Juan Carmelo Betancort Acosta

Mr. Juan Carmelo Betancort Acosta

orcid

Research Focus & Metrics

Representative Publications

View All Publications
22 May 2026 in JMIR Research Protocols
Verified
Journal Article
Open access
JAJuan Carmelo Betancort Acosta
Juan Carmelo Betancort Acosta
GZGarlene Zamora Zamorano
Garlene Zamora Zamorano
MMMaría Luisa Álvarez Malé
María Luisa Álvarez Malé
LPLilisbeth Perestelo-Pérez
Lilisbeth Perestelo-Pérez
Alezandra TorresAlezandra Torres
Alezandra Torres
AWAna M Wägner
Ana M Wägner
Background: Noncommunicable diseases are the leading cause of death worldwide. Cardiovascular and respiratory diseases, cancer, and type 2 diabetes share common risk factors that can be addressed: physical activity, a healthy diet, and avoiding smoking and alcohol. The Watching the Risk Factors (WARIFA) mobile health app was created for general health awareness and to support users in adopting healthier behaviors, as well as to support type 1 diabetes (T1D) self-management. Objective: This study aims to evaluate the effectiveness of the WARIFA app with personalized artificial intelligence (AI)–driven messages, compared to a nonpersonalized version, in promoting health-related behavior change among the general population and individuals with T1D. Methods: A total of 108 European participants, including individuals with T1D, were to be randomized (computer-generated sequence, double-blind, 1:1 ratio) to an intervention or control group. In the intervention group, participants used the WARIFA app with personalized messages and the use of AI. This applied to certain functionalities, such as providing recommendations on healthy dietary habits based on food logging and offering advice and encouragement through daily step tracking. It also provided risk predictions for cardiovascular and respiratory diseases, cancer, and type 2 diabetes. Participants with T1D were offered glucose predictions based on previous measurements. In the control group, participants used a WARIFA app without personalized messages or AI. Both WARIFA app versions offered access to air quality and UV index information for the geographical area, as well as displaying physical activity in the form of daily steps and sleep hours, as well as glucose results for participants with T1D. Both groups were provided with an activity monitor and used the WARIFA app for 8-12 weeks. The primary outcome is a self-defined goal, chosen from a set of proposed objectives at baseline and assessed at the end of the study using a Likert scale (1 to 10 points, 0 being no achievement at all and 10 being full achievement of the objective). Secondary outcomes include: engagement with the app, changes in lifestyle behavior, body composition, lipid profile, glycated hemoglobin (T1D only), hypoglycemic events (T1D only), and health-related quality of life, as well as acquired knowledge, self-efficacy, and usability. Results: The clinical trial took place between January and June 2025. A total of 88 participants were finally recruited. The data are being analyzed, and the results are expected to be published in 2026. Conclusions: There is evidence that improving lifestyle behavior can prevent noncommunicable diseases. In this study, we aim to evaluate the effectiveness of the WARIFA app to improve lifestyle behaviors and T1D management. Trial Registration: ClinicalTrials.gov NCT06918444; https://clinicaltrials.gov/study/NCT06918444 International Registered Report Identifier (IRRID): DERR1-10.2196/84510

25 August 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
Bryan Peralta-ArboledaBryan Peralta-Arboleda
Bryan Peralta-Arboleda
David Chushig-MuzoDavid Chushig-Muzo
David Chushig-Muzo
FLFrancisco J. Lara-Abelenda
Francisco J. Lara-Abelenda
JAJuan Carmelo Betancort Acosta
Juan Carmelo Betancort Acosta
AWAna M Wägner
Ana M Wägner
Cristina Soguero-RuizCristina Soguero-Ruiz
Cristina Soguero-Ruiz
Nocturnal Hypoglycemia (NH), which occurs when blood glucose levels fall below 70 mg/dL during sleep, remains a common complication in people with Type 1 Diabetes. Despite advances in Continuous Glucose Monitoring (CGM), controlling both glucose and glycemic events remains challenging. Artificial Intelligence (AI) models are promising for identifying CGM patterns associated with NH and supporting its prediction, thus reducing its occurrence and complications. However, two main challenges limit the performance of AI models for NH: (i) the class imbalance due to the low number of NH events in data; and (ii) the high-dimensionality caused by the extraction of CGM-derived features. To address this, we propose a two-stage methodology that combines ensemble Feature Selection (FS) methods and synthetic data augmentation. We performed CGM-derived feature extraction by using a time-window approach with overlapping and non-overlapping approaches. Model interpretability is provided through feature analysis using Shapley additive explanations, enabling the identification of associated NH factors. We employed CGM data from 52 individuals with T1D, collected at Complejo Hospitalario Insular-Materno Infantil de Las Palmas de Gran Canaria, Spain. Among the temporal configurations evaluated, the 6-hour window yielded the highest predictive performance. With ensemble FS retaining the top 40% of features, the best-performing model achieved an Area Under the Receiver Operating Characteristic Curve of 0.68 using a logistic regression and overlapping windows. Our findings highlighted the importance of window-based extraction in improving predictive performance. Our interpretable methodology provides a clinically relevant approach for the early prediction of NH, supporting decision-making and enhancing the effectiveness of CGM-based monitoring systems. The proposed methodology may support timely preventive interventions, reducing the occurrence of NH while improving patient safety and confidence in diabetes management.

