Pasar al contenido principal

ALGORITMOS DE APRENDIZAJE AUTOMATICO DE NUEVA GENERACION PARA EL ANALISIS DE REGISTROS MEDICOS DEL SUEÑO

PID2023-147422OB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2023
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDADE DA CORUÑA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 10
Encontrada(s) 1 página(s)

RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Quantum Fuzzy Inference Systems: Implementation and a Case Study on Sleep Apnea Detection

  • Magaz-Romero, Samuel
  • Mosqueira-Rey, Eduardo
  • Álvarez-Estévez, Diego
  • Moret-Bonillo, Vicente
Presented at: PRICAI 2025 Workshop on Quantum Computing for Search and Optimization Problems (QCSOP25). Wellington, New Zealand, November 17, 2025., [Abstract]: Fuzzy Inference Systems (FIS) are a powerful tool for problems whose domain can be formally defined thanks to extracting knowledge from experts. These systems provide certain capabilities that current trend technologies do not, but its use has decreased in the past years due to the popularity of Machine Learning methods. In this paper, we revisit FIS through the perspective of Quantum Computing, an approach to make this model more powerful, thanks to superposition and entanglement. We present a new method for implementing FIS with quantum circuits, named Quantum Fuzzy Inference Systems, providing the definitions for the logical operators and implication. We propose a practical application in sleep medicine diagnosis, more specifically for the detection of apneic events. Our results show that we are able to replicate the behavior of the classical model using the quantum proposal, up to a similarity of 99.97%. We conclude on the contribution of this work towards the development of hybrid algorithms and uncertainty management, and pose some possible lines of future work on extending the inference process and its optimization., This work is supported by project PID2023-147422OB-I00, funded by MCIU/AEI/10.13039/501100011033 and by the European Regional Development Fund (ERDF) program, and by the Xunta de Galicia (Grant ED431C 2022/44), supported by ERDF. CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia. Additionally, it is co-financed by the EU through the ERDF Galicia 2021-27 operational program (Ref. ED431G 2023/01). SMR has received funding from Xunta de Galicia (grant ED481A 2023/008). DAE has also received support from project RYC2022-038121-I, funded by MCIN/AEI/10.13039/501100011033 and European Social Fund Plus (ESF+), and project ED431F 2025/35 from Xunta de Galicia., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2023/01, Xunta de Galicia; ED481A 2023/008, Xunta de Galicia; ED431F 2025/35
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Application of Transformers for Sleep Stage Classification

  • Vázquez Lema, David
  • Álvarez-Estévez, Diego
  • Mosqueira-Rey, Eduardo
Presentado en: VIII Congreso Xove TIC: impulsando el talento científico. Octubre, 2025, A Coruña., [Abstract] Transformer architectures have revolutionized the field of artificial intelligence. This work investigates the application of Transformers to the sleep stage classification problem. Despite promising results in recent studies, the clinical application of these methods remains limited. In this paper, we propose a novel model that replaces the LSTM component of a state-of-the-art CNN+LSTM architecture with a Transformer encoder, comparing its performance against our baseline and several state-of-the-art models. The results showed faster convergence, reduced complexity, and enhanced performance. Leveraging the Transformer architecture, we propose and investigate an interpretability method based on attention mechanisms. Finally, we evaluate the inter-database generalization performance of our model., This work has been supported by project PID2023-147422OB-I00, funded by MCIU/AEI/10.13039/501100011033 and by the European Regional Development Fund (ERDF) program, and by the Xunta de Galicia (Grant ED431C 2022/44), supported by ERDF. CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia. Additionally, it is co-financed by the EU through the ERDF Galicia 2021-27 operational program (Ref. ED431G 2023/01). SMR has received funding from Xunta de Galicia (grant ED481A 2023/008). DAE has also received support from project RYC2022-038121-I, funded by MCIN/AEI/10.13039/501100011033 and European Social Fund Plus (ESF+), and project ED431F 2025/35 from Xunta de Galicia., Xunta de Galicia; ED481A 2023/008, Xunta de Galicia; ED431F 2025/35, Xunta de Galicia; ED431G 2023/01, Xunta de Galicia; ED431C 2022/44
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Evaluating Explanatory Capabilities of Machine Learning Models in Medical Diagnostics: A Human-in-the-Loop Approach

