The Artificial Intelligence Program at the FDA’s Center for Devices and Radiological Health (CDRH) is one of the 20 research programs under the Office of Science and Engineering Laboratories (OSEL). The program’s research scope includes:
- Acquisition and processing of medical images
- Early disease detection
- More accurate diagnosis, prognosis, and risk assessment
- Identification of new patterns in human physiology and disease progression
- Development of personalized diagnostics
- Monitoring therapeutic treatment responses
The application range of AI technology in the medical field is continually expanding and is not expected to decelerate in the near future. The program focuses on the rigorous evaluation of the safety and effectiveness of these products. The application of AI technology in many different clinical areas, along with the unique nature of medical data, brings numerous challenges, including:
- Lack of effective methods to enhance AI algorithm training and testing data
- Lack of methods to analyze training and testing approaches to understand, measure, and minimize bias in AI-enabled devices
- Lack of metrics for AI device performance estimation, reference standards, and uncertainty
- Lack of methods to evaluate the safety and effectiveness of continuously learning AI algorithms
- Lack of methods to evaluate the safety and effectiveness of emerging clinical applications of AI-enabled medical devices
- Lack of methods for post-market monitoring of AI devices
The Artificial Intelligence Program aims to address these challenges by developing robust AI testing methods and evaluation methodologies to assess AI performance in both pre-market and real-world settings, ensuring the safety and effectiveness of novel AI algorithms. The program’s activities include:
- Addressing the limitations of medical data in AI
- Identifying and measuring AI bias to promote health equity
- Developing evaluation methods for AI-enabled medical devices: performance assessment and uncertainty quantification
- Creating performance evaluation methods for continuously learning AI-enabled medical devices
- Conducting regulatory evaluation of new AI uses to improve and automate medical practices
- Developing effective post-market monitoring methods for AI-enabled medical devices
With the rapid advancements in high-speed internet and big data applications, AI and digital health products are rapidly evolving. In response to customer demands, Weizhou Biotechnology Co., Ltd. has developed a new model of digital healthcare clinical services. Weizhou Company has managed over 40 clinical trial projects in various medical fields, assisting a wide range of digital healthcare clients in completing their medical research, clinical needs, and product registrations. Besides common IoT devices, medical software (SaMD: Software as a Medical Device) and AI are currently popular areas. Weizhou Company can provide appropriate assistance and consultation to medical software/AI companies during their product development process, ensuring compliance with domestic and international regulatory requirements, and facilitating the rapid completion of regulatory registrations.