Prasanth Ganesan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Prasanth Ganesan has a total of 80 co-authors. Here are the top co-authors by number of shared publications:
- Sanjiv M. Narayan
Department of Medicine, Stanford University, Palo Alto, California
15 shared publications - Albert Joseph Rogers
Stanford University
12 shared publications - Behnaz Ghoraani
Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University
8 shared publications - Brototo Deb
Department of Medicine, Cardiovascular Institute and Institute for Computational and Mathematical Engineering, Stanford University, Stanford, CA, USA
6 shared publications Elizabeth M. Cherry
School of Mathematical Sciences, Rochester Institute of Technology, Rochester, NY, USA
6 shared publications- Miguel Rodrigo
Computational Multiscale Simulation Laboratory (CoMMLab), Department of Computer Science and Department of Electronic Engineering, Universitat de València, Burjassot, Spain
6 shared publications
Latest Publications
- Open Access
Feasibility of Noninvasive Atrial and Ventricular Activation, Conduction-Velocity, and Site-of-Origin Mapping with Solid-State Magnetocardiography: A Preclinical Validation Study
Background: Characterizing cardiac activation by its site of origin, propagation, and conduction velocity underlies arrhythmia diagnosis and management, but invasive electrophysiology (EP) mapping requires vascular access, fluoroscopy, and sedation. Magnetocardiography (MCG) enables contactless mapping, and recent solid-state sensors remove the cost, cryogenic, and shielding barriers of legacy systems. We assessed the feasibility of a novel solid-state MCG system for noninvasive arrhythmia site-of-origin (SOO) localization and activation reconstruction, benchmarked against electrocardiographic imaging (ECGi). Methods: In nine swine implanted with right atrial and right ventricular pacing leads, we recorded MCG and ECGi simultaneously during atrial and ventricular pacing. Invasive epicardial contact EP mapping provided the activation-time reference and MRI-derived lead-tip location the SOO reference. Local activation time (LAT), conduction velocity (CV), and SOO were compared on a co-registered chamber mesh. SOO error was the Euclidean distance to the MRI lead tip; LAT and CV agreement with EP were quantified by Pearson r and compared using Wilcoxon signed-rank tests. Results: Across 17 datasets (8 atrial, 9 ventricular), median SOO error was lower for MCG than ECGi in the atrium (19.6 vs 31.2 mm; p=0.023) and ventricle (12.0 vs 26.1 mm; p=0.074). LAT agreement with EP was comparable between modalities and higher in the ventricle (MCG r=0.63; ECGi r=0.68) compared with the atrium (MCG r=0.40; ECGi r=0.53), each correlating with invasive EP mapping above chance. CV agreement was modest and numerically higher for MCG in the ventricle. Conclusions: Solid-state MCG was feasible for noninvasive site-of-origin localization and activation mapping, with accuracy comparable to ECGi, motivating larger prospective studies to define its clinical role in noninvasive mapping. Clinical Perspective: What Is Known: Invasive electrophysiology mapping is the reference standard for localizing the arrhythmia site of origin and characterizing cardiac activation, but it requires vascular access, fluoroscopy, and prolonged sedation within the electrophysiology laboratory. Existing noninvasive options have important limitations: electrocardiographic imaging depends on concomitant thoracic imaging, size-dependent vest fit, and torso-conductivity modeling, while legacy magnetocardiography has required costly cryogenic and magnetically shielded infrastructure. What the Study Adds: In a preclinical large-mammal model referenced to invasive electrophysiology and MRI, a novel contactless solid-state magnetocardiography system feasibly localized atrial and ventricular sites of origin and reconstructed activation without body-surface electrodes. Magnetocardiography localized the site of origin more accurately than ECGi in the atrium, and showed numerically lower localization error in the ventricle. Magnetocardiography displayed activation-time and conduction-velocity agreement with invasive electrophysiology comparable to electrocardiographic imaging in both chambers. Solid-state magnetocardiography may offer a scalable, noninvasive approach for preprocedural localization and complementary activation mapping, motivating larger prospective clinical validation.
