Forecasting left ventricular systolic dysfunction in heart failure with artificial intelligence

BackgroundObjective 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. MethodsWe developed a deep learning model to Predict changes in left ventricULar Systolic function from Electrocardiograms (ECG) of patients who have Heart Failure (PULSE-HF). The model integrates 12-lead ECG waveforms with a patients 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. FindingsPULSE-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-HFs 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-HFs 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. InterpretationPULSE-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. FundingThis work was supported, in part, by a grant from Quanta Computers. Research in contextO_ST_ABSEvidence before this studyC_ST_ABSHeart 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 studyWe developed a deep learning model, called PULSE-HF, to Predict changes in left ventricULar Systolic function from ECGs of patients who have Heart Failure. 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%) within the year after the ECG was obtained. We also developed a single lead version of PULSE-HF, based on lead I, that maintains strong performance compared to the model that uses all 12 leads. Implications of all the available evidenceThe ECG contains information that can be leveraged to forecast changes in LVEF. As ECGs are typically obtained for patients with HF during yearly follow-up visits, we envision that the method could be used annually to identify patients who are at the highest risk of future LVEF decline. Screening could be routinely integrated into existing clinical workflow with minimal changes to clinical practice. Since similar performance was achieved with a single lead model (lead l), it may be possible to complete screening using wearable or pocket ECG monitoring devices. Prospective studies are needed to better define the utility of PULSE-HF in guiding HF management decisions, optimizing prediction windows, and integrating the model into clinical practice.