Logo do repositório

Percorrer por autor "Grilo, Ana"

A mostrar 1 - 10 de 30
  • Assessing the quality and reliability of ChatGPT’s responses to radiotherapy-related patient queries: comparative study with GPT-3.5 and GPT-4
    Publication . Grilo, Ana; Marques, Catarina; Corte-Real, Maria; Carolino, Elisabete; Caetano, Marco
    Background: Patients frequently resort to the internet to access cancer information. However, these websites often lack content accuracy and readability. Recently, ChatGPT, an artificial intelligence-powered chatbot, has signified a potential paradigm shift in how patients with cancer can access vast amounts of medical information, including insights into radiotherapy. However, the quality of the information provided by ChatGPT remains unclear. This is particularly significant given the general public's limited knowledge of this treatment and concerns about its possible side effects. Furthermore, evaluating the quality of responses is crucial, as misinformation can foster a false sense of knowledge and security, lead to noncompliance, and result in delays in receiving appropriate treatment. Objective: This study aims to evaluate the quality and reliability of ChatGPT's responses to common patient queries about radiotherapy, comparing the performance of ChatGPT's two versions: GPT-3.5 and GPT-4. Methods: We selected 40 commonly asked radiotherapy questions and entered the queries in both versions of ChatGPT. Response quality and reliability were evaluated by 16 radiotherapy experts using the General Quality Score (GQS), a 5-point Likert scale, with the median GQS determined based on the experts' ratings. Consistency and similarity of responses were assessed using the cosine similarity score, which ranges from 0 (complete dissimilarity) to 1 (complete similarity). Readability was analyzed using the Flesch Reading Ease Score, ranging from 0 to 100, and the Flesch-Kincaid Grade Level, reflecting the average number of years of education required for comprehension. Statistical analyses were performed using the Mann-Whitney test and effect size, with results deemed significant at a 5% level (P=.05). To assess agreement between experts, Krippendorff α and Fleiss κ were used. Results: GPT-4 demonstrated superior performance, with a higher GQS and a lower number of scores of 1 and 2, compared to GPT-3.5. The Mann-Whitney test revealed statistically significant differences in some questions, with GPT-4 generally receiving higher ratings. The median (IQR) cosine similarity score indicated substantial similarity (0.81, IQR 0.05) and consistency in the responses of both versions (GPT-3.5: 0.85, IQR 0.04; GPT-4: 0.83, IQR 0.04). Readability scores for both versions were considered college level, with GPT-4 scoring slightly better in the Flesch Reading Ease Score (34.61) and Flesch-Kincaid Grade Level (12.32) compared to GPT-3.5 (32.98 and 13.32, respectively). Responses by both versions were deemed challenging for the general public. Conclusions: Both GPT-3.5 and GPT-4 demonstrated the capability to address radiotherapy concepts, with GPT-4 showing superior performance. However, both models present readability challenges for the general population. Although ChatGPT demonstrates potential as a valuable resource for addressing common patient queries related to radiotherapy, it is imperative to acknowledge its limitations, including the risks of misinformation and readability issues. In addition, its implementation should be supported by strategies to enhance accessibility and readability.
    2025-04Artigo científico Acesso aberto Ver mais
  • Assessing the quality and reliability of ChatGPT’s responses to radiotherapy-related patient queries: GPT-3.5 versus GPT-4
    Publication . Grilo, Ana; Marques, Catarina; Corte-Real, Maria; Carolino, Elisabete; Caetano, Marco
    Patients frequently resort to the Internet to access cancer information. Nevertheless, these online websites often need more content accuracy and readability. Recently, ChatGPT, an artificial intelligence-powered chatbot, signifies a potential paradigm shift in how cancer patients can access vast medical information. However, given that ChatGPT was not explicitly trained for oncology-related inquiries, the quality of the information it provides still needs to be verified. Evaluating the quality of responses is crucial, as misinformation can foster a false sense of knowledge and security, lead to noncompliance, and delay appropriate treatment. Objective: This study aims to evaluate the quality and reliability of ChatGPT’s responses to standard patient queries about radiotherapy, comparing the performance of GPT-3.5 and GPT-4. Methods: Forty commonly asked radiotherapy questions were selected and inserted into both versions. Responses were evaluated by six radiotherapy experts using a General Quality Score (GQS), assessed for consistency and similarity using the cosine similarity score, and analyzed for readability using the Flesch Reading Ease Score (FRES) and Flesch-Kincaid Grade Level (FKGL). Statistical analysis was performed using the Mann-Whitney test. Results: GPT-4 demonstrated superior performance, with higher GQS and a complete absence of lower scores compared to GPT-3.5. The Mann-Whitney test revealed statistically significant differences in some questions, with GPT-4 generally receiving higher ratings. The cosine similarity score indicated substantial similarity and consistency in responses from both versions. Readability scores for both versions were considered college-level, with GPT-4 scoring slightly better in FRES (35.55) and FKGL (12.71) compared to GPT-3.5 (30.68 and 13.53, respectively). Both versions’ responses were deemed challenging for the public to read. Conclusions: While GPT-4 generates more accurate and reliable responses than GPT-3.5, both models present readability challenges for the public. ChatGPT reveals potential as a valuable resource for addressing common patient queries related to radiotherapy. However, it is crucial to acknowledge its limitations, including the risks of misinformation and readability issues.
