STAT+: How health systems are embracing chatbots to query and summarize patient records
Several large health systems are rolling out AI chatbots to query patient records, saying they save time and increase diagnostic accuracy.
The pathologists were puzzled when six individuals struggled to diagnose a patient's cancer from a recent lymph node biopsy. They had stained the cells 70 times in an attempt to reveal more distinguishing characteristics, but no consensus emerged. A physician at Stanford turned to a novel tool called ChatEHR, among several large language model-powered tools being employed by healthcare systems to condense patients' extensive medical records.
When prompted about the patient's history of skin lesions, ChatEHR provided an answer: the patient had previously been diagnosed with sarcomatoid squamous cell carcinoma in a different health system. This information "completely explained the findings in the lymph node," wrote the delighted doctor in their feedback for the chatbot.
"If that doesn't prove the value of ChatEHR, I don't know what does!" The physicians hoped to discover such valuable insights when health systems began experimenting with generative AI tools like ChatEHR to search and synthesize patients' health records. While finding diagnostic mysteries was the least of their selling points, numerous healthcare systems are now moving toward widespread implementation of chatbots for electronic health records (EHRs), both homegrown and vendor-built.
Written by urgent.news from STAT News's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
