Boston Children’s Hospital has teamed up with Amazon Web Services to create “clinical doppelgangers” to find patients with like conditions and boost treatment.
Clinicians at the pediatric health system use large language models and AWS managed services to surface patients with similar symptoms, illnesses and lab values, according to a Jan. 6 blog post by leaders at Boston Children’s and AWS. Boston Children’s processed over 6,000 complex pediatric cardiac ICU cases, creating a database of more than 250 clinical data points.
“When a clinician wants to find patients that have, for example, hypoplastic left heart and arrhythmia after Glenn [surgery] with good response to pacing, the LLM interprets intent and plans a multistep search across our knowledge base to develop a relevant patient cohort,” the leaders wrote. “The clinician can then look over these similar patients to help inform decisions going forward for the patient at hand.”
They are aiming to reduce chart review by 80%, expand to other specialties and embed the feature into the EHR.
The post Boston Children’s Hospital, AWS develop ‘clinical doppelgangers’ appeared first on Becker’s Hospital Review | Healthcare News & Analysis.
Health IT
