Spectral AI has finished truthing all images gathered from U.S. burn centers, a pivotal step in training the company’s proprietary DeepView System to predict wound healing outcomes accurately.

Having completed the process for burn centers, Spectral AI is now initiating truthing for images collected from emergency departments and emergency rooms nationwide, expanding the scope of its DeepView System’s capabilities.

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 for training of its AI-powered algorithm. For each patient, images are collected during the early stages of treatment and correlated with biopsies, 21-day wound assessments, and expert evaluations. This combination of data creates a “ground truth” dataset, enabling the DeepView System to distinguish between wounds likely to heal and those requiring intervention.

“By completing the truthing process for burn centers, this adds to Spectral AI’s largest comprehensive tissue dataset, encompassing over 3,000 biopsied images,” Spectral AI Board Chairman Dr. J. Michael DiMaio said. “This achievement reflects collaboration between internationally recognized burn experts, skilled dermatopathologists, and our engineers and data scientists. This multidisciplinary effort ensures that our technology evolves with precision and reliability, surpassing the limitations of traditional diagnostic methods.”

The company’s Burn Biopsy Algorithm (BBA), developed alongside leading experts, integrates advanced machine learning with clinical insights, allowing the DeepView System to identify healing trajectories with purported effectiveness. By leveraging data from the largest burn tissue bank ever assembled, the DeepView System is designed to provide clinicians with actionable information and reducing guesswork.

Spectral AI currently is expanding its focus to emergency departments, where the stakes are equally high. The truthing process will include data collected during the critical early stages of care, enabling the DeepView System to adapt to a broader range of clinical scenarios.

“Our team is committed to ensuring the DeepView System delivers unparalleled diagnostic accuracy,” Dr. DiMaio stated. “By incorporating data from diverse care settings, we aim to create a solution that seamlessly integrates into workflows across the spectrum of acute care.”

Spectral AI has successfully enrolled and completed image collection for the BARDA burn study, a critical step in training the AI algorithm for the DeepView AI-Burn device. The company expects to complete a U.S. Food and Drug Administration De Novo submission in the first half of 2025, seeking classify the DeepView AI-Burn system as a Class II medical device. Designed for use in multiple medical settings, the DeepView AI-Burn system provides fast and accurate burn-depth assessments, empowering clinicians to make informed, early treatment decisions and improving care for both adult and pediatric burn victims.

Spectral AI, Inc. is a Dallas-based predictive AI company focused on medical diagnostics for faster and more accurate treatment decisions in wound care, with initial applications involving patients with burns and diabetic foot ulcers. The company is working to revolutionize wound care management by “Seeing the Unknown” with its DeepView System, a predictive device that offers clinicians an objective and immediate assessment of a wound’s healing potential prior to treatment or other medical intervention. With algorithm-driven results and a goal of exceeding the current standard of care in the future, DeepView is expected to provide faster and more accurate treatment insight toward value care by improving patient outcomes and reducing healthcare costs.