A Deep Learning Model for Inferring Elevated Pulmonary Capillary Wedge Pressures From the 12-Lead Electrocardiogram

Schlesinger, Daphne E.; Diamant, Nathaniel; Raghu, Aniruddh; Reinertsen, Erik; Young, Katherine; Batra, Puneet; Pomerantsev, Eugene; Stultz, Collin M.

doi:10.1016/j.jacadv.2022.100003

Cited by 12 publications

(25 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning was also investigated as a potential predictor of hemodynamic parameters. A recent study proposed a DL model for estimating on a standard electrocardiogram an elevated mean pulmonary capillary wedge pressure, a parameter obtained invasively via pulmonary artery catheterization [19]. These results come from ECG features not available to the clinician's eye, making of ML a very promising disease-screening tool.…”

Section: In the Medical Fieldmentioning

confidence: 99%

Expending the power of artificial intelligence in preclinical research: an overview

Diaconu

Cojocaru

Gardikiotis

et al. 2022

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

Artificial intelligence (AI) is described as the joint set of data entry, able to receive inputs, interpret and learn from such feedbacks, and display related and flexible independent actions that help the entity reach a specific aim over a period of time. By extending its health-care applications continuously, the ultimate AI target is to use machine simulation of human intelligence processes such as learning, reasoning, and self-correction, to mimic human behaviour. AI is extensively used in diverse sectors of medicine, including clinical trials, drug discovery and development, understanding of target-disease associations, disease prediction, imaging, and precision medicine. In this review, we firstly describe the limitations and challenges of the AI tools and techniques utilized in medicine, followed by current uses and applications of AI in the translational field, highlighting the cardio-renal preclinical models with potential to contribute to future clinical research.

show abstract

Section: In the Medical Fieldmentioning

confidence: 99%

Expending the power of artificial intelligence in preclinical research: an overview

Diaconu

Cojocaru

Gardikiotis

et al. 2022

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…Considering the learned time warp strength in Figure 3(b), we observe that signals labelled negative for AFib are warped less strongly than those with AFib, again sensible since time warping may affect the label of a signal and introduce AFib in a signal where it was not originally present. are typically able to do (Schlesinger et al, 2021). Analyzing the augmentations could provide hypotheses about what features in the data encode the class label.…”

Section: Analyzing Learned Policiesmentioning

confidence: 99%

“…In certain situations, it is challenging to construct such datasets. For example, consider inferring abnormal central hemodynamics (e.g., cardiac output) from the ECG, which is important when monitoring patients with heart failure or pulmonary hypertension (Schlesinger et al, 2021). Accurate hemodynamics labels are only obtainable through specialized invasive studies (Bajorat et al, 2006;Hiemstra et al, 2019) and hence it Figure 1: The effect of data augmentation on ECG prediction tasks is task-dependent.…”

Section: Introductionmentioning

confidence: 99%

Data Augmentation for Electrocardiograms

Raghu¹,

Shanmugam²,

Pomerantsev³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Neural network models have demonstrated impressive performance in predicting pathologies and outcomes from the 12-lead electrocardiogram (ECG). However, these models often need to be trained with large, labelled datasets, which are not available for many predictive tasks of interest. In this work, we perform an empirical study examining whether training time data augmentation methods can be used to improve performance on such datascarce ECG prediction problems. We investigate how data augmentation strategies impact model performance when detecting cardiac abnormalities from the ECG. Motivated by our finding that the effectiveness of existing augmentation strategies is highly task-dependent, we introduce a new method, TaskAug, which defines a flexible augmentation policy that is optimized on a per-task basis. We outline an efficient learning algorithm to do so that leverages recent work in nested optimization and implicit differentiation. In experiments, considering three datasets and eight predictive tasks, we find that TaskAug is competitive with or improves on prior work, and the learned policies shed light on what transformations are most effective for different tasks. We distill key insights from our experimental evaluation, generating a set of best practices for applying data augmentation to ECG prediction problems.Data and Code Availability We use three datasets: two are from Massachusetts General Hospital (MGH) and are not publicly available; the third is PTB-XL (Wagner et al., 2020), which is publicly available on the PhysioNet repository (Goldberger et al., 2000). Code implementing our method is available here: https://github.com/aniruddhraghu/ ecg_aug.

show abstract

“…As ECG parameters have been shown to be correlated with abnormal hemodynamic profiles in some patient populations 16 , the 12-lead ECG serves as a potential data source that can be leveraged to estimate central pressures. Recently, we developed a deep learning model to estimate when the mPCWP is greater than 15 mmHg from ECG data using a heterogeneous cohort of patients who were referred for right heart catherization 17 . While the discriminatory ability of the model was good in a subset of patients who were referred for an evaluation of heart failure, a mPCWP cutoff of 15 mmHg at rest has not been shown to risk stratify patients with chronic heart failure 9 .…”

mentioning

confidence: 99%

“…While the discriminatory ability of the model was good in a subset of patients who were referred for an evaluation of heart failure, a mPCWP cutoff of 15 mmHg at rest has not been shown to risk stratify patients with chronic heart failure 9 . Indeed, our previous model was intended to be a screening tool to rule out an elevated mPCWP in all patients over 60 years old 17 .…”

mentioning

confidence: 99%

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

Raghu

Schlesinger

Pomerantsev

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

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.

show abstract

A Deep Learning Model for Inferring Elevated Pulmonary Capillary Wedge Pressures From the 12-Lead Electrocardiogram

Cited by 12 publications

References 26 publications

Expending the power of artificial intelligence in preclinical research: an overview

Expending the power of artificial intelligence in preclinical research: an overview

Data Augmentation for Electrocardiograms

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

Contact Info

Product

Resources

About