publications
Bibliometrics can be found in: Google Scholar and SCOPUS . I am also available in the following scientific databases: ORCID , DBLP , Lattes (in portuguese).
Working Manuscripts
[P2] - Neural network-derived electrocardiographic features have prognostic significance and important phenotypic and genotypic associations (2023).
Submitted to Nature Medicine.
[P3] - Association of lifestyle with deep-learning based ECG-age (2023).
Submitted to Frontiers in Cardiovascular Medicine.
[P4] - No Double Descent in PCA: Training and Pre-Training in High Dimensions (2023).
OpenReview.
[P5] - Screening for Chagas disease from the electrocardiogram using a deep neural network (2023).
Submitted to Plos Neglected Tropical Diseases (preprint: medRxiv).
[doi]
[P6] - Heart age gap by explainable advanced electrocardiography is associated with cardiovascular risk factors and survival (2023).
Submitted to JACC Clinical Electrophysiology.
[P7] - Deep networks for system identification: a Survey (2023).
Submitted to Automatica (preprint: arXiv:2301.12832).
[doi]
[P8] - Electrocardiographic Age Predicts Cardiovascular Events in Community: The Framingham Heart Study (2023).
Accepted upon satisfactory revision at Circulation: Cardiovascular Quality and Outcomes.
[P9] - ECG-Based Electrolyte Prediction: Evaluating Regression and Probabilistic Methods (2022).
arXiv:2212.13890.
[doi]
[P10] - Knowledge Discovery with Electrocardiography Using Interpretable Deep Neural Networks (2022).
Under review at Nature Comunications (preprint: medRxiv).
[doi]
[P11] - Detection of Left Ventricular Systolic Dysfunction from Electrocardiographic Images (2022).
Under review Circulation (preprint: medRxiv).
[doi]
[P12] - Surprises in adversarially-trained linear regression (2022).
arXiv:2205.12695.
[doi]
- [arxiv]
Journal Papers
[J1] - Overparameterized Linear Regression under Adversarial Attacks (2023).
IEEE Transactions on Signal Processing.
[doi]
- [arxiv]
[J2] - On Merging Feature Engineering and Deep Learning for Diagnosis, Risk-Prediction and Age Estimation Based on the 12-Lead ECG (2023).
IEEE Transactions on Biomedical Engineering.
[doi]
- [arxiv]
[J3] - Development and validation of deep learning ECG-based prediction of myocardial infarction in emergency department patients (2022).
Scientific Reports.
[doi]
[J4] - Automated multilabel diagnosis on electrocardiographic images and signals (2022).
Nature Communications.
[doi]
- [medrxiv]
- [webapp]
[J5] - Electrocardiographic Predictors of Mortality: Data from a Primary Care Tele-Electrocardiography Cohort of Brazilian Patients (2021).
Hearts.
[doi]
[J6] - Deep neural network estimated electrocardiographic-age as a mortality predictor (2021).
Nature Communications.
[doi]
- [code]
- [medRxiv]
- [dataset 1]
- [dataset 2]
- [model]
[J7] - Atrial fibrillation risk prediction from the 12-lead ECG using digital biomarkers and deep representation learning (2021).
European Heart Journal - Digital Health.
[doi]
[J8] - Contextualized Interpretable Machine Learning for Medical Diagnosis (2020).
Communications of the ACM.
[doi]
[J9] - Evaluation of Mortality in Atrial Fibrillation: Clinical Outcomes in Digital Electrocardiography (CODE) Study (2020).
Global Heart.
[doi]
[J10] - On the smoothness of nonlinear system identification (2020).
Automatica.
[doi]
- [code]
- [arXiv]
[J11] - Automatic diagnosis of the 12-lead ECG using a deep neural network (2020).
Nature Communications.
[doi]
- [arXiv]
- [code]
- [data]
- [models]
[J12] - SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python (2020).
Nature Methods.
[doi]
- [arXiv]
[J13] - Tele-electrocardiography and bigdata: The CODE (Clinical Outcomes in Digital Electrocardiography) study (2019).
Journal of Electrocardiology.
[doi]
[J14] - Evaluation of mortality in bundle branch block patients from an electronic cohort: Clinical Outcomes in Digital Electrocardiography (CODE) study (2019).
Journal of Electrocardiology.
