This study aimed to develop and validate a machine learning-based model for predicting 30-day mortality in cardiac surgery patients and to implement a functional, clinician-oriented web application that enables the real-time use of the model. A retrospective cohort of 325 cardiac surgery patients was analysed using supervised machine learning. After preprocessing and clinical feature selection, several models were trained and evaluated through cross-validation. XGBoost achieved the best results, with an AUC-ROC of 0.968, recall of 0.800, and Brier score of 0.058. To facilitate clinical usability, a web-based application was developed using StreamLit, enabling clinicians to input patient data and predict mortality in real time. The application includes SHAP-based explainability for each prediction, thereby ensuring model transparency. Preliminary feedback from clinicians indicated that the tool was intuitive and informative and showed potential for preoperative risk assessment. The integration of a robust ML (machine learning) model with a functional clinical application offers a practical tool for supporting decision-making in cardiac surgery. This combined approach enhances both accuracy and accessibility, which are key to real-world impacts. Future work will involve multicentre validation and user-centred refinement.

Clinical anamnesis is a fundamental skill in medical education, allowing students to develop competencies in clinical information gathering, patient communication and diagnostic reasoning. Traditionally, teaching anamnesis has been based on interaction with real patients or simulated actors, which poses logistical challenges and access limitations. Generative artificial intelligence offers an innovative alternative for clinical interview simulation through autonomous training in an interactive digital environment. This study describes the design and development of Anamnesio_bot, a prototype chatbot based on Generative Artificial Intelligence designed for clinical anamnesis simulation in medical students. Its implementation was based on the integration of multiple sources of information, including a database of 2000 virtual patients generated with advanced language models, specific medical protocols, standardized clinical history structures and medical teaching principles. The chatbot was programmed to respond in a structured, realistic and concise manner to open-ended questions posed by students, ensuring consistency in the simulation of clinical cases. The development process focused on three key aspects: The generation of a large and diverse database of clinical cases; the optimization of the response algorithms by using predefined medical structures; and the implementation of automated feedback based on anamnesis evaluation criteria. This prototype will undergo evaluation in a real-world setting with students in the near future. However, its design suggests that it may be a useful tool for anamnesis practice in an accessible and flexible environment.

INTRODUCTION:Insider threats pose a critical risk in healthcare environments, where Hospital Information Systems (HIS) manage sensitive patients data. Authorized users may intentionally or accidentally compromise data confidentiality, integrity, and availability. This study assessed information security practices from the perspective of healthcare professionals in Spanish medical centers. METHODS:A descriptive, analytical, cross-sectional study was conducted using a survey administered to 41 healthcare professionals with access to confidential data. The survey covered access control, encryption at rest and in transit, communication channels, and data usage control. Descriptive statistics, Chi-square tests, and Cramér's V were applied to identify significant associations. K-means clustering and Silhouette coefficient were used to define user profiles. Principal Component Analysis (PCA) was used to visualize behavior patterns. A Random Forest model identified the most relevant predictive variables. RESULTS:Critical security gaps were detected, 31.7 % reported no control over data usage. Only 29.3 % encrypted data at rest and 36.6 % during transmission. Over 40 % used personal email or messaging apps to share sensitive data, and 97.6 % relied solely on passwords for authentication. These practices are inadequate to mitigate insider threats. CONCLUSION:There is an urgent need to strengthen insider data protection. Security strategies should be tailored to user risk profiles. Measures must include strong authentication, full encryption, and stricter control of data transmission to reduce exposure to insider threats (intentionally or unintentionally) in healthcare settings. Additionally, there is a need to promote continuous cybersecurity training.