    2024-06Preprint Acesso aberto Ver mais
  • Attitudes toward patient-centred care, empathy, and assertiveness among students in rehabilitation areas: a longitudinal study
    Publication . Grilo, Ana; Vinagre, Graça; Santos, Margarida Custódio dos; Martinho, Joana Ferreira; Gomes, Ana Isabel
    This study assessed attitudes toward patient-centred care, empathy, assertiveness, and subjective perception of communication skills and technical knowledge among Portuguese undergraduate students in healthcare. These students may develop rehabilitation activities with patients in their person-oriented or technique-oriented professions. Portuguese nursing and allied health students from two public higher education schools completed questionnaires in the first and third academic years: Patient-Practitioner Orientation Scale, Jefferson Scale of Physician Empathy, Scale for Interpersonal Behaviour, and subjective perception of technical knowledge and communication skills. A total of 183 students completed the surveys. In the first year, students showed moderate to high scores on patient-centredness attitudes, empathy, and assertiveness and perceived themselves as having good communication skills. Students from person-oriented programmes significantly improved their Total and shared patient-centred attitudes in the third year compared with students attending technique-oriented professions. Significant differences in empathy were found between groups in the third year. Distress associated with assertive behaviours increased significantly across time in students from technique-oriented programmes compared with their peers in person-oriented programmes. The results suggest that the health profession’s orientation and the programmes’ specific curriculum might have a role in how some dimensions evolved in the two groups of students. The increasing assertiveness-related discomfort highlighted the importance of assessing and monitoring students’ emotional well-being during their initial interactions with patients.
    2023-10Artigo científico Acesso aberto Ver mais
  • Breast cancer patients’ questions about radiotherapy-induced skin toxicity: a comparative analysis of ChatGPT-4.0 and Gemini 2.5 flash
    Publication . Caetano, Marco; Vicente, D.; Caetano, Leonor; Carolino, Elisabete; Grilo, Ana
    Introduction: Artificial Intelligence (AI) is increasingly being deployed in health communication, a trend particularly visible in specialised domains, such as breast cancer radiotherapy. The subsequent clinical and educational value is fundamentally determined by the reliability and clarity of the responses generated. However, the comparative performance of different AI models in addressing patient concerns about radiotherapy side effects remains unclear, creating uncertainty regarding the optimal tool selection for patient education and support. This study aimed to compare the performance of ChatGPT 4.0 and Gemini 2.5 FLASH using a mixed-methods analytical-descriptive approach. Methods: Twenty-three unique questions, derived from a literature review and rephrased to simulate patient enquiries about the skin effects of radiotherapy, were submitted to both models. Sixteen expert Radiation Therapists (RTTs) independently assessed the responses using a seven-point Likert scale. The analyses included semantic cosine similarity and linguistic readability (Flesch Reading Ease/Flesch-Kincaid Grade Level), with statistical comparisons performed using Mann-Whitney tests. Results: Gemini 2.5 FLASH achieved higher median scores (6/7) than ChatGPT 4.0 (5/7), demonstrating particular strengths in clinical detail and empathy. Conversely, ChatGPT 4.0 produced more direct and structured answers, although it occasionally simplified complex concepts. Models showed low semantic similarity (median 0.78). Readability analysis revealed that ChatGPT aligned with an 8th-grade level, whereas Gemini operated at an 11th-grade level. Expert agreement was robust, with Gemini achieving greater consistency (α = 0.78; κ = 0.70) than ChatGPT (α = 0.72; κ = 0.65). Conclusion: Gemini was more effective for complex psychosocial issues, whereas ChatGPT provided more accessible guidance, necessitating ongoing professional validation for reliable integration into patient education workflows. Implications for practice: The use of AI in counselling patients undergoing breast radiotherapy enhances accessibility but requires ongoing professional validation to ensure clinical reliability.
