Henriques Zacarias
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Henriques Zacarias has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Mehran Pourvahab
Departamento de Informática, Universidade da Beira Interior, 6201-001 Covilhã, Portugal
4 shared publications - Nuno Manuel Garcia
LaSIGE, Faculdade de Ciências, Universidade de Lisboa, 1749-016 Lisboa, Portugal
4 shared publications - Virginie Felizardo
University of Beira Interior
4 shared publications - Leonice Souza-Pereira
Instituto Federal do Triângulo Mineiro - Campus Uberlândia Centro, Brasil; Instituto de Telecomunicações, Lisboa, Portugal; Universidade da Beira Interior, Covilhã, Portugal
3 shared publications - Joao Alexandre Lobo Marques
Laboratory of Applied Neurosciences, University of Saint Joseph, Macau 999078, China
2 shared publications André Pinho
Instituto de Telecomunicações
1 shared publication
Latest Publications
- Open Access
Navigating ECG Signal Forecasting: A Systematic Review of Current Trends and Future Directions
Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, highlighting the urgent need for effective early detection strategies. The electrocardiogram (ECG), as the gold standard for cardiac monitoring, provides critical data for clinical decision-making. Short-term ECG forecasting can support timely detection of abnormal cardiac events, enabling proactive interventions. This systematic literature review (SLR) examines ECG forecasting techniques based on time series analysis, addressing five research questions (RQ1–RQ5) regarding data sources, forecasting models, performance metrics, challenges, and methodological trends. Three databases—PubMed, IEEE Xplore, and ScienceDirect—were systematically searched for peer-reviewed articles published between 2013 and 2023. Following the PRISMA 2020 guidelines and the application of predefined eligibility criteria, eight studies were included in the final synthesis. The analysis reveals that public databases are the preferred source due to accessibility; the results also suggest that hybrid forecasting models dominate current research, preprocessing and analytical approaches vary widely, and performance is primarily evaluated using RMSE and MAE. Key research gaps include limited studies on real-time arrhythmia prediction, lack of standardized evaluation frameworks, and underexploration of hybrid and deep learning strategies in diverse patient populations. Building on these findings, the review proposes a future research agenda (2025–2030) focused on developing automated, real-time ECG forecasting systems with enhanced accuracy and interpretability, leveraging hybrid and deep learning models, and establishing standardized benchmarking protocols. Overall, ECG forecasting is identified as a promising yet underexplored field, offering substantial opportunities for innovation in predictive cardiology and clinical decision support.
Open AccessNavigating ECG Signal Forecasting: A Systematic Review of Current Trends and Future Directions
Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, highlighting the urgent need for effective early detection strategies. The electrocardiogram (ECG), as the gold standard for cardiac monitoring, provides critical data for clinical decision-making. Short-term ECG forecasting can support timely detection of abnormal cardiac events, enabling proactive interventions. This systematic literature review (SLR) examines ECG forecasting techniques based on time series analysis, addressing five research questions (RQ1–RQ5) regarding data sources, forecasting models, performance metrics, challenges, and methodological trends. Three databases—PubMed, IEEE Xplore, and ScienceDirect—were systematically searched for peer-reviewed articles published between 2013 and 2023. Following the PRISMA 2020 guidelines and the application of predefined eligibility criteria, eight studies were included in the final synthesis. The analysis reveals that public databases are the preferred source due to accessibility; the results also suggest that hybrid forecasting models dominate current research, preprocessing and analytical approaches vary widely, and performance is primarily evaluated using RMSE and MAE. Key research gaps include limited studies on real-time arrhythmia prediction, lack of standardized evaluation frameworks, and underexploration of hybrid and deep learning strategies in diverse patient populations. Building on these findings, the review proposes a future research agenda (2025–2030) focused on developing automated, real-time ECG forecasting systems with enhanced accuracy and interpretability, leveraging hybrid and deep learning models, and establishing standardized benchmarking protocols. Overall, ECG forecasting is identified as a promising yet underexplored field, offering substantial opportunities for innovation in predictive cardiology and clinical decision support.