  • Bobes-Bascarán, José
  • Mosqueira-Rey, Eduardo
  • Fernández-Leal, Ángel
  • Alonso Ríos, David
  • Figueirido Arnoso, Israel
  • Vidal-Ínsua, Yolanda
The results published here are in whole or part based upon data generated by the TCGA Research Network: https://www.cancer.gov/tcga, accessed on 5 January 2024., [Abstract]: This paper presents a broad study on the evaluation of explanatory capabilities of machine learning models, with a focus on Decision Trees, Random Forest, and XGBoost using a pancreatic cancer data set. We use Human-in-the-Loop-related techniques and medical guidelines as a source of domain knowledge to establish the importance of the different features that are relevant to select a pancreatic cancer treatment. These features are not only used as a dimensionality reduction approach for the machine learning models but also as a way to evaluate the explainability capabilities of the different models using agnostic and non-agnostic explainability techniques. To facilitate the interpretation of explanatory results, we propose the use of similarity measures such as the Weighted Jaccard Similarity coefficient. The goal is to select not only the best performing model but also the one that can best explain its conclusions and better aligns with human domain knowledge., This work has been supported by the State Research Agency of the Spanish Government (Grant PID2019-107194GB-I00/AEI/10.13039/501100011033 and Grant PID2023-147422OB-I00) and by the Xunta de Galicia (Grant ED431C 2022/44), supported by the EU European Regional Development Fund (ERDF). We wish to acknowledge support received from the Centro de Investigación de Galicia CITIC, funded by the Xunta de Galicia and ERDF (Grant ED431G 2023/01)., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Unified framework for implementing inaccurate knowledge in quantum symbolic artificial intelligence models

  • Mosqueira-Rey, Eduardo
  • Magaz-Romero, Samuel
  • Moret-Bonillo, Vicente
Trabajo presentado a: 17th International Conference on Agents and Artificial Intelligence, Porto, Portugal, 23-25 February 2025., [Abstract]; Symbolic models of Artificial Intelligence are based on defining declarative knowledge that is connected through procedural knowledge forming symbolic graphs through which reasoning flows. Both declarative and procedural knowledge can be inaccurate, which has led to the definition of different models to represent this inaccuracy. Since the functioning of quantum computers is inherently probabilistic, it has been proposed to take advantage of this nature to implement inaccurate knowledge more effectively. In this paper, we present different models for implementing inaccurate knowledge in quantum computers and propose a unified framework to represent and implement the common features of all of them., This work has been supported by the EU’s Horizon 2020 under project NEASQC (grant No 951821), the State Research Agency of the Spanish Government (Grant PID2023-147422OB-I00) and by the Xunta de Galicia (Grant ED431C 2022/44), supported by the EU European Regional Development Fund (ERDF). CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia. Additionally, it is co-financed by the EU through the FEDER Galicia 2021-27 operational program (Ref. ED431G 2023/01). We thank the support from Ministry for Digital Transformation and Civil Service and Next-GenerationEU/RRF (TSI-100925-2023-1). SMR has received funding from Xunta de Galicia (grant ED481A 2023/008)., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2023/01, Xunta de Galicia; ED481A 2023/008
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Benchmarking Quantum Machine Learning Kernel Training for Classification Tasks

  • Álvarez-Estévez, Diego
Data availability: Data and source code for the reproducibility of experimental procedures in this study are available at https://github.com/diegoalvareze/qkt_benchmarking ., [Abstract]: Quantum-enhanced machine learning is a rapidly evolving field that aims to leverage the unique properties of quantum mechanics to enhance classical machine learning. However, the practical applicability of these methods remains an open question, particularly beyond the context of specifically crafted toy problems, and given the current limitations of quantum hardware. This study focuses on quantum kernel methods in the context of classification tasks. In particular, it examines the performance of quantum kernel estimation and quantum kernel training (QKT) in connection with two quantum feature mappings, namely, ZZFeatureMap and CovariantFeatureMap. Remarkably, these feature maps have been proposed in the literature under the conjecture of possible near-term quantum advantage and have shown promising performance in ad hoc datasets. This study aims to evaluate their versatility and generalization capabilities in a more general benchmark, encompassing both artificial and established reference datasets. Classical machine learning methods, specifically support vector machines and logistic regression, are also incorporated as baseline comparisons. Experimental results indicate that quantum methods exhibit varying performance across different datasets. Despite outperforming classical methods in ad hoc datasets, mixed results are obtained for the general case among standard classical benchmarks. The experimental data call into question a general added value of applying QKT optimization, for which the additional computational cost does not necessarily translate into improved classification performance. Instead, it is suggested that a careful choice of the quantum feature map in connection with proper hyperparameterization may prove more effective., This work was supported in part by the MCIN/AEI/10.13039/501100011033 and the European Social Fund Plus (ESF+) under Project RYC2022-038121-I and in part by the MCIU/AEI/10.13039/501100011033 and the European FEDER program under Project PID2023-147422OB-I00.
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Multi-Task Deep-Learning for Sleep Event Detection and Stage Classification

