Physician in the Loop
For youSign in
Infectious disease ·

Urine antigen test detects 92% of invasive aspergillosis cases; AI model predicts prolonged ICU stays in sepsis

A petri dish of pale agar dotted with round white colonies of a few sizes and four glowing amber ones, its clear lid tilted against it.
THE SHORT READ

A rapid urine test for invasive aspergillosis, cleared by the Food and Drug Administration (FDA) in late 2025, identified 46 of 50 confirmed cases in a study in Clinical Infectious Diseases, Johns Hopkins Medicine said. Korean researchers reported an artificial intelligence model that predicts long intensive care unit stays in sepsis.

THE DETAILS
  • Research Oct 7, 2026
    FDA-cleared urine antigen test identifies 92% of invasive aspergillosis cases and 88% of negatives in Johns Hopkins study
    A rapid urine assay that detects Aspergillus antigens, cleared by the Food and Drug Administration (FDA) in late 2025 for adults with suspected invasive aspergillosis, correctly identified 46 of 50 confirmed cases (92%) and 218 of 249 negative samples (88%) in frozen samples from 290 participants, Johns Hopkins Medicine said Oct. 7 of a study in Clinical Infectious Diseases. In 171 fresh samples tested in real time, it identified six of seven positive and 35 of 39 negative cases. Pearl Diagnostics and the National Institutes of Health funded the study; co-author Dr. Kieren Marr started Pearl and is a shareholder.
    Sources: Johns Hopkins Medicine, Clinical Lab Products
  • AI Oct 9, 2026
    AI model predicts ICU stays longer than four days in patients with sepsis from first-day organ failure data
    Researchers at Chungbuk National University Hospital in South Korea reported in npj Digital Medicine on Oct. 9 a deep learning model, FT-TabNet, that uses 17 Sequential Organ Failure Assessment-based features from the first 24 hours of intensive care unit admission to predict a stay of more than four days in patients with sepsis. Developed on MIMIC-IV data, it had an area under the receiver operating characteristic curve of 0.848 in internal validation and 0.823 in external validation at Chungbuk National University Hospital; the abstract also reports 0.781 for a second cohort. The study measured prediction accuracy, not patient outcomes.
    Source: npj Digital Medicine

The weekly innovation roundup for infectious disease, published every Sunday for the week before; every item links to its sources. Latest infectious disease news · All specialties