Collin Stultz
Research Interests
Make your next move.
Prepare your application
Review drafts before you send them.
Explore related searches
Articles (14)
Year:
2026
Year:
2025
Introduction: The implantable CardioMEMS Heart Failure (HF) system, which monitors pulmonary arterial pressures in an outpatient setting, has been shown to reduce HF hospitalizations and improve functional status in patients with chronic heart failure. However, implantation is invasive and entails risk. Recent evidence suggests that a Cardiac Hemodynamic Artificial Intelligence System (CHAIS) can non-invasively identify when the mean pulmonary capillary wedge pressure (mPCWP) is elevated using ECG Lead-I signals. In this pilot study, we test whether CHAIS, without any retraining, can identify when the pulmonary artery diastolic pressure (PADP) – a correlate of the mPCWP – is elevated using ECG Lead-I signals obtained from a wearable ECG monitor. Hypothesis: CHAIS can determine when CardioMEMS-derived PADP is elevated. Methods: Ten adults (1 female, age 72 ± 11 years) with chronic HF and CardioMEMS implants were enrolled at Boston Medical Center (BMC, n=6, IRB H-44263) and Massachusetts General Hospital (MGH, n=4, IRB 2023P001291). Participants wore a single-lead ECG patch for up to 14 days. ECG data was segmented into 10 second windows, pre-processed, and input to CHAIS, which returned the probability of mPCWP > 18 mmHg. CHAIS probabilities were matched to CardioMEMS-derived PADP, producing N=76 contemporaneous pairs across all 10 patients. Results: CHAIS showed strong discriminatory ability for identifying when CardioMEMS PADP > 18 mmHg, yielding an overall AUC of 0.82 (BMC 0.85; MGH 0.81). After excluding eight ECG signals with poor signal quality (resulting in N=68 ECG-PADP pairs), the overall AUC rose to 0.85 (BMC 0.86; MGH 0.93). Moreover, CHAIS output was positively associated with contemporaneous CardioMEMS PADP (Pearson r=0.36, Spearman ρ=0.45 with N=76 and Pearson r=0.42, ρ=0.51 with N=68; all p < 0.001). P-values were computed via permutation testing using 25,000 resamples. Conclusion: This is the first study to demonstrate that a deep-learning model (CHAIS) can discriminate for elevated PADP using ECG signals obtained from a wearable ECG monitor. This non-invasive low-cost methodology for hemodynamic monitoring could expand HF surveillance, especially for patients who are ineligible to receive an invasive device. Fine-tuning CHAIS on wearable ECG data would improve its ability to non-invasively identify patients at risk for a HF exacerbation.
Year:
2025
Background Objective assessment of left ventricular function remains a key prognosticator that is used to guide therapeutic decisions for patients with heart failure (HF). However, the left ventricular ejection fraction (LVEF) is dynamic, with worsening LVEF linked to increased morbidity and mortality. Identifying patients at risk of LVEF decline would improve prognostication and enable timely therapeutic intervention. Methods We developed a deep learning model to P redict changes in left ventric UL ar S ystolic function from E lectrocardiograms (ECG) of patients who have H eart F ailure (PULSE-HF). The model integrates 12-lead ECG waveforms with a patient’s history of prior LVEF measurements to calculate the likelihood that the LVEF will be less than 40% during the year after the ECG is obtained. The model is retrospectively developed and tested using data from one hospital and externally validated on retrospective cohorts from two different hospitals. Findings PULSE–HF demonstrates strong discriminatory ability with respect to forecasting whether the LVEF would be below 40% within the next year, achieving areas under the receiver operating characteristic curve (AUROC) of 87.5-91.4% across all three HF cohorts. Among patients with HF who have a baseline LVEF above 40%, PULSE–HF effectively identified those at risk of worsening LVEF with AUROCs of 81.6-86.3% across all three datasets. PULSE–HF’s discriminatory ability remained consistently high across a range of subgroups with different comorbidities and regardless of medical therapy. Assuming an underlying prevalence of LVEF worsening of 10% per year, PULSE-HF’s negative predictive values are over 97%, assuming an underlying sensitivity of 80%. Lastly, we demonstrate that a lead I version of PULSE–HF has a performance similar to the performance of the model that uses all 12 ECG leads. Interpretation PULSE–HF robustly predicts worsening LVEF in patients who have a prior diagnosis of HF. The method provides a platform for identifying patients who are at an increased risk of worsening systolic dysfunction. Funding This work was supported, in part, by a grant from Quanta Computers. Research in context Evidence before this study Heart failure (HF) remains a leading cause of morbidity and mortality across the globe. Left ventricular ejection fraction (LVEF) plays an important role in prognostication and treatment of HF. Moreover, LVEF is dynamic, with worsening LVEF being associated with increased mortality and poor outcomes compared to patients with HF with stable LVEF. Identifying patients with HF at risk of future decline in LVEF would improve prognostication and facilitate the timely delivery of appropriate medical therapy. However, models that use the electronic health record (EHR) to forecast declines in LVEF have