[doi]
[J15] - ''Parallel Training Considered Harmful?'': Comparing series-parallel and parallel feedforward network training (2018).
Neurocomputing.
[doi]
- [arXiv]
- [code]
Conference Papers
[C1] - Deep Energy-Based NARX Models (2021).
Proceedings of the 19th IFAC Symposium on System Identification (SYSID) - IFAC-PapersOnLine.
[doi]
- [arXiv]
- [code]
[C2] - Beyond Occam's Razor in System Identification: Double-Descent when Modeling Dynamics (2021).
Proceedings of the 19th IFAC Symposium on System Identification (SYSID) - IFAC-PapersOnLine.
[doi]
- [arxiv]
- [code]
- [slides]
[C3] - How convolutional neural networks deal with aliasing (2021).
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
[doi]
- [arXiv]
- [code]
- [slides]
- [poster]
- [sigport]
[C4] - First Steps Towards Self-Supervised Pretraining of the 12-Lead ECG (2021).
Computing in Cardiology (CinC).
[doi]
[C5] - Explaining end-to-end ECG automated diagnosis using contextual features (2020).
Machine Learning and Knowledge Discovery in Databases. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD).
[doi]
- [IEEE]
- [url]
[C6] - Automatic 12-lead ECG classification using a convolutional network ensemble (2020).
2020 Computing in Cardiology (CinC).
[doi]
- [IEEE]
- [url]
- [code]
- [slides]
- [presentation]
[C7] - Beyond exploding and vanishing gradients: attractors and smoothness in the analysis of recurrent neural network training (2020).
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR.
[url]
- [presentation]
- [code]
- [models]
[C8] - Explaining black-box automated electrocardiogram classification to cardiologists (2020).
2020 Computing in Cardiology (CinC).
[doi]
- [presentation]
- [code]
[C9] - Deep Convolutional Networks in System Identification (2019).
Proceedings of the 58th IEEE Conference on Decision and Control (CDC).
[doi]
- [arXiv]
- [code]
[C10] - Lasso Regularization Paths for NARMAX Models via Coordinate Descent (2018).
2018 Annual American Control Conference (ACC).
[doi]
- [arXiv]
- [slides]
- [code]
[C11] - Shooting Methods for Parameter Estimation of Output Error Models (2017).
Proceedings of the 20th IFAC World Congress. IFAC-PapersOnLine.
[doi]
- [poster]
- [code]
[C12] - Selecting transients automatically for the identification of models for an oil well (2015).
Proceedings of the 2nd IFAC Workshop on Automatic Control in Offshore Oil and Gas Production. IFAC-PapersOnLine.
[doi]
- [slides]
Workshop Papers and Conference Extended Abstracts
[W1] - ResNet-based ECG Diagnosis of Myocardial Infarction in the Emergency Department (2021).
Machine learning from ground truth: New medical imaging datasets for unsolved medical problems Workshop at NeurIPS.
[extended abstract]
- [slides]
[W2] - Deep Energy-Based NARX Models (2021).
Workshop on Nonlinear System Identification.
[book of abstracts]
- [slides]
[W3] - Beyond Occam's Razor in System Identification: Double-Descent when Modeling Dynamics (2021).
Workshop on Nonlinear System Identification.
[book of abstracts]
- [slides]
[W4] - Overparametrized Regression Under L2 Adversarial Attacks (2021).
Workshop on the Theory of Overparameterized Machine Learning (TOPML).
[abstract]
- [slides]
[W5] - Deep Convolutional Networks are Useful in System Identification (2019).
Workshop on Nonlinear System Identification.
[extended abstract]
- [slides]
[W6] - Automatic Diagnosis of Short-Duration 12-Lead ECG using a Deep Convolutional Network (2018).
Machine Learning for Health (ML4H) Workshop at NeurIPS.
[arXiv]
- [poster]
[W7] - Clinical Outcomes in Digital Electrocardiography: Evaluation of Mortality in Atrial Fibrillation (Code Study) (2018).
Circulation. Abstracts from American Heart Association's..
[url]
National Conference Papers (in Portuguese)
[N1] - Relaçoes Estáticas de Modelos NARX MISO e sua Representaçao de Hammerstein (2014).
XX Congresso Brasileiro de Automática.
[url]
- [slides]