ECG-guided non-invasive estimation of pulmonary congestion in patients with heart failure

Abstract

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. Accurate non-invasive estimates of the mPCWP in patients with heart failure would help identify individuals at the greatest risk of a HF exacerbation. We developed a deep learning model, HFNet, that uses the 12-lead electrocardiogram (ECG) together with age and sex to identify when the mPCWP > 18 mmHg in patients who have a prior diagnosis of HF. The model was developed using retrospective data from the Massachusetts General Hospital and evaluated on both an internal test set and an independent external validation set, from another institution. We developed an uncertainty score that identifies when model performance is likely to be poor, thereby helping clinicians gauge when to trust a given model prediction. HFNet AUROC for the task of estimating mPCWP > 18 mmHg was 0.8 $$2\pm$$ 2 ± 0.01 and 0.$$81\pm$$ 81 ± 0.01 on the internal and external datasets, respectively. The AUROC on predictions with the highest uncertainty are 0.50 $$\pm$$ ± 0.02 (internal) and 0.$$56\pm$$ 56 ± 0.04 (external), while the AUROC on predictions with the lowest uncertainty were 0.86 ± 0.01 (internal) and 0.82 ± 0.01 (external). Using estimates of the prevalence of mPCWP > 18 mmHg in patients with reduced ventricular function, and a decision threshold corresponding to an 80% sensitivity, the calculated positive predictive value (PPV) is 0.$$89\pm$$ 89 ± 0.01when the corresponding chest x-ray (CXR) is consistent with interstitial edema HF. When the CXR is not consistent with interstitial edema, the estimated PPV is 0.$$78\pm$$ 78 ± 0.02, again at an 80% sensitivity threshold. HFNet can accurately predict elevated mPCWP in patients with HF using the 12-lead ECG and age/sex. The method also identifies cohorts in which the model is more/less likely to produce accurate outputs.

Artificial Intelligence for Hemodynamic Monitoring with a Wearable Electrocardiogram Monitor

“…This can help practitioners determine when to trust a model output. Hence, as a secondary analysis, we calculate the Shannon entropy using the CHAIS output to determine when the model is likely to yield a misleading result, in a manner similar to the method used in Raghu et al 26 We hypothesized that predictions associated with high entropy are more untrustworthy relative to predictions with low entropy. We define trustworthy predictions as those that have low entropies, where the entropy threshold is derived from the development dataset, as outlined in the Methods.…”

“…To determine when the model is likely to yield a misleading result, we use the Shannon Entropy, in a manner similar to the method used in Raghu et al 26 Let f y (x) denote the model probability for one of the inference tasks, y, where x is a given input ECG. Then the entropy for a given prediction is: This expression captures, in essence, how close the output model probability is to 0.5, with higher H Y reflecting a value closer to 0.5, and lower model trustworthiness.…”

“…Previously, we proposed a deep learning model that identifies when the mPCWP is elevated using the 12-lead ECG 15,24 . However, the 12-lead ECG is typically obtained during an office visit or in the inpatient setting, and requires the placement of 10 electrodes on the body.…”

Machine learning–based analysis of non-invasive measurements for predicting intracardiac pressures

“…Furthermore, there is a potential to utilize raw pre-processed ECG or PPG data to enhance the ML pipeline by sophisticated feature generation techniques to uncover new data patterns. In a study by Raghu et al , 19 a deep learning model utilizing ECG features identified patients with a PCWP exceeding 18 mmHg, achieving an AUC of 0.82. These encouraging findings imply the potential benefits of enhancing the non-invasive feature set by incorporating additional ECG features.…”

Development and validation of machine learning algorithms based on electrocardiograms for cardiovascular diagnoses at the population level

“…While the number of machine learning (ML)based models using ECG data to predict CV conditions beyond those traditionally associated with ECG patterns is currently limited, it is steadily increasing. These models focus on conditions such as mitral valve prolapse (MVP) 1 , cardiac arrest (CA) 11,12 , heart failure (HF) 13,14 , pulmonary embolism (PE) 15,16 , aortic stenosis (AS) [17][18][19] , mitral valve stenosis (MS) 20 , pulmonary hypertension (PHTN) 21,22 and hypertrophic cardiomyopathy (HCM) 18,23,24 . Furthermore, while existing studies have mainly concentrated on individual labels, there hasn't been any prior research developing a predictive system for the simultaneous detection of these specific conditions.…”