Complex prompting may yield more successful results when using AI to analyze physician interviews with pediatric cancer survivors, according to a study published March 25 in Communications Medicine.
For the study, researchers from Memphis, Tenn.-based St. Jude Children’s Research Hospital interviewed 30 pediatric cancer survivors and their caregivers. Experts then analyzed the conversations for signs of excessive pain and fatigue that may indicate patients in need of extra support.
After the initial human analysis, researchers gave the interview transcripts to ChatGPT and Llama using four prompt styles — two simple and two complex. The simple prompting approaches produced “unstable and inaccurate results,” while the complex prompts were able to distinguish the physical, cognitive and social effects certain symptoms may have on survivors.
Read the full study here.
At the Becker's Perioperative Summit, taking place September 14–15 in Chicago, perioperative leaders and healthcare executives will focus on improving operating room efficiency, enhancing patient safety, optimizing staffing and driving innovation across surgical services. Apply for complimentary registration now.
