Angélica Atehortúa
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
Angélica Atehortúa has a total of 56 co-authors. Here are the top co-authors by number of shared publications:
- Eduardo Romero
Universidad Nacional de Colombia
3 shared publications - Polyxeni Gkontra
Artificial Intelligence in Medicine Lab (BCN-AIM), Departament de Matemàtiques i Informàtica, Universitat de Barcelona, Spain (J.P.-L., G.S., E.R.P., S.J.E.K., I.S., K.L., P.G.).
3 shared publications - Karim Lekadir
Universitat de Barcelona
2 shared publications - Marina Camacho
Department of Mathematics and Computer Science, Artificial Intelligence in Medicine Lab (BCN-AIM), Universidad de Barcelona, Barcelona, Spain
2 shared publications - Mireille Garreau
LTSI—UMR_S
2 shared publications - Paula Petrone
ISGlobal, Barcelona, Spain
2 shared publications
Latest Publications
- Open Access
- 18 September 2026
- Published by Elsevier in International Journal of Medical Informatics
- Vol. 222, 106731
Sex-specific clinical history improves disease prediction while revealing context-dependent effects on fairness in multimorbid populations
- 18 September 2026
- Published by Elsevier in International Journal of Medical Informatics
- Vol. 222, 106731
Open AccessSex-specific clinical history improves disease prediction while revealing context-dependent effects on fairness in multimorbid populations
- 13 June 2026
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 213, 111789
Predicting survival in extremely preterm infants: A multicenter machine learning study from Spain
- 13 June 2026
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 213, 111789
Predicting survival in extremely preterm infants: A multicenter machine learning study from Spain
- 4 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Registration of multimodal images for characterization of cardiomyopathies
Recalage d'images multimodales pour la caractérisation de cardiomyopathies: Cette thèse présente de nouvelles méthodes pour la caractérisation de mouvement et le recalage d'images multimodales cardiaques, basées sur un descripteur spatio-temporel de saillance et sans a priori géométrique. Une première contribution porte sur la proposition d'un nouveau descripteur de saillance calculé pour extraire les changements spatio-temporels des structures observées. Cette méthode de caractérisation de mouvement a été appliquée en Imagerie par Résonance Magnétique en mode ciné (cine-IRM) et à la caractérisation de mouvements anormaux chez des sujets atteints de cardiomyopathie hypertrophique. Elle a fait l'objet d'expérimentations à partir de plusieurs bases de données publiques. Les résultats ont montré l'efficacité du descripteur proposé et sa robustesse dans un contexte d'images hétérogènes et bruitées. Une deuxième contribution porte sur le développement d'une nouvelle approche de recalage non rigide d'images multimodales cardiaques acquises en IRM et en échocardiographie 3D, dans laquelle les images traitées sont recalées dans un même espace de représentation basé sur le descripteur de saillance. La méthode a été évaluée sur données réelles et a montré des résultats pertinents. Une dernière contribution porte sur la proposition d'approches de segmentation automatique du cœur en IRM, combinant pour certaines l'exploitation de saillance spatiale à des techniques d'apprentissage profond. Les différentes approches proposées apportent des solutions et perspectives nouvelles pour l'analyse couplée des informations fonctionnelles et structurelles cardiaques et trouvent leur intérêt dans le cadre de l'aide au diagnostic et à la planification d'interventions
- 4 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Registration of multimodal images for characterization of cardiomyopathies
Recalage d'images multimodales pour la caractérisation de cardiomyopathies: Cette thèse présente de nouvelles méthodes pour la caractérisation de mouvement et le recalage d'images multimodales cardiaques, basées sur un descripteur spatio-temporel de saillance et sans a priori géométrique. Une première contribution porte sur la proposition d'un nouveau descripteur de saillance calculé pour extraire les changements spatio-temporels des structures observées. Cette méthode de caractérisation de mouvement a été appliquée en Imagerie par Résonance Magnétique en mode ciné (cine-IRM) et à la caractérisation de mouvements anormaux chez des sujets atteints de cardiomyopathie hypertrophique. Elle a fait l'objet d'expérimentations à partir de plusieurs bases de données publiques. Les résultats ont montré l'efficacité du descripteur proposé et sa robustesse dans un contexte d'images hétérogènes et bruitées. Une deuxième contribution