Open AccessFeasibility of Noninvasive Atrial and Ventricular Activation, Conduction-Velocity, and Site-of-Origin Mapping with Solid-State Magnetocardiography: A Preclinical Validation Study
Background: Characterizing cardiac activation by its site of origin, propagation, and conduction velocity underlies arrhythmia diagnosis and management, but invasive electrophysiology (EP) mapping requires vascular access, fluoroscopy, and sedation. Magnetocardiography (MCG) enables contactless mapping, and recent solid-state sensors remove the cost, cryogenic, and shielding barriers of legacy systems. We assessed the feasibility of a novel solid-state MCG system for noninvasive arrhythmia site-of-origin (SOO) localization and activation reconstruction, benchmarked against electrocardiographic imaging (ECGi). Methods: In nine swine implanted with right atrial and right ventricular pacing leads, we recorded MCG and ECGi simultaneously during atrial and ventricular pacing. Invasive epicardial contact EP mapping provided the activation-time reference and MRI-derived lead-tip location the SOO reference. Local activation time (LAT), conduction velocity (CV), and SOO were compared on a co-registered chamber mesh. SOO error was the Euclidean distance to the MRI lead tip; LAT and CV agreement with EP were quantified by Pearson r and compared using Wilcoxon signed-rank tests. Results: Across 17 datasets (8 atrial, 9 ventricular), median SOO error was lower for MCG than ECGi in the atrium (19.6 vs 31.2 mm; p=0.023) and ventricle (12.0 vs 26.1 mm; p=0.074). LAT agreement with EP was comparable between modalities and higher in the ventricle (MCG r=0.63; ECGi r=0.68) compared with the atrium (MCG r=0.40; ECGi r=0.53), each correlating with invasive EP mapping above chance. CV agreement was modest and numerically higher for MCG in the ventricle. Conclusions: Solid-state MCG was feasible for noninvasive site-of-origin localization and activation mapping, with accuracy comparable to ECGi, motivating larger prospective studies to define its clinical role in noninvasive mapping. Clinical Perspective: What Is Known: Invasive electrophysiology mapping is the reference standard for localizing the arrhythmia site of origin and characterizing cardiac activation, but it requires vascular access, fluoroscopy, and prolonged sedation within the electrophysiology laboratory. Existing noninvasive options have important limitations: electrocardiographic imaging depends on concomitant thoracic imaging, size-dependent vest fit, and torso-conductivity modeling, while legacy magnetocardiography has required costly cryogenic and magnetically shielded infrastructure. What the Study Adds: In a preclinical large-mammal model referenced to invasive electrophysiology and MRI, a novel contactless solid-state magnetocardiography system feasibly localized atrial and ventricular sites of origin and reconstructed activation without body-surface electrodes. Magnetocardiography localized the site of origin more accurately than ECGi in the atrium, and showed numerically lower localization error in the ventricle. Magnetocardiography displayed activation-time and conduction-velocity agreement with invasive electrophysiology comparable to electrocardiographic imaging in both chambers. Solid-state magnetocardiography may offer a scalable, noninvasive approach for preprocedural localization and complementary activation mapping, motivating larger prospective clinical validation.
- 7 July 2026
- Published by Wolters Kluwer Health in Circulation: Arrhythmia and Electrophysiology
- Vol. 19 (7) , e014765
Identifying the Presence and Characteristics of Mid-Myocardial and Epicardial Fibrosis From Intracardiac Electrograms in Patients Undergoing Ventricular Arrhythmia Ablation Using a Transformer-Based Self-Supervised Classifier
BACKGROUND: Catheter ablation is an essential tool for ventricular arrhythmia management, yet sustained procedural success is hindered by the limited ability to identify nonendocardial arrhythmogenic substrates during the procedure. Although delayed enhancement cardiac magnetic resonance imaging is the reference standard for detecting myocardial fibrosis, barriers including cost, workflow complexity, and artifacts in patients with implantable devices limit its preprocedural use. We hypothesized that intracardiac electrograms provide sufficient information to infer scar beyond the endocardial surface and that this information can be harnessed by machine learning techniques. METHODS: This retrospective study included a total of 131 584 cardiac contact electrogram (EGM) signals collected from 46 patients undergoing ventricular arrhythmia ablation. A stratified patient-wise split was used to create the training/validation set (N=37) and the testing set (N=9), while ensuring a similar distribution of scar types. We developed a novel image-processing workflow to create scar labels using coregistered cardiac magnetic resonance imaging and electroanatomic mapping surface meshes. We developed a transformer-based self-supervised model, EGM2Scar-AI, alongside basic convolutional neural network models using either EGM waveforms or EGM-derived short-time Fourier transform spectrograms. RESULTS: The average task-specific area under the receiver operating characteristic curve of both the basic and short-time Fourier transform-based convolutional neural networks was 0.729 (0.725–0.732) and 0.729 (0.726–0.733), respectively, while EGM2Scar-AI performed significantly better with an average area under the receiver operating characteristic curve of 0.822 (0.819–0.825) across all 3 scar types. All models performed better on endocardial and mid-myocardial fibrosis identification, with a modest reduction in performance for epicardial fibrosis. Sensitivity improved significantly with the transformer-based architecture without appreciable changes in specificity. CONCLUSIONS: Our study demonstrates that routine intracardiac electrograms enable the identification of endocardial, mid-myocardial, and epicardial scar using a transformer-based self-supervised deep learning model. Ultimately, our model has the potential to provide magnetic resonance imaging-like fibrosis maps during EP procedures without the need for external imaging and to increase the data set size for patient-specific models in ventricular arrhythmia research.
