Skip to main navigation menu Skip to main content Skip to site footer
FrancoAngeli Journals

Materiali per la ricerca e l'approfondimento

No. 135 (2025)

Artificial Intelligence in Off- Label Drug Use: The Case of the Institute for Maternal and Child Health IRCCS Burlo Garofolo

DOI
https://doi.org/10.3280/mesa2025-135oa23433
Submitted
agosto 3, 2026
Published
2026-10-01

Abstract

Off‑label prescribing is a widespread practice in hospital pediatrics, a field characterized by the limited availability of authorized indications and age‑appropriate formulations. Its clinical, organizational, and economic implications require a structured, multi‑professional governance framework and open the perspective for artificial intelligence (AI) – based decision support systems capable of simultaneously fostering prescribing appropriateness and pharmacoeconomic analysis.
This contribution aims to explore clinical practices involving off‑label drug use in pediatrics within a specialized IRCCS, to reconstruct the perceived organizational and economic impact from the perspective of the various stakeholders involved, and to investigate expectations, critical issues, and conditions of acceptability of a dedicated AI‑based system.
The study presents an interpretative qualitative case study conducted at the Burlo Garofolo Pediatric Research Hospital (Trieste), which has recently undertaken a preliminary investigation into the contribution of Large Language Models to decision‑making processes related to off‑label prescribing in pediatrics.
The analysis examines the key characteristics of the off‑label prescribing process through semi‑structured interviews with professional figures representing the main decision‑making nodes along the prescribing pathway. Participants were selected using maximum‑variation purposive sampling, a non‑probabilistic technique widely adopted in qualitative research. Thematic analysis followed a hybrid approach, combining deductive coding based on the six sections of the interview guide with inductive identification of themes emerging from open narratives.
Three structural tensions were identified: informational asymmetry between prescribing and governance levels, role‑dependent variability in technological optimism, and fragmentation of the pediatric evidence base. These findings suggest that AI systems for pediatric off‑label prescribing should be designed as human‑in‑the‑loop decision support tools, integrated upstream within the prescribing workflow and oriented toward clinical, regulatory, and economic traceability, rather than as substitutes for clinical judgment.
The analysis concludes by outlining considerations and proposals regarding future development perspectives of the experience examined.

References

  1. Agenzia Italiana del Farmaco (AIFA) (n.d.). Lista dei medicinali erogabili a carico del Servizio Sanitario Nazionale ai sensi della Legge 648/1996.
  2. Arbo A., Flamigni A., Zamagni G., Abbate S., Migliore G., & Rocchi F. (2025). Off-label prescribing in Italian pediatric practice: insights from a nationwide survey. European Journal of Pediatrics, 184(12), 807. DOI: 10.1007/s00431-025-06660-1.
  3. Associazione Ospedali Pediatrici Italiani (AOPI) (2025). Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS) Burlo Garofolo. -- Disponibile su: https://www.aopi.it/strutture/istituto-di-ricovero-e-cura-a-carattere-scientifico-irccs-burlo-garofolo/.
  4. Bava M., Mallozzi V., Dal Cin M., Cinello M., & Zanchiello S. (2019). Un ecosistema digitale per la salute della donna e del bambino: Sperimentazione di una piattaforma per l’innovazione gestionale per l’IRCCS materno‑infantile Burlo Garofolo. In Proceedings della Conferenza GARR 2019. Consortium GARR. DOI: 10.26314/GARR-Conf19-proceedings-04.
  5. Borgonovi E. (2021). Management per la salute: Scienza, diritti, responsabilità sociale, efficienza. Milano: FrancoAngeli.
  6. Braun V., & Clarke V. (2006). Using thematic analysis in psychology. Qualitative Research in Psychology, 3(2): 77-101. DOI: 10.1191/1478088706qp063oa.
  7. Consortium GARR (2019). Un ecosistema digitale per una sanità sempre più smart. -- https://www.garrnews.it/storie/un-ecosistema-digitale-per-una-sanita-sempre-piu-smart.
  8. Denzin N.K., & Lincoln Y.S. (Eds.) (2018). The SAGE handbook of qualitative research (5th ed.). SAGE Publications.
  9. Flamigni A., Zamagni G., Paternuosto G., Arbo A. (2025). Paediatric rare diseases: Can large language models assist off-label prescribing?. Br J Clin Pharmacol., 91(11): 3201-3123. DOI: 10.1002/bcp.70168.
  10. Freeman S., Wang A., Saraf S., Potts E., McKimm A., Coiera E., & Magrabi F. (2025). Developing an AI governance framework for safe and responsible AI in health care organizations: Protocol for a multimethod study. JMIR Research Protocols, 14, e75702. DOI: 10.2196/75702.
  11. Garlatti A. (2017). L’economicità nelle aziende composte pubbliche. I cinque equilibri fondamentali. In Garlatti A., Gescon F. (2017). Economia aziendale. Casi e testi. Padova: CEDAM.
  12. Magalhães J., Rodrigues A.T., Roque F., Figueiras A., Falcão A., & Herdeiro M.T. (2015). Use of off-label and unlicensed drugs in hospitalised paediatric patients: A systematic review. European Journal of Clinical Pharmacology, 71(1): 1-13. DOI: 10.1007/s00228-014-1768-9.
  13. Perez E., Ringer S., Lukošiūtė K., Nguyen K., Chen E., Heiner S. et al. (2023). Discovering language model behaviors with model-written evaluations. Findings of the Association for Computational Linguistics: ACL 2023. DOI: 10.18653/v1/2023.findings-acl.847.
  14. Regolamento (UE) 2025/327 del Parlamento europeo e del Consiglio (2025). Relativo allo Spazio europeo dei dati sanitari. Gazzetta ufficiale dell’Unione europea.
  15. Sharma M., Tong M., Korbak T., Duvenaud D., Askell A., Bowman S.R. et al. (2024). Towards understanding sycophancy in language models. Proceedings of the International Conference on Learning Representations (ICLR 2024). DOI: 10.48550/arXiv.2310.13548.
  16. Sutton R.T., Pincock D., Baumgart D.C., Sadowski D.C., Fedorak R.N., & Kroeker K.I. (2020). An overview of clinical decision support systems: Benefits, risks, and strategies for success. npj Digital Medicine, 3, 17. DOI: 10.1038/s41746-020-0221-y.
  17. Topol E.J. (2019). High-performance medicine: The convergence of human and artificial intelligence. Nature Medicine, 25: 44-56. DOI: 10.1038/s41591-018-0300-7.