AKAkshay Khunte

Akshay Khunte

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Akshay Khunte has a total of 79 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Artificial intelligence-based automated interpretation of images of electrocardiograms: development and multinational validation of ECG-GPT

    by Akshay Khunte, Veer Sangha, Evangelos K Oikonomou, Lovedeep S Dhingra, Arya Aminorroaya, Andreas Coppi, Sumukh Vasisht Shankar, Elijah Rockers, Bobak J Mortazavi, Deepak L Bhatt, et al.

    Aims: Timely, accurate assessment of electrocardiograms (ECGs) is crucial for diagnosing, triaging, and managing patients. However, this often relies on expert interpretation, a major bottleneck in low-resource settings. We developed and validated ECG-GPT, a format-independent vision encoder–decoder model that generates expert-level interpretations from 12-lead ECG images. Methods and results: We developed ECG-GPT using 12-lead ECGs and their corresponding diagnosis statements performed at a large US health system between 2000 and 2022. Using structured clinical assessment, semantic similarity, and conventional metrics, we validated ECG-GPT across seven distinct health settings, including three large and diverse US health systems, ECGs from Minas Gerais, Brazil, the UK Biobank, the Germany-based PTB-XL dataset, and a community hospital in Missouri. In total, 2.9 million ECGs were used for model development, and 4.1 million ECGs for validation. The model performed well in clinical assessment across 26 extracted labels, with diagnostic accuracy ranging from 0.93 to 0.99. For rhythm abnormalities, including atrial fibrillation, sinus tachycardia, sinus bradycardia, premature atrial contractions, and premature ventricular contractions, AUROCs ranged from 0.80 to 0.95. For conduction abnormalities, including left bundle branch block, right bundle branch block, first degree atrioventricular block, left anterior fascicular block, and left posterior fascicular block, AUROCs ranged from 0.88 to 0.96. ECG-GPT identified the full context of diagnosis statements with allied conditions with a median pairwise similarity of 0.90, significantly greater than baseline (P < 0.001). Results were comparable across external validation sites. Conclusion: We developed and validated a vision encoder-decoder model that generates expert-level interpretations from ECG images, a scalable strategy for accessible automated ECG analysis.


  • Open Access

    Development and Multinational Validation of an Ensemble Deep Learning Algorithm for Detecting and Predicting Structural Heart Disease Using Noisy Single-lead Electrocardiograms

    by Arya Aminorroaya, Lovedeep Singh Dhingra, Aline Pedroso Camargos, Sumukh Vasisht Shankar, Andreas Coppi, Akshay Khunte, Murilo Foppa, Luisa Campos Caldeira Brant, Sandhi Maria Barreto, Antonio Luiz P Ribeiro, et al.

    Background and Aims: AI-enhanced 12-lead ECG can detect a range of structural heart diseases (SHDs) but has a limited role in community-based screening. We developed and externally validated a noise-resilient single-lead AI-ECG algorithm that can detect SHD and predict the risk of their development using wearable/portable devices. Methods: Using 266,740 ECGs from 99,205 patients with paired echocardiographic data at Yale New Haven Hospital, we developed ADAPT-HEART, a noise-resilient, deep-learning algorithm, to detect SHD using lead I ECG. SHD was defined as a composite of LVEF<40%, moderate or severe left-sided valvular disease, and severe LVH. ADAPT-HEART was validated in four community hospitals in the US, and the population-based cohort of ELSA-Brasil. We assessed the model’s performance as a predictive biomarker among those without baseline SHD across hospital-based sites and the UK Biobank. Results: The development population had a median age of 66 [IQR, 54-77] years and included 49,947 (50.3%) women, with 18,896 (19.0%) having any SHD. ADAPT-HEART had an AUROC of 0.879 (95% CI, 0.870-0.888) with good calibration for detecting SHD in the test set, and consistent performance in hospital-based external sites (AUROC: 0.852-0.891) and ELSA-Brasil (AUROC: 0.859). Among those without baseline SHD, high vs. low ADAPT-HEART probability conferred a 2.8- to 5.7-fold increase in the risk of future SHD across data sources (all P<0.05). Conclusions: We propose a novel model that detects and predicts a range of SHDs from noisy single-lead ECGs obtainable on portable/wearable devices, providing a scalable strategy for community-based screening and risk stratification for SHD.


