming cardiovascular care and research.

A Responsible Framework for Applying Artificial Intelligence on Medical Images and Signals at the Point of Care: The PACS-AI Platform.

The potential of artificial intelligence (AI) in medicine lies in its ability to enhance clinicians' capacity to analyse medical images, thereby improving diagnostic precision and accuracy and thus enhancing current tests. However, the integration of AI within health care is fraught with difficulties. Heterogeneity among health care system applications, reliance on proprietary closed-source software, and rising cybersecurity threats pose significant challenges. Moreover, before their deployment in clinical settings, AI models must demonstrate their effectiveness across a wide range of scenarios and must be validated by prospective studies, but doing so requires testing in an environment mirroring the clinical workflow, which is difficult to achieve without dedicated software. Finally, the use of AI techniques in health care raises significant legal and ethical issues, such as the protection of patient privacy, the prevention of bias, and the monitoring of the device's safety and effectiveness for regulatory compliance. This review describes challenges to AI integration in health care and provides guidelines on how to move forward. We describe an open-source solution that we developed that integrates AI models into the Picture Archives Communication System (PACS), called PACS-AI. This approach aims to increase the evaluation of AI models by facilitating their integration and validation with existing medical imaging databases. PACS-AI may overcome many current barriers to AI deployment and offer a pathway toward responsible, fair, and effective deployment of AI models in health care. In addition, we propose a list of criteria and guidelines that AI researchers should adopt when publishing a medical AI model to enhance standardisation and reproducibility.

Revolutionizing Acute Cardiac Care with Artificial Intelligence: Opportunities and Challenges.

This manuscript reviews the application of artificial intelligence (AI) in acute cardiac care, highlighting its potential to transform patient outcomes in the face of the global burden of cardiovascular diseases. It explores how AI algorithms can rapidly and accurately process data for the prediction and diagnosis of acute cardiac conditions. The paper examines AI's impact on patient health across various diagnostic tools such as echocardiography, electrocardiography, coronary angiography, cardiac CT, and MRI and discusses the regulatory landscape for AI in healthcare, categorizes AI algorithms by their risk levels. Furthermore, it addresses the challenges of data quality, generalizability, bias, transparency, and regulatory considerations, underscoring the necessity for inclusive data and robust validation processes. The review concludes with future perspectives on integrating AI into clinical workflows and the ongoing need for research, regulation, and innovation to harness AI's full potential in improving acute cardiac care.

Evaluation of stenoses using AI video models applied to coronary angiography.

The coronary angiogram is the gold standard for evaluating the severity of coronary artery disease stenoses. Presently, the assessment is conducted visually by cardiologists, a method that lacks standardization. This study introduces DeepCoro, a ground-breaking AI-driven pipeline that integrates advanced vessel tracking and a video-based Swin3D model that was trained and validated on a dataset comprised of 182,418 coronary angiography videos spanning 5 years. DeepCoro achieved a notable precision of 71.89% in identifying coronary artery segments and demonstrated a mean absolute error of 20.15% (95% CI: 19.88-20.40) and a classification AUROC of 0.8294 (95% CI: 0.8215-0.8373) in stenosis percentage prediction compared to traditional cardiologist assessments. When compared to two expert interventional cardiologists, DeepCoro achieved lower variability than the clinical reports (19.09%; 95% CI: 18.55-19.58 vs 21.00%; 95% CI: 20.20-21.76, respectively). In addition, DeepCoro can be fine-tuned to a different modality type. When fine-tuned on quantitative coronary angiography assessments, DeepCoro attained an even lower mean absolute error of 7.75% (95% CI: 7.37-8.07), underscoring the reduced variability inherent to this method. This study establishes DeepCoro as an innovative video-based, adaptable tool in coronary artery disease analysis, significantly enhancing the precision and reliability of stenosis assessment.

Impact of age and comorbid heart failure on the utility of smart voice-assistant devices.

