Share:
Peer-Reviewed Publication
medRxiv2025December 5, 2025Journal Article

Pandemic-Potential Viruses are a Blind Spot for Frontier Open-Source LLMs.

Laura Luebbert1,2,3,4, Yasha Ektefaie1,3,4, Arya S Rao4,5, Colby Wilkason3,4, Dolo Nosamiefan6, Olivia Achonduh-Atijegbe6, Harouna Soumare6, Adefoye Precious Adebayo6, Olufemi Olulaja6, Judith Amadi6, Nicholas Oyejide6, Funmilayo Olayiwola6, Etim Henshaw6, Yusuf Okocha7, Nkechinyere Nwachukwu7, Elechi Friday Ewah7, Sylvanus Okoro7, Ebenezer Nwakpakpa7, Peter Okokhere8, Kelly Iraoyah8, Joseph Okoeguale8, Ireti Dada9, Andy Burris10, Karlie Zhao10, Ellory Laning10, Chase van Amburg10, Paul Cronan10, Ben Fry10, Christian Happi6,11, Al Ozonoff5,12, Pardis C Sabeti3,4,13,14,15
1Eric and Wendy Schmidt Center, Broad Institute of MIT and Harvard, MA, USA.
2FutureHouse, CA, USA.
3Department of Organismic and Evolutionary Biology, Harvard University, MA, USA.
4Infectious Disease and Microbiome Program, Broad Institute of MIT and Harvard, MA, USA.
5Harvard Medical School, MA, USA.
6Institute of Genomics and Global Health (IGH), Redeemer's University, Osun State, Nigeria.
7Alex Ekwueme Federal University Teaching Hospital, Ebonyi State, Nigeria.
8Irrua Specialist Teaching Hospital, Edo State, Nigeria.
9General Hospital Ikorodu, Lagos State, Nigeria.
10Fathom Information Design, Massachusetts, USA.
11Department of Biological Sciences, Redeemer's University, Osun State, Nigeria.
12Boston Children's Hospital, MA, USA.
13Howard Hughes Medical Institute, MD, USA.
14Department of Immunology and Infectious Diseases, Harvard T.H. Chan School of Public Health, MA, USA.
15Massachusetts Consortium on Pathogen Readiness, Harvard Medical School, MA, USA.

Abstract

We study large language models (LLMs) for front-line, pre-diagnostic infectious-disease triage, a critically understudied stage in clinical interventions, public health, and biothreat containment. We focus specifically on the operational decision of classifying symptomatic cases as viral vs. non-viral at first clinical contact, a critical decision point for resource allocation, quarantine strategy…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.