Collin M. Stultz
YOU?
Author Swipe
View article: Forecasting left ventricular systolic dysfunction in heart failure with artificial intelligence
Forecasting left ventricular systolic dysfunction in heart failure with artificial intelligence Open
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, …
View article: Artificial intelligence for hemodynamic monitoring with a wearable electrocardiogram monitor
Artificial intelligence for hemodynamic monitoring with a wearable electrocardiogram monitor Open
These results demonstrate the utility and the potential of ambulatory cardiac hemodynamic monitoring with electrocardiogram patch-monitors.
View article: MEDS-Tab: Automated tabularization and baseline methods for MEDS datasets
MEDS-Tab: Automated tabularization and baseline methods for MEDS datasets Open
Effective, reliable, and scalable development of machine learning (ML) solutions for structured electronic health record (EHR) data requires the ability to reliably generate high-quality baseline models for diverse supervised learning task…
View article: Heart Block Identification from 12-Lead ECG: Exploring the Generalizability of Self-Supervised AI
Heart Block Identification from 12-Lead ECG: Exploring the Generalizability of Self-Supervised AI Open
Timely diagnosis and treatment of heart blocks are critical for preventing fatal outcomes in patients with cardiac conduction disorders. Expert analysis of clinical 12-lead electro-cardiograms (ECG) remains the standard diagnosis apparatus…
View article: Estimating ECG Intervals from Lead-I Alone: External Validation of Supervised Models
Estimating ECG Intervals from Lead-I Alone: External Validation of Supervised Models Open
The diagnosis, prognosis, and treatment of a number of cardiovascular disorders rely on ECG interval measurements, including the PR, QRS, and QT intervals. These quantities are measured from the 12-lead ECG, either manually or using automa…
View article: Estimating ECG Intervals from Lead-I Alone: External Validation of Supervised Models
Estimating ECG Intervals from Lead-I Alone: External Validation of Supervised Models Open
The diagnosis, prognosis, and treatment of a number of cardiovascular disorders rely on ECG interval measurements, including the PR, QRS, and QT intervals. These quantities are measured from the 12-lead ECG, either manually or using automa…
View article: Detecting QT prolongation from a single-lead ECG with deep learning
Detecting QT prolongation from a single-lead ECG with deep learning Open
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 dee…
View article: Artificial Intelligence for Hemodynamic Monitoring with a Wearable Electrocardiogram Monitor
Artificial Intelligence for Hemodynamic Monitoring with a Wearable Electrocardiogram Monitor Open
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-le…
View article: Detecting QT prolongation From a Single-lead ECG With Deep Learning
Detecting QT prolongation From a Single-lead ECG With Deep Learning Open
Background and Aims For a number of antiarrhythmics, drug loading requires a 3-day hospitalization with monitoring for QT-prolongation. Automated QT monitoring with wearable ECG monitors would facilitate out-of-hospital care. We aim to dev…
View article: Detecting QT prolongation From a Single-lead ECG With Deep Learning
Detecting QT prolongation From a Single-lead ECG With Deep Learning Open
For a number of antiarrhythmics, drug loading requires a 3 day hospitalization with monitoring for QT prolongation. Automated QT monitoring with wearable ECG monitors would facilitate out-of-hospital care. We develop a deep learning model …
View article: Event-Based Contrastive Learning for Medical Time Series
Event-Based Contrastive Learning for Medical Time Series Open
In clinical practice, one often needs to identify whether a patient is at high risk of adverse outcomes after some key medical event. For example, quantifying the risk of adverse outcomes after an acute cardiovascular event helps healthcar…
View article: Machine Learning for Risk Prediction
Machine Learning for Risk Prediction Open
[Figure: see text]
View article: Deep Metric Learning for the Hemodynamics Inference with Electrocardiogram Signals
Deep Metric Learning for the Hemodynamics Inference with Electrocardiogram Signals Open
Heart failure is a debilitating condition that affects millions of people worldwide and has a significant impact on their quality of life and mortality rates. An objective assessment of cardiac pressures remains an important method for the…
View article: QTNet: Deep Learning for Estimating QT Intervals Using a Single Lead ECG
QTNet: Deep Learning for Estimating QT Intervals Using a Single Lead ECG Open
QT prolongation often leads to fatal arrhythmia and sudden cardiac death. Antiarrhythmic drugs can increase the risk of QT prolongation and therefore require strict post-administration monitoring and dosage control. Measurement of the QT i…
View article: Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series
Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series Open
Self-supervised learning (SSL) for clinical time series data has received significant attention in recent literature, since these data are highly rich and provide important information about a patient's physiological state. However, most e…
View article: ECG-guided non-invasive estimation of pulmonary congestion in patients with heart failure