  • Open Access

    Artificial Intelligence Enabled Prediction of Heart Failure Risk from Single-lead Electrocardiograms

    by Lovedeep S Dhingra, Arya Aminorroaya, Aline F Pedroso, Akshay Khunte, Veer Sangha, Daniel McIntyre, Clara K Chow, Folkert W Asselbergs, Luisa Cc Brant, Sandhi M Barreto, et al.

    Importance: Despite the availability of disease-modifying therapies, scalable strategies for heart failure (HF) risk stratification remain elusive. Portable devices capable of recording single-lead electrocardiograms (ECGs) can enable large-scale community-based risk assessment. Objective: To evaluate an artificial intelligence (AI) algorithm to predict HF risk from noisy single-lead ECGs. Design: Multicohort study. Setting: Retrospective cohort of individuals with outpatient ECGs in the integrated Yale New Haven Health System (YNHHS) and prospective population-based cohorts of UK Biobank (UKB) and Brazilian Longitudinal Study of Adult Health (ELSA-Brasil). Participants: Individuals without HF at baseline. Exposures: AI-ECG-defined risk of left ventricular systolic dysfunction (LVSD). Main Outcomes and Measures: Among individuals with ECGs, we isolated lead I ECGs and deployed a noise-adapted AI-ECG model trained to identify LVSD. We evaluated the association of the model probability with new-onset HF, defined as the first HF hospitalization. We compared the discrimination of AI-ECG against two risk scores for new-onset HF (PCP-HF and PREVENT equations) using Harrel’s C-statistic, integrated discrimination improvement (IDI), and net reclassification improvement (NRI). Results: There were 192,667 YNHHS patients (age 56 years [IQR, 41-69], 112,082 women [58%]), 42,141 UKB participants (65 years [59-71], 21,795 women [52%]), and 13,454 ELSA-Brasil participants (56 years [41-69], 7,348 women [55%]) with baseline ECGs. A total of 3,697 developed HF in YNHHS over 4.6 years (2.8-6.6), 46 in UKB over 3.1 years (2.1-4.5), and 31 in ELSA-Brasil over 4.2 years (3.7-4.5). A positive AI-ECG screen was associated with a 3- to 7-fold higher risk for HF, and each 0.1 increment in the model probability portended a 27-65% higher hazard across cohorts, independent of age, sex, comorbidities, and competing risk of death. AI-ECG’s discrimination for new-onset HF was 0.725 in YNHHS, 0.792 in UKB, and 0.833 in ELSA-Brasil. Across cohorts, incorporating AI-ECG predictions in addition to PCP-HF and PREVENT equations resulted in improved Harrel’s C-statistic (Δ PCP-HF =0.112-0.114; Δ PREVENT =0.080-0.101). AI-ECG had IDI of 0.094-0.238 and 0.090-0.192, and NRI of 15.8%-48.8% and 12.8%-36.3%, vs. PCP-HF and PREVENT, respectively. Conclusions and Relevance: Across multinational cohorts, a noise-adapted AI model defined HF risk using lead I ECGs, suggesting a potential portable and wearable device-based HF risk-stratification strategy. KEY POINTS: Question: Can single-lead electrocardiograms (ECG) predict heart failure (HF) risk? Findings: We evaluated a noise-adapted artificial intelligence (AI) algorithm for single-lead ECGs across multinational cohorts, spanning a diverse US health-system and community-based cohorts in the UK and Brazil. A positive AI-ECG screen was associated with 3- to 7-fold higher HF risk, independent of age, sex, and comorbidities. The AI model achieved incremental discrimination and improved reclassification over two established clinical risk scores for HF prediction. Meaning: A noise-adapted AI model for single-lead ECG predicted the risk of new-onset HF, representing a scalable HF risk-stratification strategy for portable and wearable devices.


  • Open Access

    Study Protocol for the Artificial Intelligence-Driven Evaluation of Structural Heart Diseases Using Wearable Electrocardiogram (ID-SHD)

    by Arya Aminorroaya, Lovedeep Singh Dhingra, Aline Pedroso Camargos, Sumukh Vasisht Shankar, Akshay Khunte, Veer Sangha, Sounok Sen, Robert L McNamara, Norrisa Haynes, Evangelos K Oikonomou, et al.

