Evidence-based pediatric dosing through human-AI interaction
The use of drugs in children, though not registered, is frequently necessary to ensure the best treatment for the individual patient. However, the off-label use of drugs for children can lead to incorrect dosing, thereby putting the child at risk. The Dutch Pediatric Formulary faces a significant challenge in keeping up-to-date with the growing literature on dosing recommendations for nearly 800 drugs across multiple age groups and indications.
To address this challenge, the AI-aided Knowledge Discovery Lab is developing a human-AI interaction pipeline that can automate the systematic review process, improve the quality and quantity of dosing recommendations, and increase transparency and reproducibility.
This technology has the potential to improve pharmacotherapy for other special populations, such as pregnant women and the elderly, and guideline development in general.