Introduction:
Over the years, the use of artificial intelligence (AI) in medical
research has shown great promise in enhancing drug discovery,
identifying new treatment targets, and predicting disease
outcomes1. AI is an umbrella term encompassing several
advanced technologies, such as machine learning, natural language
processing, and deep learning. These methods facilitate the extraction
of patterns and insights from vast amounts of data. A recent exciting
development in AI research has been the public release of
ChatGPT2, developed by OpenAI. The model architecture
behind ChatGPT (GPT; Generative Pre-trained
Transformer3 has shown to be very capable of achieving
strong natural language understanding, while its accessible graphical
user interface has resulted in widespread adoption.
Large Language Models (LLMs) such as ChatGPT are trained on an enormous
corpus of text in order to generative responses to
queries4. By devoting considerable human time labeling
the quality of generated responses and re-training the model to produce
the best responses, ChatGPT has suprised many to produce fluent and
accurate responses to human inquiries. Aside from the public interest in
the use of ChatGPT, there has also been suggestions of using the model
to assist students and researchers by editing text, answering questions,
writing code, and finding relevant literature given a
query5–8.
There already exist several publications discussing the potential impact
of LLMs on a wide range of different research
fields9–11. It however remains unknown if tools like
ChatGPT can also support researchers from relatively small research
fields, potentially resulting from a lower availability of training
data. In this work, we investigate if ChatGPT can be used to assist
during the development of population pharmacokinetic (PK) models. As an
use-case, we use ChatGPT to generate R code for predicting in vivo drug
concentrations of standard half-life factor VIII (FVIII) concentrates in
patients with haemophilia A12. Next, we query ChatGPT
to generate an interactive R shiny application that can be used for the
interpretation of the model and the selection of optimal doses. Based on
this use-case, we aim to show that researchers unfamiliar with
programming in R can nonetheless produce usable code for data analysis.