Juan Miguel Mira-Tomas

Mr. Juan Miguel Mira-Tomas

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
11 October 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
LGLorena Gallego-Viñarás
Lorena Gallego-Viñarás
Juan Miguel Mira-TomasJuan Miguel Mira-Tomas
Juan Miguel Mira-Tomas
AGAnna Michela Gaeta
Anna Michela Gaeta
GPGerard Pinol-Ripoll
Gerard Pinol-Ripoll
FBFerran Barbé
Ferran Barbé
AMArrate Muñoz-Barrutia
Arrate Muñoz-Barrutia
Alzheimer's disease (AD) and sleep disorders exhibit a close association, where disruptions in sleep patterns often precede the onset of Mild Cognitive Impairment (MCI) and early-stage AD. This study delves into the potential of utilizing sleep-related electroencephalography (EEG) signals acquired through polysomnography (PSG) for the early detection of AD. Our primary focus is on exploring semi-supervised Deep Learning techniques for the classification of EEG signals due to the clinical scenario characterized by the limited data availability. The methodology entails testing and comparing the performance of semi-supervised models, benchmarked against an unsupervised and a supervised model. The study highlights the significance of spatial and temporal analysis capabilities, conducting independent analyses of each sleep stage. Results demonstrate the effectiveness of one semi-supervised model in leveraging limited labeled data, achieving stable metrics across all sleep stages, and reaching 90% accuracy in its supervised form. Comparative analyses reveal this superior performance over the unsupervised model, while the supervised model ranges between $92-94\%$ . These findings underscore the potential of semi-supervised models in early AD detection, particularly in overcoming the challenges associated with the scarcity of labeled data. Ablation tests affirm the critical role of spatio-temporal feature extraction in semi-supervised predictive performance, and t-SNE visualizations validate the model's proficiency in distinguishing AD patterns. Overall, this research contributes to the advancement of AD detection through innovative Deep Learning approaches, highlighting the crucial role of semi-supervised learning in addressing data limitations.

24 July 2023 in Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Verified
Conference Paper
Closed access
MAMonica Albaladejo-Belmonte
Monica Albaladejo-Belmonte
PVPaula Villa-Muñoz
Paula Villa-Muñoz
FNFrancisco J. Nohales-Alfonso
Francisco J. Nohales-Alfonso
RMRogelio Monfort-Ortiz
Rogelio Monfort-Ortiz
Juan Miguel Mira-TomasJuan Miguel Mira-Tomas
Juan Miguel Mira-Tomas
JGJavier Garcia-Casado
Javier Garcia-Casado
Vestibulodynia is a gynecological condition with different treatment options available, including botulinum neurotoxin type A (BoNT/A) injections into the vulvar vestibule. Unlike other treatments, no studies have assessed changes in the myoelectrical activity of the pelvic floor muscles (PFM) after BoNT/A treatment. The aim of this study was thus to evaluate these changes and to correlate them with changes in vulvar pain sensitivity. To do this, 35 patients with vestibulodynia were recruited, the myoelectrical activity of their left and right PFM was recorded with surface electromyography (sEMG), and their vulvar pain sensitivity was monitored according to Visual Analogue Scale (VAS) and an algometer, both before and after BoNT/A treatment. According to our results, patients’ signals during PFM relaxation showed a significantly higher power than those of healthy women at baseline, as shown by their root mean square values (RMS), but became similar at follow-up. Patients’ mean vulvar pain VAS scores significantly decreased after treatment. Furthermore, baseline-to-follow-up differences of RMS at PFM rest vs. mean VAS were significantly correlated (CC=0.48, p<0.01) so that higher reductions in the PFM activity power were associated with higher decreases in vulvar pain.Clinical Relevance— Altered PFM electrophysiological condition of patients with vestibulodynia becomes similar to healthy women’s after BoNT/A treatment. This study also points to a relationship between the evolution of clinical and PFM electrophysiological conditions