Aims Despite their strong predictive performance, complex machine learning (ML) models are often criticized for their lack of interpretability, especially in high-stakes clinical settings. This study aims to compare two leading explainable artificial intelligence (XAI) methods—SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME)—when applied to a validated XGBoost model for 30-day mortality prediction after cardiac surgery. We explore their ability to provide transparent, clinically meaningful insights to support medical decision-making. Methods and Results: Building upon a previously developed XGBoost model with high discrimination (AUC-ROC = 0.964), we applied SHAP and LIME to interpret model predictions across five representative clinical cases. These cases included true positives, true negatives, false positives, false negatives, and borderline predictions. For each case, visual outputs were generated, feature attributions were analyzed, and explanations were evaluated by clinical experts based on clarity, trust, and alignment with medical reasoning. SHAP consistently identified relevant risk contributors such as MACE, creatinine, and frailty indicators, and offered both global and local interpretability. LIME explanations were more concise but showed variability in feature attribution, often omitting clinically significant variables like MACE. In false negative and borderline cases, SHAP provided clearer representations of risk, whereas LIME tended to oversimplify or misattribute contributing features. Clinician feedback favored SHAP in all dimensions evaluated. Conclusion: Our results suggest that SHAP outperforms LIME in providing clinically aligned, trustworthy, and interpretable explanations for ML-based mortality prediction in cardiac surgery. While both methods can enhance transparency, SHAP’s consistency and richer information content make it better suited for complex clinical use. These findings support the integration of SHAP-based interpretability tools into clinical decision support systems, particularly in scenarios where trust and explanation fidelity are critical for patient safety and risk communication.

Readmissions are an indicator of hospital care quality; a high readmission rate is associated with adverse outcomes. This leads to an increase in healthcare costs and quality of life for patients. Developing predictive models for hospital readmissions provides opportunities to select treatments and implement preventive measures. The aim of this study is to develop predictive models for the readmission risk of patients with schizophrenia, combining the particle swarm optimization (PSO) algorithm with machine learning classification algorithms. The database used in the study includes a total of 6089 readmission records of patients with schizophrenia. These records were collected from 11 public hospitals in Castilla and León, Spain, in the period 2005–2015. The results of the study show that the Random Forest algorithm combined with PSO achieved the best results across the evaluated performance metrics: AUC = 0.860, recall = 0.959, accuracy = 0.844, and F1-score = 0.907. The development of these new models contributes to -improving patient care. Additionally, they enable preventive measures to reduce costs in healthcare systems.

Currently, high hospital readmission rates have become a problem for mental health services, because it is directly associated with the quality of patient care. The development of predictive models with machine learning algorithms allows the assessment of readmission risk in hospitals. The main objective of this paper is to predict the readmission risk of patients with schizophrenia in a region of Spain, using machine learning algorithms. In this study, we used a dataset with 6089 electronic admission records corresponding to 3065 patients with schizophrenia disorders. Data were collected in the period 2005–2015 from acute units of 11 public hospitals in a Spain region. The Random Forest classifier obtained the best results in predicting the readmission risk, in the metrics accuracy = 0.817, recall = 0.887, F1-score = 0.877, and AUC = 0.879. This paper shows the algorithm with highest accuracy value and determines the factors associated with readmission risk of patients with schizophrenia in this population. It also shows that the development of predictive models with a machine learning approach can help improve patient care quality and develop preventive treatments.

New computational methods have emerged through science and technology to support the diagnosis of mental health disorders. Predictive models developed from machine learning algorithms can identify disorders such as schizophrenia and support clinical decision making. This research aims to compare the performance of machine learning algorithms: Decision Tree, AdaBoost, Random Forest, Naïve Bayes, Support Vector Machine, and k-Nearest Neighbor in the prediction of hospitalized patients with schizophrenia. The data set used in the study contains a total of 11,884 electronic admission records corresponding to 6933 patients with various mental health disorders; these records belong to the acute units of 11 public hospitals in a region of Spain. Of the total, 5968 records correspond to patients diagnosed with schizophrenia (3002 patients) and 5916 records correspond to patients with other mental health disorders (3931 patients). The results recommend Random Forest with the best accuracy of 72.7%. Furthermore, this algorithm presents 79.6%, 72.8%, 72.7%, and 72.7% for AUC, precision, F1-Score, and recall, respectively. The results obtained suggest that the use of machine learning algorithms can classify hospitalized patients with schizophrenia in this population and help in the hospital management of this type of disorder, to reduce the costs associated with hospitalization.