  • Anido Alonso, Adriana
  • Álvarez-Estévez, Diego
This version of the paper has been accepted for publication. The final published paper is available online at: https://doi.org/10.1109/CIHMCompanion65205.2025.11002700. Presented at: 2025 IEEE Symposium on Computational Intelligence in Health and Medicine Companion (CIHM Companion), 17-20 March 2025, Trondheim, Norway., [Abstract]: Polysomnographic sleep analysis is the standard clinical method to accurately diagnose and treat sleep disorders. It is an intricate process which involves the manual identification, classification, and location of multiple sleep event patterns. This is complex, for which identification of different types of events involves focusing on different subsets of signals, resulting on an iterative time-consuming process entailing several visual analysis passes. In this paper we propose a multi-task deep-learning approach for the simultaneous detection of sleep events and hypnogram construction in one single pass. Taking as reference state-of-the-art methodology for object-detection in the field of Computer Vision, we reformulate the problem for the analysis of multi-variate time sequences, and more specifically for pattern detection in the sleep analysis scenario. We inves-tigate the performance of the resulting method in identifying different assembly combinations of EEG arousals, respiratory events (apneas and hypopneas) and sleep stages, also considering different input signal montage configurations. Furthermore, we evaluate our approach using two independent datasets, assessing true-generalization effects involving local and external validation scenarios. Based on our results, we analyze and discuss our method's capabilities and its potential wide-range applicability across different settings and datasets., This study has been supported by project RYC2022-038121-I, funded by MCIN/AEI/10.13039/501100011033 and European Social Fund Plus (ESF+) and project PID2023-147422OB-I00 funded by MCIU/AEI/10.13039/501100011033 and by the European FEDER program.
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Analysis of federated learning on non-independent and identically distributed sleep data

  • Anido Alonso, Adriana
  • Álvarez-Estévez, Diego
[Abstract]: Objective. We investigate the application of federated learning (FL) across heterogeneous, non-independent and identically distributed (non-IID) sleep data. We evaluate three algorithms-federated stochastic gradient descent, federated averaging, and federated proximal (FedProx)-in a realistic setting where non-IID characteristics arise from distinct sensor configurations, varying acquisition protocols, and diverse patient populations across independent sleep cohort datasets. Approach. We employ a dual-layered evaluation framework. First, we systematically analyze the impact of local training epochs and aggregation schemes (weighted and unweighted) on model convergence. Second, we introduce and adapt a generalized sub-sampling strategy designed to mitigate model drift caused by heterogeneous data distribution and volume imbalances across participating clients. To ensure robust external generalization, our evaluation utilizes six independent databases in a leave-one-database-out cross-validation scheme. Main results. Our analysis has evidenced that increasing the number of local training epochs adversely affects performance across all evaluated federated schemes. This confirms that extended local training exacerbates client drift, hindering global convergence. Furthermore, weighted aggregation consistently under-performs unweighted approaches, suggesting that disproportionate client contributions bias the global data representation. While the inclusion of a proximal term partially mitigates this instability by constraining local updates, the proposed sub-sampling strategy proves most effective. This approach yields consistent generalization results across all algorithms and minimizes performance downgrading, while significantly reducing computational overhead. Significance. This work addresses critical privacy concerns in centralized automated sleep staging by validating FL in realistic, multi-center scenarios. We provide evidence that decentralized strategies can achieve performance comparable to centralized methods, effectively overcoming data silos. Ultimately, this approach enables robust collaborative training while strictly maintaining data privacy-a fundamental requirement for widespread clinical implementation., This study has been supported by project RYC2022-038121-I, funded by MCIN/AEI/10.13 039/50110 0011033 and European Social Fund Plus (ESF+), project PID2023-147422OB-I00 funded by MCIU/AEI/10.13039/501100011033 and by the European FEDER program, and project ED431F 2025/35 funded by Xunta de Galicia. Authors wish to acknowledge the support received from Universidade da Coruña and Centro de Investigación de Galicia ‘CITIC’, center accredited for excellence within the Galician University System and a member of the CIGUS Network. CITIC receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia and it is co-financed by the EU through the FEDER Galicia 2021-27 operational program ED431G 2023/01. Furthermore, this research project was made possible through the access granted by the Galician Supercomputing Center (CESGA) to its supercomputing infrastructure. The supercomputer FinisTerrae III and its permanent data storage system have been funded by the NextGeneration EU 2021 Recovery, Transformation and Resilience Plan, ICT2021-006904, and also from the Pluriregional Operational Programme of Spain 2014-2020 of the European Regional Development Fund (ERDF), ICTS-2019-02-CESGA-3, and from the State Programme for the Promotion of Scientific and Technical Research of Excellence of the State Plan for Scientific and Technical Research and Innovation 2013-2016 State subprogramme for scientific and technical infrastructures and equipment of ERDF, CESG15-DE-3114, Xunta de Galicia; ED431F 2025/35, Xunta de Galicia; ED431G 2023/01, Xunta de Galicia; ICTS-2019-02-CESGA-3, Xunta de Galicia; CESG15-DE-3114
RUC. Repositorio da Universidade da Coruña
Publicación Tesis de maestría (MasterThesis)

