Cristina Antón-Maldonado

Mrs. Cristina Antón-Maldonado


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
29 July 2025 in Electronics
Verified
Journal Article
Open access
PDF file
Amparo SantamariaAmparo Santamaria
Amparo Santamaria
MPMarcos Alfaro Pérez
Marcos Alfaro Pérez
CACristina Antón-Maldonado
Cristina Antón-Maldonado
BSBeatriz Sánchez-Quiñones
Beatriz Sánchez-Quiñones
NINataly Ibarra
Nataly Ibarra
Luis PayáLuis Payá
Luis Payá
Monoclonal Gammopathy of Undetermined Significance (MGUS) is a precursor to hematologic malignancies such as Multiple Myeloma (MM) and Waldenström Macroglobulinemia (WM). Accurate risk stratification of MGUS patients remains a clinical and computational challenge, with existing models often misclassifying both high-risk and low-risk individuals, leading to inefficient healthcare resource allocation. This study presents a machine learning (ML)-based approach for early prediction of MM/WM progression, using routinely collected hematological data, which are selected based on clinical relevance. A retrospective cohort of 292 MGUS patients, including 7 who progressed to malignancy, was analyzed. For each patient, a feature descriptor was constructed incorporating the latest biomarker values, their temporal trends over the previous year, age, and immunoglobulin subtype. To address the inherent class imbalance, data augmentation techniques were applied. Multiple ML classifiers were evaluated, with the Support Vector Machine (SVM) achieving the highest performance (94.3% accuracy and F1-score). The model demonstrates that a compact set of clinically relevant features can yield robust predictive performance. These findings highlight the potential of ML-driven decision-support systems in electronic health applications, offering a scalable solution for improving MGUS risk stratification, optimizing clinical workflows, and enabling earlier interventions.

14 January 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
Amparo SantamariaAmparo Santamaria
Amparo Santamaria
CACristina Antón-Maldonado
Cristina Antón-Maldonado
NINataly Ibarra
Nataly Ibarra
MLMaria Fernández López
Maria Fernández López
PGPedro González
Pedro González
RCRafael Carrasco
Rafael Carrasco
Background: Atrial fibrillation (AF) is independently associated with cognitive impairment and dementia through mechanisms extending far beyond traditional cardioembolic stroke risk. However, the relative contribution of distinct pathophysiological pathways and the efficacy of emerging therapeutic interventions for cognitive protection remain incompletely characterized. Objectives: This comprehensive review synthesizes current evidence on the epidemiology, pathophysiological mechanisms, therapeutic interventions (pharmacological, rhythm-control, and digital health), and research priorities addressing the AF–dementia relationship. Methods: A narrative review integrating evidence from observational studies, mechanistic research, randomized controlled trials, systematic reviews, and meta-analyses published through January 2026. Literature sources included MEDLINE/PubMed, major cardiology and neurology journals, and expert consensus statements. Searches used combinations of keywords: "atrial fibrillation," "cognitive decline," "dementia," "silent cerebral infarction," "cerebral hypoperfusion," "direct oral anticoagulants," "catheter ablation," and "digital health." Inclusion criteria encompassed studies examining the AF–cognition association, mechanistic pathways, therapeutic interventions with cognitive outcomes, and digital health technologies in AF management. Heterogeneous study designs prevented quantitative meta-analysis; qualitative synthesis focused on effect sizes, strength of evidence, and clinical implications. Results: Strong epidemiological evidence demonstrates that AF increases relative risk of dementia by 1.4–2.2 fold independently of clinical stroke, with silent cerebral infarction present in 25–40% of AF patients. Multiple interacting pathophysiological mechanisms account for AF-associated cognitive decline: cerebral microembolism (meta-analysis: OR 2.30 for silent infarction on MRI), chronic cerebral hypoperfusion (15–20% reduction in total cerebral blood flow in persistent AF), neuroinflammation, cerebral small vessel disease, and structural brain atrophy. Emerging therapeutic strategies offer complementary neuroprotective mechanisms: direct oral anticoagulants (DOACs)—particularly apixaban and rivaroxaban—reduce dementia risk by approximately 30% compared to warfarin (RR 0.69); rhythm control strategies and catheter ablation demonstrate dementia risk reduction (HR 0.52–0.69); and comprehensive digital health platforms implementing the ABC pathway reduce adverse cardiovascular events by 61% while optimizing adherence and enabling early AF detection. However, evidence-specific to cognitive endpoints remains limited, with the landmark BRAIN-AF trial showing no benefit of low-dose rivaroxaban in low-stroke-risk AF patients—suggesting that non-embolic mechanisms predominate in this population. Conclusions: AF represents a multifaceted threat to brain health requiring a paradigm shift from isolated stroke prevention toward comprehensive heart–brain health optimization. Integration of pharmacological neuroprotection (preferring DOACs), hemodynamic optimization (rhythm control in selected patients), cardiovascular risk factor management, and digital health technologies provides unprecedented opportunity for cognitive preservation. However, critical knowledge gaps persist regarding AF burden thresholds, the relative contribution of competing pathophysiological mechanisms, optimal anticoagulation strategies in low-risk populations, and the long-term cognitive benefits of emerging digital technologies. Prospective randomized clinical trials with cognitive impairment as a primary endpoint, serial neuroimaging, and diverse population representation are urgently needed to validate preventive strategies and refine therapeutic decision-making.