24 November 2025 in Acta Obstetricia et Gynecologica Scandinavica
Verified
Journal Article
Open access
Jose Alberola-RubioJose Alberola-Rubio
Jose Alberola-Rubio
Juan Miguel Mira-TomasJuan Miguel Mira-Tomas
Juan Miguel Mira-Tomas
ADAlba Díaz
Alba Díaz
PFPilar Alama Faubel
Pilar Alama Faubel
SSSergio Caballero Sanz
Sergio Caballero Sanz
Javier Garcia-CasadoJavier Garcia-Casado
Javier Garcia-Casado
Introduction: The uterus exhibits dynamic peristaltic activity across the menstrual cycle, playing a critical role in reproductive processes such as sperm transport and embryo implantation. However, current imaging methods to assess this activity provide little information and are limited by subjectivity and lack of sensitivity. A recent pilot study has shown the potential of intracavitary electrohysterography (IC‐EHG) to study peristalsis in the uterine fundus. This study aimed to generalize previous results, compare peristalsis in other uterine regions, and study more peristaltic features. Material and Methods: This prospective multicenter cohort study included 40 healthy women with proven fertility. IC‐EHG signals were recorded from different uterine sites for 30 min during three menstrual phases: mid‐follicular (MF), early luteal (EL), and late luteal (LL) using a custom‐designed multipolar catheter. Primary outcomes: contraction frequency (CT/min) and amplitude (μV); secondary outcomes: basal amplitude, contraction time percentage, contractility index and local organization index. Statistical comparisons between phases and regions were performed using Wilcoxon signed‐rank tests. Results: A total of 95 fundal and 90 lower‐segment IC‐EHG recordings were analyzed. Contraction frequency peaked during the EL phase (fundus: 3.91 CT/min; lower segment: 4.01 CT/min) and was lowest during MF (fundus: 3.28 CT/min, p = 0.042; lower segment: 3.65 CT/min, p = 0.024). Fundal contraction amplitude decreased progressively from MF (16.27 μV) to LL phase (10.56 μV, p < 0.001). Basal amplitude, contraction time percentage and contractility index were also lowest in the LL phase for both uterine regions. Except for frequency, fundus peristaltic activity features were smaller than those of the lower segment, significantly during the MF phase. Local coordination index revealed lower local cell organization in the fundus across all phases, with maximum coordination during EL in both regions ( p < 0.01). Conclusions: IC‐EHG technique enables objective, reproducible, and quantitative assessment of multiple aspects of uterine peristalsis, revealing distinct regional and cycle‐phase–dependent patterns. The decline in most contractile features during the LL phase supports the physiological uterine quiescence required for embryo implantation. The uterine fundus is more active during the MF phase. This study provided reference values for healthy, fertile conditions and could inform further investigation of alterations due to disorders or intervention strategies.

20 May 2026 in Computer Methods and Programs in Biomedicine
Verified
Journal Article
Open access
Juan Miguel Mira-TomasJuan Miguel Mira-Tomas
Juan Miguel Mira-Tomas
ADAlba Díaz
Alba Díaz
JAJose Alberola-Rubio
Jose Alberola-Rubio
JLJoaquín Llacer
Joaquín Llacer
GCGemma Castillón
Gemma Castillón
Javier Garcia-CasadoJavier Garcia-Casado
Javier Garcia-Casado
Uterine peristalsis, the rhythmic contractions of the inner layer of the myometrium during the menstrual cycle, is more challenging to identify than potent contractions during menstruation, pregnancy, or childbirth. Peristalsis plays a significant role in sperm ascension and embryo implantation, making its study valuable for fertility research. Intracavitary Electrohysterography (IC-EHG) is a promising technique for the electrophysiological assessment of uterine activity, but identifying basal, contraction, and artifact segments is a task currently performed by experts consuming substantial time, and is affected by the expert's subjectivity. This study aims to develop a deep learning model to aid clinicians in this segmentation task. A total of 306 IC-EHG signals, amounting to a total duration of 9318 min, were collected from three different clinical centers. The model architecture, based on a modified version of the U-Time model, was evaluated using event-oriented evaluation performance metrics (accuracy, recall, precision, and F1-score), episode-oriented evaluation performance metrics (Margin Validation Test, including full detection, partial detection, false detection, non-detection, and others), and typical IC-EHG contraction parameters for signal characterization (root mean square amplitude, contraction frequency, and duration). Event-oriented evaluation performance metrics results indicate accurate classification of basal, contraction, and artifact classes (mean F1-score (%): 94.6, 92.3, and 92.3, respectively). Episode-oriented evaluation performance metric results underscore model's ability to detect consistent events (basal (full + partial detection:) 88.9 + 7.3%, contraction: 84.9 + 7.7%, and artifact: 75.3 + 16.8%). Uterine peristalsis parameters derived from IC-EHG contraction events exhibited low mean absolute errors between manual and model-based segmentations: contraction frequency (4.9%), root mean square (2.8%), and duration (6.8%), along with high agreement between both approaches (ICC ≥ 0.92). The findings underscore the model's reliability and robustness. The developed deep learning-based model offers significant clinical value by not only saving time in the challenging task of uterine peristalsis segmentation but also reducing expert variability. The developed automatic annotation system has the potential to serve as a valuable instrument in the context of infertility and associated pathologies.

23 November 2022
Verified
Conference Paper
Closed access
MAMónica Albaladejo-Belmonte
Mónica Albaladejo-Belmonte
Juan Miguel Mira-TomasJuan Miguel Mira-Tomas
Juan Miguel Mira-Tomas
PMPaula- Villa- Muñoz
Paula- Villa- Muñoz
FNFrancisco José Nohales-Alfonso
Francisco José Nohales-Alfonso
EGEnrique Domingo Guijarro-Estellés
Enrique Domingo Guijarro-Estellés
FGFrancisco Javier Garcia-Casado
Francisco Javier Garcia-Casado