05-07-2026
In a crisis, every second counts — and every decision carries weight.
Large language models (LLMs) could revolutionize medical triage, enabling “triage at scale” in disaster zones and overwhelmed emergency departments. The implications extend far beyond healthcare: this innovation illustrates how AI can augment human decision-making in complex, high-stakes environments where incomplete information and time pressure collide.
Daniels School MBA alum Aaron Lai and co-author Li-Lin Liang explore these concerns in a recent ORMS Today article on a scalable AI digital first responder.
Lai and Liang’s proposed framework — combining interoperable clinical data, an open-weight LLM decision engine, and an “AI-as-judge” validation layer — offers a blueprint for scalable, responsible AI systems. The prototype matches baseline clinician accuracy while prioritizing patient safety, a critical balance in sectors where errors come at asymmetric costs.
For business leaders, the lessons are profound. The triage model exemplifies how explainable, auditable AI can enhance professional judgment without replacing it — a concept relevant to finance, logistics and any domain requiring rapid, data-informed decisions. Triage at scale is more than a healthcare innovation; it’s a new way of thinking about how organizations can use AI to allocate resources efficiently, manage risk responsibly and build trust in autonomous systems.
Read the full analysis in ORMS Today to see how AI triage is shaping the future of intelligent operations.
Aaron Lai, CFA, serves as a Senior Fellow of the Krenicki Center for Business Analytics and Machine Learning at Purdue University. He has extensive experience within the healthcare industry and is presently in the online Doctor of Technology program at Purdue, with research concentrating on LLM triage in critical care scenarios. In addition, he recently received the Certificate of Commendation from the Mayor of the City of Arcadia, CA for his contribution to the Chinese American Military Support, a group that supports military personnel and their families.
