Comparing Humans and Large Language Models in Filling Clinical Questionnaires

  • Valeria Nardoni
  • , Giulia Hyeraci
  • , Martina Maccari
  • , Alejandro Arana
  • , Ersilia Lucenteforte
  • , Giorgio Limoncella
  • , Sima Mohammadi
  • , Giuseppe Roberto
  • , Amirreza Dehghan Tarazjani
  • , Gianni Virgili
  • , Daniel Weibel
  • , Rosa Gini
  • , Marco Lippi*
  • , Simone Marinai
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Filling clinical questionnaires to perform retrospective studies is a time-consuming task that requires strong expertise in specific domains. We exploit prompt engineering techniques to optimize the completion of clinical questionnaires through Large Language Models (LLMs), aiming to compare their performance with respect to human experts. Despite challenges related to limited access to input data, our preliminary experimental results demonstrate the potential of LLMs to streamline clinical data collection, greatly reducing the manual workload for healthcare professionals. However, human validation remains essential to ensure accuracy and reliability in real-world applications.

Original languageEnglish
Title of host publicationHHAI 2025 - Proceedings of the 4th International Conference on Hybrid Human-Artificial Intelligence
EditorsDino Pedreschi, Michela Milano, Ilaria Tiddi, Stuart Russell, Chiara Boldrini, Luca Pappalardo, Andrea Passerini, Shenghui Wang
PublisherIOS Press
Pages525-527
Number of pages3
ISBN (Electronic)9781643686110
DOIs
Publication statusPublished - 22 Sept 2025
Event4th International Conference on Hybrid Human-Artificial Intelligence, HHAI 2025 - Pisa, Italy
Duration: 9 Jun 202513 Jun 2025

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume408
ISSN (Print)0922-6389
ISSN (Electronic)1879-8314

Conference

Conference4th International Conference on Hybrid Human-Artificial Intelligence, HHAI 2025
Country/TerritoryItaly
CityPisa
Period9/06/2513/06/25

Keywords

  • Clinical Records
  • Large Language Models
  • Questionnaire Filling

Fingerprint

Dive into the research topics of 'Comparing Humans and Large Language Models in Filling Clinical Questionnaires'. Together they form a unique fingerprint.

Cite this