Dataset Information

A deep learning-based electrocardiogram risk score for long term cardiovascular death and disease.

ABSTRACT: The electrocardiogram (ECG) is the most frequently performed cardiovascular diagnostic test, but it is unclear how much information resting ECGs contain about long term cardiovascular risk. Here we report that a deep convolutional neural network can accurately predict the long-term risk of cardiovascular mortality and disease based on a resting ECG alone. Using a large dataset of resting 12-lead ECGs collected at Stanford University Medical Center, we developed SEER, the Stanford Estimator of Electrocardiogram Risk. SEER predicts 5-year cardiovascular mortality with an area under the receiver operator characteristic curve (AUC) of 0.83 in a held-out test set at Stanford, and with AUCs of 0.78 and 0.83 respectively when independently evaluated at Cedars-Sinai Medical Center and Columbia University Irving Medical Center. SEER predicts 5-year atherosclerotic disease (ASCVD) with an AUC of 0.67, similar to the Pooled Cohort Equations for ASCVD Risk, while being only modestly correlated. When used in conjunction with the Pooled Cohort Equations, SEER accurately reclassified 16% of patients from low to moderate risk, uncovering a group with an actual average 9.9% 10-year ASCVD risk who would not have otherwise been indicated for statin therapy. SEER can also predict several other cardiovascular conditions such as heart failure and atrial fibrillation. Using only lead I of the ECG it predicts 5-year cardiovascular mortality with an AUC of 0.80. SEER, used alongside the Pooled Cohort Equations and other risk tools, can substantially improve cardiovascular risk stratification and aid in medical decision making.

SUBMITTER: Hughes JW

PROVIDER: S-EPMC10497604 | biostudies-literature | 2023 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A deep learning-based electrocardiogram risk score for long term cardiovascular death and disease.

Hughes J Weston JW Tooley James J Torres Soto Jessica J Ostropolets Anna A Poterucha Tim T Christensen Matthew Kai MK Yuan Neal N Ehlert Ben B Kaur Dhamanpreet D Kang Guson G Rogers Albert A Narayan Sanjiv S Elias Pierre P Ouyang David D Ashley Euan E Zou James J Perez Marco V MV

NPJ digital medicine 20230912 1

The electrocardiogram (ECG) is the most frequently performed cardiovascular diagnostic test, but it is unclear how much information resting ECGs contain about long term cardiovascular risk. Here we report that a deep convolutional neural network can accurately predict the long-term risk of cardiovascular mortality and disease based on a resting ECG alone. Using a large dataset of resting 12-lead ECGs collected at Stanford University Medical Center, we developed SEER, the Stanford Estimator of El ...[more]

PMID: 37700032

Similar Datasets

Project description:BackgroundDiabetes is a major public health concern. We aimed to evaluate the long-term risk of incident type 2 diabetes in a non-diabetic population using a deep learning model (DLM) detecting prevalent type 2 diabetes using electrocardiogram (ECG).MethodsIn this retrospective study, participants who underwent health checkups at two tertiary hospitals in Seoul, South Korea, between Jan 1, 2001 and Dec 31, 2022 were included. Type 2 diabetes was defined as glucose ≥126 mg/dL or glycated haemoglobin (HbA1c) ≥ 6.5%. For survival analysis on incident type 2 diabetes, we introduced an additional variable, diabetic ECG, which is determined by the DLM trained on ECG and corresponding prevalent diabetes. It was assumed that non-diabetic individuals with diabetic ECG had a higher risk of incident type 2 diabetes than those with non-diabetic ECG. The one-dimensional ResNet-based model was adopted for the DLM, and the Guided Grad-CAM was used to localise important regions of ECG. We divided the non-diabetic group into the diabetic ECG group (false positive) and the non-diabetic ECG (true negative) group according to the DLM decision, and performed a Cox proportional hazard model, considering the occurrence of type 2 diabetes more than six months after the visit.Findings190,581 individuals were included in the study with a median follow-up period of 11.84 years. The areas under the receiver operating characteristic curve for prevalent type 2 diabetes detection were 0.816 (0.807-0.825) and 0.762 (0.754-0.770) for the internal and external validations, respectively. The model primarily focused on the QRS duration and, occasionally, P or T waves. The diabetic ECG group exhibited an increased risk of incident type 2 diabetes compared with the non-diabetic ECG group, with hazard ratios of 2.15 (1.82-2.53) and 1.92 (1.74-2.11) for internal and external validation, respectively.InterpretationIn the non-diabetic group, those whose ECG was classified as diabetes by the DLM were at a higher risk of incident type 2 diabetes than those whose ECG was not. Additional clinical research on the relationship between the phenotype of ECG and diabetes to support the results and further investigation with tracked data and various ECG recording systems are suggested for future works.FundingNational Research Foundation of Korea.

