Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 7
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Responsive and Minimalist App Based on Explainable AI to Assess Palliative Care Needs during Bedside Consultations on Older Patients

  • Blanes-Selva, Vicent|||0000-0002-0056-0329
  • Garcia-Gomez, Juan M
  • Doñate-Martínez, Ascensión
  • Linklater, Gordon
  • Garcés-Ferrer, Jorge
[EN] Palliative care is an alternative to standard care for gravely ill patients that has demonstrated many clinical benefits in cost-effective interventions. It is expected to grow in demand soon, so it is necessary to detect those patients who may benefit from these programs using a personalised objective criterion at the correct time. Our goal was to develop a responsive and minimalist web application embedding a 1-year mortality explainable predictive model to assess palliative care at bedside consultation. A 1-year mortality predictive model has been trained. We ranked the input variables and evaluated models with an increasing number of variables. We selected the model with the seven most relevant variables. Finally, we created a responsive, minimalist and explainable app to support bedside decision making for older palliative care. The selected variables are age, medication, Charlson, Barthel, urea, RDW-SD and metastatic tumour. The predictive model achieved an AUC ROC of 0.83 [CI: 0.82, 0.84]. A Shapley value graph was used for explainability. The app allows identifying patients in need of palliative care using the bad prognosis criterion, which can be a useful, easy and quick tool to support healthcare professionals in obtaining a fast recommendation in order to allocate health resources efficiently., This work was supported by the InAdvance project (H2020-SC1-BHC-2018-2020 grant agreement number 825750.) and the CANCERLEss project (H2020-SC1-2020-Single-Stage-RTD grant agreement number 965351), both funded by the European Union's Horizon 2020 research and innovation programme.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Cancer Prevention and Screening for People Experiencing Homelessness: Co-Designing the Health Navigator Model

  • Gil-Salmeron, Alejandro
  • Carmichael, Christina
  • Fragner, Tobias
  • Moudatsou, Maria
  • Tabaki, Ioanna
  • Cortes, Jaime Barrio
  • Smith, Lee
  • Grabovac, Igor
  • Doñate-Martínez, Ascensión
[EN] Background: People experiencing homelessness (PEH) face major barriers to accessing healthcare, including cancer preventive services, which results in increased cancer morbidity and mortality. However, tailored integrated care interventions addressing these disparities are scarce. Methods: Using a qualitative, participatory approach, seven focus group discussions were conducted with 15 PEH and 41 health and social care professionals in Austria, Greece, Spain, and the UK. Data were thematically analysed using a framework based on ten core components of navigation interventions. Results: Collaborative discussions led to a consensus on the Health Navigator Model (HNM), designed to improve cancer prevention for PEH. This model introduces "health navigators" from health and social care backgrounds to identify health needs, raise cancer awareness, coordinate healthcare access, and provide practical support. Thematic analysis ensured consistency across countries, shaping a person-centred approach. Comprehensive training and supervision were identified as critical for the effectiveness of the HNM. Conclusion: The co-design approach allowed PEH and professionals to actively shape the intervention, addressing gaps in cancer prevention. The HNM offers a structured, internationally consistent model that could bridge access gaps in cancer care for PEH. Further research using implementation science frameworks is needed to evaluate its effectiveness in real-world settings., This research received funding from the European Union's Horizon 2020 Research and Innovation Programme under grant agreement No. 965351. The content of this publication reflects only the authors' views, and the European Commission is not responsible for any use that may be made of the information it contains.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

An AI-based microsimulation for predicting health outcomes among people experiencing homelessness

  • Blasco-Calafat, Antonio
  • Blanes-Selva, Vicent|||0000-0002-0056-0329
  • Doñate-Martínez, Ascensión
  • Garcia-Gomez, Juan M
  • Fragner, Tobias
  • Alhambra-Borrás, Tamara
  • Gawronska, Julia
  • Moudatsou, Maria
  • Tabaki, Ioanna
  • Belogianni, Katerina
  • Karnaki, Pania
  • Rico Varadé, Miguel
  • Gómez Trenado, Rosa
  • Barrio-Cortes, Jaime
  • Smith, Lee
  • Gil-Salmeron, Alejandro
  • Grabovac, Igor
[EN] Background and objective People experiencing homelessness (PEH) face higher cancer risk due to social exclusion, housing and limited access to healthcare. This study proposes a microsimulation model using machine learning (ML) to predict the effect of quality of life, healthcare utilisation and empowerment at the end of the intervention under the Health Navigator Model, enabling cost-effective resource allocation and identifying high-risk subgroups. Materials & Methods We used data from 652 PEH recruited in four European countries (June 2022 - November 2023); 255 completed an 18-month Health Navigator Model programme. Standardised questionnaires were administered at baseline, four weeks and post-intervention. A modular ML microsimulation was built that (1) creates a constraint-based synthetic cohort, (2) estimates outcome changes by matching each simulated case to real program completers, and (3) sums those differences to gauge the intervention's impact. Multiple ML techniques were tested to keep the synthetic sample true to the original and to improve effect-size predictions. Results CTGAN generated the most realistic synthetic baseline (propensity score = 0.152; 95 % CI 0.148-0.162), markedly outperforming univariant, multivariant and SMOTE approaches (> 0.21). Regression models reproduced most numerical outcomes with good fidelity (e.g., EQ-5D-5L MAE = 0.10 on a 0-1 scale; Health-Rating MAE = 10 on a 0-100 scale), while categorical outcomes were predicted within roughly one category. Binary classifiers yielded F1-scores of 0.58 for smoking status and 0.64 for programme adherence. An online demonstrator (https://epione.upv.es) visualises the process. Conclusion The proposed ML-based microsimulation generates realistic PEH profiles and projects intervention outcomes, providing a flexible, evidence-driven tool to optimise cancer-prevention strategies for PEH supporting evidence-based decision-making and optimise resource allocation, enhancing intervention outcomes by predicting the intervention before implementation., The CANCERLESS project has been funded by the European Commission's Programme Horizon 2020 under the Grant Agreement 965351. This publication reflects the author's views. The European Commission is not responsible for any use that may be made of the information it contains.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Evaluating the Impact of the Health Navigator Model on Housing Status Among People Experiencing Homelessness in Four European Countries