- 7 July 2026
- Published by Wolters Kluwer Health in Circulation: Arrhythmia and Electrophysiology
- Vol. 19 (7) , e014765
Identifying the Presence and Characteristics of Mid-Myocardial and Epicardial Fibrosis From Intracardiac Electrograms in Patients Undergoing Ventricular Arrhythmia Ablation Using a Transformer-Based Self-Supervised Classifier
BACKGROUND: Catheter ablation is an essential tool for ventricular arrhythmia management, yet sustained procedural success is hindered by the limited ability to identify nonendocardial arrhythmogenic substrates during the procedure. Although delayed enhancement cardiac magnetic resonance imaging is the reference standard for detecting myocardial fibrosis, barriers including cost, workflow complexity, and artifacts in patients with implantable devices limit its preprocedural use. We hypothesized that intracardiac electrograms provide sufficient information to infer scar beyond the endocardial surface and that this information can be harnessed by machine learning techniques. METHODS: This retrospective study included a total of 131 584 cardiac contact electrogram (EGM) signals collected from 46 patients undergoing ventricular arrhythmia ablation. A stratified patient-wise split was used to create the training/validation set (N=37) and the testing set (N=9), while ensuring a similar distribution of scar types. We developed a novel image-processing workflow to create scar labels using coregistered cardiac magnetic resonance imaging and electroanatomic mapping surface meshes. We developed a transformer-based self-supervised model, EGM2Scar-AI, alongside basic convolutional neural network models using either EGM waveforms or EGM-derived short-time Fourier transform spectrograms. RESULTS: The average task-specific area under the receiver operating characteristic curve of both the basic and short-time Fourier transform-based convolutional neural networks was 0.729 (0.725–0.732) and 0.729 (0.726–0.733), respectively, while EGM2Scar-AI performed significantly better with an average area under the receiver operating characteristic curve of 0.822 (0.819–0.825) across all 3 scar types. All models performed better on endocardial and mid-myocardial fibrosis identification, with a modest reduction in performance for epicardial fibrosis. Sensitivity improved significantly with the transformer-based architecture without appreciable changes in specificity. CONCLUSIONS: Our study demonstrates that routine intracardiac electrograms enable the identification of endocardial, mid-myocardial, and epicardial scar using a transformer-based self-supervised deep learning model. Ultimately, our model has the potential to provide magnetic resonance imaging-like fibrosis maps during EP procedures without the need for external imaging and to increase the data set size for patient-specific models in ventricular arrhythmia research.
- 1 March 2026
- Published by Wolters Kluwer Health in Circulation: Arrhythmia and Electrophysiology
- Vol. 19 (3) , e014061
Impact of Catheter Configuration on the Mapping of Atrial Fibrillation
BACKGROUND: Mapping of heart rhythms is influenced by the size and configuration of the mapping electrodes. Whether a recorded electrogram represents near (local) or remote activity influences diagnosis and treatment, yet is affected by mapping characteristics that are often undefined. METHODS: We developed biophysical computational models to predict interactions between the recording tool and cardiac tissue in coherent and disorganized rhythms, which we validated in clinical recordings. RESULTS: Biophysical computational models demonstrated the ability to quantify and visualize the recording antennae for different electrode configurations. Our results show that unipolar electrograms reflected a recording antenna within 3-dimensional ellipsoids of radius 8 mm across-tissue and 2.7 mm transmurally. Bipolar electrogram antennae align with propagation direction in ellipsoids of long axis radius 1.7, 5.7, and 8.3 mm for 2, 5, and 10 mm spacing, respectively, and often extend beyond the physical extent of electrodes. Notably, omnipolar electrograms, constructed from orthogonal bipoles in a triangular configuration, retained some directional preferences of bipolar electrograms, with a complex relationship between electrode orientation and wave direction. When tested clinically on high-resolution, narrow field (grid) catheters and moderate-to-low resolution, global (basket) catheters, antennae varied more with electrode type (correlation coefficient of 0.43 unipolar, 0.05 bipolar, and 0.26 omnipolar; P P =0.002) than the precise electrode size. CONCLUSIONS: This novel computational-clinical system approach enabled us to systematically compare electrode configurations. This work may help interpret signals in complex biological rhythms, such as atrial fibrillation, and may influence the design of novel catheter configurations and signal processing approaches to identify local tissue signals.
- 1 March 2026
- Published by Wolters Kluwer Health in Circulation: Arrhythmia and Electrophysiology
- Vol. 19 (3) , e014061
Impact of Catheter Configuration on the Mapping of Atrial Fibrillation
BACKGROUND: Mapping of heart rhythms is influenced by the size and configuration of the mapping electrodes. Whether a recorded electrogram represents near (local) or remote activity influences diagnosis and treatment, yet is affected by mapping characteristics that are often undefined. METHODS: We developed biophysical computational models to predict interactions between the recording tool and cardiac tissue in coherent and disorganized rhythms, which we validated in clinical recordings. RESULTS: Biophysical computational models demonstrated the ability to quantify and visualize the recording antennae for different electrode configurations. Our results show that unipolar electrograms reflected a recording antenna within 3-dimensional ellipsoids of radius 8 mm across-tissue and 2.7 mm transmurally. Bipolar electrogram antennae align with propagation direction in ellipsoids of long axis radius 1.7, 5.7, and 8.3 mm for 2, 5, and 10 mm spacing, respectively, and often extend beyond the physical extent of electrodes. Notably, omnipolar electrograms, constructed from orthogonal bipoles in a triangular configuration, retained some directional preferences of bipolar electrograms, with a complex relationship between electrode orientation and wave direction. When tested clinically on high-resolution, narrow field (grid) catheters and moderate-to-low resolution, global (basket) catheters, antennae varied more with electrode type (correlation coefficient of 0.43 unipolar, 0.05 bipolar, and 0.26 omnipolar; P P =0.002) than the precise electrode size. CONCLUSIONS: This novel computational-clinical system approach enabled us to systematically compare electrode configurations. This work may help interpret signals in complex biological rhythms, such as atrial fibrillation, and may influence the design of novel catheter configurations and signal processing approaches to identify local tissue signals.
