Probability of elevated pulmonary artery wedge pressure at pre-discharge, assessed by a deep learning model on chest x-rays, predicted cardiac death or heart failure readmission (HR 1.46).
Cohort (n=192)
No
Does a deep learning model predicting elevated PAWP from chest X-rays improve the prediction of cardiac death or heart failure readmission in hospitalized heart failure patients?
A deep learning model analyzing chest X-rays to predict elevated PAWP provides independent and incremental prognostic value for predicting cardiac death and readmission in hospitalized heart failure patients.
Hazard Ratio: 1.46 (95% CI 1.23–1.72)
p-value: p=<0.001
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.
Kusunose et al. (Fri,) conducted a cohort in Heart failure (n=192). Probability of elevated PAWP based on deep learning of chest x-rays vs. Clinical and echocardiographic parameters was evaluated on Cardiac death or readmission due to heart failure (HR 1.46, 95% CI 1.23-1.72, p=<0.001). Probability of elevated pulmonary artery wedge pressure at pre-discharge, assessed by a deep learning model on chest x-rays, predicted cardiac death or heart failure readmission (HR 1.46).