porte sur le développement d'une nouvelle approche de recalage non rigide d'images multimodales cardiaques acquises en IRM et en échocardiographie 3D, dans laquelle les images traitées sont recalées dans un même espace de représentation basé sur le descripteur de saillance. La méthode a été évaluée sur données réelles et a montré des résultats pertinents. Une dernière contribution porte sur la proposition d'approches de segmentation automatique du cœur en IRM, combinant pour certaines l'exploitation de saillance spatiale à des techniques d'apprentissage profond. Les différentes approches proposées apportent des solutions et perspectives nouvelles pour l'analyse couplée des informations fonctionnelles et structurelles cardiaques et trouvent leur intérêt dans le cadre de l'aide au diagnostic et à la planification d'interventions
- Open Access
- 21 December 2024
- Published by Springer Nature in Health and Technology
- Vol. 15 (2) , 355-365
Low-cost predictive models of dementia risk using machine learning and exposome predictors
Purpose: Diagnosing dementia, affecting over 55 million people globally, is challenging and costly, often leading to late-stage diagnoses. This study aims to develop early, accurate, and cost-effective dementia screening methods using exposome predictors and machine learning. We investigate whether low-cost exposome predictors combined with machine learning models can reliably identify individuals at risk of dementia. Methods: We analyzed data from 500,000 UK Biobank participants, selecting 1523 diagnosed with dementia and an equal number of healthy controls, matched by age and sex. A total of 3046 participants were included: 2740 for internal validation and 306 for external validation. We used 128 low-cost exposome factors from baseline visits, imputed missing data, and assessed two predictive models: a classical logistic regression and a machine learning ensemble classifier (XGBoost). Feature importance was estimated within the predictive models. Results: The XGBoost model outperformed the logistic regression model, achieving a mean AUC of 0.88 in external validation. We identified novel exposome factors that might be combined as potential markers for dementia, such as facial aging, the frequency of use of sun/ultraviolet light protection, and the length of mobile phone use. Conclusions: Machine learning models utilizing exposome data can reliably identify individuals at risk of dementia, with XGBoost showing superior performance. This approach highlights the potential of low-cost, readily available exposome factors as markers for dementia. Future studies should validate these findings in diverse populations and explore the integration of additional exposome factors to enhance prediction accuracy.
- 21 December 2024
- Published by Springer Nature in Health and Technology
- Vol. 15 (2) , 355-365
Open AccessLow-cost predictive models of dementia risk using machine learning and exposome predictors
Purpose: Diagnosing dementia, affecting over 55 million people globally, is challenging and costly, often leading to late-stage diagnoses. This study aims to develop early, accurate, and cost-effective dementia screening methods using exposome predictors and machine learning. We investigate whether low-cost exposome predictors combined with machine learning models can reliably identify individuals at risk of dementia. Methods: We analyzed data from 500,000 UK Biobank participants, selecting 1523 diagnosed with dementia and an equal number of healthy controls, matched by age and sex. A total of 3046 participants were included: 2740 for internal validation and 306 for external validation. We used 128 low-cost exposome factors from baseline visits, imputed missing data, and assessed two predictive models: a classical logistic regression and a machine learning ensemble classifier (XGBoost). Feature importance was estimated within the predictive models. Results: The XGBoost model outperformed the logistic regression model, achieving a mean AUC of 0.88 in external validation. We identified novel exposome factors that might be combined as potential markers for dementia, such as facial aging, the frequency of use of sun/ultraviolet light protection, and the length of mobile phone use. Conclusions: Machine learning models utilizing exposome data can reliably identify individuals at risk of dementia, with XGBoost showing superior performance. This approach highlights the potential of low-cost, readily available exposome factors as markers for dementia. Future studies should validate these findings in diverse populations and explore the integration of additional exposome factors to enhance prediction accuracy.