    2026-07Artigo científico Acesso aberto Ver mais
  • Conhecimentos, atitudes e práticas dos estudantes em relação à exposição ocupacional a radiações ionizantes
    Publication . Sousa, Bruna; Canhoto, Joana; Grilo, Ana; Ferreira, Aida; Caetano, Marco; Fonseca, Virgínia; Raminhas Carapinha, Maria João
    Os estudantes de ensino superior de algumas áreas da saúde possuem risco de exposição a radiações. Este facto levou à necessidade de aplicação de legislação, bem como à definição de estratégias de proteção contra radiações. Assim, está regulamentada a obrigatoriedade de monitorização individual através de dosímetros individuais dos sujeitos suscetíveis de receber “doses anuais superiores a um décimo dos limites da dose anual fixada para os trabalhadores”. Não obstante a existência de regulamentação a literatura tem vindo a apontar para a existência de desconfianças e incertezas quanto aos valores das leituras dosimétricas. Denota-se ainda que as perceções de riscos são subjetivas e que influenciam fortemente os comportamentos e atitudes dos sujeitos. Objetivos do estudo: 1) Avaliar o grau de confiança dos estudantes de saúde, expostos a radiações ionizantes, nas leituras de dosimetria individual; 2) Avaliar atitudes/comportamentos dos estudantes expostos a radiações ionizantes; 3) Delinear um plano de intervenção para potenciar mudanças de comportamentos/atitudes, no sentido de os otimizar em Proteção e Segurança contra as Radiações.
    2017-03Documento de conferência Acesso aberto Ver mais
  • Conhecimentos, crenças e consumo de antibióticos na Europa: uma revisão de âmbito
    Publication . Andrade, Graça; Galvão, Andreia; Gonçalves, Margarida; Grilo, Ana; Coelho, André
    Introdução – O consumo excessivo e inadequado de antibióticos corresponde a um problema grave de saúde pública, essencialmente pela disseminação das resistências bacterianas. O presente artigo tem como objetivo realizar uma revisão de âmbito sobre conhecimentos, crenças e consumo de antibióticos na população europeia e a relação entre estas variáveis, bem como com variáveis sociodemográficas (idade, sexo, escolaridade, área de residência), visando uma síntese da investigação original sobre o tema. Métodos – A revisão foi realizada nas bases de dados PubMed, Web of Science, SciELO e Lilacs, incluindo artigos publicados entre 2008 e 2021. Dos 246 registos inicialmente obtidos, 26 artigos preencheram os critérios de inclusão. Resultados – A maioria dos estudos recorreu ao questionário de autopreenchimento como método de recolha de dados. O nível de conhecimento sobre antibióticos revelou-se bastante heterogéneo. Contudo, só uma minoria dos estudos identificou um bom grau de conhecimentos. Em doze dos estudos analisados, as variáveis sociodemográficas apresentaram uma elevada relação com o conhecimento sobre antibióticos, sendo este superior em inquiridos com um maior grau de escolaridade, adultos jovens e de meia-idade, com formação na área da saúde ou com familiares no ramo da saúde. A crença de que os antibióticos servem para tratar mais rapidamente doenças como gripes e constipações é a mais frequentemente relatada. O consumo de antibióticos revelou-se superior em inquiridos do sexo feminino e com menor escolaridade. Poucos estudos encontraram relações significativas do consumo de antibióticos com a idade e a área de residência. Conclusões – Os estudos indicam que, de um modo geral, o nível de conhecimento não é suficiente para permitir um consumo adequado de antibióticos, salientando-se a importância de se realizarem campanhas mais efetivas sobre a utilização destes medicamentos, que foquem o conhecimento e as crenças associadas ao seu uso inadequado. Só assim será possível reduzir a disseminação das resistências bacterianas.
    2022-11Artigo científico Acesso aberto Ver mais
  • Current impact of COVID-19 on mental health and wellbeing: young adults' perspective
    Publication . Andrade, Graça; Luís, Tamara; Santos, Margarida; Grilo, Ana; Pinto, Marta Vasconcelos; Rodrigues, Matilde A.; Almeida-Silva, Marina
    The European Commission referred to the COVID generation and highlighted an increase of 25% in the number of mental illness problems in adolescents and young people, related to COVID-19 and associated lockdown measures. A critical review of longitudinal studies about the impact of COVID-19 on youth mental health points out the increase in: externalized disorders; suicide ideation and attempts; frequency and problematic use of substances in some higher-risk youth; disordered eating symptomatology. Aims of the study: to understand how young adults perceive short and long-term consequences (positive and negative) of the pandemic on their mental health and psychological well-being; to relate the individual characteristics relevant to psychological adaptation to the pandemic with positive and negative perceptions of pandemic consequences.