demonstrated modest discriminatory ability. For instance, a model incorporating echocardiographic features, demographics, and comorbidities from the EHR had areas under the receiver operating characteristic curve (AUROC) between 54%–68% for predicting a 30% decline in LVEF within one year after HF diagnosis. Electrocardiograms (ECG) may contain information about LVEF, as deep learning models of ECGs have been used to estimate the contemporaneous LVEF. A prior method uses ECG to forecast LVEF below 40%, but this method was developed for a much shorter future time window of six months and specifically for patients with premature ventricular complexes. To date, the ECG has not been used to forecast future changes in LVEF among HF patients. Overall, no robust method exists for identifying patients with HF at high risk of future LVEF decline. Added value of this study We developed a deep learning model, called PULSE–HF, to P redict changes in left ventric UL ar S ystolic function from E CGs of patients who have H eart F ailure. The model leverages both the 12-lead ECG and history of prior LVEF measurements to identify patients at risk of having a reduced LVEF (≤ 40%) wit
Year:
2025
For a number of antiarrhythmics, drug loading requires a 3-day hospitalization with continuous monitoring for QT-prolongation. Automated QT monitoring with wearable ECG monitors would enable out-of-hospital care. We therefore develop a deep learning model that infers QT intervals from ECG Lead-I—the lead that is often available in ambulatory ECG monitors—and use this model to detect clinically meaningful QT-prolongation episodes during Dofetilide drug loading. QTNet–a deep neural network that infers QT intervals from Lead-I ECG–was trained using over 3 million ECGs from 653 thousand patients at the Massachusetts General Hospital and tested on an internal-test set consisting of 633 thousand ECGs from 135 thousand patients. QTNet is further evaluated on an external-validation set containing 3.1 million ECGs from 667 thousand patients at another healthcare institution. On both evaluations, the model achieves mean absolute errors of 12.63ms (internal-test) and 12.30ms (external-validation) for estimating absolute QT intervals. The associated Pearson correlation coefficients are 0.91 (internal-test) and 0.92 (external-validation). Finally, QTNet was used to detect Dofetilide-induced QT prolongation in a publicly available database (ECGRDVQ-dataset) containing ECGs from subjects enrolled in a clinical trial evaluating the effects of antiarrhythmic drugs. QTNet detects Dofetilide-induced QTc prolongation with 87% sensitivity and 77% specificity. The negative predictive value of the model is greater than 95% when the pre-test probability of drug-induced QTc prolongation is below 25%. These results show that drug-induced QT prolongation risk can be tracked from ECG Lead-I using deep learning.
Year:
2024
Introduction: While smartwatches that acquire Lead-I electrocardiogram (ECG) have shown promise in detecting arrhythmias, the detection of ischemic events using Lead-I alone remains understudied. We aim to build and evaluate a deep-learning model to determine whether Lead-I ECG can identify ischemia/infarction in a 12-lead ECG. Methods: We developed a deep-learning model that can identify MI/ischemia using only Lead-I ECG signal as input. For this task, we utilized PTB-XL, a large publicly available dataset of 12-Lead clinical ECG with associated diagnostic labels. Our experiment utilized 8781 ECGs whose labels were validated by at-least one cardiologist with 100% confidence scores. This dataset includes 1391 ECGs that are labeled as either ischemic ST/T changes or MI, and 7390 ECGs with either “normal” labels or non-ischemic ST/T abnormalities. We split the dataset in training, validation, and holdout sets (80-10-10) with equal stratification of the diagnosis classes. The holdout test set contains 909 non-ischemic ECGs and 233 ECGs with MI/ischemia diagnosis, 106 of which are labeled as acute MI or ischemic ST/T changes and 127 labeled as other MI chronicity. The discriminatory ability of the model is evaluated with the Area Under the receiver-operating Curve (AUC), sensitivity, specificity, and the predictive values. We further analyze the model’s capability in discriminating the cohort of acute MI and ischemia diagnoses from other MI as well as from the non-ischemic cohort. Results: The model has an AUC of 0.88 for discriminating an MI/ischemia vs normal. Using a threshold corresponding to 80% sensitivity, the corresponding specificity is 79% and the negative and positive predictive values are 94% and 50% (Table-1). Although the model was trained to identify the combined class of MI/ischemia, it can differentiate acute MI and ischemia cohorts from other MI as well as from non-ischemic diagnoses with p-values<10 -4 (Table-2). Lastly, with the same threshold, the sensitivity for detecting acute inferior myocardial infarctions or inferior ischemia – a class that is difficult to detect with Lead-I alone – is 82%. Conclusions: Our deep learning model, which was trained on Lead-I ECG alone, can effectively detect acute MI and ischemia that would have been identified using a 12-lead ECG. This method presents a proof-of-concept for applications in home settings. Further prospective validation using wearable ECG monitors that record lead-I is warranted.
