Search

Background: Timely diagnosis of structural heart disease improves patient outcomes, yet many remain underdiagnosed. While population screening with echocardiography is impractical, ECG-based prediction models can help target high-risk patients. We developed a novel ECG-based machine learning approach to predict multiple structural heart conditions, hypothesizing that a composite model would yield higher prevalence and positive predictive values to facilitate meaningful recommendations for echocardiography. Methods: Using 2 232 130 ECGs linked to electronic health records and echocardiography reports from 484 765 adults between 1984 to 2021, we trained machine learning models to predict the presence or absence of any of 7 echocardiography-confirmed diseases within 1 year. This composite label included the following: moderate or severe valvular disease (aortic/mitral stenosis or regurgitation, tricuspid regurgitation), reduced ejection fraction 15 mm. We tested various combinations of input features (demographics, laboratory values, structured ECG data, ECG traces) and evaluated model performance using 5-fold cross-validation, multisite validation trained on 1 site and tested on 10 independent sites, and simulated retrospective deployment trained on pre-2010 data and deployed in 2010. Results: Our composite rECHOmmend model used age, sex, and ECG traces and had a 0.91 area under the receiver operating characteristic curve and a 42% positive predictive value at 90% sensitivity, with a composite label prevalence of 17.9%. Individual disease models had area under the receiver operating characteristic curves from 0.86 to 0.93 and lower positive predictive values from 1% to 31%. Area under the receiver operating characteristic curves for models using different input features ranged from 0.80 to 0.93, increasing with additional features. Multisite validation showed similar results to cross-validation, with an aggregate area under the receiver operating characteristic curve of 0.91 across our independent test set of 10 clinical sites after training on a separate site. Our simulated retrospective deployment showed that for ECGs acquired in patients without preexisting structural heart disease in the year 2010, 11% were classified as high risk and 41% (4.5% of total patients) developed true echocardiography-confirmed disease within 1 year. Conclusions: An ECG-based machine learning model using a composite end point can identify a high-risk population for having undiagnosed, clinically significant structural heart disease while outperforming single-disease models and improving practical utility with higher positive predictive values. This approach can facilitate targeted screening with echocardiography to improve underdiagnosis of structural heart disease.

Supplemental Digital Content is available in the text., Background: Atrial fibrillation (AF) is associated with substantial morbidity, especially when it goes undetected. If new-onset AF could be predicted, targeted screening could be used to find it early. We hypothesized that a deep neural network could predict new-onset AF from the resting 12-lead ECG and that this prediction may help identify those at risk of AF-related stroke. Methods: We used 1.6 M resting 12-lead digital ECG traces from 430 000 patients collected from 1984 to 2019. Deep neural networks were trained to predict new-onset AF (within 1 year) in patients without a history of AF. Performance was evaluated using areas under the receiver operating characteristic curve and precision-recall curve. We performed an incidence-free survival analysis for a period of 30 years following the ECG stratified by model predictions. To simulate real-world deployment, we trained a separate model using all ECGs before 2010 and evaluated model performance on a test set of ECGs from 2010 through 2014 that were linked to our stroke registry. We identified the patients at risk for AF-related stroke among those predicted to be high risk for AF by the model at different prediction thresholds. Results: The area under the receiver operating characteristic curve and area under the precision-recall curve were 0.85 and 0.22, respectively, for predicting new-onset AF within 1 year of an ECG. The hazard ratio for the predicted high- versus low-risk groups over a 30-year span was 7.2 (95% CI, 6.9–7.6). In a simulated deployment scenario, the model predicted new-onset AF at 1 year with a sensitivity of 69% and specificity of 81%. The number needed to screen to find 1 new case of AF was 9. This model predicted patients at high risk for new-onset AF in 62% of all patients who experienced an AF-related stroke within 3 years of the index ECG. Conclusions: Deep learning can predict new-onset AF from the 12-lead ECG in patients with no previous history of AF. This prediction may help identify patients at risk for AF-related strokes.

