Does a machine learning model using echocardiographic images improve the diagnostic accuracy of pulmonary hypertension compared to traditional methods in patients with suspected pulmonary hypertension?
A machine learning model using parasternal short axis-papillary muscle level echocardiographic views outperformed traditional methods in diagnosing pulmonary hypertension.
Abstract Echocardiography, a simple and noninvasive tool, is the first choice for screening pulmonary hypertension (PH). However, accurate assessment of PH, incorporating both the pulmonary artery pressures and additional signs for PH remained unsatisfied. Thus, this study aimed to develop a machine learning (ML) model that can automatically evaluate the probability of PH. This cohort included data from 346 (275 for training set and internal validation set and 71 for external validation set) patients with suspected PH patients and receiving right heart catheterization. Echocardiographic images on parasternal short axis‐papillary muscle level (PSAX‐PML) view from all patients were collected, labeled, and preprocessed. Local features from each image were extracted and subsequently integrated to build a ML model. By adjusting the parameters of the model, the model with the best prediction effect is finally constructed. We used receiver‐operating characteristic analysis to evaluate model performance and compared the ML model with the traditional methods. The accuracy of the ML model for diagnosis of PH was significantly higher than the traditional method (0.945 vs. 0.892, p = 0.027 area under the curve [AUC]). Similar findings were observed in subgroup analysis and validated in the external validation set (AUC = 0.950 95% CI: 0.897−1.000). In summary, ML methods could automatically extract features from traditional PSAX‐PML view and automatically assess the probability of PH, which were found to outperform traditional echocardiographic assessments.
Liao et al. (Sat,) studied this question.