Estela Ribeiro

Estela Ribeiro

Auto-generated profile, based on publicly available information

Estela Ribeiro

Heart Institute (InCor), Clinics Hospital, University of São Paulo Medical School (HCFMUSP), São Paulo, SP, Brazil

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 April 2025 in Physiological Measurement
Verified
Journal Article
Closed access
FDFelipe Meneguitti Dias
Felipe Meneguitti Dias
DCDiego A C Cardenas
Diego A C Cardenas
MTMarcelo A F Toledo
Marcelo A F Toledo
FOFilipe A C Oliveira
Filipe A C Oliveira
EREstela Ribeiro
Estela Ribeiro
MGMarco Antonio Gutierrez
Marco Antonio Gutierrez
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 1.29 ± 6.33 mmHg for systolic pressure and 1.17 ± 5.78 for diastolic pressure. In contrast, N-PPG based inference exhibited inferior performance than N-IABP, presenting 1.49 ± 11.82 mmHg and 0.89 ± 7.27 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
Verified
Journal Article
Open access
PDF file
EREstela Ribeiro
Estela Ribeiro
DCDiego A C Cardenas
Diego A C Cardenas
FDFelipe Meneguitti Dias
Felipe Meneguitti Dias
JKJose Krieger
Jose Krieger
MGMarco Antonio Gutierrez
Marco Antonio Gutierrez
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
Verified
Journal Article
Closed access
PDF file
EREstela Ribeiro
Estela Ribeiro
FDFelipe M. Dias
Felipe M. Dias
QSQuenaz B. Soares
Quenaz B. Soares
JKJose E. Krieger
Jose E. Krieger
MGMarco A. Gutierrez
Marco A. Gutierrez

29 September 2025
Verified
Conference Paper
Closed access
EREstela Ribeiro
Estela Ribeiro
QSQuenaz Bezerra Soares
Quenaz Bezerra Soares
FDFelipe Meneguitti Dias
Felipe Meneguitti Dias
JKJose Krieger
Jose Krieger
MGMarco Antonio Gutierrez
Marco Antonio Gutierrez
Atrial Fibrillation (AFib) and Atrial Flutter (AFlut) are prevalent arrhythmias that present similar clinical features, challenging automated ECG differentiation. This study investigates the classification of AFib and AFlut using 12-lead ECGs from the CinC2021 dataset and a private dataset. We evaluated both 1D and 2D deep learning models. For 1D models, LiteVGG-11 demonstrated the highest performance, achieving an Acc of 77.91, AUROC of 87.17, and F1 score of 76.59. For 2D models, the EfficientNet-B2 outperformed other architectures, with an Acc of 75.20, AUROC of 85.50, and F1 of 71.59. Our results show that 1D models outperform 2D ones and that performance varies significantly across datasets, highlighting the difficulty in distinguishing AFib from AFlut.

9 June 2025
Verified
Conference Paper
Open access
PDF file
FDFelipe Meneguitti Dias
Felipe Meneguitti Dias
EREstela Ribeiro
Estela Ribeiro
QSQuenaz B. Soares
Quenaz B. Soares
JKJose Krieger
Jose Krieger
MGMarco Antonio Gutierrez
Marco Antonio Gutierrez
Artificial intelligence is increasingly used to extract health insights from 12-lead (12L) electrocardiograms (ECG). Here, we propose a deeplearning model to predict sex and age from 12L and reduced-lead ECGs (6L–1L) and assess their impact on mortality risk. Using a ResNeXt-based model trained on the CODE15 dataset, our best models achieved an F1-score of 0.800 for sex classification (12L) and a mean absolute error of 8.961 for age estimation (4L). We found that overestimated age predictions and incorrect sex classifications were associated with higher mortality risk, whereas underestimated age predictions correlated with lower risk. These findings highlight the potential of reduced-lead ECGs for risk assessment, expanding their clinical utility.

31 August 2023 in medRxiv
Verified
Preprint
Open access
PDF file
EREstela Ribeiro
Estela Ribeiro
DCDiego Armando Cardona Cardenas
Diego Armando Cardona Cardenas
FDFelipe Meneguitti Dias
Felipe Meneguitti Dias
JKJose Krieger
Jose Krieger
MGMarco Antonio Gutierrez
Marco Antonio Gutierrez
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.