CHOP develops AI guidelines for pediatric neuro-oncology
These new guidelines aim to foster ethical AI deployment in pediatric neuro-oncology, guiding clinicians on techniques, reporting standards, and the importance of unbiased, precise AI tools for better patient care.
A group of scientists from Children’s Hospital of Philadelphia (CHOP) has developed new guidelines that outline artificial intelligence (AI) best practices in pediatric neuro-oncology. Key recommendations are summarized in a press release.
The goal of this action is to foster the responsible use of AI in pediatric neuro-oncology settings. Elements of the guidance are “a policy review from the AI in Response Assessment in Pediatric Neuro-Oncology (AI-RAPNO) subcommittee and a companion review in TheLancet Oncology, detailing how AI can enhance tumor assessment, support treatment planning and improve outcomes for children with brain tumors.”
AI-RAPNO suggests:
Be specific; use “standardized imaging inputs and labels”
Make sure techniques aren’t biased
Thoroughly report results and take “the limits and accuracy of the techniques” into account