Aims: The accuracy of voice-assisted technologies, such as Amazon Alexa, to collect data in patients who are older or have heart failure (HF) is unknown. The aim of this study is to analyse the impact of increasing age and comorbid HF, when compared with younger participants and caregivers, and how these different subgroups classify their experience using a voice-assistant device, for screening purposes. Methods and results: Subgroup analysis (HF vs. caregivers and younger vs. older participants) of the VOICE-COVID-II trial, a randomized controlled study where participants were assigned with subsequent crossover to receive a SARS-CoV2 screening questionnaire by Amazon Alexa or a healthcare personnel. Overall concordance between the two methods was compared using unweighted kappa scores and percentage of agreement. From the 52 participants included, the median age was 51 (34-65) years and 21 (40%) were HF patients. The HF subgroup showed a significantly lower percentage of agreement compared with caregivers (95% vs. 99%, P = 0.03), and both the HF and older subgroups tended to have lower unweighted kappa scores than their counterparts. In a post-screening survey, both the HF and older subgroups were less acquainted and found the voice-assistant device more difficult to use compared with caregivers and younger individuals. Conclusion: This subgroup analysis highlights important differences in the performance of a voice-assistant-based technology in an older and comorbid HF population. Younger individuals and caregivers, serving as facilitators, have the potential to bridge the gap and enhance the integration of these technologies into clinical practice. Study Registration: ClinicalTrials.gov Identifier: NCT04508972.

Advancing Fairness in Cardiac Care: Strategies for Mitigating Bias in Artificial Intelligence Models Within Cardiology.

In the dynamic field of medical artificial intelligence (AI), cardiology stands out as a key area for its technological advancements and clinical application. In this review we explore the complex issue of data bias, specifically addressing those encountered during the development and implementation of AI tools in cardiology. We dissect the origins and effects of these biases, which challenge their reliability and widespread applicability in health care. Using a case study, we highlight the complexities involved in addressing these biases from a clinical viewpoint. The goal of this review is to equip researchers and clinicians with the practical knowledge needed to identify, understand, and mitigate these biases, advocating for the creation of AI solutions that are not just technologically sound, but also fair and effective for all patients.

Artificial Intelligence in Cardiovascular Care-Part 2: Applications: JACC Review Topic of the Week.

Recent artificial intelligence (AI) advancements in cardiovascular care offer potential enhancements in effective diagnosis, treatment, and outcomes. More than 600 U.S. Food and Drug Administration-approved clinical AI algorithms now exist, with 10% focusing on cardiovascular applications, highlighting the growing opportunities for AI to augment care. This review discusses the latest advancements in the field of AI, with a particular focus on the utilization of multimodal inputs and the field of generative AI. Further discussions in this review involve an approach to understanding the larger context in which AI-augmented care may exist, and include a discussion of the need for rigorous evaluation, appropriate infrastructure for deployment, ethics and equity assessments, regulatory oversight, and viable business cases for deployment. Embracing this rapidly evolving technology while setting an appropriately high evaluation benchmark with careful and patient-centered implementation will be crucial for cardiology to leverage AI to enhance patient care and the provider experience.

Artificial Intelligence for Cardiovascular Care-Part 1: Advances: JACC Review Topic of the Week.

Recent artificial intelligence (AI) advancements in cardiovascular care offer potential enhancements in diagnosis, treatment, and outcomes. Innovations to date focus on automating measurements, enhancing image quality, and detecting diseases using novel methods. Applications span wearables, electrocardiograms, echocardiography, angiography, genetics, and more. AI models detect diseases from electrocardiograms at accuracy not previously achieved by technology or human experts, including reduced ejection fraction, valvular heart disease, and other cardiomyopathies. However, AI's unique characteristics necessitate rigorous validation by addressing training methods, real-world efficacy, equity concerns, and long-term reliability. Despite an exponentially growing number of studies in cardiovascular AI, trials showing improvement in outcomes remain lacking. A number are currently underway. Embracing this rapidly evolving technology while setting a high evaluation benchmark will be crucial for cardiology to leverage AI to enhance patient care and the provider experience.

Applying Artificial Intelligence for Phenotyping of Inherited Arrhythmia Syndromes.

Inherited arrhythmia disorders account for a significant proportion of sudden cardiac death, particularly among young individuals. Recent advances in our understanding of these syndromes have improved patient diagnosis and care, yet certain clinical gaps remain, particularly within case ascertainment, access to genetic testing, and risk stratification. Artificial intelligence (AI), specifically machine learning and its subset deep learning, present promising solutions to these challenges. The capacity of AI to process vast amounts of patient data and identify disease patterns differentiates them from traditional methods, which are time- and resource-intensive. To date, AI models have shown immense potential in condition detection (including asymptomatic/concealed disease) and genotype and phenotype identification, exceeding expert cardiologists in these tasks. Additionally, they have exhibited applicability for general population screening, improving case ascertainment in a set of conditions that are often asymptomatic such as left ventricular dysfunction. Third, models have shown the ability to improve testing protocols; through model identification of disease and genotype, specific clinical testing (eg, drug challenges or further diagnostic imaging) can be avoided, reducing health care expenses, speeding diagnosis, and possibly allowing for more incremental or targeted genetic testing approaches. These significant benefits warrant continued investigation of AI, particularly regarding the development and implementation of clinically applicable screening tools. In this review we summarize key developments in AI, including studies in long QT syndrome, Brugada syndrome, hypertrophic cardiomyopathy, and arrhythmogenic cardiomyopathies, and provide direction for effective future AI implementation in clinical practice.

