Pasar al contenido principal

Resultados relacionados

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

Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

No clues good clues: out of context Lexical Relation Classification

  • Pitarch, Lucia
  • Bernad, Jordi
  • Dranca, Lacramioara
  • Bobed Lisbona, Carlos
  • Gracia, Jorge
The accurate prediction of lexical relations between words is a challenging task in Natural Language Processing (NLP). The most recent advances in this direction come with the use of pre-trained language models (PTLMs). A PTLM typically needs “well-formed” verbalized text to interact with it, either to fine-tune it or to exploit it. However, there are indications that commonly used PTLMs already encode enough linguistic knowledge to allow the use of minimal (or none) textual context for some linguistically motivated tasks, thus notably reducing human effort, the need for data pre-processing, and favoring techniques that are language neutral since do not rely on syntactic structures. In this work, we explore this idea for the tasks of lexical relation classification (LRC) and graded Lexical Entailment (LE). After fine-tuning PTLMs for LRC with different verbalizations, our evaluation results show that very simple prompts are competitive for LRC and significantly outperform graded LE SoTA. In order to gain a better insight into this phenomenon, we perform a number of quantitative statistical analyses on the results, as well as a qualitative visual exploration based on embedding projections.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Improving shared decision-making about cancer treatment through design-based data-driven decision-support tools and redesigning care paths: an overview of the 4D PICTURE project

  • Rietjens, Judith A. C.
  • Griffioen, Ingeborg
  • Sierra-Pérez, Jorge
  • Sroczynski, Gaby
  • Siebert, Uwe
  • Buyx, Alena
  • Peric, Barbara
  • Svane, Inge Marie
  • Brands, Jasper B. P.
  • Steffensen, Karina D.
  • Romero Piqueras, Carlos
  • Hedayati, Elham
  • Karsten, Maria M.
  • Couespel, Norbert
  • Akoglu, Canan
  • Pazo-Cid, Roberto
  • Rayson, Paul
  • Lingsma, Hester F.
  • Schermer, Maartje H. N.
  • Steyerberg, Ewout W.
  • Payne, Sheila A.
  • Korfage, Ida J.
  • Stiggelbout, Anne M.
  • Oliveira, Claudia Cruz
  • Semino, Elena
  • Roobol, Monique
  • López-Forniés, Ignacio
  • Kunneman, Marleen
  • Verberne, Suzan
  • Kuld, Anne
  • van Mulligen, Erik M.
  • Knudsen, Bettina Mølri
  • Kors, Jan A.
  • Venderbos, Lionne D. F.
  • Donia, Marco
  • Koppert, Linetta B.
  • Nwosu, Amara C.
  • Verheul, Elfi M.
  • Sañudo, Yeray
  • Kremer, Marie
  • Gracia, Jorge
  • Antón, Antonio
  • Schreijer, Maud
  • Bangma, Chris
  • Hartman, Laura
  • van Klaveren, David
  • Aiger Valles, Monserrat
  • Pitarch, Lucia
  • Hallsson, Lara R.
  • Wouters, Michel
  • Kapiteijn, Ellen
  • de Glas, Nienke
  • van Buchem, Marieke
  • Doornkamp, Frank
  • Borštnar, Simona
  • Wee, Leonard
  • Pross, Therese
  • Silva, Marta
  • Venegoni, Enea
  • Lorenzo, Nora
  • Wallberg, Susanne
  • Dankl, Kathrina
  • de Jesús, Teresa Puértolas
  • Romera, Juan Lao
  • Pons, Paula Gomila
  • Signerez, Paula Melo
  • Secomandi, Fernando
  • Snelders, Dirk: on behalf of 4D Picture Consortium
Background: Patients with cancer often have to make complex decisions about treatment, with the options varying in risk profiles and effects on survival and quality of life. Moreover, inefficient care paths make it hard for patients to participate in shared decision-making. Data-driven decision-support tools have the potential to empower patients, support personalized care, improve health outcomes and promote health equity. However, decision-support tools currently seldom consider quality of life or individual preferences, and their use in clinical practice remains limited, partly because they are not well integrated in patients’ care paths. Aim and objectives: The central aim of the 4D PICTURE project is to redesign patients’ care paths and develop and integrate evidence-based decision-support tools to improve decision-making processes in cancer care delivery. This article presents an overview of this international, interdisciplinary project. Design, methods and analysis: In co-creation with patients and other stakeholders, we will develop data-driven decision-support tools for patients with breast cancer, prostate cancer and melanoma. We will support treatment decisions by using large, high-quality datasets with state-of-the-art prognostic algorithms. We will further develop a conversation tool, the Metaphor Menu, using text mining combined with citizen science techniques and linguistics, incorporating large datasets of patient experiences, values and preferences. We will further develop a promising methodology, MetroMapping, to redesign care paths. We will evaluate MetroMapping and these integrated decision-support tools, and ensure their sustainability using the Nonadoption, Abandonment, Scale-Up, Spread, and Sustainability (NASSS) framework. We will explore the generalizability of MetroMapping and the decision-support tools for other types of cancer and across other EU member states. Ethics: Through an embedded ethics approach, we will address social and ethical issues. Discussion: Improved care paths integrating comprehensive decision-support tools have the potential to empower patients, their significant others and healthcare providers in decision-making and improve outcomes. This project will strengthen health care at the system level by improving its resilience and efficiency.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

