Pub Date : 2026-02-01DOI: 10.1016/j.rceng.2026.502450
J. Casado , D. Abad , G. Ropero-Luis , M. Francisco Dávila , A. Muela , A. Bustos-Merlo , J.C. Arévalo-Lorido , M. Sánchez-Marteles , J. Pérez-Silvestre , J.C. Trullas , en representación de los investigadores del registro RICA-2
Objective
To describe the diuretic strategy used in patients hospitalized for acute heart failure (AHF), as well as to identify the clinical profiles of these patients according to the diuretic regimen received.
Materials and methods
A multicenter observational study of patients hospitalized for AHF in Internal Medicine departments and included in the Heart Failure Registry (RICA-2). Patients were categorized into three groups based on the diuretic treatment received: intravenous (IV) furosemide alone, IV furosemide plus thiazide diuretics (TD), and IV furosemide plus acetazolamide (ACZ).
Results
A total of 588 patients were analyzed (median age 84 [77–88] years; 51.2% female). IV furosemide alone was administered in 78% of cases, while 22% received combination diuretic therapy (17% with TD and 5% with ACZ). Patients treated with combination diuretics had a higher burden of comorbidities (diabetes, obesity, chronic kidney disease, and renal function impairment at admission), worse NYHA functional class, higher clinical and biochemical markers of congestion, and were more frequently on loop diuretics prior to admission. No significant differences were found in the length of hospital stay according to the diuretic strategy used. Combination diuretic therapy was associated with greater weight loss during hospitalization (3 kg in the TD group and 2.75 kg in the ACZ group) compared to IV furosemide alone (2 kg) (P = .005).
Conclusions
The most frequently used diuretic strategy in patients hospitalized for AHF in the Internal Medicine departments included in the RICA-2 registry is IV furosemide alone. The combination of diuretics (especially with TD) is more commonly used in patients with more comorbidities and congestion.
{"title":"Combined diuretic treatment in acute heart failure: Insights from RICA-2 registry","authors":"J. Casado , D. Abad , G. Ropero-Luis , M. Francisco Dávila , A. Muela , A. Bustos-Merlo , J.C. Arévalo-Lorido , M. Sánchez-Marteles , J. Pérez-Silvestre , J.C. Trullas , en representación de los investigadores del registro RICA-2","doi":"10.1016/j.rceng.2026.502450","DOIUrl":"10.1016/j.rceng.2026.502450","url":null,"abstract":"<div><h3>Objective</h3><div>To describe the diuretic strategy used in patients hospitalized for acute heart failure (AHF), as well as to identify the clinical profiles of these patients according to the diuretic regimen received.</div></div><div><h3>Materials and methods</h3><div>A multicenter observational study of patients hospitalized for AHF in Internal Medicine departments and included in the Heart Failure Registry (RICA-2). Patients were categorized into three groups based on the diuretic treatment received: intravenous (IV) furosemide alone, IV furosemide plus thiazide diuretics (TD), and IV furosemide plus acetazolamide (ACZ).</div></div><div><h3>Results</h3><div>A total of 588 patients were analyzed (median age 84 [77–88] years; 51.2% female). IV furosemide alone was administered in 78% of cases, while 22% received combination diuretic therapy (17% with TD and 5% with ACZ). Patients treated with combination diuretics had a higher burden of comorbidities (diabetes, obesity, chronic kidney disease, and renal function impairment at admission), worse NYHA functional class, higher clinical and biochemical markers of congestion, and were more frequently on loop diuretics prior to admission. No significant differences were found in the length of hospital stay according to the diuretic strategy used. Combination diuretic therapy was associated with greater weight loss during hospitalization (3 kg in the TD group and 2.75 kg in the ACZ group) compared to IV furosemide alone (2 kg) (<em>P</em> = .005).</div></div><div><h3>Conclusions</h3><div>The most frequently used diuretic strategy in patients hospitalized for AHF in the Internal Medicine departments included in the RICA-2 registry is IV furosemide alone. The combination of diuretics (especially with TD) is more commonly used in patients with more comorbidities and congestion.</div></div>","PeriodicalId":94354,"journal":{"name":"Revista clinica espanola","volume":"226 2","pages":"Article 502450"},"PeriodicalIF":0.0,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145954681","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-01DOI: 10.1016/j.rceng.2026.502455
Á. Velasco , I. Pascual Ramos , P. Rodríguez Alonso , C. Denche Sanz , R. Tello , J. Solís
Introduction
GLP-1 receptor agonists, such as semaglutide, have demonstrated cardiovascular benefits in trials such as SELECT and SOUL. This study assesses the proportion of post-myocardial infarction patients who meet eligibility criteria to benefit from semaglutide.