20 September 2025 in JMIR Preprints
Verified
Preprint
Open access
JAJuan Carmelo Betancort Acosta
Juan Carmelo Betancort Acosta
GZGarlene Zamora Zamorano
Garlene Zamora Zamorano
MMMaría Luisa Álvarez Malé
María Luisa Álvarez Malé
LPLilisbeth Perestelo-Pérez
Lilisbeth Perestelo-Pérez
Alezandra TorresAlezandra Torres
Alezandra Torres
AWAna M Wägner
Ana M Wägner
BACKGROUND Noncommunicable diseases are the leading cause of death worldwide. Cardiovascular and respiratory diseases, cancer, and type 2 diabetes share common risk factors that can be addressed: physical activity, a healthy diet, and avoiding smoking and alcohol. The Watching the Risk Factors (WARIFA) mobile health app was created for general health awareness and to support users in adopting healthier behaviors, as well as to support type 1 diabetes (T1D) self-management. OBJECTIVE This study aims to evaluate the effectiveness of the WARIFA app with personalized artificial intelligence (AI)–driven messages, compared to a nonpersonalized version, in promoting health-related behavior change among the general population and individuals with T1D. METHODS A total of 108 European participants, including individuals with T1D, were to be randomized (computer-generated sequence, double-blind, 1:1 ratio) to an intervention or control group. In the intervention group, participants used the WARIFA app with personalized messages and the use of AI. This applied to certain functionalities, such as providing recommendations on healthy dietary habits based on food logging and offering advice and encouragement through daily step tracking. It also provided risk predictions for cardiovascular and respiratory diseases, cancer, and type 2 diabetes. Participants with T1D were offered glucose predictions based on previous measurements. In the control group, participants used a WARIFA app without personalized messages or AI. Both WARIFA app versions offered access to air quality and UV index information for the geographical area, as well as displaying physical activity in the form of daily steps and sleep hours, as well as glucose results for participants with T1D. Both groups were provided with an activity monitor and used the WARIFA app for 8-12 weeks. The primary outcome is a self-defined goal, chosen from a set of proposed objectives at baseline and assessed at the end of the study using a Likert scale (1 to 10 points, 0 being no achievement at all and 10 being full achievement of the objective). Secondary outcomes include: engagement with the app, changes in lifestyle behavior, body composition, lipid profile, glycated hemoglobin (T1D only), hypoglycemic events (T1D only), and health-related quality of life, as well as acquired knowledge, self-efficacy, and usability. RESULTS The clinical trial took place between January and June 2025. A total of 88 participants were finally recruited. The data are being analyzed, and the results are expected to be published in 2026. CONCLUSIONS There is evidence that improving lifestyle behavior can prevent noncommunicable diseases. In this study, we aim to evaluate the effectiveness of the WARIFA app to improve lifestyle behaviors and T1D management. CLINICALTRIAL ClinicalTrials.gov NCT06918444; https://clinicaltrials.gov/study/NCT06918444 INTERNATIONAL REGISTERED REPORT DERR1-10.2196/84510

5 November 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Bryan Peralta-ArboledaBryan Peralta-Arboleda
Bryan Peralta-Arboleda
David Chushig-MuzoDavid Chushig-Muzo
David Chushig-Muzo
FLFrancisco J. Lara-Abelenda
Francisco J. Lara-Abelenda
JAJuan Carmelo Betancort Acosta
Juan Carmelo Betancort Acosta
AWAna M Wägner
Ana M Wägner
Cristina Soguero-RuizCristina Soguero-Ruiz
Cristina Soguero-Ruiz
Nocturnal hypoglycemia (NH), which occurs when blood glucose levels fall below 70 mg/dL during sleep, remains a common complication in people with type 1 diabetes. Despite advances in continuous glucose monitoring (CGM), controlling both glucose and glycemic events remains challenging. Artificial Intelligence (AI) models are promising for identifying CGM patterns associated with NH and support its prediction, thereby reducing associated complications. However, two main challenges limit the performance of AI-based models for NH: (i) the class imbalance caused by the low number of NH events in the datasets; and (ii) the high-dimensionality caused by the extraction of CGM-derived features. To address this, we propose a two-stage methodology that combines ensemble feature selection (FS) methods and synthetic data augmentation techniques. We employed CGM features extracted using two window-based approaches (non-overlapping and overlapping) with three, four, and six windows. Model interpretability is provided through feature analysis using Shapley additive explanations (SHAP), enabling the identification of associated NH factors. We employed CGM data from 52 individuals with T1D, collected at Complejo Hospitalario Insular-Materno Infantil de Las Palmas de Gran Canaria, Spain. Among the evaluated configurations, the six-window configuration yielded the highest reported predictive performance. The two LR models examined in the SHAP analysis, both trained with RUS and overlapping windows, achieved test-set AUCROC values of 0.7403 using all features and 0.7400 using the selected feature subset, calculated from continuous prediction scores. Our findings extend prior evidence on temporal CGM representations to an adult NH setting not restricted to exercise-associated nights, using bootstrap-based Relief FS and alternative windowing configurations. Our interpretable methodology provides a clinically relevant approach for the early prediction of NH, supporting decision-making and enhancing the effectiveness of CGM-based monitoring systems. The proposed methodology may support timely preventive interventions and contribute to improving patient safety and confidence in diabetes management.