Healthcare institutions must meet a series of requirements for ensuring the privacy of data. Technology has been taking huge steps forward over the years. To avoid security breaches, work is done to make user data information as secure as possible. Some of these techniques include, among others, data modification, cryptographic methods and protocols for data sharing and query auditing methods. As years go by, privacy will continue to gain prominence in any business, to the extent that more investment will be made to improve it. Only when users are convinced that their medical information is completely confidential, will they share data with the system with the same confidence with which they visit the doctor in their health center. The main objective of this chapter is an analysis of issues related to health privacy. We also present some technical suggestions to preserve it. This chapter does not discuss ethical issues or the best techniques that definitely solve these problems. It is a reflection on the need to prioritize the security and confidentiality of customers of eHealth and mHealth applications.

Neuropsychological evaluation is an important factor in the treatment of cognitive impairment in people with mental disorders. The main objective of our paper is to show an evaluation of Gradior computer-based program, in terms of usability and satisfaction degree standards, for the treatment of neurocognitive deficits. The "Satisfaction Evaluation of the Gradior centers" questionnaire was used to measure the usability and satisfaction of the program. This research includes a multi-method analysis of information, through combination of quantitative and qualitative strategies. The evaluation made to the Gradior program by 56 professionals from different centers indicates that the tool is very useful and effective in the treatment of cognitive deficiencies. The application of factorial analysis to the questionnaire shows that are 5 factors that exceed a percentage of explained variance of 5% and with an eigenvalue higher than 2, which was considered a factor with sufficient clinical significance, hence the α value of Cronbach’s obtained in reliability study is 0.913, which shows that applied questionnaire has good reliability. In general terms, the program is satisfactory, its management and use is adequate, and it allows seeing implementation capacity in clinical environments, this being one of few studies that show this subject in field of cognitive rehabilitation.

COVID-19 had led to severe clinical manifestations. In the current scenario, 98 794 942 people are infected, and it has responsible for 2 124 193 deaths around the world as reported by World Health Organization on 25 January 2021. Telemedicine has become a critical technology for providing medical care to patients by trying to reduce transmission of the virus among patients, families, and doctors. The economic consequences of coronavirus have affected the entire world and disrupted daily life in many countries. The development of telemedicine applications and eHealth services can significantly help to manage pandemic worldwide better. Consequently, the main objective of this paper is to present a systematic review of the implementation of telemedicine and e-health systems in the combat to COVID-19. The main contribution is to present a comprehensive description of the state of the art considering the domain areas, organizations, funding agencies, researcher units and authors involved. The results show that the United States and China have the most significant number of studies representing 42.11% and 31.58%, respectively. Furthermore, 35 different research units and 9 funding agencies are involved in the application of telemedicine systems to combat COVID-19.

Technology integration in the field of mental health helps prevent cognitive decline in patients. If older users do not adopt service-based Information and Communication Technologies, they will face problems in managing their daily lives. The main objective of our work is to analyze the usability of the Long Lasting Memories program among mental health professionals. This study sample consisted of 23 participants: psychologists (52.2 % ) and qualified assistants (47.8 % ). Once the intervention with the program had concluded, the participants answered a usability questionnaire with different variables. Questions relating to aspects such as the ease of use of the program, its satisfaction and sustainability were included in the questionnaire. From the point of view of the professional in charge of the intervention, the degree of usability is high.

BACKGROUND:In the era of big data, networks are becoming a popular factor in the field of data analysis. Networks are part of the main structure of BeGraph software, which is a 3D visualization application dedicated to the analysis of complex networks.OBJECTIVE:The main objective of this research was to visually analyze tendencies of mental health diseases in a region of Spain, using the BeGraph software, in order to make the most appropriate health-related decisions in each case.METHODS:For the study, a database was used with 13,531 records of patients with mental health disorders in three acute medical units from different health care complexes in a region of Spain. For the analysis, BeGraph software was applied. It is a web-based 3D visualization tool that allows the exploration and analysis of data through complex networks.RESULTS:The results obtained with the BeGraph software allowed us to determine the main disease in each of the health care complexes evaluated. We noted 6.50% (463/7118) of admissions involving unspecified paranoid schizophrenia at the University Clinic of Valladolid, 9.62% (397/4128) of admissions involving chronic paranoid schizophrenia with acute exacerbation at the Zamora Hospital, and 8.84% (202/2285) of admissions involving dysthymic disorder at the Rio Hortega Hospital in Valladolid.CONCLUSIONS:The data analysis allowed us to focus on the main diseases detected in the health care complexes evaluated in order to analyze the behavior of disorders and help in diagnosis and treatment.