- Open Access
- 12 September 2023
- Published by Elsevier in International Journal of Medical Informatics
- Vol. 179, 105209
Cardiometabolic risk estimation using exposome data and machine learning
- 12 September 2023
- Published by Elsevier in International Journal of Medical Informatics
- Vol. 179, 105209
Open AccessCardiometabolic risk estimation using exposome data and machine learning
- Open Access
Low-cost predictive models of dementia risk using machine learning and exposome predictors
Diagnosing dementia, a syndrome that currently affects more than 55 million people worldwide, remains a particularly challenging and costly task. It may involve undertaking several medical tests such as brain scans, cognitive tests and genetic tests to determine the presence and degree of cognitive decline. These procedures are associated with long procedures, subjective evaluations and high costs. As a result, patients are often diagnosed at a late stage, when symptoms become highly pronounced. Therefore, there is an urgent need for developing new strategies for early, accurate and cost-effective dementia screening and risk prediction. To overcome current limitations, we explored readily available exposome predictors for identifying individuals at risk of dementia and compared traditional statistical modeling and advanced machine learning. From approximately 500,000 participants from the UK Biobank, 1523 participants diagnosed with dementia after their baseline assessment visit were included in our study. An equal number of healthy participants were randomly selected as the control group by matching statistical age mean and sex distribution. This resulted in a total of 3046 participants being selected for our study; 2740 participants from 19 of the 22 UK Biobank assessment centers were used for internal validation, and 306 participants from the remaining three centers were selected for external validation. We include data from the participants’ baseline visit and selected 128 low-cost exposome factors related to life course exposures that may be easily acquired through simple questionnaires. Subsequently, data imputation was performed to account for missing patient data. Two different predictive models were assessed for discriminating between participants that remained healthy and participants diagnosed with dementia after the baseline visit, i.e. (1) a classical logistic regression linear classifier and (2) a machine learning ensemble classifier based on XGBoost. We interpreted the results by estimating feature importance within the predictive models. Our results demonstrate that machine learning models based on exposome data can reliably identify individuals that will be diagnosed with dementia. The XGBoost based model outperforms logistic regression model, achieving a mean AUC of 0.88 in the external validation tests. We identified novel exposome factors that might be combined as potential markers for dementia, such as facial aging, the frequency of use of sun/ultraviolet light protection, and the length of mobile phone use. Finally, we propose a novel neurocognitive assessment test that could be used as an online tool to screen individuals at risk of dementia for enrolment in preventive interventions and future clinical trials.
Open AccessLow-cost predictive models of dementia risk using machine learning and exposome predictors
Diagnosing dementia, a syndrome that currently affects more than 55 million people worldwide, remains a particularly challenging and costly task. It may involve undertaking several medical tests such as brain scans, cognitive tests and genetic tests to determine the presence and degree of cognitive decline. These procedures are associated with long procedures, subjective evaluations and high costs. As a result, patients are often diagnosed at a late stage, when symptoms become highly pronounced. Therefore, there is an urgent need for developing new strategies for early, accurate and cost-effective dementia screening and risk prediction. To overcome current limitations, we explored readily available exposome predictors for identifying individuals at risk of dementia and compared traditional statistical modeling and advanced machine learning. From approximately 500,000 participants from the UK Biobank, 1523 participants diagnosed with dementia after their baseline assessment visit were included in our study. An equal number of healthy participants were randomly selected as the control group by matching statistical age mean and sex distribution. This resulted in a total of 3046 participants being selected for our study; 2740 participants from 19 of the 22 UK Biobank assessment centers were used for internal validation, and 306 participants from the remaining three centers were selected for external validation. We include data from the participants’ baseline visit and selected 128 low-cost exposome factors related to life course exposures that may be easily acquired through simple questionnaires. Subsequently, data imputation was performed to account for missing patient data. Two different predictive models were assessed for discriminating between participants that remained healthy and participants diagnosed with dementia after the baseline visit, i.e. (1) a classical logistic regression linear classifier and (2) a machine learning ensemble classifier based on XGBoost. We interpreted the results by estimating feature importance within the predictive models. Our results demonstrate that machine learning models based on exposome data can reliably identify individuals that will be diagnosed with dementia. The XGBoost based model outperforms logistic regression model, achieving a mean AUC of 0.88 in the external validation tests. We identified novel exposome factors that might be combined as potential markers for dementia, such as facial aging, the frequency of use of sun/ultraviolet light protection, and the length of mobile phone use. Finally, we propose a novel neurocognitive assessment test that could be used as an online tool to screen individuals at risk of dementia for enrolment in preventive interventions and future clinical trials.