ECG-guided non-invasive estimation of pulmonary congestion in patients with heart failure Open
Quantifying hemodynamic severity in patients with heart failure (HF) is an integral part of clinical care. A key indicator of hemodynamic severity is the mean Pulmonary Capillary Wedge Pressure (mPCWP), which is ideally measured invasively…
View article: Identifying Aortic Stenosis With a Single Parasternal Long-Axis Video Using Deep Learning
Identifying Aortic Stenosis With a Single Parasternal Long-Axis Video Using Deep Learning Open
The accurate diagnosis of aortic stenosis (AS) involves both the acquisition of cardiac ultrasound images and the interpretation of these images by skilled personnel.1Otto C.M. Nishimura R.A. Bonow R.O. et al.2020 ACC/AHA guideline for the…
View article: Reply: More Than Meets the AI: Electrocardiograms in Heart Failure Prognosis
Reply: More Than Meets the AI: Electrocardiograms in Heart Failure Prognosis Open
View article: Predicting outcomes in patients with aortic stenosis using machine learning: the Aortic Stenosis Risk (ASteRisk) score
Predicting outcomes in patients with aortic stenosis using machine learning: the Aortic Stenosis Risk (ASteRisk) score Open
Objective To use echocardiographic and clinical features to develop an explainable clinical risk prediction model in patients with aortic stenosis (AS), including those with low-gradient AS (LGAS), using machine learning (ML). Methods In 1…
View article: Data Augmentation for Electrocardiograms
Data Augmentation for Electrocardiograms Open
Neural network models have demonstrated impressive performance in predicting pathologies and outcomes from the 12-lead electrocardiogram (ECG). However, these models often need to be trained with large, labelled datasets, which are not ava…
View article: A Deep Learning Model for Inferring Elevated Pulmonary Capillary Wedge Pressures From the 12-Lead Electrocardiogram
A Deep Learning Model for Inferring Elevated Pulmonary Capillary Wedge Pressures From the 12-Lead Electrocardiogram Open
View article: Patient contrastive learning: A performant, expressive, and practical approach to electrocardiogram modeling
Patient contrastive learning: A performant, expressive, and practical approach to electrocardiogram modeling Open
Supervised machine learning applications in health care are often limited due to a scarcity of labeled training data. To mitigate the effect of small sample size, we introduce a pre-training approach, P atient C ontrastive L earning of R e…
View article: DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics
DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics Open
Myocardial strain analysis from cinematic magnetic resonance imaging (cine-MRI) data provides a more thorough characterization of cardiac mechanics than volumetric parameters such as left-ventricular ejection fraction, but sources of varia…
View article: Patient Contrastive Learning: a Performant, Expressive, and Practical Approach to ECG Modeling
Patient Contrastive Learning: a Performant, Expressive, and Practical Approach to ECG Modeling Open
Supervised machine learning applications in health care are often limited due to a scarcity of labeled training data. To mitigate this effect of small sample size, we introduce a pre-training approach, Patient Contrastive Learning of Repre…
View article: Learning to predict with supporting evidence
Learning to predict with supporting evidence Open
The impact of machine learning models on healthcare will depend on the degree of trust that healthcare professionals place in the predictions made by these models. In this paper, we present a method to provide individuals with clinical exp…
View article: Learning to Predict with Supporting Evidence: Applications to Clinical Risk Prediction
Learning to Predict with Supporting Evidence: Applications to Clinical Risk Prediction Open
The impact of machine learning models on healthcare will depend on the degree of trust that healthcare professionals place in the predictions made by these models. In this paper, we present a method to provide people with clinical expertis…
View article: Learning to Predict with Supporting Evidence: Applications to Clinical\n Risk Prediction
Learning to Predict with Supporting Evidence: Applications to Clinical\n Risk Prediction Open
The impact of machine learning models on healthcare will depend on the degree\nof trust that healthcare professionals place in the predictions made by these\nmodels. In this paper, we present a method to provide people with clinical\nexper…
View article: DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics
DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics Open
Myocardial strain analysis from cinematic magnetic resonance imaging (cine-MRI) data could provide a more thorough characterization of cardiac mechanics than volumetric parameters such as left-ventricular ejection fraction, but sources of …
View article: Deep Learning for Cardiovascular Risk Stratification
Deep Learning for Cardiovascular Risk Stratification Open
Purpose of review Although deep learning represents an exciting platform for the development of risk stratification models, it is challenging to evaluate these models beyond simple statistical measures of success, which do not always provi…
View article: Deep Learning for Cardiovascular Risk Stratification
Deep Learning for Cardiovascular Risk Stratification Open