- Top Cited Papers
- 6 January 2026
- Published by Wolters Kluwer Health in Circulation
- Vol. 153 (1) , 35-46
Deep Learning–Based Continuous QT Monitoring to Identify High-Risk Prolongation Events After Class III Antiarrhythmic Initiation
BACKGROUND: Drug-induced QT prolongation after successful inpatient loading of class III antiarrhythmics may occur during routine outpatient care. Insertable cardiac monitors offer continuous signals but are limited by single-lead configuration. We hypothesized that a spatially aware deep learning system (3DRECON-QT) can reconstruct spatial information from a single lead vector to quantify QT/QTc and identify high-risk prolongation. METHODS: We developed 3DRECON-QT using a multitask encoder–decoder that ingests a 10-s single-lead signal, reconstructs 12 leads, and predicts QT/QTc. The model was developed using 12-lead ECGs with clinician-adjudicated QT/RR from a large health system and tested in an external center with different ECG hardware. Continuous monitoring performance was assessed in a public dofetilide‐loading data set with serial ECGs. In a real-world cohort of outpatients on dofetilide or sotalol presenting to the hospital or emergency room for any reason, rates of ventricular arrhythmias and QT prolongation were assessed. Device validation was tested in patients with insertable cardiac monitor recordings paired with clinical 12-lead ECGs. RESULTS: 3DRECON-QT classified prolonged QTc from single-lead signals with area under the receiver operating characteristics curve, 0.942 (mean absolute error, 17.5 ms) in the internal test set and 0.943 (mean absolute error, 21.1 ms) externally. During continuous dofetilide monitoring, predictions correlated with ground truth ( r , 0.851; mean absolute error, 17.8 ms; area under the receiver operating characteristics curve, 0.936 for prolonged QTc, 0.816 for ≥15% QTc rise). QTc prediction from true insertable cardiac monitor recordings showed r =0.824 and mean absolute error, 17.5 ms. In outpatients on class III antiarrhythmics (n=1676), 16.5% had high-risk QTc prolongation. Ventricular arrhythmia events were 3.97% versus 0.86% without prolongation (adjusted odds ratio, 4.24 [95% CI, 1.81–9.90]). 3DRECON-QT detected these events with area under the receiver operating characteristics curve 0.94 (F1 score, 0.60). CONCLUSIONS: A single-lead, deep-learning approach can achieve guideline-level measurement accuracy, enable continuous QTc surveillance from nonstandard ECG vectors, and identify clinically meaningful outpatient QTc prolongation associated with a >4-fold increase in serious ventricular arrhythmias. This strategy may enhance safety monitoring after class III antiarrhythmic initiation and support targeted intervention.
- 6 January 2026
- Published by Wolters Kluwer Health in Circulation
- Vol. 153 (1) , 35-46
Top Cited PapersDeep Learning–Based Continuous QT Monitoring to Identify High-Risk Prolongation Events After Class III Antiarrhythmic Initiation
BACKGROUND: Drug-induced QT prolongation after successful inpatient loading of class III antiarrhythmics may occur during routine outpatient care. Insertable cardiac monitors offer continuous signals but are limited by single-lead configuration. We hypothesized that a spatially aware deep learning system (3DRECON-QT) can reconstruct spatial information from a single lead vector to quantify QT/QTc and identify high-risk prolongation. METHODS: We developed 3DRECON-QT using a multitask encoder–decoder that ingests a 10-s single-lead signal, reconstructs 12 leads, and predicts QT/QTc. The model was developed using 12-lead ECGs with clinician-adjudicated QT/RR from a large health system and tested in an external center with different ECG hardware. Continuous monitoring performance was assessed in a public dofetilide‐loading data set with serial ECGs. In a real-world cohort of outpatients on dofetilide or sotalol presenting to the hospital or emergency room for any reason, rates of ventricular arrhythmias and QT prolongation were assessed. Device validation was tested in patients with insertable cardiac monitor recordings paired with clinical 12-lead ECGs. RESULTS: 3DRECON-QT classified prolonged QTc from single-lead signals with area under the receiver operating characteristics curve, 0.942 (mean absolute error, 17.5 ms) in the internal test set and 0.943 (mean absolute error, 21.1 ms) externally. During continuous dofetilide monitoring, predictions correlated with ground truth ( r , 0.851; mean absolute error, 17.8 ms; area under the receiver operating characteristics curve, 0.936 for prolonged QTc, 0.816 for ≥15% QTc rise). QTc prediction from true insertable cardiac monitor recordings showed r =0.824 and mean absolute error, 17.5 ms. In outpatients on class III antiarrhythmics (n=1676), 16.5% had high-risk QTc prolongation. Ventricular arrhythmia events were 3.97% versus 0.86% without prolongation (adjusted odds ratio, 4.24 [95% CI, 1.81–9.90]). 3DRECON-QT detected these events with area under the receiver operating characteristics curve 0.94 (F1 score, 0.60). CONCLUSIONS: A single-lead, deep-learning approach can achieve guideline-level measurement accuracy, enable continuous QTc surveillance from nonstandard ECG vectors, and identify clinically meaningful outpatient QTc prolongation associated with a >4-fold increase in serious ventricular arrhythmias. This strategy may enhance safety monitoring after class III antiarrhythmic initiation and support targeted intervention.