Deep Learning-Augmented ECG Analysis for Screening and Genotype Prediction of Congenital Long QT Syndrome.

Importance: Congenital long QT syndrome (LQTS) is associated with syncope, ventricular arrhythmias, and sudden death. Half of patients with LQTS have a normal or borderline-normal QT interval despite LQTS often being detected by QT prolongation on resting electrocardiography (ECG). Objective: To develop a deep learning-based neural network for identification of LQTS and differentiation of genotypes (LQTS1 and LQTS2) using 12-lead ECG. Design, Setting, and Participants: This diagnostic accuracy study used ECGs from patients with suspected inherited arrhythmia enrolled in the Hearts in Rhythm Organization Registry (HiRO) from August 2012 to December 2021. The internal dataset was derived at 2 sites and an external validation dataset at 4 sites within the HiRO Registry; an additional cross-sectional validation dataset was from the Montreal Heart Institute. The cohort with LQTS included probands and relatives with pathogenic or likely pathogenic variants in KCNQ1 or KCNH2 genes with normal or prolonged corrected QT (QTc) intervals. Exposures: Convolutional neural network (CNN) discrimination between LQTS1, LQTS2, and negative genetic test results. Main Outcomes and Measures: The main outcomes were area under the curve (AUC), F1 scores, and sensitivity for detecting LQTS and differentiating genotypes using a CNN method compared with QTc-based detection. Results: A total of 4521 ECGs from 990 patients (mean [SD] age, 42 [18] years; 589 [59.5%] female) were analyzed. External validation within the national registry (101 patients) demonstrated the CNN's high diagnostic capacity for LQTS detection (AUC, 0.93; 95% CI, 0.89-0.96) and genotype differentiation (AUC, 0.91; 95% CI, 0.86-0.96). This surpassed expert-measured QTc intervals in detecting LQTS (F1 score, 0.84 [95% CI, 0.78-0.90] vs 0.22 [95% CI, 0.13-0.31]; sensitivity, 0.90 [95% CI, 0.86-0.94] vs 0.36 [95% CI, 0.23-0.47]), including in patients with normal or borderline QTc intervals (F1 score, 0.70 [95% CI, 0.40-1.00]; sensitivity, 0.78 [95% CI, 0.53-0.95]). In further validation in a cross-sectional cohort (406 patients) of high-risk patients and genotype-negative controls, the CNN detected LQTS with an AUC of 0.81 (95% CI, 0.80-0.85), which was better than QTc interval-based detection (AUC, 0.74; 95% CI, 0.69-0.78). Conclusions and Relevance: The deep learning model improved detection of congenital LQTS from resting ECGs and allowed for differentiation between the 2 most common genetic subtypes. Broader validation over an unselected general population may support application of this model to patients with suspected LQTS.

Continuous Atrial Fibrillation Monitoring From Photoplethysmography: Comparison Between Supervised Deep Learning and Heuristic Signal Processing.

BACKGROUND: Continuous monitoring for atrial fibrillation (AF) using photoplethysmography (PPG) from smartwatches or other wearables is challenging due to periods of poor signal quality during motion or suboptimal wearing. As a result, many consumer wearables sample infrequently and only analyze when the user is at rest, which limits the ability to perform continuous monitoring or to quantify AF. OBJECTIVES: This study aimed to compare 2 methods of continuous monitoring for AF in free-living patients: a well-validated signal processing (SP) heuristic and a convolutional deep neural network (DNN) trained on raw signal. METHODS: We collected 4 weeks of continuous PPG and electrocardiography signals in 204 free-living patients. Both SP and DNN models were developed and validated both on holdout patients and an external validation set. RESULTS: The results show that the SP model demonstrated receiver-operating characteristic area under the curve (AUC) of 0.972 (sensitivity 99.6%, specificity: 94.4%), which was similar to the DNN receiver-operating characteristic AUC of 0.973 (sensitivity 92.2, specificity: 95.5%); however, the DNN classified significantly more data (95% vs 62%), revealing its superior tolerance of tracings prone to motion artifact. Explainability analysis revealed that the DNN automatically suppresses motion artifacts, evaluates irregularity, and learns natural AF interbeat variability. The DNN performed better and analyzed more signal in the external validation cohort using a different population and PPG sensor (AUC, 0.994; 97% analyzed vs AUC, 0.989; 88% analyzed). CONCLUSIONS: DNNs perform at least as well as SP models, classify more data, and thus may be better for continuous PPG monitoring.