Several large trials have employed age or clinical features to select patients for atrial fibrillation (AF) screening to reduce strokes. We hypothesized that a machine learning (ML) model trained to predict AF risk from 12‑lead electrocardiogram (ECG) would be more efficient than criteria based on clinical variables in indicating a population for AF screening to potentially prevent AF-related stroke.We retrospectively included all patients with clinical encounters in Geisinger without a prior history of AF. Incidence of AF within 1 year and AF-related strokes within 3 years of the encounter were identified. AF-related stroke was defined as a stroke where AF was diagnosed at the time of stroke or within a year after the stroke. The efficiency of five methods was evaluated for selecting a cohort for AF screening. The methods were selected from four clinical trials (mSToPS, GUARD-AF, SCREEN-AF and STROKESTOP) and the ECG-based ML model. We simulated patient selection for the five methods between the years 2011 and 2014 and evaluated outcomes for 1 year intervals between 2012 and 2015, resulting in a total of twenty 1-year periods. Patients were considered eligible if they met the criteria before the start of the given 1-year period or within that period. The primary outcomes were numbers needed to screen (NNS) for AF and AF-associated stroke.The clinical trial models indicated large proportions of the population with a prior ECG for AF screening (up to 31%), coinciding with NNS ranging from 14 to 18 for AF and 249-359 for AF-associated stroke. At comparable sensitivity, the ECG ML model indicated a modest number of patients for screening (14%) and had the highest efficiency in NNS for AF (7.3; up to 60% reduction) and AF-associated stroke (223; up to 38% reduction).An ECG-based ML risk prediction model is more efficient than contemporary AF-screening criteria based on age alone or age and clinical features at indicating a population for AF screening to potentially prevent AF-related strokes.

Background Heart failure is a prevalent, costly disease for which new value-based payment models demand optimized population management strategies. Objectives This study sought to generate a strategy for managing populations of patients with heart failure by leveraging large clinical datasets and machine learning. Methods Geisinger electronic health record data were used to train machine learning models to predict 1-year all-cause mortality in 26,971 patients with heart failure who underwent 276,819 clinical episodes. There were 26 clinical variables (demographics, laboratory test results, medications), 90 diagnostic codes, 41 electrocardiogram measurements and patterns, 44 echocardiographic measurements, and 8 evidence-based “care gaps”: flu vaccine, blood pressure of Results Machine learning models achieved areas under the receiver-operating characteristic curve (AUCs) of 0.74 to 0.77 in a split-by-year training/test scheme, with the nonlinear XGBoost model (AUC: 0.77) outperforming linear logistic regression (AUC: 0.74). Out of 13,238 currently living patients, 2,844 were predicted to die within a year, and closing all care gaps was predicted to save 231 of these lives. Prioritizing patients for intervention by using the predicted reduction in 1-year mortality risk outperformed all other priority rankings (e.g., random selection or Seattle Heart Failure risk score). Conclusions Machine learning can be used to priority-rank patients most likely to benefit from interventions to optimize evidence-based therapies. This approach may prove useful for optimizing heart failure population health management teams within value-based payment models.

Use of machine learning for automated annotation of heart structures from echocardiographic videos is an active research area, but understanding of comparative, generalizable performance among models is lacking. This study aimed to 1) assess the generalizability of five state-of-the-art machine learning-based echocardiography segmentation models within a large clinical dataset, and 2) test the hypothesis that a quality control (QC) method based on segmentation uncertainty can further improve segmentation results. Five models were applied to 47,431 echocardiography studies that were independent from any training samples. Chamber volume and mass from model segmentations were compared to clinically-reported values. The median absolute errors (MAE) in left ventricular (LV) volumes and ejection fraction exhibited by all five models were comparable to reported inter-observer errors (IOE). MAE for left atrial volume and LV mass were similarly favorable to respective IOE for models trained for those tasks. A single model consistently exhibited the lowest MAE in all five clinically-reported measures. We leveraged the 10-fold cross-validation training scheme of this best-performing model to quantify segmentation uncertainty for potential application as QC. We observed that filtering segmentations with high uncertainty improved segmentation results, leading to decreased volume/mass estimation errors. The addition of contour-convexity filters further improved QC efficiency. In conclusion, five previously published echocardiography segmentation models generalized to a large, independent clinical dataset—segmenting one or multiple cardiac structures with overall accuracy comparable to manual analyses—with variable performance. Convexity-reinforced uncertainty QC efficiently improved segmentation performance and may further facilitate the translation of such models.