    Introduction Portable devices capable of electrocardiogram (ECG) acquisition have the potential to enhance structural heart disease (SHD) management by enabling early detection through artificial intelligence-ECG (AI-ECG) algorithms. However, the performance of these AI algorithms for identifying SHD in a real-world screening setting is unknown. To address this gap, we aim to evaluate the validity of our wearable-adapted AI algorithm, which has been previously developed and validated for detecting SHD from single-lead portable ECGs in patients undergoing routine echocardiograms in the Yale New Haven Hospital (YNHH). Research Methods and Analysis This is the protocol for a cross-sectional study in the echocardiographic laboratories of YNHH. The study will enroll 585 patients referred for outpatient transthoracic echocardiogram (TTE) as part of their routine clinical care. Patients expressing interest in participating in the study will undergo a screening interview, followed by enrollment upon meeting eligibility criteria and providing informed consent. During their routine visit, patients will undergo a 1-lead ECG with two devices - one with an Apple Watch and the second with another portable 1-lead ECG device. With participant consent, these 1-lead ECG data will be linked to participant demographic and clinical data recorded in the YNHH electronic health records (EHR). The study will assess the performance of the AI-ECG algorithm in identifying SHD, including left ventricular systolic dysfunction (LVSD), valvular disease and severe left ventricular hypertrophy (LVH), by comparing the algorithm’s results with data obtained from TTE, which is the established gold standard for diagnosing SHD. Ethics and Dissemination All patient EHR data required for assessing eligibility and conducting the AI-ECG will be accessed through secure servers approved for protected health information. Data will be maintained on secure, encrypted servers for a minimum of five years after the publication of our findings in a peer-reviewed journal, and any unanticipated adverse events or risks will be reported by the principal investigator to the Yale Institutional Review Board, which has reviewed and approved this protocol (Protocol Number: 2000035532).


  • Open Access

    Artificial Intelligence-Based Automated Interpretation of Images of Electrocardiograms: Development and Multinational Validation of ECG-GPT

    by Akshay Khunte, Veer Sangha, Evangelos K Oikonomou, Lovedeep S Dhingra, Arya Aminorroaya, Andreas Coppi, Sumukh Vasisht Shankar, Elijah Rockers, Bobak J Mortazavi, Deepak L Bhatt, et al.

    Background: Timely and accurate assessment of electrocardiograms (ECGs) is crucial for diagnosing, triaging, and clinically managing patients. Current workflows rely on computerized ECG interpretation tools built into ECG signal acquisition systems, which use rule-based algorithms that are unreliable and frequently not available in low-resource settings. We developed and validated a format-independent vision encoder-decoder model – ECG-GPT – that can generate free-text, expert-level interpretations directly from 12-lead ECG images. Methods: Using 12-lead ECGs and their corresponding diagnosis statements collected at the Yale-New Haven Health System (YNHHS) between 2000 and 2022, we developed a vision-text transformer model to generate interpretation statements from images of ECGs. Using structured clinical assessment, semantic similarity, and conventional natural language generation metrics, we validated ECG-GPT across 7 geographically distinct health settings. These include (1) 3 large and diverse US health systems, (2) consecutive ECGs from a central reading system in Minas Gerais, Brazil, (3) the prospective cohort study, UK Biobank, (4) a Germany-based, publicly available repository, PTB-XL, and (5) a community hospital in Missouri. Results: Overall, 2.9 million ECGs were used for model development. The model performed well in clinical assessment across 26 extracted labels: for atrial fibrillation, sinus tachycardia, sinus bradycardia, premature atrial contractions, and premature ventricular contractions, AUROCs and AUPRCs ranged from 0.80-0.95 and 0.50-0.86, respectively. For left bundle branch block, right bundle branch block, first degree atrioventricular block, left anterior fascicular block, and left posterior fascicular block, AUROCs and AUPRCs ranged from 0.88-0.96 and 0.23-0.86, respectively. Across all 26 conditions, diagnostic accuracy ranged between 0.93-0.99. ECG-GPT identified the full context of the diagnosis statements with allied conditions. It had a median pairwise cosine similarity of 0.90 (IQR 0.83-0.97), significantly greater than the median baseline similarity of 0.73 (IQR 0.67-0.78, p<0.001). This separation between median pairwise and baseline similarity remained consistent across all 26 condition-specific subsets. The results were comparable across external validation sites. Conclusions: We developed and extensively validated a vision encoder-decoder model that generates expert-level interpretations from ECG images. This represents a scalable and accessible strategy for automated ECG analysis, especially in low-resource settings. CLINICAL PERSPECTIVE: What is New?: ECG-GPT is a vision encoder-decoder model capable of generating full-text ECG interpretations directly from ECG images, regardless of layout or format. The model was trained on over 2.7 million ECGs and externally validated across 3.8 million additional ECGs from demographically and geographically diverse populations. What are the clinical implications?: ECG-GPT enables automated, expert-level ECG interpretation directly from images, eliminating the need for signal data or device integration. The model demonstrates consistent performance across diverse patient populations, ECG formats, and care settings. This scalable, image-based approach may expand access to accurate ECG interpretation in low-resource settings.