Methods
A retrospective, single-centre observational study was conducted including 100 consecutive patients following myocardial infarction. Clinical, demographic, and laboratory data were analysed. Eligibility was assessed using the criteria from the SELECT trial (body mass index ≥27 kg/m², no diabetes, established atherosclerotic disease) and the SOUL trial (type 2 diabetes mellitus and atherosclerotic cardiovascular disease).
Results
SELECT criteria were met by 42 patients, SOUL criteria by 34, and both by 76. This combined group was characterised by older age, greater comorbidity burden (hypertension, dyslipidaemia, type 2 diabetes mellitus), higher body mass index, and a more atherogenic lipid profile.
Discussion
The high proportion of eligible patients suggests that these trials truly represent real-world clinical practice. The SELECT + SOUL group exhibited features consistent with metabolic syndrome, potentially explaining their elevated cardiovascular risk and the likely benefit from semaglutide.
Conclusions
Semaglutide shows high potential for prescription in specialties managing patients with cardiovascular events, identifying a target group with characteristics typical of metabolic syndrome.
{"title":"Patients after acute myocardial infarction: potential of semaglutide in prognosis for reducing events and mortality","authors":"Á. Velasco , I. Pascual Ramos , P. Rodríguez Alonso , C. Denche Sanz , R. Tello , J. Solís","doi":"10.1016/j.rceng.2026.502455","DOIUrl":"10.1016/j.rceng.2026.502455","url":null,"abstract":"<div><h3>Introduction</h3><div>GLP-1 receptor agonists, such as semaglutide, have demonstrated cardiovascular benefits in trials such as SELECT and SOUL. This study assesses the proportion of post-myocardial infarction patients who meet eligibility criteria to benefit from semaglutide.</div></div><div><h3>Methods</h3><div>A retrospective, single-centre observational study was conducted including 100 consecutive patients following myocardial infarction. Clinical, demographic, and laboratory data were analysed. Eligibility was assessed using the criteria from the SELECT trial (body mass index ≥27<!--> <!-->kg/m², no diabetes, established atherosclerotic disease) and the SOUL trial (type 2 diabetes mellitus and atherosclerotic cardiovascular disease).</div></div><div><h3>Results</h3><div>SELECT criteria were met by 42 patients, SOUL criteria by 34, and both by 76. This combined group was characterised by older age, greater comorbidity burden (hypertension, dyslipidaemia, type 2 diabetes mellitus), higher body mass index, and a more atherogenic lipid profile.</div></div><div><h3>Discussion</h3><div>The high proportion of eligible patients suggests that these trials truly represent real-world clinical practice. The SELECT<!--> <!-->+<!--> <!-->SOUL group exhibited features consistent with metabolic syndrome, potentially explaining their elevated cardiovascular risk and the likely benefit from semaglutide.</div></div><div><h3>Conclusions</h3><div>Semaglutide shows high potential for prescription in specialties managing patients with cardiovascular events, identifying a target group with characteristics typical of metabolic syndrome.</div></div>","PeriodicalId":94354,"journal":{"name":"Revista clinica espanola","volume":"226 2","pages":"Article 502455"},"PeriodicalIF":0.0,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145954636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-21DOI: 10.1016/j.rceng.2026.502468
María Montserrat Chimeno, Luis Duarte Costa, Vasco Barreto, Jose Luis Bianchi, Luis Campos, João Araújo Correia, Javier Moreno Díaz, José Manuel Porcel, Joao Porto, Lèlita Santos, Pablo Perez-Martinez
Introduction: Internal medicine, owing to its comprehensive and cross-sectional approach, is uniquely positioned to lead the integration of social determinants of health (SDOH) into clinical practice.
Methods: Based on the Delphi methodology promoted by the Spanish Society of Internal Medicine (SEMI) and the Portuguese Society of Internal Medicine (SPMI), this study explored perceptions, barriers, and strategies for integrating SDOH into hospital care. Experts from both countries participated in a two-round consultation process, followed by a consensus meeting, which resulted in a prioritized roadmap of action.
