Spectral AI Achieves 25% Patient Enrolment at Emergency Departments for U.S. Burn Pivotal Study and Adds Two New Clinical Trial Sites

Spectral AI, Inc an artificial intelligence (AI) company focused on medical diagnostics for faster and more accurate treatment decisions in wound care, today announced that it has achieved 25% patient enrolment at Emergency Departments (“ED”) for its U.S. Burn Pivotal Study and added two new ED Clinical Trial Sites for this study: MedStar Washington Hospital Centr in Washington, DC led by Principal Investigator Shawn Tejiram, MD and the University of Utah led by Principal Investigator Giavonni Lewis, MD, FACS. The addition of these two clinical research sites expands participating EDs to 11 facilities.

One of the largest domestic burn studies ever conducted, the U.S. Burn Pivotal Study is designed to validate the AI-driven algorithm used by the Company’s DeepView® System for burn indication (“DeepView AI®-Burn”).

“We are continuing to build momentum and advance towards achieving our ED enrollment goals,” said Peter M. Carlson, Chief Executive Officer of Spectral AI. “Access to specialized burn treatment in the United States has declined significantly, resulting in an increasing number of front-line ED clinicians assuming the initial responsibility of assessing the severity and healing trajectory of a burn wound. We believe that the use of DeepView AI®-Burn can deliver burn expert-level clinical support to a busy, oftentimes chaotic, ED setting.”

As previously announced, the Company has completed both adult and pediatric patient enrollment at U.S. burn centers for the U.S. Burn Pivotal Study. Using data from these burn center patients, the Company will pursue a De Novo submission to the U.S. Food and Drug Administration (“FDA”) requesting classification of DeepView AI®-Burn as a Class II medical device. The Company expects to submit this request to the FDA in the second quarter of 2025.

Spectral AI’s DeepView® System for burn indication is designed to distinguish between healing and non-healing tissue by providing an immediate and binary prediction of wound healing on Day One that can support clinical decision-making regarding next step treatment plans.