Will artificial intelligence chatbots replace clinical pharmacologists? An exploratory study in clinical practice.
François Montastruc, Wilhelm Storck, Claire de Canecaude, Léa Victor, Julien Li, Candice Cesbron, Yoann Zelmat, Romain Barus
Author Information
François Montastruc: Department of Medical and Clinical Pharmacology, Centre of Pharmacovigilance and Pharmacoepidemiology, Faculty of Medicine, Toulouse University Hospital (CHU), Toulouse, France.
Wilhelm Storck: Department of Medical and Clinical Pharmacology, Centre of Pharmacovigilance and Pharmacoepidemiology, Faculty of Medicine, Toulouse University Hospital (CHU), Toulouse, France.
Claire de Canecaude: Department of Medical and Clinical Pharmacology, Centre of Pharmacovigilance and Pharmacoepidemiology, Faculty of Medicine, Toulouse University Hospital (CHU), Toulouse, France.
Léa Victor: Department of Medical and Clinical Pharmacology, Centre of Pharmacovigilance and Pharmacoepidemiology, Faculty of Medicine, Toulouse University Hospital (CHU), Toulouse, France.
Julien Li: Department of Medical and Clinical Pharmacology, Centre of Pharmacovigilance and Pharmacoepidemiology, Faculty of Medicine, Toulouse University Hospital (CHU), Toulouse, France.
Candice Cesbron: Department of Medical and Clinical Pharmacology, Centre of Pharmacovigilance and Pharmacoepidemiology, Faculty of Medicine, Toulouse University Hospital (CHU), Toulouse, France.
Yoann Zelmat: Department of Medical and Clinical Pharmacology, Centre of Pharmacovigilance and Pharmacoepidemiology, Faculty of Medicine, Toulouse University Hospital (CHU), Toulouse, France.
Romain Barus: Department of Medical and Clinical Pharmacology, Centre of Pharmacovigilance and Pharmacoepidemiology, Faculty of Medicine, Toulouse University Hospital (CHU), Toulouse, France. romain.barus@univ-tlse3.fr.
PURPOSE: Recently, there has been a growing interest in using ChatGPT for various applications in Medicine. We evaluated the interest of OpenAI chatbot (GPT 4.0) for drug information activities at Toulouse Pharmacovigilance Center. METHODS: Based on a series of 50 randomly selected questions sent to our pharmacovigilance center by healthcare professionals or patients, we compared the level of responses from the chatbot GPT 4.0 with those provided by specialists in pharmacovigilance. RESULTS: Chatbot answers were globally not acceptable. Responses to inquiries regarding the assessment of drug causality were not consistently precise or clinically meaningful. CONCLUSION: The interest of chatbot assistance needs to be confirmed or rejected through further studies conducted in other pharmacovigilance centers.
Introducing ChatGPT. https://openai.com/blog/chatgpt . Accessed 12 May 2023
Ayers JW, Poliak A, Dredze M et al (2023) Comparing physician and artificial intelligence chatbot responses to patient questions posted to a public social media forum. JAMA Intern Med. https://doi.org/10.1001/jamainternmed.2023.1838
[DOI: 10.1001/jamainternmed.2023.1838]
Lee P, Bubeck S, Petro J (2023) Benefits, limits, and risks of GPT-4 as an AI chatbot for medicine. N Engl J Med 388:1233–1239. https://doi.org/10.1056/NEJMsr2214184
[DOI: 10.1056/NEJMsr2214184]
Johnson M, Patel M, Phipps A et al (2023) The potential and pitfalls of artificial intelligence in clinical pharmacology. CPT Pharmacomet Syst Pharmacol 12:279–284. https://doi.org/10.1002/psp4.12902
[DOI: 10.1002/psp4.12902]
van der Lee M, Swen JJ (2023) Artificial intelligence in pharmacology research and practice. Clin Transl Sci 16:31–36. https://doi.org/10.1111/cts.13431
[DOI: 10.1111/cts.13431]
Zhavoronkov A, Vanhaelen Q, Oprea TI (2020) Will artificial intelligence for drug discovery impact clinical pharmacology? Clin Pharmacol Ther 107:780–785. https://doi.org/10.1002/cpt.1795
[DOI: 10.1002/cpt.1795]
Carpenter KA, Altman RB (2023) Using GPT-3 to build a lexicon of drugs of abuse synonyms for social media pharmacovigilance. Biomolecules 13:387. https://doi.org/10.3390/biom13020387
[DOI: 10.3390/biom13020387]
Wang H, Ding YJ, Luo Y (2023) Future of ChatGPT in pharmacovigilance. Drug Saf. https://doi.org/10.1007/s40264-023-01315-2
[DOI: 10.1007/s40264-023-01315-2]
Krumborg JR, Mikkelsen N, Damkier P et al (2023) ChatGPT: first glance from a perspective of clinical pharmacology. Basic Clin Pharmacol Toxicol 133:3–5. https://doi.org/10.1111/bcpt.13879
[DOI: 10.1111/bcpt.13879]
Dave T, Athaluri SA, Singh S (2023) ChatGPT in medicine: an overview of its applications, advantages, limitations, future prospects, and ethical considerations. Front Artif Intell 6
Krumborg J, Mikkelsen N, Damkier P et al (2023) ChatGPT: first glance from a perspective of clinical pharmacology. Preprints
Nori H, King N, McKinney SM et al (2023) Capabilities of GPT-4 on medical challenge problems