Year:
2024
Year:
2024
Year:
2024
Background Risk stratification models estimate the probabilities of adverse outcomes after cardiac surgical procedures, which helps clinicians and patients make informed decisions. Objectives We used the 12-lead electrocardiogram (ECG) and/or Society for Thoracic Surgeons (STS) variables to predict postoperative outcomes using deep learning methods that can incorporate diverse data types. Methods We developed a deep convolutional neural network (“ECGNet”) that predicts operative mortality and other adverse outcomes using preoperative 12-lead ECGs (n=30,877) from 12,933 patients who underwent 13,299 cardiac surgical procedures. We also developed a deep neural network applied to preoperative STS variables (“STSNet”). STSNet and ECGNet are multi-task neural networks that utilize secondary outcomes to augment prediction of mortality using the same neural network. Results ECGNet achieved a mean area under the receiver operating characteristic curve (AUC) of 0.85 for predicting operative mortality for all procedures and 0.93 for valve procedures. STSNet achieved a mean AUC of 0.85 for all procedures, with statistically similar performance as ECGNet for all procedures. Combining ECGNet and STSNet achieved a mean AUC of 0.90 for predicting operative mortality after all procedures, which is significantly higher than either ECGNet or STSNet alone. Conclusions A deep neural network trained on STS features has higher predictive performance than previously reported for existing conventional models and is not limited to certain types of cardiac surgical procedures. A model trained on ECG alone can predict operative mortality with similar performance as STS features and adding ECG to STS features in a neural network can improve performance. These findings demonstrate the potential in leveraging deep learning on multidimensional data sources to predict outcomes after cardiac surgery. Condensed abstract In this study, deep learning (DL) is applied to electrocardiograms and clinical features used in the standard STS risk prediction tools to generate new high-performing risk calculators for cardiac surgical procedures. Preoperative voltage waveforms contain information about cardiovascular risk and cardiac function and are passed as inputs to the deep learning model. These risk models apply to all cardiac procedures including those procedures that do not have standard STS risk calculators and provide improved performance. DL models enable the incorporation of additional modalities of data to improve risk prediction in cardiac surgery.
Year:
2024
Background The ability to non-invasively measure left atrial pressure would facilitate the identification of patients at risk of pulmonary congestion and guide proactive heart failure care. Wearable cardiac monitors, which record single-lead electrocardiogram data, provide information that can be leveraged to infer left atrial pressures. Methods We developed a deep neural network using single-lead electrocardiogram data to determine when the left atrial pressure is elevated. The model was developed and internally evaluated using a cohort of 6739 samples from the Massachusetts General Hospital (MGH) and externally validated on a cohort of 4620 samples from a second institution. We then evaluated model on patch-monitor electrocardiographic data on a small prospective cohort. Results The model achieves an area under the receiver operating characteristic curve of 0.80 for detecting elevated left atrial pressures on an internal holdout dataset from MGH and 0.76 on an external validation set from a second institution. A further prospective dataset was obtained using single-lead electrocardiogram data with a patch-monitor from patients who underwent right heart catheterization at MGH. Evaluation of the model on this dataset yielded an area under the receiver operating characteristic curve of 0.875 for identifying elevated left atrial pressures for electrocardiogram signals acquired close to the time of the right heart catheterization procedure. Conclusions These results demonstrate the utility and the potential of ambulatory cardiac hemodynamic monitoring with electrocardiogram patch-monitors. Plain Language Summary Heart failure is a prevalent disorder that is challenging to manage. Part of what makes heart failure management challenging is that the onset of symptoms can be insidious as there are few robust tools that a clinical can leverage to estimate when a patient is likely to experience an episode of acute heart failure. While elevated intracardiac pressures are a reliable harbinger of worsening heart failure, these pressures are typically measured using an invasive, gold-standard approach, which can only be performed in an inpatient setting. A non-invasive method for detecting higher pressures inside of heart would be especially helpful for identifying worsening heart failure in an expeditious manner in the home environment. For this reason, we developed an artificial intelligence model to detect elevated pressures inside the heart using a non-invasive signal, the electrocardiogram (ECG, or EKG), which can be acquired from a wearable patch monitor device. Our results demonstrate that the model provides a reliable platform for the non-invasive assessment of cardiac pressures using data that can be obtained in the outpatient setting.
Year:
2024
Year:
2023
Year:
2023
Year:
2023
Year:
2023
Collaborators (2)
Isaac Kohane
Professor
Harvard University
Chin Siang Ong
Assistant Professor of Surgery
Yale University
Make your next move.
Prepare your application
Review drafts before you send them.