Introduction: Timely diagnosis of structural heart disease improves patient outcomes, yet millions remain undiagnosed. ECG-based prediction models can help identify high-risk patients for targeted screening, but existing individual disease models often have low positive predictive values (PPV) and limited clinical utility. Hypothesis: An ECG-based composite model can predict one of multiple, actionable structural heart conditions and yield higher prevalence and PPVs than individual models. Methods: Using 2,141,366 ECGs linked to echocardiography and EHR records from 461,466 adults from 1984-2021, we trained machine learning models to predict any of 7 echocardiography-confirmed diseases within 1 year. This composite label included: moderate or severe valvular disease (aortic stenosis or regurgitation, mitral stenosis or regurgitation, tricuspid regurgitation), reduced ejection fraction of 15mm. We tested various combinations of inputs and evaluated model performance with 1) cross-validation and 2) a simulated retrospective deployment. We measured area under the receiver operating characteristic curve (AUROC) and precision-recall curve (AUPRC), and PPV at 90% sensitivity. Results: Our composite "rECHOmmend" model using age, sex and ECG traces had an AUROC of 0.91, AUPRC of 0.78, and PPV of 52% at 90% sensitivity and 23% disease prevalence. Individual disease models had similar AUROCs (0.88-0.93), but lower AUPRCs (0.07-0.71) and PPVs (2%-41%; Figure). Across inputs, model AUROCs ranged from 0.85 to 0.93. Our simulated deployment model classified 22% of at-risk patients in 2010 as high-risk, of whom 40% developed true, echo-confirmed disease within 1 year. Conclusions: An ECG-based machine learning model using a composite endpoint can predict undiagnosed structural heart disease, outperforming single disease models with higher PPVs to facilitate targeted screening with echocardiography.

Background: Several large trials have employed age or clinical features to select patients for atrial fibrillation (AF) screening to reduce strokes. We hypothesized that a deep neural network (DNN) model risk prediction based on ECG would be superior to age and clinical variables at selecting a population at high risk for AF and AF-related stroke. Methods: We retrospectively included all patients with an ECG at Geisinger without a prior history of AF. Incidence of AF and AF-related strokes were identified as outcomes within 1 and 3 years after the ECG, respectively. AF-related stroke was defined as a stroke where AF was diagnosed at the time of stroke or within a year after the stroke. We selected a high-risk cohort for AF screening based on five risk stratification methods - criteria from four clinical trials (mSToPS, STROKESTOP, GUARD-AF and SCREEN-AF) and the DNN model at the qualifying ECG. We simulated patient selection and evaluated outcomes for twenty 1-year periods between 2010-2014 centered around the ECG encounter. For the clinical trials, the patients were considered eligible if they met the criteria before or within the period unless they satisfied exclusion criteria at the time of ECG. Results: The DNN model achieved optimal sensitivity (65%), PPV (10%), NNS for AF (10) within this population compared with all other risk models with a NNS for AF-related stroke of 160. Total screening number, sensitivity, positive predictive value (PPV) and number needed to screen (NNS) to capture AF and AF-related stroke are summarized in Table 1. The number of additional screens for the DNN model was slightly higher for two of the other models (SCREEN-AF and STROKESTOP) but lower than the other two (mSToPS and GUARD-AF). Conclusions: A DNN ECG-based risk prediction model is superior to contemporary AF-screening criteria based on age alone or age and clinical features in selecting a population for additional screening due to high risk for future AF and potential AF-related strokes.

Introduction: Initiation of QTc-prolonging medications may lead to the rare but potentially catastrophic event, torsades de pointes (TDP). At present, no adequate, generalizable tools exist to predict drug-induced long QTc (LQT); machine learning from ECG data is a promising approach. Hypothesis: Prediction of drug-induced LQT using an ECG-based machine learning model is feasible, and outperforms a model trained on baseline QTc, age, and sex alone. Methods: We identified baseline 12-lead ECGs with QTc values < 500 ms for patients who had not received any known, conditional, or possible QTc prolonging medication per CredibleMeds at the time of ECG or within the past 90 days. We matched these with ECGs from the same patients while they were taking at least one CredibleMeds drug (“on-drug” ECGs). Using 5-fold cross-validation, we trained and tested two machine learning models using the baseline ECGs of the 92,848 resulting pairs to predict drug-induced LQT (≥500 ms) in the on-drug ECGs: a deep neural network using ECG voltage data, and a gradient-boosted tree using the baseline QTc. Age and sex were also inputs to both models. Results: On-drug LQT prevalence was 16%. The ECG model demonstrated superior performance in predicting on-drug LQT (area under the receiver operating characteristic curve (AUC) = 0.756) compared to the QTc model (0.710). At a potential operating point (Figure), the ECG model had 89% sensitivity and 95% negative predictive value. Even in the subset of patients with baseline QTc < 470/480 ms (male/female; post-drug LQT prevalence = 14%), the ECG model demonstrated good performance (AUC = 0.736). Conclusions: An ECG-based machine learning model can stratify patients by risk of developing drug-induced LQT better than a model using baseline QTc alone. This model may have clinical value to identify high-risk drug starts that would benefit from closer monitoring and others who are at low risk of drug-induced LQT.