- 24 February 2022
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 218, 106714
Characterization of motion patterns by a spatio-temporal saliency descriptor in cardiac cine MRI
- 24 February 2022
- Published by Elsevier in Computer Methods and Programs in Biomedicine
- Vol. 218, 106714
Characterization of motion patterns by a spatio-temporal saliency descriptor in cardiac cine MRI
- 3 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 25 (9) , 3541-3553
Left Ventricle Quantification Challenge: A Comprehensive Comparison and Evaluation of Segmentation and Regression for Mid-Ventricular Short-Axis Cardiac MR Data
Automatic quantification of the left ventricle (LV) from cardiac magnetic resonance (CMR) images plays an important role in making the diagnosis procedure efficient, reliable, and alleviating the laborious reading work for physicians. Considerable efforts have been devoted to LV quantification using different strategies that include segmentation-based (SG) methods and the recent direct regression (DR) methods. Although both SG and DR methods have obtained great success for the task, a systematic platform to benchmark them remains absent because of differences in label information during model learning. In this paper, we conducted an unbiased evaluation and comparison of cardiac LV quantification methods that were submitted to the Left Ventricle Quantification (LVQuan) challenge, which was held in conjunction with the Statistical Atlases and Computational Modeling of the Heart (STACOM) workshop at the MICCAI 2018. The challenge was targeted at the quantification of 1) areas of LV cavity and myocardium, 2) dimensions of the LV cavity, 3) regional wall thicknesses (RWT), and 4) the cardiac phase, from mid-ventricle short-axis CMR images. First, we constructed a public quantification dataset Cardiac-DIG with ground truth labels for both the myocardium mask and these quantification targets across the entire cardiac cycle. Then, the key techniques employed by each submission were described. Next, quantitative validation of these submissions were conducted with the constructed dataset. The evaluation results revealed that both SG and DR methods can offer good LV quantification performance, even though DR methods do not require densely labeled masks for supervision. Among the 12 submissions, the DR method LDAMT offered the best performance, with a mean estimation error of 301 mm 2 for the two areas, 2.15 mm for the cavity dimensions, 2.03 mm for RWTs, and a 9.5% error rate for the cardiac phase classification. Three of the SG methods also delivered comparable performances. Finally, we discussed the advantages and disadvantages of SG and DR methods, as well as the unsolved problems in automatic cardiac quantification for clinical practice applications.
- 3 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 25 (9) , 3541-3553
Left Ventricle Quantification Challenge: A Comprehensive Comparison and Evaluation of Segmentation and Regression for Mid-Ventricular Short-Axis Cardiac MR Data
Automatic quantification of the left ventricle (LV) from cardiac magnetic resonance (CMR) images plays an important role in making the diagnosis procedure efficient, reliable, and alleviating the laborious reading work for physicians. Considerable efforts have been devoted to LV quantification using different strategies that include segmentation-based (SG) methods and the recent direct regression (DR) methods. Although both SG and DR methods have obtained great success for the task, a systematic platform to benchmark them remains absent because of differences in label information during model learning. In this paper, we conducted an unbiased evaluation and comparison of cardiac LV quantification methods that were submitted to the Left Ventricle Quantification (LVQuan) challenge, which was held in conjunction with the Statistical Atlases and Computational Modeling of the Heart (STACOM) workshop at the MICCAI 2018. The challenge was targeted at the quantification of 1) areas of LV cavity and myocardium, 2) dimensions of the LV cavity, 3) regional wall thicknesses (RWT), and 4) the cardiac phase, from mid-ventricle short-axis CMR images. First, we constructed a public quantification dataset Cardiac-DIG with ground truth labels for both the myocardium mask and these quantification targets across the entire cardiac cycle. Then, the key techniques employed by each submission were described. Next, quantitative validation of these submissions were conducted with the constructed dataset. The evaluation results revealed that both SG and DR methods can offer good LV quantification performance, even though DR methods do not require densely labeled masks for supervision. Among the 12 submissions, the DR method LDAMT offered the best performance, with a mean estimation error of 301 mm 2 for the two areas, 2.15 mm for the cavity dimensions, 2.03 mm for RWTs, and a 9.5% error rate for the cardiac phase classification. Three of the SG methods also delivered comparable performances. Finally, we discussed the advantages and disadvantages of SG and DR methods, as well as the unsolved problems in automatic cardiac quantification for clinical practice applications.