  • Guzman-Benitez, Juan Esteban
  • Fragner, Tobias
  • Alhambra-Borras, Tamara
  • Doñate-Martínez, Ascensión
  • Barbu, Simona
  • Gawronska, Julia
  • Moudatsou, Maria
  • Tabaki, Ioanna
  • Belogianni, Katerina
  • Karnaki, Pania
  • Varade, Miguel Rico
  • Gomez-Trenado, Rosa
  • Barrio-Cortes, Jaime
  • Blanes-Selva, Vicent|||0000-0002-0056-0329
  • Garcia-Gomez, Juan M
[EN] Background: People experiencing homelessness (PEH) face significant health disparities and systemic barriers to healthcare, elevating their risk for cancer and other chronic diseases. To tackle PEHs' challenges in accessing cancer preventive care, the CANCERLESS project implemented the Health Navigator Model (HNM)-a person-centered intervention that utilizes trained Health Navigators to provide tailored support and facilitate service access. Recognizing housing as a key determinant of health, this analysis assessed changes in housing status associated with participation in the HNM among CANCERLESS participants in Austria, Greece, Spain, and the UK. Methods: This was a secondary analysis of cross-national data collected during a single-arm interventional study. Of 652 enrolled PEH, 277 (42.5%) completed the HNM intervention follow-up and were included in the analysis. Changes in housing status from baseline to follow-up were categorized using the European Typology of Homelessness and Housing Exclusion (ETHOS) and treated as an ordered outcome. Descriptive statistics were complemented by a cumulative link mixed model with a participant random intercept to estimate the association between time (follow-up vs. baseline) and housing transitions among completers, adjusting for age, residence/legal status, and daily smoking. Results: Participants had a mean age of 47.4 (SD 13.8), primarily identified as male (64.1%), reported upper secondary education (33.9%), and were from Western European countries (39.7%), with varying housing situations. Among intervention completers, time (follow-up vs. baseline) was associated with higher odds of being in a higher ETHOS category (OR = 1.49, 95% CI = 1.02-2.20, p = 0.042), consistent with a modest improvement in housing status. Larger estimates were observed among migrants without legal documents (OR = 24.13, 95% CI = 6.41-90.89, p < 0.001), while daily smoking was associated with lower odds (OR = 0.33, 95% CI = 0.11-0.96, p = 0.041); other residence status categories were not statistically significant. Conclusions: Suggesting that tailored, navigation-based models, such as the HNM, may be linked to improved housing stability for PEH, these findings can inform piloting and context-aligned integration of the HNM within public health strategies as an alternative approach to address the complex, interconnected health and social needs of PEH. However, the lack of a comparison group and high attrition limit the results' conclusiveness, and future evaluations should aim to include assessments of housing-associated contextual factors., This research was funded by the European Union's Horizon 2020 Research and Innovation Program, grant agreement number 965351.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

User-centred design of a clinical decision support system for palliative care: Insights from healthcare professionals