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.

Authorship Correction: Voice-Based Screening for SARS-CoV-2 Exposure in Cardiovascular Clinics (VOICE-COVID-19-II): Protocol for a Randomized Controlled Trial.

[This corrects the article DOI: 10.2196/41209.].

CathAI: fully automated coronary angiography interpretation and stenosis estimation.

Coronary angiography is the primary procedure for diagnosis and management decisions in coronary artery disease (CAD), but ad-hoc visual assessment of angiograms has high variability. Here we report a fully automated approach to interpret angiographic coronary artery stenosis from standard coronary angiograms. Using 13,843 angiographic studies from 11,972 adult patients at University of California, San Francisco (UCSF), between April 1, 2008 and December 31, 2019, we train neural networks to accomplish four sequential necessary tasks for automatic coronary artery stenosis localization and estimation. Algorithms are internally validated against criterion-standard labels for each task in hold-out test datasets. Algorithms are then externally validated in real-world angiograms from the University of Ottawa Heart Institute (UOHI) and also retrained using quantitative coronary angiography (QCA) data from the Montreal Heart Institute (MHI) core lab. The CathAI system achieves state-of-the-art performance across all tasks on unselected, real-world angiograms. Positive predictive value, sensitivity and F1 score are all ≥90% to identify projection angle and ≥93% for left/right coronary artery angiogram detection. To predict obstructive CAD stenosis (≥70%), CathAI exhibits an AUC of 0.862 (95% CI: 0.843-0.880). In UOHI external validation, CathAI achieves AUC 0.869 (95% CI: 0.830-0.907) to predict obstructive CAD. In the MHI QCA dataset, CathAI achieves an AUC of 0.775 (95%. CI: 0.594-0.955) after retraining. In conclusion, multiple purpose-built neural networks can function in sequence to accomplish automated analysis of real-world angiograms, which could increase standardization and reproducibility in angiographic coronary stenosis assessment.

Automated Assessment of Cardiac Systolic Function From Coronary Angiograms With Video-Based Artificial Intelligence Algorithms.

Importance: Understanding left ventricular ejection fraction (LVEF) during coronary angiography can assist in disease management. Objective: To develop an automated approach to predict LVEF from left coronary angiograms. Design, Setting, and Participants: This was a cross-sectional study with external validation using patient data from December 12, 2012, to December 31, 2019, from the University of California, San Francisco (UCSF). Data were randomly split into training, development, and test data sets. External validation data were obtained from the University of Ottawa Heart Institute. Included in the analysis were all patients 18 years or older who received a coronary angiogram and transthoracic echocardiogram (TTE) within 3 months before or 1 month after the angiogram. Exposure: A video-based deep neural network (DNN) called CathEF was used to discriminate (binary) reduced LVEF (≤40%) and to predict (continuous) LVEF percentage from standard angiogram videos of the left coronary artery. Guided class-discriminative gradient class activation mapping (GradCAM) was applied to visualize pixels in angiograms that contributed most to DNN LVEF prediction. Results: A total of 4042 adult angiograms with corresponding TTE LVEF from 3679 UCSF patients were included in the analysis. Mean (SD) patient age was 64.3 (13.3) years, and 2212 patients were male (65%). In the UCSF test data set (n = 813), the video-based DNN discriminated (binary) reduced LVEF (≤40%) with an area under the receiver operating characteristic curve (AUROC) of 0.911 (95% CI, 0.887-0.934); diagnostic odds ratio for reduced LVEF was 22.7 (95% CI, 14.0-37.0). DNN-predicted continuous LVEF had a mean absolute error (MAE) of 8.5% (95% CI, 8.1%-9.0%) compared with TTE LVEF. Although DNN-predicted continuous LVEF differed 5% or less compared with TTE LVEF in 38.0% (309 of 813) of test data set studies, differences greater than 15% were observed in 15.2% (124 of 813). In external validation (n = 776), video-based DNN discriminated (binary) reduced LVEF (≤40%) with an AUROC of 0.906 (95% CI, 0.881-0.931), and DNN-predicted continuous LVEF had an MAE of 7.0% (95% CI, 6.6%-7.4%). Video-based DNN tended to overestimate low LVEFs and underestimate high LVEFs. Video-based DNN performance was consistent across sex, body mass index, low estimated glomerular filtration rate (≤45), presence of acute coronary syndromes, obstructive coronary artery disease, and left ventricular hypertrophy. Conclusion and relevance: This cross-sectional study represents an early demonstration of estimating LVEF from standard angiogram videos of the left coronary artery using video-based DNNs. Further research can improve accuracy and reduce the variability of DNNs to maximize their clinical utility.

