Continuing the Chat: How Can we Improve the Performance of an Artificial Intelligence Chatbot in Answering Clinical Infectious Diseases Pharmacotherapy Questions?

Open Forum Infectious Diseases, Journal Year: 2025, Volume and Issue: 12(2)

Published: Jan. 31, 2025

Language: Английский

---

A decalogue for personalized travel health assistance with AI-driven chatbots

Journal of Travel Medicine, Journal Year: 2024, Volume and Issue: 31(4)

Published: Feb. 9, 2024

This article delves into the innovative integration of AI-driven chatbots in travel medicine, proposing a decalogue for creating effective, personalized health assistance tools with practical example (a custom GPT, OpenAI GPT-4).

Language: Английский

---

Performance of ChatGPT-4o in the diagnostic workup of fever among returning travelers requiring hospitalization: a validation study

Journal of Travel Medicine, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 17, 2025

Febrile illness in returned travelers presents a diagnostic challenge non-endemic settings. Chat generative pretrained transformer (ChatGPT) has the potential to assist medical tasks, yet its performance clinical settings rarely been evaluated. We conducted preliminary validation assessment of ChatGPT-4o's workup fever returning travelers. retrieved records hospitalized with during 2009-2024. The scenarios these cases at time presentation emergency department were prompted ChatGPT-4o, using detailed uniform format. model was further four consistent questions concerning differential diagnosis and recommended workup. To avoid training, we kept blinded final diagnosis. Our primary outcome success rates predicting (gold standard) when requested specify top 3 diagnoses. Secondary outcomes single most likely diagnosis, all necessary diagnostics. also assessed ChatGPT-4o as tool for malaria qualitatively evaluated failures. predicted 68% (95% CI 59-77%), 78% 69-85%), 83% 74-89%) 114 cases, three diagnoses, possible respectively. showed sensitivity 100% 93-100%) specificity 94% 85-98%) malaria. failed provide 18% (20/114) primarily by failing predict globally endemic infections (16/21, 76%). demonstrated high accuracy real-life febrile presenting department, especially Model training is expected yield an improved facilitate decision-making field.

Language: Английский

---

Implementation of ChatGPT to enhance pre-travel consultation in a specialist tertiary centre in Singapore

Journal of Travel Medicine, Journal Year: 2024, Volume and Issue: unknown

Published: July 18, 2024

We designed and implemented an interactive artificial intelligence tool based on ChatGPT to complement the pre-travel consultation in a specialist tertiary centre that cares for range of travellers including those who have undergone solid organ or bone marrow transplantation, as well persons living with HIV.

Language: Английский

---