Background: Atrial fibrillation (AF) is associated with stroke, especially when AF goes undetected. Deep neural networks (DNN) can predict incident AF from a 12-lead resting ECG. We hypothesize that use of a DNN to predict new onset AF from an ECG may identify patients at risk of sustaining a potentially preventable AF-related stroke. Methods: We trained a DNN model to predict new-onset AF using 382,604 ECGs prior to 2010. We then evaluated the model performance on a test set of ECGs from 2010 through 2014 linked to patients in an institutional stroke registry. There were 181,969 patients in the test set with at least one ECG and no prior history of AF. Of those patients 3,497 (1.9%) had a stroke following an ECG that did not show AF. Within the set of patients with stroke, 375 had the stroke within 3 years of the ECG and were diagnosed with new AF between -3 and 365 days of the stroke. We considered these potentially preventable AF-related strokes. We report the sensitivity and positive predictive value (PPV) of the model for appropriately risk stratifying these 375 patients who sustained a potentially preventable AF-related stroke. Results: We used F β scores to identify different risk prediction thresholds (operating points) for the model. Operating points chosen by F 0.5 , F 1 , and F 2 scores identified 4, 12, and 21% of the population as high risk for the development of AF within 1 year (Figure 1). Screening 1, 4, 12, and 21% of the overall population resulted in PPV of 28, 21, 15, and 12%, respectively, for identification of new onset AF in one year. Using those same thresholds yielded sensitivities of 4, 17, 45, and 62% for identifying potentially preventable AF-related strokes. The different risk prediction thresholds resulted in a low (120-162) number needed to screen to detect one potentially preventable AF-related stroke at 3 years. Conclusions: Use of a deep learning model to predict new onset AF may identify patients at high risk of sustaining a potentially preventable AF-related stroke.

Introduction: The use of convolutional neural networks (CNN) to automatically segment the heart from echocardiography images has garnered recent attention, but generalizable performance segmenting multiple cardiac structures has not been demonstrated. The objective of the present work was to develop a 2D CNN model to automatically and accurately segment the left ventricular (LV) endo- and epicardial and left atrial (LA) endocardial surfaces from an independent, external clinical dataset. Methods: A modified U-net CNN was trained using 10-fold cross-validation and augmentation within the published CAMUS echocardiography dataset to segment the LV and LA from apical 2- and 4-chamber images. For external validation, this model was applied to 3,087 echocardiograms from Geisinger for which the physician-reported LV ejection fraction (EF) was within 10% of the reported bi-plane EF, signifying confidence in quality of the underlying images. LV end-diastolic and end-systolic volumes (EDV, ESV), LA volume (LAV), and LV mass (LVM) were estimated using Simpson’s bi-plane summation. We compared performance against two published segmentation models. Results: Our model agreed well with clinically-reported values, based on small median absolute errors in percent of clinical measures (MAE; Table 1) and biases, and narrow limits of agreement (mean bias/coefficient of variation (%): LV EDV 10.3/10.6, ESV 6.3/13.1, EF 0.5/6.3, LVM 13.9/10.1, and LAV 3.1/9.5). Moreover, the observed MAE for each metric was within the previously reported limits of inter-observer variability for 2D echo. Compared to two previously published models, our model exhibited smaller MAE in all measures tested (Table 1). Conclusions: Our model exhibits accurate, generalizable performance in multi-structural echocardiography segmentation, with accuracy meeting or exceeding current leading models. Such models hold great promise for translational research and precision medicine efforts.

Increased clinical use of chest high-resolution computed tomography results in increased identification of lung adenocarcinomas and persistent subsolid opacities. However, these lesions range from very indolent to extremely aggressive tumors. Clinically relevant diagnostic tools to noninvasively risk stratify and guide individualized management of these lesions are lacking. Research efforts investigating semiquantitative measures to decrease interrater and intrarater variability are emerging, and in some cases steps have been taken to automate this process. However, many such methods currently are still suboptimal, require validation and are not yet clinically applicable. The computer-aided nodule assessment and risk yield software application represents a validated tool for the automated, quantitative, and noninvasive tool for risk stratification of adenocarcinoma lung nodules. Computer-aided nodule assessment and risk yield correlates well with consensus histology and postsurgical patient outcomes, and therefore may help to guide individualized patient management, for example, in identification of nodules amenable to radiological surveillance, or in need of adjunctive therapy.