Project description:Estimates of the risk of recurrent cardiovascular events (residual risk) among patients with acute coronary syndromes have largely been based on clinical trial populations. Our objective was to estimate the residual risk associated with common comorbidities in a large, unselected, population-based cohort of acute coronary syndrome patients. 31,056 ACS patients (49.5%-non-ST segment elevation myocardial infarction [NSTEMI], 34.0%-ST segment elevation myocardial infarction [STEMI] and 16.5%-unstable angina [UA]) hospitalised in Alberta between April 2010 and March 2016 were included. The primary composite outcome was major adverse cardiovascular events (MACE) including: death, stroke or recurrent myocardial infarction. The secondary outcome was death from any cause. Cox-proportional hazard models were used to identify the impact of ACS type and commonly observed comorbidities (heart failure, hypertension, peripheral vascular disease, renal disease, cerebrovascular disease and diabetes). At 3.0 +/- 3.7 years, rates of MACE were highest in the NSTEMI population followed by STEMI and UA (3.58, 2.41 and 1.68 per 10,000 person years respectively). Mortality was also highest in the NSTEMI population followed by STEMI and UA (2.23, 1.38 and 0.95 per 10,000 person years respectively). Increased burden of comorbidities was associated with an increased risk of MACE, most prominently seen with heart failure (adjusted HR 1.83; 95% CI 1.73-1.93), renal disease (adjusted HR 1.52; 95% CI 1.40-1.65) and diabetes (adjusted HR 1.51; 95% CI 1.44-1.59). The cumulative presence of each of examined comorbidities was associated with an incremental increase in the rate of MACE ranging from 1.7 to 9.98 per 10,000 person years. Rates of secondary prevention medications at discharge were high including: statin (89.5%), angiotensin converting enzyme inhibitor/angiotensin receptor blocker (84.1%) and beta-blockers (85.9%). Residual cardiovascular risk following an acute coronary syndrome remains high despite advances in secondary prevention. A higher burden of comorbidities is associated with increased residual risk that may benefit from aggressive or novel therapies.

Project description:The secondary prevention strategy for cardiovascular disease (CVD) does not include anti-inflammatory treatment, which may lead to long-term inflammation in some patients. The aim of this study was to assess the association between inflammatory risk based on the Glasgow Prognostic Score (GPS) and long-term mortality risk in patients with CVD. This study included 3833 patients (≥ 20 years old) with CVD in the National Health and Nutrition Survey from 1999 to 2010 in the United States. The mortality rate was determined by correlation with the National Death Index on December 31, 2019. The GPS consists of the serum C-reactive protein and the serum albumin. The primary outcome was all-cause death, which included cardiac death and non-cardiac death. Cox proportional hazards adjusted for demographic factors and traditional cardiovascular risk factors were used to test the impact of the GPS on mortality. The sensitivity analysis was conducted on subsets within the cohort of patients with CVD, including congestive heart failure, coronary artery disease, angina, heart attack, and stroke. Among 3833 CVD patients with a median follow-up of 9.6 years, 2431 (63.4%) all-cause deaths, 822 (21.4%) cardiac deaths, and 1609 (41.9%) non-cardiac deaths were recorded. After full model adjustment, compared with those of the GPS (0) group, the hazard ratios (HRs) of all-cause death for GPS (1) and GPS (2) were 1.66 (95% confidence interval (CI), 1.48-1.86) and 2.75 (95% CI 2.01-3.75), respectively (P for trend < 0.001). Compared with those of the GPS (0) group, the HRs of cardiac death for the GPS (1) and GPS (2) groups were 1.69 (95% CI 1.39-2.05) and 2.18 (95% CI 1.22-3.91), respectively (P for trend < 0.001). Compared with those of the GPS (0) group, the HRs of non-cardiac death for the GPS (1) and GPS (2) groups were 1.65 (95% CI 1.44-1.89) and 3.05 (95% CI 2.11-4.40), respectively (P for trend < 0.001). The results of the sensitivity analysis were similar to those of the overall cohort. In our analysis of the United States National Database, we discovered that the GPS, a measure of inflammatory risk, was significantly associated with an increased risk of mortality among patients with CVD. Specifically, we observed that patients with a higher GPS had significantly higher risks of all-cause, cardiac, and non-cardiac mortality compared to those with a lower score. These findings suggest that the GPS, comprising easily obtainable biomarkers, could serve as a valuable tool for risk stratification in CVD patients and may contribute to the improvement of patient outcomes.

