22 April 2025 in Physiological Measurement
Objetive. Hypertension, a leading contributor to cardiovascular morbidity, underscores the need for accurate and continuous blood pressure (BP) monitoring. Photoplethysmography (PPG) emerges as a promising approach for continuous BP monitoring. However, the precision of BP estimates derived from PPG signals has been the subject of ongoing debate, requiring a comprehensive evaluation of their efficacy. This paper aims to provide the potentials and limitations regarding BP estimation from single-site PPG signals. Approach. We developed a calibration-based Siamese ResNet model for BP estimation. We compared the use of normalized PPG (N-PPG) against the normalized invasive arterial BP (N-IABP) signals as input. N-IABP signals, while not directly presenting systolic (SBP) and diastolic (DBP) BP values, are expected to offer more precise estimations than PPG since it is a direct pressure sensor inside the body. Thus, if N-IABP poses challenges in BP estimation, predicting BP from PPG signals might be even more challenging. Main results. Our evaluation, conducted using the AAMI and BHS standards on the VitalDB dataset, revealed that inference using N-IABP signals meet with AAMI standards for both SBP and DBP, with errors of mmHg for systolic pressure and for diastolic pressure. In contrast, N-PPG based inference exhibited inferior performance than N-IABP, presenting mmHg and mmHg for systolic and diastolic pressure respectively in their best setup. Significance. Our findings establish a critical benchmark for PPG performance, providing realistic expectations for its BP estimation capabilities. We concluded that while PPG signals contain BP-correlated information, they may not suffice for accurate prediction.
25 June 2024 in European Heart Journal - Digital Health
Aims: Aortic elongation can result from age-related changes, congenital factors, aneurysms, or conditions affecting blood vessel elasticity. It is associated with cardiovascular diseases and severe complications like aortic aneurysms and dissection. We assess qualitatively and quantitatively explainable methods to understand the decisions of a deep learning model for detecting aortic elongation using chest X-ray (CXR) images. Methods and results: In this study, we evaluated the performance of deep learning models (DenseNet and EfficientNet) for detecting aortic elongation using transfer learning and fine-tuning techniques with CXR images as input. EfficientNet achieved higher accuracy (86.7% ± 2.1), precision (82.7% ± 2.7), specificity (89.4% ± 1.7), F1 score (82.5% ± 2.9), and area under the receiver operating characteristic (92.7% ± 0.6) but lower sensitivity (82.3% ± 3.2) compared with DenseNet. To gain insights into the decision-making process of these models, we employed gradient-weighted class activation mapping and local interpretable model-agnostic explanations explainability methods, which enabled us to identify the expected location of aortic elongation in CXR images. Additionally, we used the pixel-flipping method to quantitatively assess the model interpretations, providing valuable insights into model behaviour. Conclusion: Our study presents a comprehensive strategy for analysing CXR images by integrating aortic elongation detection models with explainable artificial intelligence techniques. By enhancing the interpretability and understanding of the models’ decisions, this approach holds promise for aiding clinicians in timely and accurate diagnosis, potentially improving patient outcomes in clinical practice.
13 September 2025 in Research on Biomedical Engineering
31 August 2023 in medRxiv
Aim: Aortic Elongation can result from age-related changes, congenital factors, aneurysms, or conditions affecting blood vessel elasticity. It is associated with cardiovascular diseases and severe complications like aortic aneurysms and dissection. We aim to assess qualitatively and quantitatively explainable methods in order to understand the decisions of a deep learning model for Aortic Elongation detection with Chest X-Ray (CXR) images. Methods and Results: In this work, we evaluated the performance of deep learning models (DenseNet and EfficientNet) for aortic elongation detection based on transfer learning and fine-tunning techniques using CXR as input. DenseNet achieved higher accuracy (84.7% ± 0.7), precision (75.6% ± 1.3), sensitivity (88.7% ± 2.7), specificity (82.3% ± 1.6), F1-score (81.6% ± 1.0), and AUROC (93.1% ± 0.4) than EfficientNet. To gain insights into the decision-making process of the deep learning models, we employed Grad-CAM and LIME explainability methods. Through these techniques, we were able to successfully identify the expected location of aortic elongation in the x-ray images. Moreover, we used the pixel-flipping method to assess quantitatively the interpretations providing valuable insights into models behavior. Conclusion: Our study presents a comprehensive strategy for analyzing CXR by integrating Aortic Elongation detection models with explainable methods. By incorporating explainable AI techniques, we enhanced the interpretability and understanding of the models’ decisions. This approach holds promise for aiding clinicians in timely and accurate diagnosis, potentially improving patient outcomes in clinical practice.