Application of Transformers for Sleep Stage Classification

  • Vázquez Lema, David
[Abstract]: Transformer architectures have revolutionized the field of artificial intelligence in recent years. This work investigates the application of Transformers to sleep stage classification, a complex medical problem that remains an active area of research. Despite promising results in recent studies, the clinical application of these methods remains limited. In this paper, we propose a novel model that replaces the LSTM component of a state-of-the-art CNN+LSTM architecture with a Transformer encoder. We compare the performance of our proposed approach against our baseline and several successful state-of-the-art models. The results demonstrate several advantages for our proposed method, including faster convergence during training, reduced model complexity, and enhanced performance. Leveraging the Transformer architecture, we also propose and investigate an interpretability method based on attention score analysis. Finally, we evaluate the inter-database generalization performance of our proposed model using an external database., Project PID2023-147422OB-I00 funded by MCIU/AEI/10.13039/501100011033 and by European FEDER program, Traballo fin de mestrado (UDC.FIC). Intelixencia Artificial. Curso 2024/2025
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Segmentation, classification and interpretation of breast cancer medical images using human-in-the-loop machine learning

  • Vázquez Lema, David
  • Mosqueira-Rey, Eduardo
  • Hernández-Pereira, Elena
  • Fernández-Lozano, Carlos
  • Seara-Romera, Fernando
  • Pombo-Otero, Jorge
Data availability: The dataset analyzed during the current study is available in the TCGA repository, URL: https://portal.gdc.cancer.gov/projects/ TCGA-BRCA. The images analyzed during the current study is available in the TCIA repository, URL: https://www.cancerimagingarchive.net/collection/ tcga-brca/., This is an Accepted Manuscript. This version of the article has been accepted for publication, after peer review and is subject to Springer Nature’s AM terms of use (https://www.springernature.com/gp/open-science/policies/accepted-manuscript-terms), but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/s00521-024-10799-7 ., [Abstract]: This paper explores the application of Human-in-the-Loop (HITL) strategies in the training of machine learning models in the medical domain. In this case, a doctor-in-the-loop approach is proposed to leverage human expertise in dealing with large and complex data. Specifically, the paper deals with the use of Whole Slide Imaging (WSI) for the analysis and prediction of the genomic subtype of breast cancer. Three different tasks were developed: segmentation of histopathological images, classification of these images regarding the genomic subtype of the cancer, and finally, interpretation of the machine learning results. The involvement of a pathologist helped us to develop a better segmentation model trying to group areas to make it more useful for further diagnosis. Because the classification models underperformed due to the complexity of the problem and insufficient data for certain cancer types, we focus our efforts in using the feedback from the pathologist to enhance model interpretability through a HITL hyperparameter optimization process., Xunta de Galicia; ED431C 2022/44, This work has been supported by the State Research Agency of the Spanish Government (Grants PID2019-107194GBI00/ AEI/10.13039/501100011033 and Project PID2023-147422OB-I00) and by the Xunta de Galicia (Grant ED431C 2022/44), supported by the EU European Regional Development Fund (ERDF). We wish to acknowledge support received from the Centro de Investigación de Galicia CITIC, funded by the Xunta de Galicia and ERDF (Grant ED431C 2022/44). The results published here are in whole or part based upon data generated by the TCGA Research Network: https://www.cancer.gov/tcga .
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Quantum and Classical Kernels Applied to Classification of Unbalanced Datasets

  • Mondragón Sampedro, Fernando
  • Álvarez-Estévez, Diego
Presentado en: VIII Congreso Xove TIC: impulsando el talento científico. Octubre, 2025, A Coruña., [Abstract] This work investigates quantum kernel methods for classification on unbalanced datasets. The study considers the effect of techniques commonly used in classical machine learning, such as kernel centering and cost-sensitive learning, when applied to quantum models. Experiments are conducted on five datasets, including MNIST-1D, the real-world dataset Glass6, and synthetic datasets tailored for quantum classifiers. Results indicate that quantum kernel methods can address unbalanced classification tasks albeit none of the techniques studied showed a statistically significant improvement of the scoring metrics. Results also highlight the influence of hyperparameterization and in particular, quantum bandwidth is identified as a critical hyperparameter for the performance of quantum models., This study has been supported by project RYC2022-038121-I, funded by MCIN/AEI/10.13039/501100011033 and European Social Fund Plus (ESF+), project PID2023-147422OB-I00 funded by MCIU/AEI/10.13039/501100011033 and by the European FEDER program, and by project ED431F 2025/35 from Xunta de Galicia., Xunta de Galicia; ED431F 2025/35