- Open Access
- 6 November 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 300
Reducing diverse sources of noise in ventricular electrical signals using variational autoencoders
- 6 November 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 300
Open AccessReducing diverse sources of noise in ventricular electrical signals using variational autoencoders
- 1 February 2025
- Published by Wolters Kluwer Health in Circulation: Arrhythmia and Electrophysiology
- Vol. 18 (2) , e012860
Comparing Phenotypes for Acute and Long-Term Response to Atrial Fibrillation Ablation Using Machine Learning
BACKGROUND: It is difficult to identify patients with atrial fibrillation (AF) most likely to respond to ablation. While any arrhythmia patient may recur after acutely successful ablation, AF is unusual in that patients may have long-term arrhythmia freedom despite a lack of acute success. We hypothesized that acute and chronic AF ablation outcomes may reflect distinct physiology and used machine learning of multimodal data to identify their phenotypes. METHODS: We studied 561 consecutive patients in the Stanford AF ablation registry (66±10 years, 28% women, 67% nonparoxysmal), from whom we extracted 72 data features of electrograms, electrocardiogram, cardiac structure, lifestyle, and clinical variables. We compared 6 machine learning models to predict acute and long-term end points after ablation and used Shapley explainability analysis to contrast phenotypes. We validated our results in an independent external population of n=77 patients with AF. RESULTS: The 1-year success rate was 69.5%, and the acute termination rate was 49.6%, which correlated poorly on a patient-by-patient basis (φ coefficient=0.08). The best model for acute termination (area under the curve=0.86, Random Forest) was more predictive than for long-term outcomes (area under the curve=0.67, logistic regression; P <0.001). Phenotypes for long-term success reflected clinical and lifestyle features, while phenotypes for AF termination reflected electrical features. The need for AF induction predicted both phenotypes. The external validation cohort showed similar results (area under the curve=0.81 and 0.64, respectively) with similar phenotypes. CONCLUSIONS: Long-term and acute responses to AF ablation reflect distinct clinical and electrical physiology, respectively. This de-linking of phenotypes raises the question of whether long-term success operates through factors such as attenuated AF progression. There remains an urgent need to develop procedural predictors of long-term AF ablation success.
- 1 February 2025
- Published by Wolters Kluwer Health in Circulation: Arrhythmia and Electrophysiology
- Vol. 18 (2) , e012860
Comparing Phenotypes for Acute and Long-Term Response to Atrial Fibrillation Ablation Using Machine Learning
BACKGROUND: It is difficult to identify patients with atrial fibrillation (AF) most likely to respond to ablation. While any arrhythmia patient may recur after acutely successful ablation, AF is unusual in that patients may have long-term arrhythmia freedom despite a lack of acute success. We hypothesized that acute and chronic AF ablation outcomes may reflect distinct physiology and used machine learning of multimodal data to identify their phenotypes. METHODS: We studied 561 consecutive patients in the Stanford AF ablation registry (66±10 years, 28% women, 67% nonparoxysmal), from whom we extracted 72 data features of electrograms, electrocardiogram, cardiac structure, lifestyle, and clinical variables. We compared 6 machine learning models to predict acute and long-term end points after ablation and used Shapley explainability analysis to contrast phenotypes. We validated our results in an independent external population of n=77 patients with AF. RESULTS: The 1-year success rate was 69.5%, and the acute termination rate was 49.6%, which correlated poorly on a patient-by-patient basis (φ coefficient=0.08). The best model for acute termination (area under the curve=0.86, Random Forest) was more predictive than for long-term outcomes (area under the curve=0.67, logistic regression; P <0.001). Phenotypes for long-term success reflected clinical and lifestyle features, while phenotypes for AF termination reflected electrical features. The need for AF induction predicted both phenotypes. The external validation cohort showed similar results (area under the curve=0.81 and 0.64, respectively) with similar phenotypes. CONCLUSIONS: Long-term and acute responses to AF ablation reflect distinct clinical and electrical physiology, respectively. This de-linking of phenotypes raises the question of whether long-term success operates through factors such as attenuated AF progression. There remains an urgent need to develop procedural predictors of long-term AF ablation success.
