Spectral AI, a predictive AI company focused on medical diagnostics for treatment decisions in wound care, announces that it has completed the vetting, or “truthing” of an image database of over 3,000 biopsied images from burn centers located throughout the U.S.
“Truthing” is the rigorous process of gathering ground-truth data that verifies whether portions of a wound did or did not heal and then using this data to train AI-powered algorithms.
The company said that for each patient, images were collected during the early stages of treatment and correlated with biopsies, 21-day wound assessments, and expert evaluation. The combination creates a ground-truth data set that Spectral AI says enables its DeepView system to distinguish between wounds likely to heal and those requiring intervention.
Spectral AI also announced that it is expanding its focus beyond burn victims to include emergency department patients with wounds. It is planning to initiate a truthing process to include data collected during critical early stages of care at hospital admittance to enable the DeepView System to adapt to a broader range of clinical scenarios.
