EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Inteligencia artificial generativa para el razonamiento clínico y el diagnóstico diferencial en medicina interna

Luis Corral-Gudino, Manuel Ramos-Casals, Miguel Marcos, Juan Jose Ríos-Blanco

Medicina Clínica · 2026

DOI: 10.1016/j.medcli.2026.107567 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Medicina Clínica, 2026. Verfasst von Luis Corral-Gudino und 3 weiteren Autor:innen. Beteiligte Einrichtung: Departamento de Medicina, Dermatología y Toxicología, Facultad de Medicina, Universidad de Valladolid. Servicio de Medicina Interna, Hospital Univers…. Hauptthemen laut MEDLINE: Generative Artificial Intelligence, Internal Medicine, Clinical Reasoning, Artificial Intelligence. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Clinical reasoning and differential diagnosis are core competencies in medicine. Large language models (LLMs) have generated considerable interest as potential tools to support these skills. This article presents a narrative review of the available evidence, organized around five key questions: the effect of LLMs on diagnostic reasoning, the optimal design of clinician-LLM interaction, the appropriate timing of consultation during the clinical encounter, the safest models of clinical-AI integration, and the main risks associated with their use. The evidence shows that LLMs improve differential diagnosis when used by trained professionals within structured workflows. However, passive use generates biases, and clinician-AI collaboration may not consistently outperform autonomous LLMs. A practical framework stratified by degree of diagnostic uncertainty is proposed, with operational and educational recommendations oriented toward "physician-in-the-loop" models, in which LLMs amplify, challenge, and make explicit the diagnostic reasoning process under critical human oversight.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Generative Artificial IntelligenceInternal MedicineClinical ReasoningArtificial IntelligenceHumansDiagnosis, DifferentialLarge Language ModelsClinical Competence

Stichwörter der Autor:innen

Clinical CompetenceClinical Decision-MakingClinical ReasoningCompetencia clínicaDiagnosis DifferentialDiagnóstico diferencialGenerative Artificial IntelligenceInteligencia artificial generativaRazonamiento clínicoToma de decisiones clínicas

Autor:innen und Institutionen

  • Departamento de Medicina, Dermatología y Toxicología, Facultad de Medicina, Universidad de Valladolid. Servicio de Medicina Interna, Hospital Universitario Río Hortega, Valladolid, España. Electronic address: luis.corra…
  • Departamento de Medicina, Universidad de Barcelona, Barcelona, España. Servicio de Enfermedades Autoinmunes, ICMiD, Hospital Clínic, Barcelona, España.
  • Departamento de Medicina, Universidad de Salamanca, Salamanca, España. Servicio de Medicina Interna, Hospital Universitario de Salamanca, Salamanca, España.
  • Departamento de Medicina, Universidad Autónoma de Madrid, Madrid, España. Servicio de Medicina Interna, Hospital Universitario La Paz, Madrid, España.

Zitieren

APA

Corral-Gudino, L., Ramos-Casals, M., Marcos, M., & Ríos-Blanco, J. J. (2026). Inteligencia artificial generativa para el razonamiento clínico y el diagnóstico diferencial en medicina interna. Medicina Clínica. https://doi.org/10.1016/j.medcli.2026.107567

Vancouver

Corral-Gudino L, Ramos-Casals M, Marcos M, Ríos-Blanco JJ. Inteligencia artificial generativa para el razonamiento clínico y el diagnóstico diferencial en medicina interna. Medicina Clínica. 2026. doi:10.1016/j.medcli.2026.107567

BibTeX
@article{CorralGudino2026,
  author = {Corral-Gudino, Luis and Ramos-Casals, Manuel and Marcos, Miguel and Ríos-Blanco, Juan Jose},
  title = {Inteligencia artificial generativa para el razonamiento clínico y el diagnóstico diferencial en medicina interna},
  journal = {Medicina Clínica},
  year = {2026},
  doi = {10.1016/j.medcli.2026.107567}
}
Kostenlos starten →