  • Open Access

    Deep Learning-enabled Detection of Aortic Stenosis from Noisy Single Lead Electrocardiograms

    by Arya Aminorroaya, Lovedeep Singh Dhingra, Veer Sangha, Evangelos K Oikonomou, Akshay Khunte, Sumukh Vasisht Shankar, Aline Pedroso Camargos, Norrisa A Haynes, Ira Hofer, David Ouyang, et al.

    Background: Due to the lack of a feasible screening strategy, aortic stenosis (AS) is often diagnosed after the development of clinical symptoms, representing advanced stages of disease. Portable and wearable devices capable of recording electrocardiograms (ECGs) can be used for scalable screening for AS, if the diagnosis can be made with a single-lead ECG, despite potentially noisy acquisition. Methods: Using electronic health records and imaging data from a large, diverse hospital system (2015-2022), we developed a deep learning-based approach to detect moderate/severe AS using a single-lead ECG. We used ECGs paired with echocardiograms obtained within 30 days of each other to develop the model. We extracted lead I signal data from clinical ECG and augmented it with random Gaussian noise. We trained a convolutional neural network (CNN) to identify TTE-confirmed AS using noisy single-lead ECGs. Finally, we used the CNN model probabilities, along with patient age and sex, as predictive inputs to train an extreme gradient boosting (XGBoost) model to detect moderate/severe AS. Results: The model was developed in 75,901 ECGs/35,992 patients (median age 61 [interquartile range (IQR) 47-72] years, 54.3% women, 9.5% Black) and validated in 3,733 patients (median age 61 [IQR 47-72] years, 53.4% women, 9.7% Black). In the held-out validation set, the ensemble XGBoost model achieved an AUROC of 0.829 (95% CI: 0.800-0.855), with a sensitivity of 90.4% and specificity of 58.7% for detecting moderate/severe AS. For detecting severe AS, the model’s AUROC was 0.846 (95% CI, 0.778-0.899), with a sensitivity of 94.3% and specificity of 57.0%. In the test set with a 4.5% prevalence of moderate/severe AS, the model had a PPV of 9.3% and an NPV of 99.2%. In simulated cohorts with 1% and 20% prevalence of moderate/severe AS, the model’s NPVs varied from 99.8% to 96.1%, and PPV from 2.2% to 35.4%, respectively. Conclusion: We developed a novel portable– and wearable-adapted deep learning approach for the detection of moderate/severe AS from noisy single-lead ECGs. Our approach represents a highly sensitive, feasible, and scalable strategy for community-based AS screening.


  • Open Access

    Biometric Contrastive Learning for Data-Efficient Deep Learning from Electrocardiographic Images

    by Veer Sangha, Akshay Khunte, Gregory Holste, Bobak J Mortazavi, Zhangyang Wang, Evangelos K Oikonomou, Rohan Khera