Voice-assisted Artificial Intelligence-enabled Screening for Severe Acute Respiratory Syndrome Coronavirus 2 Exposure in Cardiovascular Clinics: Primary Results of the VOICE-COVID-19-II Randomized Trial.

BACKGROUND: Voice-assisted artificial intelligence-based systems may streamline clinical care among patients with heart failure (HF) and caregivers; however, randomized clinical trials are needed. We evaluated the potential for Amazon Alexa (Alexa), a voice-assisted artificial intelligence-based system, to conduct screening for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in a HF clinic. METHODS AND RESULTS: We enrolled 52 participants (patients and caregivers) from a HF clinic who were randomly assigned with a subsequent cross-over to receive a SARS-CoV-2 screening questionnaire via Alexa or health care personnel. The primary outcome was overall response concordance, as measured by the percentage of agreement and unweighted kappa scores between groups. A postscreening survey evaluated comfort with using the artificial intelligence-based device. In total, 36 participants (69%) were male, the median age was 51 years (range 34-65 years) years and 36 (69%) were English speaking. Twenty-one participants (40%) were patients with HF. For the primary outcome, there were no statistical differences between the groups: Alexa-research coordinator group 96.9% agreement and unweighted kappa score of 0.92 (95% confidence interval 0.84-1.00) vs research coordinator-Alexa group 98.5% agreement and unweighted kappa score of 0.95 (95% confidence interval 0.88-1.00) (P value for all comparisons > .05). Overall, 87% of participants rated their screening experience as good or outstanding. CONCLUSIONS: Alexa demonstrated comparable performance to a health care professional for SARS-CoV-2 screening in a group of patients with HF and caregivers and may represent an attractive approach to symptom screening in this population. Future studies evaluating such technologies for other uses among patients with HF and caregivers are warranted. NCT04508972.

Deep learning augmented ECG analysis to identify biomarker-defined myocardial injury.

Chest pain is a common clinical complaint for which myocardial injury is the primary concern and is associated with significant morbidity and mortality. To aid providers' decision-making, we aimed to analyze the electrocardiogram (ECG) using a deep convolutional neural network (CNN) to predict serum troponin I (TnI) from ECGs. We developed a CNN using 64,728 ECGs from 32,479 patients who underwent ECG within 2 h prior to a serum TnI laboratory result at the University of California, San Francisco (UCSF). In our primary analysis, we classified patients into groups of TnI < 0.02 or ≥ 0.02 µg/L using 12-lead ECGs. This was repeated with an alternative threshold of 1.0 µg/L and with single-lead ECG inputs. We also performed multiclass prediction for a set of serum troponin ranges. Finally, we tested the CNN in a cohort of patients selected for coronary angiography, including 3038 ECGs from 672 patients. Cohort patients were 49.0% female, 42.8% white, and 59.3% (19,283) never had a positive TnI value (≥ 0.02 µg/L). CNNs accurately predicted elevated TnI, both at a threshold of 0.02 µg/L (AUC = 0.783, 95% CI 0.780-0.786) and at a threshold of 1.0 µg/L (AUC = 0.802, 0.795-0.809). Models using single-lead ECG data achieved significantly lower accuracy, with AUCs ranging from 0.740 to 0.773 with variation by lead. Accuracy of the multi-class model was lower for intermediate TnI value-ranges. Our models performed similarly on the cohort of patients who underwent coronary angiography. Biomarker-defined myocardial injury can be predicted by CNNs from 12-lead and single-lead ECGs.