Project description:The global mortality rate is known to be the highest due to cardiovascular disease (CVD). Thus, preventive, and early CVD risk identification in a non-invasive manner is vital as healthcare cost is increasing day by day. Conventional methods for risk prediction of CVD lack robustness due to the non-linear relationship between risk factors and cardiovascular events in multi-ethnic cohorts. Few recently proposed machine learning-based risk stratification reviews without deep learning (DL) integration. The proposed study focuses on CVD risk stratification by the use of techniques mainly solo deep learning (SDL) and hybrid deep learning (HDL). Using a PRISMA model, 286 DL-based CVD studies were selected and analyzed. The databases included were Science Direct, IEEE Xplore, PubMed, and Google Scholar. This review is focused on different SDL and HDL architectures, their characteristics, applications, scientific and clinical validation, along with plaque tissue characterization for CVD/stroke risk stratification. Since signal processing methods are also crucial, the study further briefly presented Electrocardiogram (ECG)-based solutions. Finally, the study presented the risk due to bias in AI systems. The risk of bias tools used were (I) ranking method (RBS), (II) region-based map (RBM), (III) radial bias area (RBA), (IV) prediction model risk of bias assessment tool (PROBAST), and (V) risk of bias in non-randomized studies-of interventions (ROBINS-I). The surrogate carotid ultrasound image was mostly used in the UNet-based DL framework for arterial wall segmentation. Ground truth (GT) selection is vital for reducing the risk of bias (RoB) for CVD risk stratification. It was observed that the convolutional neural network (CNN) algorithms were widely used since the feature extraction process was automated. The ensemble-based DL techniques for risk stratification in CVD are likely to supersede the SDL and HDL paradigms. Due to the reliability, high accuracy, and faster execution on dedicated hardware, these DL methods for CVD risk assessment are powerful and promising. The risk of bias in DL methods can be best reduced by considering multicentre data collection and clinical evaluation.

Project description:Little is known about electrocardiogram (ECG) markers of Parkinson's disease (PD) during the prodromal stage. The aim of the study was to build a generalizable ECG-based fully automatic artificial intelligence (AI) model to predict PD risk during the prodromal stage, up to 5 years before disease diagnosis. This case-control study included samples from Loyola University Chicago (LUC) and University of Tennessee-Methodist Le Bonheur Healthcare (MLH). Cases and controls were matched according to specific characteristics (date, age, sex and race). Clinical data were available from May, 2014 onward at LUC and from January, 2015 onward at MLH, while the ECG data were available as early as 1990 in both institutes. PD was denoted by at least two primary diagnostic codes (ICD9 332.0; ICD10 G20) at least 30 days apart. PD incidence date was defined as the earliest of first PD diagnostic code or PD-related medication prescription. ECGs obtained at least 6 months before PD incidence date were modeled to predict a subsequent diagnosis of PD within three time windows: 6 months-1 year, 6 months-3 years, and 6 months-5 years. We applied a novel deep neural network using standard 10-s 12-lead ECGs to predict PD risk at the prodromal phase. This model was compared to multiple feature engineering-based models. Subgroup analyses for sex, race and age were also performed. Our primary prediction model was a one-dimensional convolutional neural network (1D-CNN) that was built using 131 cases and 1058 controls from MLH, and externally validated on 29 cases and 165 controls from LUC. The model was trained on 90% of the MLH data, internally validated on the remaining 10% and externally validated on LUC data. The best performing model resulted in an external validation AUC of 0.67 when predicting future PD at any time between 6 months and 5 years after the ECG. Accuracy increased when restricted to ECGs obtained within 6 months to 3 years before PD diagnosis (AUC 0.69) and was highest when predicting future PD within 6 months to 1 year (AUC 0.74). The 1D-CNN model based on raw ECG data outperformed multiple models built using more standard ECG feature engineering approaches. These results demonstrate that a predictive model developed in one cohort using only raw 10-s ECGs can effectively classify individuals with prodromal PD in an independent cohort, particularly closer to disease diagnosis. Standard ECGs may help identify individuals with prodromal PD for cost-effective population-level early detection and inclusion in disease-modifying therapeutic trials.

Dataset Information

A deep learning-based electrocardiogram risk score for long term cardiovascular death and disease.

Publications

A deep learning-based electrocardiogram risk score for long term cardiovascular death and disease.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets