Deep Learning for Detection of Elevated Pulmonary Artery Wedge Pressure Using Standard Chest X-Ray

Heart failure monitoring with a single‑lead electrocardiogram at home

BACKGROUND

Repeated hospitalization due to heart failure (HF) is a significant predictor of mortality. However, there are limited early detection systems for HF progression that can be utilized by patients at home without a cardiac implantable electrical device (CIED). This study aimed to develop an artificial intelligence (AI)-based system utilizing convolutional neural network (CNN) algorithms for the early detection of HF progression using single‑lead electrocardiograms (ECGs), including those obtained from wearable devices such as the Apple Watch®.

METHODS

ECG data from 9518 participants, encompassing both HF patients and healthy controls, were used to train the CNN model to diagnose HF status. New York Heart Association (NYHA) classifications were determined by multiple cardiologists at the time of ECG recording. The CNN model was designed to calculate a novel HF-index, derived from the NYHA grades predicted by the AI, as a quantitative measure of real-time HF severity.

RESULTS

The CNN model achieved a 91.6 % accuracy in classifying HF severity into NYHA I-II (asymptomatic to mild HF) and NYHA III-IV grades (moderate to severe HF) categories. Furthermore, the model generated a novel HF-index as a real-time indicator of HF severity, which showed a positive correlation (R = 0.74) with plasma B-type natriuretic peptide (BNP) levels, thereby validating its effectiveness in reflecting HF severity.

CONCLUSIONS

We successfully constructed a novel at-home HF monitoring system utilizing a portable single‑lead ECG device. This system has been validated for its effectiveness in at-home HF monitoring, representing a significant advancement in remote healthcare for HF management.

Applications and potential of machine, learning augmented chest X-ray interpretation in cardiology

The chest X-ray (CXR) has a wide range of clinical indications in the field of cardiology, from the assessment of acute pathology to disease surveillance and screening. Despite many technological advancements, CXR interpretation error rates have remained constant for decades. The application of machine learning has the potential to substantially improve clinical workflow efficiency, pathology detection accuracy, error rates and clinical decision making in cardiology. To date, machine learning has been developed to improve image processing, facilitate pathology detection, optimize the clinical workflow, and facilitate risk stratification. This review explores the current and potential future applications of machine learning for chest radiography to facilitate clinical decision making in cardiology. It maps the current state of the science and considers additional potential use cases from the perspective of clinicians and technologists actively engaged in the development and deployment of deep learning driven clinical decision support systems.

Deep learning prediction of survival in patients with heart failure using chest radiographs

Heart failure (HF) is associated with high rates of morbidity and mortality. The value of deep learning survival prediction models using chest radiographs in patients with heart failure is currently unclear. The aim of our study is to develop and validate a deep learning survival prediction model using chest X-ray (DLSPCXR) in patients with HF. The study retrospectively enrolled a cohort of 353 patients with HF who underwent chest X-ray (CXR) at our institution between March 2012 and March 2017. The dataset was randomly divided into training (n = 247) and validation (n = 106) datasets. Univariate and multivariate Cox analysis were conducted on the training dataset to develop clinical and imaging survival prediction models. The DLSPCXR was trained and the selected clinical parameters were incorporated into DLSPCXR to establish a new model called DLSPinteg. Discrimination performance was evaluated using the time-dependent area under the receiver operating characteristic curves (TD AUC) at 1, 3, and 5-years survival. Delong's test was employed for the comparison of differences between two AUCs of different models. The risk-discrimination capability of the optimal model was evaluated by the Kaplan-Meier curve. In multivariable Cox analysis, older age, higher N-terminal pro-B-type natriuretic peptide (NT-ProBNP), systolic pulmonary artery pressure (sPAP) > 50 mmHg, New York Heart Association (NYHA) functional class III-IV and cardiothoracic ratio (CTR) ≥ 0.62 in CXR were independent predictors of poor prognosis in patients with HF. Based on the receiver operating characteristic (ROC) curve analysis, DLSPCXR had better performance at predicting 5-year survival than the imaging Cox model in the validation cohort (AUC: 0.757 vs. 0.561, P = 0.01). DLSPinteg as the optimal model outperforms the clinical Cox model (AUC: 0.826 vs. 0.633, P = 0.03), imaging Cox model (AUC: 0.826 vs. 0.555, P < 0.001), and DLSPCXR (AUC: 0.826 vs. 0.767, P = 0.06). Deep learning models using chest radiographs can predict survival in patients with heart failure with acceptable accuracy.

