Dataset Information

Utility of an Artificial Intelligence Enabled Electrocardiogram for Risk Assessment in Liver Transplant Candidates.

ABSTRACT:

Background

Post-operative cardiac complications occur infrequently but contribute to mortality after liver transplantation (LT). Artificial intelligence-based algorithms based on electrocardiogram (AI-ECG) are attractive for use during pre-operative evaluation to screen for risk of post-operative cardiac complications, but their use for this purpose is unknown.

Aims

The aim of this study was to evaluate the performance of an AI-ECG algorithm in predicting cardiac factors such as asymptomatic left ventricular systolic dysfunction or potential for developing post-operative atrial fibrillation (AF) in cohorts of patients with end-stage liver disease either undergoing evaluation for transplant or receiving a liver transplant.

Methods

A retrospective study was performed in two consecutive adult cohorts of patients who were either evaluated for LT or underwent LT at a single center between 2017 and 2019. ECG were analyzed using an AI-ECG trained to recognize patterns from a standard 12-lead ECG which could identify the presence of left ventricular systolic dysfunction (LVEF < 50%) or subsequent atrial fibrillation.

Results

The performance of AI-ECG in patients undergoing LT evaluation is similar to that in a general population but was lower in the presence of prolonged QTc. AI-ECG analysis on ECG in sinus rhythm had an AUROC of 0.69 for prediction of de novo post-transplant AF. Although post-transplant cardiac dysfunction occurred in only 2.3% of patients in the study cohorts, AI-ECG had an AUROC of 0.69 for prediction of subsequent low left ventricular ejection fraction.

Conclusions

A positive screen for low EF or AF on AI-ECG can alert to risk of post-operative cardiac dysfunction or predict new onset atrial fibrillation after LT. The use of an AI-ECG can be a useful adjunct in persons undergoing transplant evaluation that can be readily implemented in clinical practice.

SUBMITTER: Zaver HB

PROVIDER: S-EPMC10077316 | biostudies-literature | 2023 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Utility of an Artificial Intelligence Enabled Electrocardiogram for Risk Assessment in Liver Transplant Candidates.

Zaver Himesh B HB Mzaik Obaie O Thomas Jonathan J Roopkumar Joanna J Adedinsewo Demilade D Keaveny Andrew P AP Patel Tushar T

Digestive diseases and sciences 20230406 6

<h4>Background</h4>Post-operative cardiac complications occur infrequently but contribute to mortality after liver transplantation (LT). Artificial intelligence-based algorithms based on electrocardiogram (AI-ECG) are attractive for use during pre-operative evaluation to screen for risk of post-operative cardiac complications, but their use for this purpose is unknown.<h4>Aims</h4>The aim of this study was to evaluate the performance of an AI-ECG algorithm in predicting cardiac factors such as a ...[more]

PMID: 37022601

Similar Datasets

Project description:BackgroundResearchers routinely evaluate novel biomarkers for incorporation into clinical risk models, weighing tradeoffs between cost, availability, and ease of deployment. For risk assessment in population health initiatives, ideal inputs would be those already available for most patients. We hypothesized that common hematologic markers (eg, hematocrit), available in an outpatient complete blood count without differential, would be useful to develop risk models for cardiovascular events.MethodsWe developed Cox proportional hazards models for predicting heart attack, ischemic stroke, heart failure hospitalization, revascularization, and all-cause mortality. For predictors, we used 10 hematologic indices (eg, hematocrit) from routine laboratory measurements, collected March 2016 to May 2017 along with demographic data and diagnostic codes. As outcomes, we used neural network-based automated event adjudication of 1 028 294 discharge summaries. We trained models on 23 238 patients from one hospital in Boston and evaluated them on 29 671 patients from a second one. We assessed calibration using Brier score and discrimination using Harrell's concordance index. In addition, to determine the utility of high-dimensional interactions, we compared our proportional hazards models to random survival forest models.ResultsEvent rates in our cohort ranged from 0.0067 to 0.075 per person-year. Models using only hematology indices had concordance index ranging from 0.60 to 0.80 on an external validation set and showed the best discrimination when predicting heart failure (0.80 [95% CI, 0.79-0.82]) and all-cause mortality (0.78 [0.77-0.80]). Compared with models trained only on demographic data and diagnostic codes, models that also used hematology indices had better discrimination and calibration. The concordance index of the resulting models ranged from 0.75 to 0.85 and the improvement in concordance index ranged up to 0.072. Random survival forests had minimal improvement over proportional hazards models.ConclusionsWe conclude that low-cost, ubiquitous inputs, if biologically informative, can provide population-level readouts of risk.

Project description:BackgroundArtificial intelligence-enabled electrocardiogram has become a substitute tool for echocardiography in left ventricular ejection fraction estimation. However, the direct use of artificial intelligence-enabled electrocardiogram may be not trustable due to the uncertainty of the prediction.ObjectiveThe study aimed to establish an artificial intelligence-enabled electrocardiogram with a degree of confidence to identify left ventricular dysfunction.MethodsThe study collected 76,081 and 11,771 electrocardiograms from an academic medical center and a community hospital to establish and validate the deep learning model, respectively. The proposed deep learning model provided the point estimation of the actual ejection fraction and its standard deviation derived from the maximum probability density function of a normal distribution. The primary analysis focused on the accuracy of identifying patients with left ventricular dysfunction (ejection fraction ≤ 40%). Since the standard deviation was an uncertainty indicator in a normal distribution, we used it as a degree of confidence in the artificial intelligence-enabled electrocardiogram. We further explored the clinical application of estimated standard deviation and followed up on the new-onset left ventricular dysfunction in patients with initially normal ejection fraction.ResultsThe area under receiver operating characteristic curves (AUC) of detecting left ventricular dysfunction were 0.9549 and 0.9365 in internal and external validation sets. After excluding the cases with a lower degree of confidence, the artificial intelligence-enabled electrocardiogram performed better in the remaining cases in internal (AUC = 0.9759) and external (AUC = 0.9653) validation sets. For the application of future left ventricular dysfunction risk stratification in patients with initially normal ejection fraction, a 4.57-fold risk of future left ventricular dysfunction when the artificial intelligence-enabled electrocardiogram is positive in the internal validation set. The hazard ratio was increased to 8.67 after excluding the cases with a lower degree of confidence. This trend was also validated in the external validation set.ConclusionThe deep learning model with a degree of confidence can provide advanced improvements in identifying left ventricular dysfunction and serve as a decision support and management-guided screening tool for prognosis.

Dataset Information

Utility of an Artificial Intelligence Enabled Electrocardiogram for Risk Assessment in Liver Transplant Candidates.

Background

Aims

Methods

Results

Conclusions

Publications

Utility of an Artificial Intelligence Enabled Electrocardiogram for Risk Assessment in Liver Transplant Candidates.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets