Prompting Large Language Models for Supporting the Differential Diagnosis of Anemia - Centre de recherche des Cordeliers
Communication Dans Un Congrès Année : 2024

Prompting Large Language Models for Supporting the Differential Diagnosis of Anemia

Résumé

In practice, clinicians achieve a diagnosis by following a sequence of steps, such as laboratory exams, observations, or imaging. The pathways to reach diagnosis decisions are documented by guidelines authored by expert organizations, which guide clinicians to reach a correct diagnosis through these sequences of steps. While these guidelines are beneficial for following medical reasoning and consolidating medical knowledge, they have some drawbacks. They often fail to address patients with uncommon conditions due to their focus on the majority population, and are slow and costly to update, making them unsuitable for rapidly emerging diseases or new practices. Inspired by clinical guidelines, our study aimed to develop pathways similar to those that can be obtained in clinical guidelines. We tested three Large Language Models (LLMs) -Generative Pretrained Transformer 4 (GPT-4), Large Language Model Meta AI (LLaMA), and Mistral -on a synthetic yet realistic dataset to differentially diagnose anemia and its subtypes. By using advanced prompting techniques to enhance the decision-making process, we generated diagnostic pathways using these models. Experimental results indicate that LLMs hold huge potential in clinical pathway discovery from patient data, with GPT-4 exhibiting the best performance in all conducted experiments.
Fichier principal
Vignette du fichier
castagnari_et_al.pdf (1.39 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
licence

Dates et versions

hal-04695193 , version 1 (19-09-2024)

Licence

Identifiants

  • HAL Id : hal-04695193 , version 1

Citer

Elisa Castagnari, Lillian Muyama, Adrien Coulet. Prompting Large Language Models for Supporting the Differential Diagnosis of Anemia. LLMs4MI 2024 @FLLM 2024 - First International Workshop on Large Language Models Applications in Medical Informatics In conjunction with the The Second International Conference on Foundation and Large Language Models, IEEE, Nov 2024, Dubai, United Arab Emirates. ⟨hal-04695193⟩
48 Consultations
40 Téléchargements

Partager

More