Early Detection of Heart Failure with Autonomous AI-Based Model Using Chest Radiographs: A Multicenter Study

The opportunistic use of radiological examinations for disease detection can potentially enable timely management. We assessed if an index created by an AI software to quantify chest radiography (CXR) findings associated with heart failure (HF) could distinguish between patients who would develop HF or not within a year of the examination. Our multicenter retrospective study included patients who underwent CXR without an HF diagnosis. We included 1117 patients (age 67.6 ± 13 years; m:f 487:630) that underwent CXR. A total of 413 patients had the CXR image taken within one year of their HF diagnosis. The rest (n = 704) were patients without an HF diagnosis after the examination date. All CXR images were processed with the model (qXR-HF, Qure.AI) to obtain information on cardiac silhouette, pleural effusion, and the index. We calculated the accuracy, sensitivity, specificity, and area under the curve (AUC) of the index to distinguish patients who developed HF within a year of the CXR and those who did not. We report an AUC of 0.798 (95%CI 0.77-0.82), accuracy of 0.73, sensitivity of 0.81, and specificity of 0.68 for the overall AI performance. AI AUCs by lead time to diagnosis (<3 months: 0.85; 4-6 months: 0.82; 7-9 months: 0.75; 10-12 months: 0.71), accuracy (0.68-0.72), and specificity (0.68) remained stable. Our results support the ongoing investigation efforts for opportunistic screening in radiology.

Artificial intelligence-assisted interpretation of systolic function by echocardiogram

OBJECTIVE

Precise and reliable echocardiographic assessment of left ventricular ejection fraction (LVEF) is needed for clinical decision-making. Recently, artificial intelligence (AI) models have been developed to estimate LVEF accurately. The aim of this study was to evaluate whether an AI model could estimate an expert read of LVEF and reduce the interinstitutional variability of level 1 readers with the AI-LVEF displayed on the echocardiographic screen.

METHODS

This prospective, multicentre echocardiographic study was conducted by five cardiologists of level 1 echocardiographic skill (minimum level of competency to interpret images) from different hospitals. Protocol 1: Visual LVEFs for the 48 cases were measured without input from the AI-LVEF. Protocol 2: the 48 cases were again shown to all readers with inclusion of AI-LVEF data. To assess the concordance and accuracy with or without AI-LVEF, each visual LVEF measurement was compared with an average of the estimates by five expert readers as a reference.

RESULTS

A good correlation was found between AI-LVEF and reference LVEF (r=0.90, p<0.001) from the expert readers. For the classification LVEF, the area under the curve was 0.95 on heart failure with preserved EF and 0.96 on heart failure reduced EF. For the precision, the SD was reduced from 6.1±2.3 to 2.5±0.9 (p<0.001) with AI-LVEF. For the accuracy, the root-mean squared error was improved from 7.5±3.1 to 5.6±3.2 (p=0.004) with AI-LVEF.

CONCLUSIONS

AI can assist with the interpretation of systolic function on an echocardiogram for level 1 readers from different institutions.

Deep learning approach for analyzing chest x-rays to predict cardiac events in heart failure

Background

A deep learning (DL) model based on a chest x-ray was reported to predict elevated pulmonary artery wedge pressure (PAWP) as heart failure (HF).

Objectives

The aim of this study was to (1) investigate the role of probability of elevated PAWP for the prediction of clinical outcomes in association with other parameters, and (2) to evaluate whether probability of elevated PAWP based on DL added prognostic information to other conventional clinical prognostic factors in HF.

Methods

We evaluated 192 patients hospitalized with HF. We used a previously developed AI model to predict HF and calculated probability of elevated PAWP. Readmission following HF and cardiac mortality were the primary endpoints.

Results

Probability of elevated PAWP was associated with diastolic function by echocardiography. During a median follow-up period of 58 months, 57 individuals either died or were readmitted. Probability of elevated PAWP appeared to be associated with worse clinical outcomes. After adjustment for readmission score and laboratory data in a Cox proportional-hazards model, probability of elevated PAWP at pre-discharge was associated with event free survival, independent of elevated left atrial pressure (LAP) based on echocardiographic guidelines (p < 0.001). In sequential Cox models, a model based on clinical data was improved by elevated LAP (p = 0.005), and increased further by probability of elevated PAWP (p < 0.001). In contrast, the addition of pulmonary congestion interpreted by a doctor did not statistically improve the ability of a model containing clinical variables (compared p = 0.086).

Conclusions

This study showed the potential of using a DL model on a chest x-ray to predict PAWP and its ability to add prognostic information to other conventional clinical prognostic factors in HF. The results may help to enhance the accuracy of prediction models used to evaluate the risk of clinical outcomes in HF, potentially resulting in more informed clinical decision-making and better care for patients.

