Search papers, labs, and topics across Lattice.
2
0
3
2
A large language model (gpt-4o-mini) for surgical site infection adjudication, achieving 100% sensitivity but 69.4% specificity is evaluated, underscoring the need for refined models to improve specificity without compromising accuracy.
Automating surgical patient triage with an LLM achieves 94% sensitivity, but discrepancies reveal more about clinical workflow gaps than AI errors.