The implementation of design methodologies for supporting shared decision making in healthcare services: A systematic review.

  • Sañudo, Yeray
  • Akoglu, Canan
  • Rietjens, Judith A.C.
  • Snelders, Dirk
  • Stiggelbout, Anne M.
  • Sierra-Pérez, Jorge
Objectives This systematic review examines how design methodologies support Shared Decision Making (SDM), identifies the most suitable for future use, explores types of methodologies used, challenges faced, and the impact on patients, clinicians, and care pathways. Methods Studies were searched on Medline, Web of Science, Scopus and grey literature (Google Scholar, CORDIS) up to July 2024, following PRISMA guidelines. Results were analysed to identify patient involvement, design strategies, SDM solutions, and their impact on care paths, professionals, and patients. Results Out of 2499 studies and 39 grey literature projects identified, 22 studies (reported in 35 publications) were selected, primarily from the USA and Europe (2015 onward). User-Centered Design predominated, involving health professionals more than patients. IPDAS standards were common. Evaluations showed improved patient experience and SDM role, with a potential increase in healthcare professionals' workload. Conclusion Although design methodologies are used in SDM implementation, improvement is needed. Service Design can enhance implementation by analysing the entire SDM process, while co-creative approaches develop patient-focused solutions that integrate smoothly into health professionals' workflows. Practical implications Introducing SDM in healthcare is complex, but design methodologies can help by analysing stakeholder needs, providing a broader care path view, and facilitating SDM implementation.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Reseña (Review)

Cancer experience in metaphors: patients, carers, professionals, students – a scoping review

  • Liu, Yufeng
  • Semino, Elena
  • Rietjens, Judith
  • Payne, Sheila
  • Romero Piqueras, Carlos
  • Sierra Pérez, Jorge
  • Pitarch, Lucía
  • Pazo Cid, Roberto
  • Puertolas, Teresa
  • On behalf of 4D PICTURE Consortium
The use of metaphors to talk about cancer experiences has attracted much research and debate, especially in the case of military metaphors. However, questions remain about what metaphors are used by different populations for different aspects of the cancer experience. This scoping review aims to answer them.We searched PubMed, PsycINFO, CINAHL, Scopus and Web of Science databases. Eligible sources include peer-reviewed scientific research published in English between 2013 and 2023, investigating patterns of metaphor use from adult populations (age ≥18) for cancer-related topics, such as cancer itself, the general experience of being ill, treatment, and people and relationships.Out of 1929 articles identified, 30 met the criteria, spanning over different populations. While most papers focused on cancer in general, some focused on specific cancer types, such as breast cancer. Both spontaneous and elicited data were collected in ten languages: mostly English (N=12), Swedish (N=3) and Arabic (N=3). The identified metaphors were subsumed under various broad categories, including particularly violence and journey. Other categories include education and non-human animate entity for the cancer itself, confinement and deprivation and cleanliness for the general experience of being ill with cancer, Poison and gardening for cancer treatment, and distance for patients’ social relationships.It was found that metaphors help to identify how patients describe experiences of vulnerability and empowerment. To provide patient-centred care, clinicians and researchers should avoid blanket conclusions about helpful or unhelpful metaphors, but consider the ways in which different metaphors are used by different populations in different contexts.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

The EMPATHS method: assessing patients’ emotional reactions to healthcare from a service design approach

  • Sañudo, Yeray
  • Aguado-González, Laura
  • Medina-Castillo, Alba
  • Sierra-Pérez, Jorge
Measuring patients’ emotions can improve the service experience. This study proposes a methodology to identify and measure patients’ emotional reactions in healthcare services from a service design perspective, using an oncology service as a test case study. The methodology design started by evaluating emotion measurement methods from psychology and design, focusing on their compatibility with service design and healthcare characteristics. A combination of self-report, observation, and audio sentiment analysis was proposed. The methodology was tested in a Spanish oncology service analysis. Cohen's Kappa statistical analyses showed a strong correlation between the different methods. The proposed methodology effectively gathers emotional reactions, providing valuable insights into patients’ experiences during service interactions while minimising the intrusiveness of traditional methods. The primary negative emotional reactions during the oncology service analysis were associated with treatment side effects, issues related to the treatment process, and the diagnosis itself. It is the first approach developed from a service design perspective that allows emotional assessment without influencing patients’ movements. The case study findings align with previous literature findings. This methodology could help analyse and design care-paths more aligned with patients’ needs and experiences.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Identifying emotional variations in Spanish oncology patients during treatment decision consultations: a qualitative study