- 1 January 2025
- Published by Wolters Kluwer Health in Circulation: Arrhythmia and Electrophysiology
- Vol. 18 (1) , e013023
Engineering of Generative Artificial Intelligence and Natural Language Processing Models to Accurately Identify Arrhythmia Recurrence
BACKGROUND: Large language models (LLMs) such as Chat Generative Pre-trained Transformer (ChatGPT) excel at interpreting unstructured data from public sources, yet are limited when responding to queries on private repositories, such as electronic health records (EHRs). We hypothesized that prompt engineering could enhance the accuracy of LLMs for interpreting EHR data without requiring domain knowledge, thus expanding their utility for patients and personalized diagnostics. METHODS: We designed and systematically tested prompt engineering techniques to improve the ability of LLMs to interpret EHRs for nuanced diagnostic questions, referenced to a panel of medical experts. In 490 full-text EHR notes from 125 patients with prior life-threatening heart rhythm disorders, we asked GPT-4-turbo to identify recurrent arrhythmias distinct from prior events and tested 220 563 queries. To provide context, results were compared with rule-based natural language processing and Bidirectional Encoder Representations from Transformer-based language models. Experiments were repeated for 2 additional LLMs. RESULTS: In an independent hold-out set of 389 notes, GPT-4-turbo had a balanced accuracy of 64.3%±4.7% out-of-the-box at baseline. This increased when asking GPT-4-turbo to provide a rationale for its answers, a structured data output, and in-context exemplars, to a balanced accuracy of 91.4%±3.8% ( P P <0.05). Results were consistent for GPT-3.5-turbo and Jurassic-2 LLMs. CONCLUSIONS: The use of prompt engineering strategies enables LLMs to identify clinical end points from EHRs with an accuracy that surpassed natural language processing and approximated experts, yet without the need for expert knowledge. These approaches could be applied to LLM queries for other domains, to facilitate automated analysis of nuanced data sets with high accuracy by nonexperts.
- 1 January 2025
- Published by Wolters Kluwer Health in Circulation: Arrhythmia and Electrophysiology
- Vol. 18 (1) , e013023
Engineering of Generative Artificial Intelligence and Natural Language Processing Models to Accurately Identify Arrhythmia Recurrence
BACKGROUND: Large language models (LLMs) such as Chat Generative Pre-trained Transformer (ChatGPT) excel at interpreting unstructured data from public sources, yet are limited when responding to queries on private repositories, such as electronic health records (EHRs). We hypothesized that prompt engineering could enhance the accuracy of LLMs for interpreting EHR data without requiring domain knowledge, thus expanding their utility for patients and personalized diagnostics. METHODS: We designed and systematically tested prompt engineering techniques to improve the ability of LLMs to interpret EHRs for nuanced diagnostic questions, referenced to a panel of medical experts. In 490 full-text EHR notes from 125 patients with prior life-threatening heart rhythm disorders, we asked GPT-4-turbo to identify recurrent arrhythmias distinct from prior events and tested 220 563 queries. To provide context, results were compared with rule-based natural language processing and Bidirectional Encoder Representations from Transformer-based language models. Experiments were repeated for 2 additional LLMs. RESULTS: In an independent hold-out set of 389 notes, GPT-4-turbo had a balanced accuracy of 64.3%±4.7% out-of-the-box at baseline. This increased when asking GPT-4-turbo to provide a rationale for its answers, a structured data output, and in-context exemplars, to a balanced accuracy of 91.4%±3.8% ( P P <0.05). Results were consistent for GPT-3.5-turbo and Jurassic-2 LLMs. CONCLUSIONS: The use of prompt engineering strategies enables LLMs to identify clinical end points from EHRs with an accuracy that surpassed natural language processing and approximated experts, yet without the need for expert knowledge. These approaches could be applied to LLM queries for other domains, to facilitate automated analysis of nuanced data sets with high accuracy by nonexperts.
- Open Access
- 17 July 2024
- Published by MDPI AG in Diagnostics
- Vol. 14 (14) , 1538
Novel Domain Knowledge-Encoding Algorithm Enables Label-Efficient Deep Learning for Cardiac CT Segmentation to Guide Atrial Fibrillation Treatment in a Pilot Dataset
Background: Segmenting computed tomography (CT) is crucial in various clinical applications, such as tailoring personalized cardiac ablation for managing cardiac arrhythmias. Automating segmentation through machine learning (ML) is hindered by the necessity for large, labeled training data, which can be challenging to obtain. This article proposes a novel approach for automated, robust labeling using domain knowledge to achieve high-performance segmentation by ML from a small training set. The approach, the domain knowledge-encoding (DOKEN) algorithm, reduces the reliance on large training datasets by encoding cardiac geometry while automatically labeling the training set. The method was validated in a hold-out dataset of CT results from an atrial fibrillation (AF) ablation study. Methods: The DOKEN algorithm parses left atrial (LA) structures, extracts “anatomical knowledge” by leveraging digital LA models (available publicly), and then applies this knowledge to achieve high ML segmentation performance with a small number of training samples. The DOKEN-labeled training set was used to train a nnU-Net deep neural network (DNN) model for segmenting cardiac CT in N = 20 patients. Subsequently, the method was tested in a hold-out set with N = 100 patients (five times larger than training set) who underwent AF ablation. Results: The DOKEN algorithm integrated with the nn-Unet model achieved high segmentation performance with few training samples, with a training to test ratio of 1:5. The Dice score of the DOKEN-enhanced model was 96.7% (IQR: 95.3% to 97.7%), with a median error in surface distance of boundaries of 1.51 mm (IQR: 0.72 to 3.12) and a mean centroid–boundary distance of 1.16 mm (95% CI: −4.57 to 6.89), similar to expert results (r = 0.99; p < 0.001). In digital hearts, the novel DOKEN approach segmented the LA structures with a mean difference for the centroid–boundary distances of −0.27 mm (95% CI: −3.87 to 3.33; r = 0.99; p < 0.0001). Conclusions: The proposed novel domain knowledge-encoding algorithm was able to perform the segmentation of six substructures of the LA, reducing the need for large training data sets. The combination of domain knowledge encoding and a machine learning approach could reduce the dependence of ML on large training datasets and could potentially be applied to AF ablation procedures and extended in the future to other imaging, 3D printing, and data science applications.
