(85 days)
The PillCam SB 3 capsule is intended for visualization of the small bowel mucosa.
- . It may be used in the visualization and monitoring of lesions that may indicate Crohn's disease not detected by upper and lower endoscopy.
- . It may be used in the visualization and monitoring of lesions that may be a source of obscure bleeding (either overt or occult) not detected by upper and lower endoscopy.
- It may be used in the visualization and monitoring of lesions that may be potential causes of iron deficiency anemia (IDA) not detected by upper and lower endoscopy.
The Suspected Blood Indicator (SBI) feature is intended to mark frames of the video suspected of containing blood or red areas.
The PillCam SB 3 capsule may be used as a tool in the detection of abnormalities of the small bowel and is intended for use in adults and children from two years of age.
The subject device, PillCam Cloud Reader SW, is an additional cloud data management option which enables users to review PillCam CE videos stored on the public cloud repository.
The PillCam Cloud Reader SW utilizes Amazon Cloud Services (also referred to as "HCP Cloud" or "AWS") offering a vast standardized, robust, and verified platform that facilities multiple containers while utilizing various cloud services. AWS enables easy and efficient scaling up and down, leveraging the system's efficiency for the PillCam Cloud Reader SW.
The AWS cloud environment is comprised of 2 components: the Cloud Reader Video Storage and HCP Software Application, refer to Section 5.3 for further technological details of each component.
The PillCam Sync Agent is a local software component that is installed in the PillCam Software 9.0E workstation. The PSA continuously sycronizes the local data from the local database (predicate component #4 in the figure below) back and forth to the PillCam Cloud Reader Video Storage component.
The provided text describes the regulatory submission for the PillCam SB 3 Capsule Endoscopy System with PillCam Software 9.0E (including PillCam Cloud Reader Software). This submission focuses on the addition of a cloud data management option (PillCam Cloud Reader SW) to an already cleared device.
Crucially, the document states: "PillCam Cloud Reader is a software application that is utilized to view videos and create reports and does not process and/or analyze acquired images. Input videos are displayed with no processing or alteration. The compilation of the video from the acquired images is still conducted using the predicate device PillCam capsule endoscopy system with PillCam Software 9.0E workstation component." This means the device itself (the cloud reader software) does not have performance characteristics related to diagnostic accuracy, as it merely displays previously processed video.
Therefore, the typical acceptance criteria and study design for evaluating the diagnostic performance of an AI-powered medical device are not applicable here. The "acceptance criteria" for this device relate to its functionality as a cloud-based viewing and reporting tool, and its compliance with software and cybersecurity standards. The document outlines a Non-Clinical Performance Assessment, focusing on software verification and risk management.
Here's an interpretation based on the provided text:
1. A table of acceptance criteria and the reported device performance
The document does not provide a table with specific diagnostic performance acceptance criteria (e.g., sensitivity, specificity, AUC) because the PillCam Cloud Reader SW is a viewing and reporting tool, not an image analysis or diagnostic device. Its performance is evaluated based on software functionality, data integrity, and compliance with regulatory standards.
The "acceptance criteria" would be met by demonstrating:
- Functional performance: The ability to correctly display video, create reports, and utilize cloud services as intended.
- Data integrity and security: Ensuring that video data is accurately stored, retrieved, and secure within the AWS cloud environment.
- Compliance: Adherence to established software development lifecycle processes, risk management, and relevant FDA-recognized consensus standards.
The reported device performance in this context is that the device has undergone "Non-Clinical Performance Assessment" involving "protocols, test methods, and acceptance criteria used for verification of the proposed PillCam Cloud Reader are well established methods." It states: "The information summarized in Table 7-1: Design Controls Activities Summary for PillCam Cloud Reader Software, including related risks and risk mitigations, are based on the PillCam Cloud Reader Software risk management plan and summary. These well established methods are in agreement with recommendations in the applicable FDA recognized census standards listed in Section 9.0."
Since this acceptance is for a cloud viewer and not an image analysis tool, detailed performance metrics like sensitivity/specificity are not relevant given the information provided.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
Not applicable, as this is a software functionality and cybersecurity evaluation, not a diagnostic performance study using a medical image test set. The testing would involve simulated or real operational scenarios for the software.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
Not applicable, as there is no diagnostic "ground truth" to establish for this particular software component. The software does not interpret images or provide diagnoses.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
Not applicable. The PillCam Cloud Reader SW does not involve AI assistance for image interpretation.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Not applicable. The PillCam Cloud Reader SW is a viewing platform, not a standalone diagnostic algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
Not applicable for diagnostic performance. If "ground truth" were to be considered for software functionality, it would refer to the expected behavior of the software according to its design specifications.
8. The sample size for the training set
Not applicable, as this device does not involve a machine learning model that requires a training set.
9. How the ground truth for the training set was established
Not applicable.
§ 876.1300 Ingestible telemetric gastrointestinal capsule imaging system.
(a)
Identification. An ingestible telemetric gastrointestinal capsule imaging system is used for visualization of the small bowel mucosa as an adjunctive tool in the detection of abnormalities of the small bowel. The device captures images of the small bowel with a wireless camera contained in a capsule. This device includes an ingestible capsule (containing a light source, camera, transmitter, and battery), an antenna array, a receiving/recording unit, a data storage device, computer software to process the images, and accessories.(b)
Classification. Class II (special controls). The special control is FDA's guidance, “Class II Special Controls Guidance Document: Ingestible Telemetric Gastrointestinal Capsule Imaging Systems; Final Guidance for Industry and FDA.”