Background Mental health disorders are a problem that affects patients, their families, and the professionals who treat them. Hospital admissions play an important role in caring for people with these diseases due to their effect on quality of life and the high associated costs. In Spain, at the Healthcare Complex of Zamora, a new disease management model is being implemented, consisting of not admitting patients with mental diseases to the hospital. Instead, they are supervised in sheltered apartments or centers for patients with these types of disorders. Objective The main goal of this research is to evaluate the evolution of hospital days of stay of patients with mental disorders in different hospitals in a region of Spain, to analyze the impact of the new hospital management model. Methods For the development of this study, a database of patients with mental disorders was used, taking into account the acute inpatient psychiatry unit of 11 hospitals in a region of Spain. SPSS Statistics for Windows, version 23.0 (IBM Corp), was used to calculate statistical values related to hospital days of stay of patients. The data included are from the periods of 2005-2011 and 2012-2015. Results After analyzing the results, regarding the days of stay in the different health care complexes for the period between 2005 and 2015, we observed that since 2012 at the Healthcare Complex of Zamora, the total number of days of stay were reduced by 64.69%. This trend is due to the implementation of a new hospital management model in this health complex. Conclusions With the application of a new hospital management model at the Healthcare Complex of Zamora, the number of days of stay of patients with mental diseases as well as the associated hospital costs were considerably reduced.

The main objective of this paper is to present a systematic analysis and review of the state of the art regarding the prediction of absenteeism and temporary incapacity using machine learning techniques. Moreover, the main contribution of this research is to reveal the most successful prediction models available in the literature. A systematic review of research papers published from 2010 to the present, related to the prediction of temporary disability and absenteeism in available in different research databases, is presented in this paper. The review focuses primarily on scientific databases such as Google Scholar, Science Direct, IEEE Xplore, Web of Science, and ResearchGate. A total of 58 articles were obtained from which, after removing duplicates and applying the search criteria, 18 have been included in the review. In total, 44% of the articles were published in 2019, representing a significant growth in scientific work regarding these indicators. This study also evidenced the interest of several countries. In addition, 56% of the articles were found to base their study on regression methods, 33% in classification, and 11% in grouping. After this systematic review, the efficiency and usefulness of artificial neural networks in predicting absenteeism and temporary incapacity are demonstrated. The studies regarding absenteeism and temporary disability at work are mainly conducted in Brazil and India, which are responsible for 44% of the analyzed papers followed by Saudi Arabia, and Australia which represented 22%. ANNs are the most used method in both classification and regression models representing 83% and 80% of the analyzed works, respectively. Only 10% of the literature use SVM, which is the less used method in regression models. Moreover, Naïve Bayes is the less used method in classification models representing 17%.

At present, network analysis based on the graph theory has become a widely used technique in the field of Mental Health. The networks are part of the main structure of BeGraph software, a 3D visualization cloud application that allows the analysis of complex networks. The main objective of this study is to analyze, through the BeGraph software, the behavior of Mental Health prevalent diseases in a region of Spain, in order to make health decisions. The study used a database with a total of 9403 patient’s records with Mental Health diseases, which belong to two hospitals in Castilla and Leon, Spain, and the 3D visualization software, BeGraph. The results obtained allow us to determine the main diseases detected in each hospital included in the study: 6.5% of admissions from the University Clinic of Valladolid with unspecified paranoid schizophrenia and 8.84% of admissions from Rio Hortega Hospital with dysthymic disorder. The analysis of the data allows us to focus on the Mental Health main pathologies detected in the hospitals evaluated, and propose prediction algorithms that help in their diagnosis and treatment.

