Alberto Díaz Cáceres

Alberto Díaz Cáceres

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
19 February 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
PMPablo Caballero María
Pablo Caballero María
JCJavier Caballero-Villarraso
Javier Caballero-Villarraso
JAJavier Arenas-Montes
Javier Arenas-Montes
ACAlberto Díaz Cáceres
Alberto Díaz Cáceres
SNSofía Castañeda Nieto
Sofía Castañeda Nieto
ACAntonio Camargo
Antonio Camargo
Type 2 diabetes mellitus (T2DM) is a chronic metabolic disease. Gut microbiota plays a key role in metabolic homeostasis and the development of T2DM and its complications. With the advance of artificial intelligence (AI), it is possible to develop novel models based on machine learning (ML) that can predict the risk of developing certain diseases and facilitate their early diagnosis, or even take preventive measures in advance. This can be the case of T2DM, for example. Our objective was to develop a predictive model of the risk of developing T2DM based on clinical, biochemical, and intestinal microbiota parameters, which estimates the time margin for developing this disease. To this end, a Deep Learning Multilayer Perceptron (MLP) algorithm was developed and trained with data from real patients from a current large population epidemiological study. The data were normalised and augmented to increase their diversity and avoid overfitting. The neural network developed was optimised, and the best hyperparameters were chosen for model building by Bayesian optimisation. We succeeded in getting the model to return a numerical result corresponding to the number of months it will take for a particular individual to develop T2DM with an accuracy of 95.2%.

13 March 2025 in Journal of the American Heart Association
Verified
Journal Article
Open access
EPEsther Porras‐Pérez
Esther Porras‐Pérez
JRJuan Luis Romero-Cabrera
Juan Luis Romero-Cabrera
ACAlberto Díaz Cáceres
Alberto Díaz Cáceres
ASAlejandro Serrán‐Jiménez
Alejandro Serrán‐Jiménez
JAJavier Arenas-Montes
Javier Arenas-Montes
PPPABLO PEREZ-MARTINEZ
PABLO PEREZ-MARTINEZ
Background: Food insecurity is linked to poorer cardiovascular health (CVH) outcomes, particularly in underresourced communities, where social determinants of health play a critical role. Despite the recognized connections, there remains a lack of empirical evidence delineating the implications of food insecurity on CVH. CVH, a broader concept than cardiovascular disease, encompasses the overall well‐being of the cardiovascular system and is supported by favorable lifestyle choices and physiological metrics. Particularly in underresourced communities, the study of CVH could provide valuable insights for early intervention and targeted public health initiatives. This study aimed to fill this knowledge gap. Methods and Results: We conducted a cross‐sectional analysis of baseline data from the E‐DUCASS (Educational Strategy on a Vulnerable Population to Improve Cardiovascular Health and Food Insecurity) program (NCT05379842), a 24‐month randomized study targeting participants at risk for food insecurity. CVH was assessed using the Life's Essential 8 score. The sample included 451 participants aged 12 to 80 years, stratified by age (30.6% children [aged 12–19 years], 35.9% young adults [aged 20–39 years], and 33.5% adults [aged 40–80 years]) and sex (42.1% men and 57.9% women). The mean CVH score was 65.1 (95% CI, 63.9–66.4), with diet, physical activity, nicotine exposure, and body mass index being the lowest‐scoring metrics. Food insecurity significantly influenced CVH; those participants with severe food insecurity had lower CVH scores than those without (effect size, −2.83 [95% CI, −5.10 to −0.56]; P <0.05). Conclusions: Our findings highlight the negative association between food insecurity and CVH in underresourced Mediterranean communities. These results underscore the need for strategies aimed at reducing cardiovascular risk, potentially through health literacy programs like E‐DUCASS, that focus on improving lifestyle and alleviating food insecurity. Registration: URL: https://www.clinicaltrials.gov ; Unique Identifier: NCT05379842.

16 March 2022 in Spanish Journal of Medicine
Verified
Journal Article
Open access
JRJuan Luis Romero-Cabrera
Juan Luis Romero-Cabrera
IDIsabel De-Castro-Burón
Isabel De-Castro-Burón
EYElena Yubero-Serrano
Elena Yubero-Serrano
ACAlberto Díaz Cáceres
Alberto Díaz Cáceres
ASAlejandro Serrán-Jiménez
Alejandro Serrán-Jiménez
PPPABLO PEREZ-MARTINEZ
PABLO PEREZ-MARTINEZ

6 November 2025 in medRxiv
Verified
Preprint
Open access
PDF file
RMRafael M. Molero-Payan
Rafael M. Molero-Payan
OROriol Alberto Rangel-Zuñiga
Oriol Alberto Rangel-Zuñiga
ACAlberto Díaz Cáceres
Alberto Díaz Cáceres
OMOvidio Muñiz-Grijalvo
Ovidio Muñiz-Grijalvo
JDJose luis Díaz Díaz
Jose luis Díaz Díaz
FJFRANCISCO FUENTES JIMENEZ
FRANCISCO FUENTES JIMENEZ
Background: Familial hypercholesterolemia (FH) is an autosomal dominant disorder associated with a markedly increased risk of premature atherosclerotic cardiovascular disease (ASCVD). Genetic and molecular factors, including microRNAs (miRNAs), may serve as biomarkers to improve disease risk prediction. miRNAs are key regulators of biological processes involved in cardiovascular pathology. This study aimed to identify miRNAs that, combined with clinical variables, enhance ASCVD prediction in asymptomatic FH patients from the SAFEHEART cohort. Methods: A total of 400 subjects diagnosed with FH were included. Coronary calcium score (Agatston score) was measured by computed tomography and stratified into three risk categories (0–99, 100–299, >300). Circulating plasma miRNA levels were quantified using the OpenArray platform. Statistical analyses characterized baseline features and assessed predictive performance using ROC curve analysis. Functional enrichment was explored through the MIENTURNET database. Results: Individuals carrying the null allele for the LDL-R gene showed significantly higher plasma miR-1 levels than those carrying the defective allele (p=0.042). Likewise, subjects with an Agatston score of 0–99 exhibited higher miR-1 levels than those with scores >300 (p=0.025). A predictive model based on clinical variables including age, sex, hypertension, smoking, BMI, LDL burden, and lipoprotein(a) achieved an AUC of 0.846 for ASCVD prediction. Incorporating miR-1 increased the AUC to 0.878, representing a statistically significant improvement (DeLong test, p=0.005). Conclusions: miR-1 emerged as a promising biomarker for ASCVD risk prediction in FH patients. When integrated with conventional clinical variables, miR-1 improved the model’s predictive accuracy. These findings suggest that miR-1 could serve as a useful molecular marker for enhanced cardiovascular risk stratification in asymptomatic individuals with familial hypercholesterolemia.