    Objective: Artificial intelligence (AI) detects heart disease from images of electrocardiograms (ECGs), however traditional supervised learning is limited by the need for large amounts of labeled data. We report the development of Biometric Contrastive Learning (BCL), a self-supervised pretraining approach for label-efficient deep learning on ECG images. Materials and Methods: Using pairs of ECGs from 78,288 individuals from Yale (2000-2015), we trained a convolutional neural network to identify temporally-separated ECG pairs that varied in layouts from the same patient. We fine-tuned BCL-pretrained models to detect atrial fibrillation (AF), gender, and LVEF<40%, using ECGs from 2015-2021. We externally tested the models in cohorts from Germany and the US. We compared BCL with random initialization and general-purpose self-supervised contrastive learning for images (simCLR). Results: While with 100% labeled training data, BCL performed similarly to other approaches for detecting AF/Gender/LVEF<40% with AUROC of 0.98/0.90/0.90 in the held-out test sets, it consistently outperformed other methods with smaller proportions of labeled data, reaching equivalent performance at 50% of data. With 0.1% data, BCL achieved AUROC of 0.88/0.79/0.75, compared with 0.51/0.52/0.60 (random) and 0.61/0.53/0.49 (simCLR). In external validation, BCL outperformed other methods even at 100% labeled training data, with AUROC of 0.88/0.88 for Gender and LVEF<40% compared with 0.83/0.83 (random) and 0.84/0.83 (simCLR). Discussion and Conclusion: A pretraining strategy that leverages biometric signatures of different ECGs from the same patient enhances the efficiency of developing AI models for ECG images. This represents a major advance in detecting disorders from ECG images with limited labeled data.


  • Top Cited Papers

    Detection of Left Ventricular Systolic Dysfunction From Electrocardiographic Images

    by Veer Sangha, Arash A. Nargesi, Lovedeep S. Dhingra, Akshay Khunte, Bobak J. Mortazavi, Antônio H. Ribeiro, Evgeniya Banina, Oluwaseun Adeola, Nadish Garg, Cynthia A. Brandt, et al.

    BACKGROUND: Left ventricular (LV) systolic dysfunction is associated with a >8-fold increased risk of heart failure and a 2-fold risk of premature death. The use of ECG signals in screening for LV systolic dysfunction is limited by their availability to clinicians. We developed a novel deep learning–based approach that can use ECG images for the screening of LV systolic dysfunction. METHODS: Using 12-lead ECGs plotted in multiple different formats, and corresponding echocardiographic data recorded within 15 days from the Yale New Haven Hospital between 2015 and 2021, we developed a convolutional neural network algorithm to detect an LV ejection fraction 27-fold higher odds of LV systolic dysfunction on transthoracic echocardiogram (odds ratio, 27.5 [95% CI, 22.3–33.9] in the held-out set). Class-discriminative patterns localized to the anterior and anteroseptal leads (V 2 and V 3 ), corresponding to the left ventricle regardless of the ECG layout. A positive ECG screen in individuals with an LV ejection fraction ≥40% at the time of initial assessment was associated with a 3.9-fold increased risk of developing incident LV systolic dysfunction in the future (hazard ratio, 3.9 [95% CI, 3.3–4.7]; median follow-up, 3.2 years). CONCLUSIONS: We developed and externally validated a deep learning model that identifies LV systolic dysfunction from ECG images. This approach represents an automated and accessible screening strategy for LV systolic dysfunction, particularly in low-resource settings.


  • Top Cited Papers
    Open Access

    Detection of left ventricular systolic dysfunction from single-lead electrocardiography adapted for portable and wearable devices

    by Akshay Khunte, Veer Sangha, Evangelos K. Oikonomou, Lovedeep S. Dhingra, Arya Aminorroaya, Bobak J. Mortazavi, Andreas Coppi, Cynthia A. Brandt, Harlan M. Krumholz, Rohan Khera

    Artificial intelligence (AI) can detect left ventricular systolic dysfunction (LVSD) from electrocardiograms (ECGs). Wearable devices could allow for broad AI-based screening but frequently obtain noisy ECGs. We report a novel strategy that automates the detection of hidden cardiovascular diseases, such as LVSD, adapted for noisy single-lead ECGs obtained on wearable and portable devices. We use 385,601 ECGs for development of a standard and noise-adapted model. For the noise-adapted model, ECGs are augmented during training with random gaussian noise within four distinct frequency ranges, each emulating real-world noise sources. Both models perform comparably on standard ECGs with an AUROC of 0.90. The noise-adapted model performs significantly better on the same test set augmented with four distinct real-world noise recordings at multiple signal-to-noise ratios (SNRs), including noise isolated from a portable device ECG. The standard and noise-adapted models have an AUROC of 0.72 and 0.87, respectively, when evaluated on ECGs augmented with portable ECG device noise at an SNR of 0.5. This approach represents a novel strategy for the development of wearable-adapted tools from clinical ECG repositories.