Advances & More News / Newly reported from the NIH: Large Language Model Good for Chest Radiography

Outputs of the large language model (LLM) Vicuna-13B show moderate-to-substantial agreement with existing labelers for 13 findings on chest radiography reports, according to a study published online Oct. 10 in Radiology. Pritam Mukherjee, Ph.D., from the National Institutes of Health (NIH) Clinical Center in Bethesda, Maryland, and colleagues examined the feasibility of using an alternative LLM, Vicuna-13B, which can be run locally for labeling radiography reports, in a retrospective study that included chest radiography reports from the MIMIC-CXR and NIH data sets. Reports were assessed for 13 findings. Source: Advances and More licensed by HealthDay

read more

MORE NEWS
From China: SARS-CoV-2 Infection Linked to Incidence of BPH Complications
Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection is associated with an increased incidence of benign ... read more
Directly from Lithuania: Bowel Habits May Be Tied to Severity of Menopause Symptoms
Perceived stress and some gastrointestinal symptoms are associated with menopausal symptoms, according to a study published ... read more
From the UK: Selenium Not Linked to Recurrence of Non-Muscle-Invasive Bladder Cancer
For patients with non-muscle-invasive bladder cancer (NMIBC), selenium supplementation does not reduce the risk for recurrence, ... read more
Newscasting from the USA: Early Pregnancy Obesity Linked to Adverse Pregnancy Outcomes
Early pregnancy obesity is associated with a higher incidence of postpartum hypertension, hyperlipidemia, and diabetes, according ... read more