- 17 July 2024
- Published by MDPI AG in Diagnostics
- Vol. 14 (14) , 1538
Open AccessNovel Domain Knowledge-Encoding Algorithm Enables Label-Efficient Deep Learning for Cardiac CT Segmentation to Guide Atrial Fibrillation Treatment in a Pilot Dataset
Background: Segmenting computed tomography (CT) is crucial in various clinical applications, such as tailoring personalized cardiac ablation for managing cardiac arrhythmias. Automating segmentation through machine learning (ML) is hindered by the necessity for large, labeled training data, which can be challenging to obtain. This article proposes a novel approach for automated, robust labeling using domain knowledge to achieve high-performance segmentation by ML from a small training set. The approach, the domain knowledge-encoding (DOKEN) algorithm, reduces the reliance on large training datasets by encoding cardiac geometry while automatically labeling the training set. The method was validated in a hold-out dataset of CT results from an atrial fibrillation (AF) ablation study. Methods: The DOKEN algorithm parses left atrial (LA) structures, extracts “anatomical knowledge” by leveraging digital LA models (available publicly), and then applies this knowledge to achieve high ML segmentation performance with a small number of training samples. The DOKEN-labeled training set was used to train a nnU-Net deep neural network (DNN) model for segmenting cardiac CT in N = 20 patients. Subsequently, the method was tested in a hold-out set with N = 100 patients (five times larger than training set) who underwent AF ablation. Results: The DOKEN algorithm integrated with the nn-Unet model achieved high segmentation performance with few training samples, with a training to test ratio of 1:5. The Dice score of the DOKEN-enhanced model was 96.7% (IQR: 95.3% to 97.7%), with a median error in surface distance of boundaries of 1.51 mm (IQR: 0.72 to 3.12) and a mean centroid–boundary distance of 1.16 mm (95% CI: −4.57 to 6.89), similar to expert results (r = 0.99; p < 0.001). In digital hearts, the novel DOKEN approach segmented the LA structures with a mean difference for the centroid–boundary distances of −0.27 mm (95% CI: −3.87 to 3.33; r = 0.99; p < 0.0001). Conclusions: The proposed novel domain knowledge-encoding algorithm was able to perform the segmentation of six substructures of the LA, reducing the need for large training data sets. The combination of domain knowledge encoding and a machine learning approach could reduce the dependence of ML on large training datasets and could potentially be applied to AF ablation procedures and extended in the future to other imaging, 3D printing, and data science applications.
- 1 March 2024
- Published by Wolters Kluwer Health in Circulation: Arrhythmia and Electrophysiology
- Vol. 17 (3) , e012041
Spatially Conserved Spiral Wave Activity During Human Atrial Fibrillation
BACKGROUND: Atrial fibrillation is the most common cardiac arrhythmia in the world and increases the risk for stroke and morbidity. During atrial fibrillation, the electric activation fronts are no longer coherently propagating through the tissue and, instead, show rotational activity, consistent with spiral wave activation, focal activity, collision, or partial versions of these spatial patterns. An unexplained phenomenon is that although simulations of cardiac models abundantly demonstrate spiral waves, clinical recordings often show only intermittent spiral wave activity. METHODS: In silico data were generated using simulations in which spiral waves were continuously created and annihilated and in simulations in which a spiral wave was intermittently trapped at a heterogeneity. Clinically, spatio-temporal activation maps were constructed using 60 s recordings from a 64 electrode catheter within the atrium of N=34 patients (n=24 persistent atrial fibrillation). The location of clockwise and counterclockwise rotating spiral waves was quantified and all intervals during which these spiral waves were present were determined. For each interval, the angle of rotation as a function of time was computed and used to determine whether the spiral wave returned in step or changed phase at the start of each interval. RESULTS: In both simulations, spiral waves did not come back in phase and were out of step.” In contrast, spiral waves returned in step in the majority (68%; P =0.05) of patients. Thus, the intermittently observed rotational activity in these patients is due to a temporally and spatially conserved spiral wave and not due to ones that are newly created at the onset of each interval. CONCLUSIONS: Intermittency of spiral wave activity represents conserved spiral wave activity of long, but interrupted duration or transient spiral activity, in the majority of patients. This finding could have important ramifications for identifying clinically important forms of atrial fibrillation and in guiding treatment.