Results: Our findings show strong agreement on the relevance of SDOH for health outcomes, the need for mandatory and transversal training at all educational levels, and the importance of validated tools for systematic screening. Key barriers include lack of time, insufficient specific training, limited human resources, and the absence of structured SDOH data in electronic health records. Additionally, the results emphasize the importance of interdisciplinary teams, coordination with social services, and adapting care pathways to patients' social contexts. Emerging determinants include population aging, mental health, climate change, and digital transformation, including artificial intelligence.
Conclusions: This decalogue provides a practical and prioritized roadmap to transform Internal Medicine care towards a more equitable, comprehensive, and SDOH-sensitive model, with training, service organization, technological resources, and collaboration as fundamental pillars.
{"title":"Position statement of the spanish society of internal medicine (SEMI) and the portuguese society of internal medicine (SPMI).","authors":"María Montserrat Chimeno, Luis Duarte Costa, Vasco Barreto, Jose Luis Bianchi, Luis Campos, João Araújo Correia, Javier Moreno Díaz, José Manuel Porcel, Joao Porto, Lèlita Santos, Pablo Perez-Martinez","doi":"10.1016/j.rceng.2026.502468","DOIUrl":"https://doi.org/10.1016/j.rceng.2026.502468","url":null,"abstract":"<p><strong>Introduction: </strong>Internal medicine, owing to its comprehensive and cross-sectional approach, is uniquely positioned to lead the integration of social determinants of health (SDOH) into clinical practice.</p><p><strong>Methods: </strong>Based on the Delphi methodology promoted by the Spanish Society of Internal Medicine (SEMI) and the Portuguese Society of Internal Medicine (SPMI), this study explored perceptions, barriers, and strategies for integrating SDOH into hospital care. Experts from both countries participated in a two-round consultation process, followed by a consensus meeting, which resulted in a prioritized roadmap of action.</p><p><strong>Results: </strong>Our findings show strong agreement on the relevance of SDOH for health outcomes, the need for mandatory and transversal training at all educational levels, and the importance of validated tools for systematic screening. Key barriers include lack of time, insufficient specific training, limited human resources, and the absence of structured SDOH data in electronic health records. Additionally, the results emphasize the importance of interdisciplinary teams, coordination with social services, and adapting care pathways to patients' social contexts. Emerging determinants include population aging, mental health, climate change, and digital transformation, including artificial intelligence.</p><p><strong>Conclusions: </strong>This decalogue provides a practical and prioritized roadmap to transform Internal Medicine care towards a more equitable, comprehensive, and SDOH-sensitive model, with training, service organization, technological resources, and collaboration as fundamental pillars.</p>","PeriodicalId":94354,"journal":{"name":"Revista clinica espanola","volume":" ","pages":"502468"},"PeriodicalIF":0.0,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146041922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01DOI: 10.1016/j.rceng.2025.502367
F. Borrell Carrió , J. Vidal-Alaball
After decades of specialization, new opportunities are opening up for general clinical practice thanks to three key tools: continuing education focused on transforming clinical habits, access to advanced technology at the service of each professional, and the use of artificial intelligence to support more personalized clinical reflection. These tools could empower physicians to offer more complex, evidence-based, and personalized care.
Some erroneous beliefs about artificial intelligence – such as the idea that it will make studying unnecessary – are simply manifestations of resistance to change. However, it is also important to recognize the challenges it poses, such as the risk of over-reliance on its proposals or accepting them without critical judgment. In any case, the ultimate responsibility for the outcome of a consultation rests with the medical professional.
Technological advances should complement, not replace, the humanistic values of medicine. To make the most of these opportunities, it is essential to have continuing education, institutional support, and personal judgment based on clinical experience and semiological observation.
