Summaries that include a confidence level about what the system extracted from medical records or conversations—'high confidence on medication list, lower confidence on allergy severity'—so you know what to double-check yourself. Not all information is equally reliable.
Confidence scoring is a measure of how certain an AI system is about a particular output, sometimes expressed as a percentage or a low, medium, or high rating attached to a response.
When using AI to summarize care histories or interpret test results, understanding confidence scores helps caregivers know when to trust an AI summary and when to seek human verification from a clinician.
Peri can explain this concept, give practical examples, help you decide whether it applies to your situation, or recommend a journey if appropriate.
Explore related journeys or tell Peri what you're working through.