- 1 March 2024
- Published by Wolters Kluwer Health in Circulation: Arrhythmia and Electrophysiology
- Vol. 17 (3) , e012041
Spatially Conserved Spiral Wave Activity During Human Atrial Fibrillation
BACKGROUND: Atrial fibrillation is the most common cardiac arrhythmia in the world and increases the risk for stroke and morbidity. During atrial fibrillation, the electric activation fronts are no longer coherently propagating through the tissue and, instead, show rotational activity, consistent with spiral wave activation, focal activity, collision, or partial versions of these spatial patterns. An unexplained phenomenon is that although simulations of cardiac models abundantly demonstrate spiral waves, clinical recordings often show only intermittent spiral wave activity. METHODS: In silico data were generated using simulations in which spiral waves were continuously created and annihilated and in simulations in which a spiral wave was intermittently trapped at a heterogeneity. Clinically, spatio-temporal activation maps were constructed using 60 s recordings from a 64 electrode catheter within the atrium of N=34 patients (n=24 persistent atrial fibrillation). The location of clockwise and counterclockwise rotating spiral waves was quantified and all intervals during which these spiral waves were present were determined. For each interval, the angle of rotation as a function of time was computed and used to determine whether the spiral wave returned in step or changed phase at the start of each interval. RESULTS: In both simulations, spiral waves did not come back in phase and were out of step.” In contrast, spiral waves returned in step in the majority (68%; P =0.05) of patients. Thus, the intermittently observed rotational activity in these patients is due to a temporally and spatially conserved spiral wave and not due to ones that are newly created at the onset of each interval. CONCLUSIONS: Intermittency of spiral wave activity represents conserved spiral wave activity of long, but interrupted duration or transient spiral activity, in the majority of patients. This finding could have important ramifications for identifying clinically important forms of atrial fibrillation and in guiding treatment.
- Open Access
- 18 March 2023
- Published by Oxford University Press (OUP) in EP Europace
- Vol. 25 (5)
Quantifying a spectrum of clinical response in atrial tachyarrhythmias using spatiotemporal synchronization of electrograms
There is a clinical spectrum for atrial tachyarrhythmias wherein most patients with atrial tachycardia (AT) and some with atrial fibrillation (AF) respond to ablation, while others do not. It is undefined if this clinical spectrum has pathophysiological signatures. This study aims to test the hypothesis that the size of spatial regions showing repetitive synchronized electrogram (EGM) shapes over time reveals a spectrum from AT, to AF patients who respond acutely to ablation, to AF patients without acute response. We studied n = 160 patients (35% women, 65.0 ± 10.4 years) of whom (i) n = 75 had AF terminated by ablation propensity matched to (ii) n = 75 without AF termination and (iii) n = 10 with AT. All patients had mapping by 64-pole baskets to identify areas of repetitive activity (REACT) to correlate unipolar EGMs in shape over time. Synchronized regions (REACT) were largest in AT, smaller in AF termination, and smallest in non-termination cohorts (0.63 ± 0.15, 0.37 ± 0.22, and 0.22 ± 0.18, P < 0.001). Area under the curve for predicting AF termination in hold-out cohorts was 0.72 ± 0.03. Simulations showed that lower REACT represented greater variability in clinical EGM timing and shape. Unsupervised machine learning of REACT and extensive (50) clinical variables yielded four clusters of increasing risk for AF termination (P < 0.01, χ2), which were more predictive than clinical profiles alone (P < 0.001). The area of synchronized EGMs within the atrium reveals a spectrum of clinical response in atrial tachyarrhythmias. These fundamental EGM properties, which do not reflect any predetermined mechanism or mapping technology, predict outcome and offer a platform to compare mapping tools and mechanisms between AF patient groups.
- 18 March 2023
- Published by Oxford University Press (OUP) in EP Europace
- Vol. 25 (5)
Open AccessQuantifying a spectrum of clinical response in atrial tachyarrhythmias using spatiotemporal synchronization of electrograms
There is a clinical spectrum for atrial tachyarrhythmias wherein most patients with atrial tachycardia (AT) and some with atrial fibrillation (AF) respond to ablation, while others do not. It is undefined if this clinical spectrum has pathophysiological signatures. This study aims to test the hypothesis that the size of spatial regions showing repetitive synchronized electrogram (EGM) shapes over time reveals a spectrum from AT, to AF patients who respond acutely to ablation, to AF patients without acute response. We studied n = 160 patients (35% women, 65.0 ± 10.4 years) of whom (i) n = 75 had AF terminated by ablation propensity matched to (ii) n = 75 without AF termination and (iii) n = 10 with AT. All patients had mapping by 64-pole baskets to identify areas of repetitive activity (REACT) to correlate unipolar EGMs in shape over time. Synchronized regions (REACT) were largest in AT, smaller in AF termination, and smallest in non-termination cohorts (0.63 ± 0.15, 0.37 ± 0.22, and 0.22 ± 0.18, P < 0.001). Area under the curve for predicting AF termination in hold-out cohorts was 0.72 ± 0.03. Simulations showed that lower REACT represented greater variability in clinical EGM timing and shape. Unsupervised machine learning of REACT and extensive (50) clinical variables yielded four clusters of increasing risk for AF termination (P < 0.01, χ2), which were more predictive than clinical profiles alone (P < 0.001). The area of synchronized EGMs within the atrium reveals a spectrum of clinical response in atrial tachyarrhythmias. These fundamental EGM properties, which do not reflect any predetermined mechanism or mapping technology, predict outcome and offer a platform to compare mapping tools and mechanisms between AF patient groups.