    2022-09Documento de conferência Acesso aberto Ver mais
  • Development and validation of a Portuguese psychologist's empathy scale: a pilot study
    Publication . Cruz, Márcia; Grilo, Ana; Custódio, Susana; Dores, Artemisa R.; Silva, Carina; Alves, Paulo
    The systematic assessment of empathy is essential for identifying psychologists' competencies and developmental needs, ultimately contributing to more effective clinical practice. Given the multidimensional nature of empathy, comprehensive evaluation requires consideration of its cognitive, affective, and behavioural dimensions. However, no existing instrument is specifically validated to assess psychologists' self-perceived empathy in clinical contexts. To address this limitation, the present pilot study aimed to develop and undertake a preliminarily validation of the Portuguese Psychologists' Empathy Scale (PPES), a self-report instrument designed to assess empathy among psychologists working in Portuguese-speaking contexts across these three components. The study proceeded in two phases: item construction and initial psychometric testing. A total of 106 Portuguese psychologists completed a 57-item Likert-type instrument. Bartlett's test of sphericity was significant (χ2(45) = 811.56, p < .001), and the KMO index (0.73) indicated moderate adequacy for factor analysis. Exploratory factor analysis revealed three core factors explaining 48% of the total variance, with strong internal consistency. A subsequent confirmatory factor analysis supported model refinement, leading to the removal of items with low factor loadings. The final PPES comprises 43 items distributed across cognitive (16), affective (16), and behavioural (11) dimensions. The findings provide encouraging preliminary evidence for the PPES, demonstrating robust internal consistency and acceptable initial factorial validity. Nevertheless, further studies using independent samples and external validation procedures are required to fully establish its psychometric soundness and clinical applicability with Portuguese-speaking psychologists.
    2026-03Artigo científico Acesso aberto Ver mais
  • EANM procedural recommendations for managing the paediatric patient in diagnostic nuclear medicine
    Publication . Camoni, Luca; Santos, Andrea; Luporsi, Marie; Grilo, Ana; Pietrzak, Agata; Gear, Jonathan; Zucchetta, Pietro; Bar-Sever, Zvi
    Purpose: The manuscript aims to characterize the principles of best practice in performing nuclear medicine procedures in paediatric patients. The paper describes all necessary technical skills that should be developed by healthcare professionals to ensure the best possible care for paediatric patients, as it is particularly challenging due to the psychological and physical conditions of children. Methods: We performed a comprehensive literature review to establish the most relevant elements of nuclear medicine studies in paediatric patients. We focused our attention on the technical aspects of the study, such as patient preparation, imaging protocols, and immobilization techniques, that adhere to best practice principles. Furthermore, we considered the psychological elements of working with children, including comforting and distraction strategies. Results: The extensive literature review combined with practical conclusions and recommendations presented and explained by the authors summarizes the most important principles of care for paediatric patients in the nuclear medicine field. Conclusion: Nuclear medicine applied to the paediatric patient is a very special and challenging area, requiring proper education and experience in order to be performed at the highest level and with the maximum safety for the child.
    2023-08Artigo científico Acesso aberto Ver mais
  • Effectiveness of educational videos on patient’s preparation for diagnostic procedures: systematic review and meta-analysis
    Publication . Grilo, Ana; Ferreira, Ana Catarina; Ramos, Marta Pedro; Carolino, Elisabete; Pires, Ana Filipa; Vieira, Lina Oliveira
    Although diagnostic procedures are crucial for secondary prevention and patient disease control, they often trigger fear and anxiety. These reactions highlight the need to adopt effective interventions to improve patients' experience and satisfaction. Recently, educational videos have been employed in preparing diagnostic procedures; however, there is no integrated understanding of their effects. This systematic review and meta-analysis aimed to assess the effectiveness of educational videos on patients' anxiety and satisfaction regarding preparation for diagnostic procedures. Three scientific databases (PubMed; Web of Science, Scopus), were used in this systematic review. Studies about educational videos as a form of preparation for patients undergoing diagnostic procedures published between 2000 and 2021 were included. A meta-analysis was also conducted. Sixteen studies met the inclusion criteria for systematic review, and seven were included in the meta-analysis. Nine studies of the total sample were about vascular procedures and seven studies about other medical image procedures. Of the fourteen studies that evaluated the use of educational videos on patients' anxiety, nine proved to reduce it significantly. Of the thirteen studies that evaluated satisfaction, seven showed a significant increase in the experimental group. Studies included in the meta-analysis show that educational video patient groups had lower anxiety levels than the control groups after the procedure. Although future studies are required, the results suggest that educational videos effectively prepare patients for diagnostic procedures, improving care quality.
    2022-08Artigo científico Acesso aberto Ver mais