Objective: The main aim of our research is to assess the use, satisfaction, and pedagogy of software for neuropsychological rehabilitation by computer, called "Gradior™," to obtain relevant information on the impact of information and communications technology on people with severe and prolonged mental illness. Methods: To evaluate the usability and satisfaction standards, the questionnaire "Usability survey on the use of the cognitive rehabilitation and assessment program by computer" was completed by 83 patients of the Rodríguez Chamorro Hospital. Results: The results of the study show that Gradior has 81.2% acceptance and 83.7% general assessment. This indicates that those who responded to the survey consider that the Gradior program improves cognitive functions and abilities in patients with severe and prolonged mental illness and therefore their quality of life. Conclusion: This research is oriented toward professionals of the Health Area and Systems Engineers, who develop software for neuropsychological rehabilitation with neurocognitive deficit. The purpose is to make the learning process more effective among the people who use it and to improve usability for specific groups. We hope that the reading of the work contributes to the activities, techniques and materials planned are in accordance with the needs of the population affected with cognitive disorders.

The main objective of this work is to provide a review of existing research work into predictive, personalized, preventive and participatory medicine in telemedicine and ehealth. The academic databases used for searches are IEEE Xplore, PubMed, Science Direct, Web of Science and ResearchGate, taking into account publication dates from 2010 up to the present day. These databases cover the greatest amount of information on scientific texts in multidisciplinary fields, from engineering to medicine. Various search criteria were established, such as ("Predictive" OR "Personalized" OR "Preventive" OR "Participatory") AND "Medicine" AND ("eHealth" OR "Telemedicine") selecting the articles of most interest. A total of 184 publications about predictive, personalized, preventive and participatory (4P) medicine in telemedicine and ehealth were found, of which 48 were identified as relevant. Many of the publications found show how the P4 medicine is being developed in the world and the benefits it provides for patients with different illnesses. After the revision that was undertaken, it can be said that P4 medicine is a vital factor for the improvement of medical services. It is hoped that one of the main contributions of this study is to provide an insight into how P4 medicine in telemedicine and ehealth is being applied, as well as proposing outlines for the future that contribute to the improvement of prevention and prediction of illnesses.

Background:Social robots are currently a form of assistive technology for the elderly, healthy, or with cognitive impairment, helping to maintain their independence and improve their well-being.Objective:The main aim of this article is to present a review of the existing research in the literature, referring to the use of social robots for people with dementia and/or aging.Methods:Academic databases that were used to perform the searches are IEEE Xplore, PubMed, Science Direct, and Google Scholar, taking into account as date of publication the last 10 years, from 2007 to the present. Several search criteria were established such as "robot" AND "dementia," "robot" AND "cognitive impairment," "robot" AND "social" AND "aging," and so on., selecting the articles of greatest interest regarding the use of social robots in elderly people with or without dementia.Results:This search found a total of 96 articles on social robots in healthy people and with dementia, of which 38 have been identified as relevant work. Many of the articles show the acceptance of older people toward social robots.Conclusion:From the review of the research articles analyzed, it can be said that use of social robots in elderly people without cognitive impairment and with dementia, help in a positive way to work independently in basic activities and mobility, provide security, and reduce stress.

The QoE measurement has become a novel theme today. To achieve a quality service and minimize the negative impact that traffic on network can cause, it's very important to manage the devices that intervene in this service. Hence, the QoE evaluation allows obtaining benefits both customers and service providers. The main objective of this paper is to measure QoE of a teleconsultation application in Mental Health named Psiconnect, using an approach based on pentagram model. For the QoE evaluation of Psiconnect application we used the pentagram model based on the measurement of 5 factors (integrality, retainability, availability, usability, and instantaneousness). This model allows to design quantifiable metrics for quality evaluations. Using the model cited the value of QoE for Psiconnect is 1.793 (between 1.6 and 1.8). Comparing with Mean Opinion Scores (MOS) test, some users are dissatisfied with the use of the application although the result is near 1.8, so the most of users are satisfied with the use of teleconsultation service based in Skype in the Psiconnect app. There are different models to measure QoE having into account subjective parameters. This is important an estimation of QoE in a quantitative form. Other models can be used to improve the quality of apps.