Classification of chest X-ray images by incorporation of medical domain knowledge into operation branch networks

BACKGROUND

This study was conducted to alleviate a common difficulty in chest X-ray image diagnosis: The attention region in a convolutional neural network (CNN) does not often match the doctor's point of focus. The method presented herein, which guides the area of attention in CNN to a medically plausible region, can thereby improve diagnostic capabilities.

METHODS

The model is based on an attention branch network, which has excellent interpretability of the classification model. This model has an additional new operation branch that guides the attention region to the lung field and heart in chest X-ray images. We also used three chest X-ray image datasets (Teikyo, Tokushima, and ChestX-ray14) to evaluate the CNN attention area of interest in these fields. Additionally, after devising a quantitative method of evaluating improvement of a CNN's region of interest, we applied it to evaluation of the proposed model.

RESULTS

Operation branch networks maintain or improve the area under the curve to a greater degree than conventional CNNs do. Furthermore, the network better emphasizes reasonable anatomical parts in chest X-ray images.

CONCLUSIONS

The proposed network better emphasizes the reasonable anatomical parts in chest X-ray images. This method can enhance capabilities for image interpretation based on judgment.

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

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 [Formula: see text] 0.01 and 0.[Formula: see text] 0.01 on the internal and external datasets, respectively. The AUROC on predictions with the highest uncertainty are 0.50 [Formula: see text] 0.02 (internal) and 0.[Formula: see text] 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.[Formula: see text] 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.[Formula: see text] 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.

Utilizing Artificial Intelligence to Enhance Health Equity Among Patients with Heart Failure

Patients with heart failure (HF) are heterogeneous with various intrapersonal and interpersonal characteristics contributing to clinical outcomes. Bias, structural racism, and social determinants of health have been implicated in unequal treatment of patients with HF. Through several methodologies, artificial intelligence (AI) can provide models in HF prediction, prognostication, and provision of care, which may help prevent unequal outcomes. This review highlights AI as a strategy to address racial inequalities in HF; discusses key AI definitions within a health equity context; describes the current uses of AI in HF, strengths and harms in using AI; and offers recommendations for future directions.

Quantitative estimation of pulmonary artery wedge pressure from chest radiographs by a regression convolutional neural network

Recent studies reported that a convolutional neural network (CNN; a deep learning model) can detect elevated pulmonary artery wedge pressure (PAWP) from chest radiographs, the diagnostic images most commonly used for assessing pulmonary congestion in heart failure. However, no method has been published for quantitatively estimating PAWP from such radiographs. We hypothesized that a regression CNN, an alternative type of deep learning, could be a useful tool for quantitatively estimating PAWP in cardiovascular diseases. We retrospectively enrolled 936 patients with cardiovascular diseases who had undergone right heart catheterization (RHC) and chest radiography and estimated PAWP by constructing a regression CNN based on the VGG16 model. We randomly categorized 80% of the data as training data (training group, n = 748) and 20% as test data (test group, n = 188). Moreover, we tuned the learning rate—one of the model parameters—by 5-hold cross-validation of the training group. Correlations between PAWP measured by RHC [ground truth (GT) PAWP] and PAWP derived from the regression CNN (estimated PAWP) were tested. To visualize how the regression CNN assessed the images, we created a regression activation map (RAM), a visualization technique for regression CNN. Estimated PAWP correlated significantly with GT PAWP in both the training (r = 0.76, P < 0.001) and test group (r = 0.62, P < 0.001). Bland–Altman plots found a mean (SEM) difference between GT and estimated PAWP of − 0.23 (0.16) mm Hg in the training and − 0.05 (0.41) mm Hg in the test group. The RAM showed that our regression CNN model estimated high PAWP by focusing on the cardiomegaly and pulmonary congestion. In the test group, the area under the curve (AUC) for detecting elevated PAWP (≥ 18 mm Hg) produced by the regression CNN model was similar to the AUC of an experienced cardiologist (0.86 vs 0.83, respectively; P = 0.24). This proof-of-concept study shows that regression CNN can quantitatively estimate PAWP from standard chest radiographs in cardiovascular diseases.

Deep learning for chest X-ray analysis: A survey

Recent advances in deep learning have led to a promising performance in many medical image analysis tasks. As the most commonly performed radiological exam, chest radiographs are a particularly important modality for which a variety of applications have been researched. The release of multiple, large, publicly available chest X-ray datasets in recent years has encouraged research interest and boosted the number of publications. In this paper, we review all studies using deep learning on chest radiographs published before March 2021, categorizing works by task: image-level prediction (classification and regression), segmentation, localization, image generation and domain adaptation. Detailed descriptions of all publicly available datasets are included and commercial systems in the field are described. A comprehensive discussion of the current state of the art is provided, including caveats on the use of public datasets, the requirements of clinically useful systems and gaps in the current literature.