{"title":"Challenges and opportunities for generalist practice in the era of technology and AI","authors":"F. Borrell Carrió , J. Vidal-Alaball","doi":"10.1016/j.rceng.2025.502367","DOIUrl":"10.1016/j.rceng.2025.502367","url":null,"abstract":"<div><div>After decades of specialization, new opportunities are opening up for general clinical practice thanks to three key tools: continuing education focused on transforming clinical habits, access to advanced technology at the service of each professional, and the use of artificial intelligence to support more personalized clinical reflection. These tools could empower physicians to offer more complex, evidence-based, and personalized care.</div><div>Some erroneous beliefs about artificial intelligence – such as the idea that it will make studying unnecessary – are simply manifestations of resistance to change. However, it is also important to recognize the challenges it poses, such as the risk of over-reliance on its proposals or accepting them without critical judgment. In any case, the ultimate responsibility for the outcome of a consultation rests with the medical professional.</div><div>Technological advances should complement, not replace, the humanistic values of medicine. To make the most of these opportunities, it is essential to have continuing education, institutional support, and personal judgment based on clinical experience and semiological observation.</div></div>","PeriodicalId":94354,"journal":{"name":"Revista clinica espanola","volume":"226 1","pages":"Article 502367"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145246281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01DOI: 10.1016/j.rceng.2025.502416
J.P. Lara Muñoz , J.A. Vargas Núñez , J.J. García Seoane , A.F. Compañ Rosique
The training required for a Medical Degree requires a sufficient faculty structure to guarantee the acquisition of general practitioner skills. The National Conference of Deans of Spanish Medical Schools (CNDFME) has highlighted the significant faculty shortage, maintaining collaboration with university and healthcare institutions, promoting an increase in accredited faculty, modifications to the accreditation model, and the implementation of new teaching positions.
The evolution of accredited faculty for the Health Sciences Branch (2019–2024) is described: the number of accredited permanent teachers has increased significantly. The modifications to the accreditation processes incorporated in the Organic Law of the University System (LOSU) and the new accreditation model (RD 678/2023) are considered positive in encouraging the best professionals to join the faculty of the Schools of Medicine.
{"title":"Evolution of the ANECA-accredited permanent medical teacher for the Degree in Medicine (2019–2024). Expectations for the new accreditation model","authors":"J.P. Lara Muñoz , J.A. Vargas Núñez , J.J. García Seoane , A.F. Compañ Rosique","doi":"10.1016/j.rceng.2025.502416","DOIUrl":"10.1016/j.rceng.2025.502416","url":null,"abstract":"<div><div>The training required for a Medical Degree requires a sufficient faculty structure to guarantee the acquisition of general practitioner skills. The National Conference of Deans of Spanish Medical Schools (CNDFME) has highlighted the significant faculty shortage, maintaining collaboration with university and healthcare institutions, promoting an increase in accredited faculty, modifications to the accreditation model, and the implementation of new teaching positions.</div><div>The evolution of accredited faculty for the Health Sciences Branch (2019–2024) is described: the number of accredited permanent teachers has increased significantly. The modifications to the accreditation processes incorporated in the Organic Law of the University System (LOSU) and the new accreditation model (RD 678/2023) are considered positive in encouraging the best professionals to join the faculty of the Schools of Medicine.</div></div>","PeriodicalId":94354,"journal":{"name":"Revista clinica espanola","volume":"226 1","pages":"Article 502416"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145829492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01DOI: 10.1016/j.rceng.2025.502413
J. Mora-Delgado , L. Ramos-Ruperto , M.J. Pardilla , M.Á. Sicilia , A. Rodríguez-González , J.M Sempere , R. Puchades
This work aims to provide internists with a practical, focused overview of how generative AI based on large language models can be effectively integrated into daily clinical practice. It describes the primary adaptation mechanisms like fine-tuning and retrieval-augmented generation (RAG) for tasks such as report generation, synthesis of clinical findings, and support in differential diagnoses, highlighting real-world examples in Internal Medicine. Technical and organizational requirements for adoption are analyzed, including computing infrastructure, integration with electronic health records, and security/privacy protocols under GDPR and the EU AI Act. Opportunities for enhancing clinical decision-making, optimizing workflows, and reducing administrative burden are emphasized, alongside current limitations like bias, hallucinations, and the need for human oversight. Finally, recommendations are offered for prospective validation in real-world settings and for ensuring explainable transparency, with the goal of empowering internists to incorporate these innovative tools responsibly and efficiently.