25 February 2026 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
Amparo SantamariaAmparo Santamaria
Amparo Santamaria
CACristina Antón-Maldonado
Cristina Antón-Maldonado
NINataly Ibarra
Nataly Ibarra
MLMaria Fernández López
Maria Fernández López
PGPedro González
Pedro González
RCRafael Carrasco
Rafael Carrasco
Background: Atrial fibrillation (AF) is consistently associated with cognitive impairment and dementia through mechanisms that extend beyond classical cardioembolic stroke. However, the relative contribution of these pathways and the effectiveness of available therapeutic strategies for preserving cognition remain uncertain, as most data come from observational studies with a substantial risk of bias. Objectives: This review narratively synthesizes contemporary evidence on epidemiology, pathophysiological mechanisms, therapeutic strategies—including anticoagulation, rhythm control, and comprehensive risk-factor management—and the role of digital health technologies in the relationship between AF and cognitive decline. Methods: We performed a narrative, PRISMA-informed scoping review of observational cohorts, mechanistic studies, randomized clinical trials, systematic reviews, and meta-analyses published up to January 2026, identified through structured searches in MEDLINE/PubMed and complementary sources. Studies were selected if they examined (i) associations between AF and cognitive impairment or dementia, (ii) mechanistic pathways linking AF to brain injury, (iii) therapeutic interventions with cognitive or brain imaging outcomes, or (iv) digital health technologies applied to AF management. Heterogeneity in study design and outcome assessment precluded meta-analysis; therefore, we provide a qualitative synthesis, explicitly distinguishing observational evidence from randomized data and discussing key sources of confounding. Risk of bias was evaluated using validated tools: ROBINS-I for non-randomized studies, RoB 2.0 for RCTs, Newcastle–Ottawa Scale for observational cohorts, and AMSTAR-2 for systematic reviews. Results: Large population-based cohorts and meta-analyses indicate that AF is associated with a 1.4–2.2-fold higher risk of cognitive impairment or incident dementia, even after adjustment for shared vascular risk factors and exclusion of patients with prior stroke; nevertheless, residual confounding and selection bias cannot be excluded. Silent cerebral infarcts are detected in roughly one-quarter to two-fifths of AF patients without clinical stroke and are themselves associated with cognitive deficits, suggesting that subclinical embolism represents one important, but not exclusive, pathway. Additional mechanisms include chronic cerebral hypoperfusion, neuroinflammation, small vessel disease, and structural brain atrophy, all of which are incompletely disentangled from comorbidities. Observational data suggest that oral anticoagulation, particularly with direct oral anticoagulants (DOACs), is associated with lower rates of dementia compared with no anticoagulation or warfarin, but randomized trials such as BRAIN-AF and GIRAF have not demonstrated a clear cognitive benefit, underlining the low-to-moderate certainty of this evidence. Rhythm-control interventions, especially catheter ablation, are associated with lower dementia incidence in registry studies, yet strong selection effects and short follow-up limit causal inference. Digital health tools and ABC-pathway mobile applications improve cardiovascular outcomes and adherence, although cognitive endpoints remain largely unexplored. Conclusions: AF should be conceptualized as a neurovascular condition with important implications for brain health, rather than a purely cardiac rhythm disorder confined to stroke prevention. A comprehensive heart–brain management strategy that combines optimal anticoagulation, individualized rhythm control, aggressive vascular risk factor modification, routine cognitive screening in older or high-risk patients, and judicious use of digital health technologies may offer the best opportunity for preserving cognition, although rigorous trials with cognitive endpoints are still needed to establish causality.