  • Blanes-Selva, Vicent|||0000-0002-0056-0329
  • Asensio-Cuesta, Sabina|||0000-0003-0246-3773
  • Garcia-Gomez, Juan M
  • Doñate-Martínez, Ascensión
  • Pereira Mesquita, Felipe
[EN] Objective:Although clinical decision support systems (CDSS) have many benefits for clinical practice, they also have several barriers to their acceptance by professionals. Our objective in this study was to design and validate The Aleph palliative care (PC) CDSS through a user-centred method, considering the predictions of the artificial intelligence (AI) core, usability and user experience (UX). Methods:We performed two rounds of individual evaluation sessions with potential users. Each session included a model evaluation, a task test and a usability and UX assessment. Results:The machine learning (ML) predictive models outperformed the participants in the three predictive tasks. System Usability Scale (SUS) reported 62.7 +/- 14.1 and 65 +/- 26.2 on a 100-point rating scale for both rounds, respectively, while User Experience Questionnaire - Short Version (UEQ-S) scores were 1.42 and 1.5 on the -3 to 3 scale. Conclusions:The think-aloud method and including the UX dimension helped us to identify most of the workflow implementation issues. The system has good UX hedonic qualities; participants were interested in the tool and responded positively to it. Performance regarding usability was modest but acceptable., The authors disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was supported by the InAdvance project (H2020-SC1-BHC-2018¿2020 grant number 825750) and the CANCERLESS project (H2020-SC1-2020-Single-Stage-RTD grant number 965351), both funded by the European Union¿s Horizon 2020 research and innovation programme. Also, it was partially supported by the ALBATROSS project (National Plan for Scientific and Technical Research and Innovation 2017¿ 2020, grant number PID2019-104978RB-I00)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Multisource Coherence Analysis of the First European Multicenter Cohort Study for Cancer Prevention in People Experiencing Homelessness: Data Quality Study

  • Blasco-Calafat, Antonio
  • Blanes-Selva, Vicent|||0000-0002-0056-0329
  • Doñate-Martínez, Ascensión
  • Garcia-Gomez, Juan M
  • Sáez Silvestre, Carlos|||0000-0003-2678-8249
  • Fragner, Tobias
  • Alhambra-Borrás, Tamara
  • Gawronska, Julia
  • Smith, Lee
  • Grabovac, Igor
[EN] Background: Coherence across sites in multicenter datasets is one substantial data quality dimension for reliable health data reuse, as unexpected heterogeneity in data can lead to biases in data analyses and suboptimal generalization of results. Objective: This work aims to characterize and label the data coherence across sites in the first European multicenter dataset for cancer prevention in people and early detection among the homeless population in Europe: coadapting and implementing the health navigator model. This dataset emerged to enable research to address disparities in health challenges and health care access due to barriers such as unstable housing, limited resources, and social stigma in people experiencing homelessness. Methods: The dataset comprises 652 cases: 142 from Austria, 158 from Greece, 197 from Spain, and 155 from the United Kingdom. All participants fit classifications from the European Typology of Homelessness and Housing Exclusion. This longitudinal study collected questionnaires at baseline, after 4 weeks, and at the end of the intervention. The 180-question survey covered sociodemographic data, overall health, mental health, empowerment, and interpersonal communication. Data variability was assessed using information theory and geometric methods to analyze discrepancies in distributions and completeness across the Results: Substantial variability was observed among the 4 pilot countries, both in the overall analysis and within specific domains. In particular, measures of health care empowerment, quality of life, and interpersonal communication demonstrated the greatest discrepancies among pilot sites, with the exception of the health domain. Notably, Spain exhibited the most pronounced differences, characterized by a high number of missing values related to interpersonal communication and the use of health care services. Conclusions: Health data may be comparable across the 4 countries; however, substantial differences were observed in the other questionnaires, requiring independent, country-specific analyses. This study underscores the heterogeneity among people experiencing homelessness and the critical need for data quality assessments to inform future research and policymaking in this field., The CANCERLESS project has been funded by the European Commission's Programme Horizon 2020 (grant agreement 965351) . This publication reflects the author's views. The European Commission is not responsible for any use that may be made of the information it contains. The study is partly funded through the QUANTUM project HORIZON-HLTH-2023-TOOL-05-09-Developing a Data Quality and Utility Label for the European Health Data Space (grant agreement 101137057) .
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publication Artículo científico (JournalArticle)

Cancer prevention in people experiencing homelessness: ethical considerations and experiences from the CANCERLESS project

  • Coronado-Vázquez, María del Valle
  • Gómez-Trenado, Rosa
  • Benito-Sánchez, Beatriz
  • Barrio-Cortes, Jaime
  • Gil-Salmerón, Alejandro
  • Amengual-Pliego, Miguel
  • Grabovac, Igor
The incidence of cancer in Europe has been increasing in recent years. Despite this, cancer prevention has remained a low priority in health policies. Cancer is one of the main causes of mortality among people experiencing homelessness, who continue to have difficulties accessing prevention programs. A strategy that has been tested to favor cancer prevention is the health navigator figure. The objective of CANCERLESS project is to implement this model among populations experiencing homelessness in four European countries to foster the prevention and early detection of cancer. In this perspective, a presentation of CANCERLESS project is made, and its ethical aspects are discussed according to the ethics of public health, the ethics of care, solidarity, relational autonomy, and the social recognition of the virtue of just generosity. The ethical foundations of CANCERLESS project are rooted in social justice and in equity in access to health systems in general and cancer screening programs in particular. The ethics of public health guided by utilitarianism are insufficient in serving the interests of the most disadvantaged groups of the population. Hence, it is necessary to resort to relational bioethics that includes the ethics of care and solidarity and that recognizes the moral identity of socially excluded persons, reaffirming their position of equality in society. Relational autonomy therefore provides a broader conception by including the influence of living conditions in decisions. For this reason, the CANCERLESS project opts for a dialogue with those affected to incorporate their preferences and values into decisions about cancer prevention.