{"title":"Generative AI: foundational models. Natural Language Processing (NLP) and LARGE Language Models (LLM)","authors":"J. Mora-Delgado , L. Ramos-Ruperto , M.J. Pardilla , M.Á. Sicilia , A. Rodríguez-González , J.M Sempere , R. Puchades","doi":"10.1016/j.rceng.2025.502413","DOIUrl":"10.1016/j.rceng.2025.502413","url":null,"abstract":"<div><div>This work aims to provide internists with a practical, focused overview of how generative AI based on large language models can be effectively integrated into daily clinical practice. It describes the primary adaptation mechanisms like fine-tuning and retrieval-augmented generation (RAG) for tasks such as report generation, synthesis of clinical findings, and support in differential diagnoses, highlighting real-world examples in Internal Medicine. Technical and organizational requirements for adoption are analyzed, including computing infrastructure, integration with electronic health records, and security/privacy protocols under GDPR and the EU AI Act. Opportunities for enhancing clinical decision-making, optimizing workflows, and reducing administrative burden are emphasized, alongside current limitations like bias, hallucinations, and the need for human oversight. Finally, recommendations are offered for prospective validation in real-world settings and for ensuring explainable transparency, with the goal of empowering internists to incorporate these innovative tools responsibly and efficiently.</div></div>","PeriodicalId":94354,"journal":{"name":"Revista clinica espanola","volume":"226 1","pages":"Article 502413"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145812653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01DOI: 10.1016/j.rceng.2025.502421
J. García Alegría , C. García Tortosa , M.D. Martín Escalante , F. Miralles Linares , R. Puchades-Rincón de Arellano , M.M. Chimeno-Viñas
Background/objective
Artificial intelligence (AI) has been revolutionising medical practice in recent years. The aim of this study was to analyze the perception of self-knowledge, personal experience, degree of use and training needs in AI among Spanish internists who are members of the Spanish Society of Internal Medicine (SEMI) in order to guide their educational activities.
Materials and methods
Cross-sectional study using an anonymous survey with demographic variables, categorical questions, multiple-choice questions, and open-ended qualitative questions. Descriptive analysis with differences between age groups. The minimum estimated sample size of representative members was 368.
Results
504 valid responses were analyzed (82% specialists, 16% residents). Self-perceived knowledge of AI was mainly intermediate or basic, with higher levels among those under 30 and lower levels among those over 60. Three out of four respondents had used AI, mainly in clinical practice, followed by research and teaching. The main perceived barriers were lack of specific training, doubts about reliability and ethical-legal issues, as well as technological limitations and resistance to change. The vast majority considered AI training to be important or very important, with particular interest in practical clinical applications, basic fundamentals and tool evaluation. The willingness to incorporate AI into practice was high across all age groups.
Conclusions
Spanish internists have varying levels of knowledge about artificial intelligence, with younger doctors having greater knowledge, and its main current use is in clinical practice. Lack of training is the main barrier to its incorporation, despite high demand for training and a general willingness to adopt it, highlighting the need for training programs and strategies for integrating AI into internal medicine.
{"title":"Artificial intelligence in internal medicine: knowledge, clinical use and training needs","authors":"J. García Alegría , C. García Tortosa , M.D. Martín Escalante , F. Miralles Linares , R. Puchades-Rincón de Arellano , M.M. Chimeno-Viñas","doi":"10.1016/j.rceng.2025.502421","DOIUrl":"10.1016/j.rceng.2025.502421","url":null,"abstract":"<div><h3>Background/objective</h3><div>Artificial intelligence (AI) has been revolutionising medical practice in recent years. The aim of this study was to analyze the perception of self-knowledge, personal experience, degree of use and training needs in AI among Spanish internists who are members of the Spanish Society of Internal Medicine (SEMI) in order to guide their educational activities.</div></div><div><h3>Materials and methods</h3><div>Cross-sectional study using an anonymous survey with demographic variables, categorical questions, multiple-choice questions, and open-ended qualitative questions. Descriptive analysis with differences between age groups. The minimum estimated sample size of representative members was 368.</div></div><div><h3>Results</h3><div>504 valid responses were analyzed (82% specialists, 16% residents). Self-perceived knowledge of AI was mainly intermediate or basic, with higher levels among those under 30 and lower levels among those over 60. Three out of four respondents had used AI, mainly in clinical practice, followed by research and teaching. The main perceived barriers were lack of specific training, doubts about reliability and ethical-legal issues, as well as technological limitations and resistance to change. The vast majority considered AI training to be important or very important, with particular interest in practical clinical applications, basic fundamentals and tool evaluation. The willingness to incorporate AI into practice was high across all age groups.</div></div><div><h3>Conclusions</h3><div>Spanish internists have varying levels of knowledge about artificial intelligence, with younger doctors having greater knowledge, and its main current use is in clinical practice. Lack of training is the main barrier to its incorporation, despite high demand for training and a general willingness to adopt it, highlighting the need for training programs and strategies for integrating AI into internal medicine.</div></div>","PeriodicalId":94354,"journal":{"name":"Revista clinica espanola","volume":"226 1","pages":"Article 502421"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145829533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01DOI: 10.1016/j.rceng.2025.502418
A. Carrasco Laraña , J. Álvarez Troncoso , J.J. Ríos Blanco
Introduction
Systemic autoimmune diseases (SADs) pose a diagnostic challenge due to the heterogeneity of their manifestations and the frequent overlap of symptoms. The integration of large language models (LLMs), such as GPT-4, could complement clinical judgment through the systematic analysis of standardized clinical data.