- Top Cited PapersOpen Access
- 17 March 2025
- Published by Elsevier in Artificial Intelligence in Medicine
- Vol. 163, 103109
Voice analysis in Parkinson’s disease - a systematic literature review
- 17 March 2025
- Published by Elsevier in Artificial Intelligence in Medicine
- Vol. 163, 103109
Top Cited PapersOpen AccessVoice analysis in Parkinson’s disease - a systematic literature review
- Open Access
- 17 January 2024
- Published by MDPI AG in Bioengineering
- Vol. 11 (1) , 89
ECG Forecasting System Based on Long Short-Term Memory
Worldwide, cardiovascular diseases are some of the primary causes of death; yet the early detection and diagnosis of such diseases have the potential to save many lives. Technological means of detection are becoming increasingly essential and numerous techniques have been created for this purpose, such as forecasting. Of these techniques, the time series forecasting technique seeks to predict future events. The long-term time series forecasting of physiological data could assist medical professionals in predicting and treating patients based on very early diagnosis. This article presents a model that utilizes a deep learning technique to predict long-term ECG signals. The forecasting model can learn signals’ nonlinearity, nonstationarity, and complexity based on a long short-term memory architecture. However, this is not a trivial task as the correct forecasting of a signal that closely resembles the original complex signal’s structure and behavior while minimizing any differences in amplitude continues to pose challenges. To achieve this goal, we used a dataset available on the Physio net database, called MIT-BIH, with 48 ECG recordings of 30 min each. The developed model starts with pre-processing to reduce interference in the original signals, then applies a deep learning algorithm, based on a long short-term memory (LTSM) neural network with two hidden layers. Next, we applied the root mean square error (RMSE) and mean absolute error (MAE) metrics to evaluate the performance of the model and obtained an average RMSE of and an average MAE of across all simulations. The results indicate that the proposed LSTM model is a promising technique for ECG forecasting, considering the trends of the changes in the original data series, most notably in R-peak amplitude. Given the model’s accuracy and the features of the physiological signals, the system could be used to improve existing predictive healthcare systems for cardiovascular monitoring.- 17 January 2024
- Published by MDPI AG in Bioengineering
- Vol. 11 (1) , 89
Open AccessECG Forecasting System Based on Long Short-Term Memory
Worldwide, cardiovascular diseases are some of the primary causes of death; yet the early detection and diagnosis of such diseases have the potential to save many lives. Technological means of detection are becoming increasingly essential and numerous techniques have been created for this purpose, such as forecasting. Of these techniques, the time series forecasting technique seeks to predict future events. The long-term time series forecasting of physiological data could assist medical professionals in predicting and treating patients based on very early diagnosis. This article presents a model that utilizes a deep learning technique to predict long-term ECG signals. The forecasting model can learn signals’ nonlinearity, nonstationarity, and complexity based on a long short-term memory architecture. However, this is not a trivial task as the correct forecasting of a signal that closely resembles the original complex signal’s structure and behavior while minimizing any differences in amplitude continues to pose challenges. To achieve this goal, we used a dataset available on the Physio net database, called MIT-BIH, with 48 ECG recordings of 30 min each. The developed model starts with pre-processing to reduce interference in the original signals, then applies a deep learning algorithm, based on a long short-term memory (LTSM) neural network with two hidden layers. Next, we applied the root mean square error (RMSE) and mean absolute error (MAE) metrics to evaluate the performance of the model and obtained an average RMSE of and an average MAE of across all simulations. The results indicate that the proposed LSTM model is a promising technique for ECG forecasting, considering the trends of the changes in the original data series, most notably in R-peak amplitude. Given the model’s accuracy and the features of the physiological signals, the system could be used to improve existing predictive healthcare systems for cardiovascular monitoring. - 16 March 2023
- Published by Springer Nature
- p. 108-120
Gender Classification Using nonstandard ECG Signals - A Conceptual Framework of Implementation
- 16 March 2023
- Published by Springer Nature
- p. 108-120
Gender Classification Using nonstandard ECG Signals - A Conceptual Framework of Implementation