  • Sañudo, Yeray
  • Aguado-González, Laura
  • Medina Castillo, Alba
  • Sierra-Pérez, Jorge
Objectives This qualitative study aims to identify which themes cause the most emotional variation in patients' decisions about cancer treatment. Patients' emotional variations are analysed to detect negative and positive variations to certain themes during the consultations. This analysis helps to detect what themes or elements affect patients' experiences.Design and settings A total of 31 clinical consultations from cancer care pathways were recorded, transcribed and analysed. Patients were followed up until they decided and started treatment for their cancer. An inductive content analysis is followed to interpret patients' emotional variations. All patients were from Hospital Universitario Miguel Servet of Zaragoza, Spain.Participants Twelve patients participated in the study, consisting of eight with breast cancer and four with melanoma. Of these patients, nine were female and three were male. Eligible participants were required to be new to the care pathways or to have used them more than 10 years ago. Participants were also required to be aged 18 or older, be fluent in Spanish and be available to participate for 3 months. Participants were excluded if the authors or oncologists noticed poor health conditions that could be exacerbated by the stress and additional effort involved in participating in the study.Results Patients' emotional variations identify five main themes: clinical history, cancer diagnosis, discussion of possible treatment choice, side effects (possible side effects of the selected treatment) and next steps (require complementary medical tests and more consultations to decide the treatment). Most of the emotional variations detected were negative and were mostly grouped into the categories of treatment, side effects and next steps. The most pronounced negative variations were related to delays in starting treatment and the possibility of hair loss.Conclusions The themes and emotional variations identified in this study can help to understand patients' experiences during their initial oncology consultations. These results represent a significant step towards enhancing communication and the patient experience within oncology practices. Oncologists could use these data and procedures to identify where patients experience negative emotions and respond appropriately.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Prediction models for adverse events from prostate cancer curative radiotherapy: a systematic review of methodological quality

  • Oliveira, Claudia Cruz
  • Jongen, Christian A M
  • Mikolic, Ana
  • Incrocci, Luca
  • Lingsma, Hester F
  • Roobol, Monique J
  • Korfage, Ida
  • Heemsbergen, Wilma D
  • van Klaveren, David
  • Romero, Carlos
  • de Wreede, Liesbeth C.
  • Doornkamp, Frank
  • Engelberts, Yassin
  • Fornara, Olesja
  • Frank, Kasper
  • Hackmann, Toby
  • Hallsson, Lára R.
  • Koch, Lennart
  • Lal, Daisy Monika
  • Nwosu, Amara Callistus
  • Pazo-Cid, Roberto
  • Rietjens, Judith
  • Siebert, Uwe
  • Steyerberg, E.W.
  • Verheul, Elfi M.
  • Wit, Tamara
  • Wouters, Michel W.
Background Predicting risks of urinary, bowel, sexual, and other adverse effects following prostate cancer curative radiotherapy (PCa-RT) is essential for treatment personalization and patient counseling. Several clinical prediction models (CPMs) have been published; however, their methodological quality remains unclear. Methods We systematically reviewed studies developing or validating CPMs for adverse events after PCa-RT. Embase and Medline were searched for CPM studies for patient- or clinician-reported outcomes (PROs/ClinROs), published between January 1, 2004, and August 6, 2024. To focus the appraisal on methodologically more robust models, models were pre-selected based on events per variable ≥10 or the reporting of optimism-corrected performance metrics or effect estimates. We appraised models based on performance and ROB, using a six-item short form of the Prediction model Risk Of Bias ASsessment Tool (SF-PROBAST). Results Of 3606 records screened, 136 CPM studies were identified, and 35 were included, yielding 107 CPMs. Most models (n = 87) were developed in external beam radiation therapy populations. 22 models were externally validated. Only two models (AUC= 0.59 and 0.80) – developed in two different studies – were classified as low risk of bias (fulfilled all the SF-PROBAST criteria). 32 models, from 13 studies, met at least four SF-PROBAST criteria and showed at least moderate discrimination (AUC ≥ 0.70) at internal (n = 25) and/or external (n = 11) validation. Conclusion Ready-to-use CPMs in PCa-RT remain scarce due to methodological limitations, miscalibration, and lack of external validation. Future efforts should prioritize validation and refinement of existing models rather than development of new ones.