Objective
To evaluate the diagnostic capability of GPT-4 in patients with SADs at a tertiary care center, comparing its results with the final consensus diagnosis issued by specialists.
Methods
A retrospective study was conducted on a cohort of 101 consecutively treated patients between January 1 and March 31, 2024, at the SAD Unit of La Paz University Hospital. Data collection was carried out using the unit's standardized anamnesis protocol. The “my GPT” model, based on GPT-4 and trained according to international diagnostic criteria, was evaluated following TRIPOD‐AI guidelines.
Results
The overall diagnostic accuracy rate was 97.03%. Analysis based solely on anamnesis data achieved an accuracy of 82.18%, which increased by 14.85% when immunological results were included. A 100% accuracy was achieved in diagnosing systemic lupus erythematosus, Sjögren's syndrome, inflammatory myopathies, Behçet's disease, and scleroderma. In contrast, for sarcoidosis and vasculitis—conditions that often require histological confirmation—accuracy was 91.67% and 80%, respectively.
Conclusion
The use of GPT-4, grounded in systematic clinical data collection and evaluated in accordance with TRIPOD‐AI guidelines, demonstrates strong potential as an auxiliary tool in the diagnosis of SADs. Integrating this approach into clinical practice could help reduce interobserver variability and optimize decision-making.
{"title":"Integration of natural language models in the diagnosis of systemic autoimmune diseases: validation of GPT-4 in a tertiary care center","authors":"A. Carrasco Laraña , J. Álvarez Troncoso , J.J. Ríos Blanco","doi":"10.1016/j.rceng.2025.502418","DOIUrl":"10.1016/j.rceng.2025.502418","url":null,"abstract":"<div><h3>Introduction</h3><div>Systemic autoimmune diseases (SADs) pose a diagnostic challenge due to the heterogeneity of their manifestations and the frequent overlap of symptoms. The integration of large language models (LLMs), such as GPT-4, could complement clinical judgment through the systematic analysis of standardized clinical data.</div></div><div><h3>Objective</h3><div>To evaluate the diagnostic capability of GPT-4 in patients with SADs at a tertiary care center, comparing its results with the final consensus diagnosis issued by specialists.</div></div><div><h3>Methods</h3><div>A retrospective study was conducted on a cohort of 101 consecutively treated patients between January 1 and March 31, 2024, at the SAD Unit of La Paz University Hospital. Data collection was carried out using the unit's standardized anamnesis protocol. The “my GPT” model, based on GPT-4 and trained according to international diagnostic criteria, was evaluated following TRIPOD‐AI guidelines.</div></div><div><h3>Results</h3><div>The overall diagnostic accuracy rate was 97.03%. Analysis based solely on anamnesis data achieved an accuracy of 82.18%, which increased by 14.85% when immunological results were included. A 100% accuracy was achieved in diagnosing systemic lupus erythematosus, Sjögren's syndrome, inflammatory myopathies, Behçet's disease, and scleroderma. In contrast, for sarcoidosis and vasculitis—conditions that often require histological confirmation—accuracy was 91.67% and 80%, respectively.</div></div><div><h3>Conclusion</h3><div>The use of GPT-4, grounded in systematic clinical data collection and evaluated in accordance with TRIPOD‐AI guidelines, demonstrates strong potential as an auxiliary tool in the diagnosis of SADs. Integrating this approach into clinical practice could help reduce interobserver variability and optimize decision-making.</div></div>","PeriodicalId":94354,"journal":{"name":"Revista clinica espanola","volume":"226 1","pages":"Article 502418"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145812649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号