- 11 November 2019
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 15 (2) , 277-285
Fusion of 3D real-time echocardiography and cine MRI using a saliency analysis
This paper presents a novel 3D multimodal registration strategy to fuse 3D real-time echocardiography images with cardiac cine MRI images. This alignment is performed in a saliency space, which is designed to maximize similarity between the two imaging modalities. This fusion improves the quality of the available information.
- 11 November 2019
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 15 (2) , 277-285
Fusion of 3D real-time echocardiography and cine MRI using a saliency analysis
This paper presents a novel 3D multimodal registration strategy to fuse 3D real-time echocardiography images with cardiac cine MRI images. This alignment is performed in a saliency space, which is designed to maximize similarity between the two imaging modalities. This fusion improves the quality of the available information.
- Open Access
- 1 March 2017
- Published by Universidad Nacional de Colombia in Revista de Salud Pública
- Vol. 19 (2) , 241-249
Modelo para el análisis de la mortalidad en Colombia 2000-2012
Objetivo Proponer y evaluar un modelo para el ajuste y predicción de la mortalidad en Colombia que permita analizar tendencias por edad, sexo, Departamento y causa.Metodología Los registros de defunciones no fetales fueron utilizados como fuente primaria de análisis. Estos datos se pre-procesaron recodificando las causas y redistribuyendo los códigos basura. El modelo de predicción se formuló como una aproximaciónlineal de un conjunto de variables de interés, en particular la población y el producto interno bruto departamental.Resultados Como caso particular de estudio se tomó la mortalidad de menores de 5 años, se observó una disminución sostenida a partir del año 2000 tanto a nivel nacional como departamental, con excepción de tres departamentos. La evaluación del poderpredictivo de la metodología propuesta se realizó ajustando el modelo con los datos de 2000 a 2011, la predicción para el 2012 fue comparada con la tasa observada, estos resultados muestran que el modelo es suficientemente confiable para la mayor parte de las combinaciones departamento-causa.Conclusiones La metodología y modelo propuesto tienen el potencial de convertirse en un instrumento que permita orientar las prioridades del gasto en salud utilizando algún tipo de evidencia.
- 1 March 2017
- Published by Universidad Nacional de Colombia in Revista de Salud Pública
- Vol. 19 (2) , 241-249
Open AccessModelo para el análisis de la mortalidad en Colombia 2000-2012
Objetivo Proponer y evaluar un modelo para el ajuste y predicción de la mortalidad en Colombia que permita analizar tendencias por edad, sexo, Departamento y causa.Metodología Los registros de defunciones no fetales fueron utilizados como fuente primaria de análisis. Estos datos se pre-procesaron recodificando las causas y redistribuyendo los códigos basura. El modelo de predicción se formuló como una aproximaciónlineal de un conjunto de variables de interés, en particular la población y el producto interno bruto departamental.Resultados Como caso particular de estudio se tomó la mortalidad de menores de 5 años, se observó una disminución sostenida a partir del año 2000 tanto a nivel nacional como departamental, con excepción de tres departamentos. La evaluación del poderpredictivo de la metodología propuesta se realizó ajustando el modelo con los datos de 2000 a 2011, la predicción para el 2012 fue comparada con la tasa observada, estos resultados muestran que el modelo es suficientemente confiable para la mayor parte de las combinaciones departamento-causa.Conclusiones La metodología y modelo propuesto tienen el potencial de convertirse en un instrumento que permita orientar las prioridades del gasto en salud utilizando algún tipo de evidencia.