27 April 2025 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
Amparo SantamariaAmparo Santamaria
Amparo Santamaria
CACristina Antón-Maldonado
Cristina Antón-Maldonado
BSBeatriz Sánchez-Quiñones
Beatriz Sánchez-Quiñones
NVNataly Ibarra Vega
Nataly Ibarra Vega
PGPedro González
Pedro González
RCRafael Carrasco
Rafael Carrasco
Background: The aim of this study was to evaluate, for the first time, the feasibility of implementing LOLA, a speech-AI-driven conversational assistant, in monitoring and managing OAT for patients with non-valvular atrial fibrillation (AF). Methods: In 2023, we conducted a pilot prospective observational study of patients with non-valvular atrial fibrillation (AF) and TAO. All patients received a first-contact call from LOLATAO and then monthly calls following a protocol predefined by haematologists. At the end of the study, a satisfaction questionnaire was carried out. Results: Of the fifty patients, the mean age was 75 years, and 33% were women. One-third of the patients (n = 16) were receiving antivitamin K treatment, and two-thirds (33) DOACs. A total of 579 calls were made with a median follow-up of 278 days. LOLATAO had high rates of acceptability (85%), adherence (90%), and satisfaction (>95%). A total of 42% of the patients reported at least one missed dose within the last month, and 18% reported having a scheduled intervention requiring bridging therapy. In patients with AVKs, 94% (n = 15) reported being unaware of their TRT at least once, and 75% (n = 12) of patients reported having a TRT < 65%. Those patients in whom the TRT was <65% were switched to DOACs. LOLATAO saved a total of 10 h per month for haematologists during follow-up. Conclusions: This study suggests that LOLATAO can be a helpful tool in the management of chronic follow-up of patients with AF and undergoing OAT, reducing the burden of care and with high rates of acceptance and satisfaction by patients.

10 March 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
ASAmparo Santamaria
Amparo Santamaria
CACristina Antón-Maldonado
Cristina Antón-Maldonado
BSBeatriz Sánchez-Quiñones
Beatriz Sánchez-Quiñones
NVNataly Ibarra Vega
Nataly Ibarra Vega
PGPedro Gónzalez
Pedro Gónzalez
RCRafael Carrasco
Rafael Carrasco
The aim of this study was to evaluate for the first time the feasibility of implementing LOLA, a speech AI-driven conversational assistant, in monitoring and managing OAT in patients with non-valvular Methods. In 2023, we conducted a pilot prospective observational study of patients with AF and TAO. All patients received a first contact call from LOLATAO, and then monthly calls, following a predefined protocol by the hematologists . At the end of the study, a satisfaction questionnaire was carried out. Results Fifty patient. The mean age was 75 years with 33% women. One-third of the patients (n=16) were with antivitamin K treatment and two-thirds (33) with DOACs. A total of 579 calls were made with a median follow-up of 278 days. LOLATAO had high rates of acceptability (85%), adherence (90%) and satisfaction (>95%). 42% of the patients reported at least one forgetfulness dose in the last month, 18% ( reported having a scheduled intervention needing bridging therapy. In patients with VKAs , 94% (n=15) reported at least once being unaware of their TRT and, 75% (n=12) of patients reported having a TRT< 65%. Those patients in whom TRT was < 65% were switched to DOACs. LOLA saved a total of 10 hours per month for the hematologists in the follow-up. Conclusions The study suggests that LOLATAO seems to be a tool to help in the management of chronic follow-up of patients with AF and OAT that reduces the burden of care with high rates of acceptance and satisfaction by patients.