VELMENI for DENTISTS (V4D)

“V4D software medical device comprises of the following key components:”

“Machine Learning (ML) Engine delivers V4D's core ML capabilities through the radiograph type classifier, condition detection module, tooth numbering module, and merging module. This submission provided a set of PCCPs that Velmeni will follow to validate the standalone updates to the identified Machine Learning Software Device functions (ML-DSF) of the device, namely the Condition Detection Modules for each radiograph type (bitewing, periapical, and panoramic) that contains the models trained for detecting predetermined conditions (caries and fillings/restorations, fixed prostheses, and implants).”

“The PCCPs include key components (data management, retraining, performance evaluation, update procedures, and impact assessments) that describe the plan for developing, validating, and implementing the modifications using post-market and real-world data to reduce false positives and negatives. The predefined performance and validation requirements must be met prior to the manual update of the device. Re-training will be triggered if performance or data drift metrics are observed.”

“FDA's substantial equivalence determination also included the review and clearance of your Predetermined Change Control Plan (PCCP).”

“Velmeni maintains adherence to FDA guidance, Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions, throughout the course of model modifications under the authorized PCCP.”