Search Results

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.

Ask a specific question about this device

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 PillCam SB 3 Capsule endoscopy system is a device that provides visualization of the small bowel mucosa. The device was previously cleared under 510(k) submission K123864 for the SB 3 Capsule, PillCam DR3 recorder and accessories, and K170210 incorporated the PillCam Software 9.0 to the device is comprised of four main subsystems further described below.
Ingestible PillCam SB 3 Capsule: The disposable, ingestible PillCam SB 3 Capsule is designed to acquire images during the natural propulsion through the digestive system. The capsule transmits the acquired images via a RF communication channel to the PillCam DR3 recorder located outside the body.
PillCam DR3 Recorder: The PillCam DR3 recorder is an external receiving/recording unit that receives and stores the acquired images from the capsule.
PillCam Software: The PillCam Software 9.0E is a software application that is utilized to process, analyze, store, and view the acquired images collected from the PillCam DR3 recorder to create a video of the images. The software also includes a reporting function to create detailed clinical reports, in-service training videos, and patient instruction forms. PillCam Software 9.0E supports PillCam capsule endoscopy of the gastrointestinal (GI) tract with all PillCam capsules (SB, COLON, UGI and SBC (renamed Crohn's)).
Workstation and Accessories: The Workstation is a user-provided modified standard personal computer, that is the operational platform for the PillCam software. The Sensor array or sensor belt receive data from the PillCam capsule and transfer the data to the PillCam Recorder DR3.

The provided text does not contain detailed acceptance criteria for standalone device performance and specific study data to prove that the device meets these criteria. Instead, it focuses on demonstrating substantial equivalence to predicate devices, particularly regarding a new remote administration option.

However, based on the information provided, here's a breakdown of what can be inferred about the device's performance characteristics and the supporting evidence:

1. Table of Acceptance Criteria (Inferred) and Reported Device Performance

Since explicit acceptance criteria for a "new" device performance study are not provided, we must infer that the accepted performance is based on the previously cleared predicate devices. The document explicitly states: "Prior testing provided in support of the Given PillCam SB 3 capsule endoscopy system (K123864) and PillCam Desktop Software 9.0 (cleared in K170210 with SBC capsule endoscopy system), verified the device's components, as well as the performance."

2. Sample Size Used for the Test Set and Data Provenance

• For remote administration usability and safety:

  • Test Set Sample Size: 35 procedures.
  • Data Provenance: Commercial centers, since October 2020. This indicates prospective real-world use data. The country of origin is not explicitly stated, but the submitter is an Israeli company.

• For core device performance (visualization, lesion detection):

  • The document implies that the performance data for these aspects come from the predicate device clearances (K123864 and K170210). The sample sizes and data provenance for those original studies are not provided in this document.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications

• For remote administration usability: The document mentions "usability testing... consisted of simulated-use sessions with the device and a healthcare provider." It does not specify the number of healthcare providers or their qualifications.
• For remote administration safety: The 35 procedures involved patients, and "no complications reported" would likely be based on clinical observation by medical staff. No independent experts establishing "ground truth" are mentioned for this aspect, as it relates to complication rates rather than diagnostic accuracy.
• For core device performance: This information would be within the predicate device submissions (K123864, K170210) and is not provided in this document.

4. Adjudication Method for the Test Set

• The document does not describe any formal adjudication method for the remote administration usability and safety data. For usability, errors were "captured," but the process for classifying or adjudicating these errors (e.g., by multiple experts) is not detailed.
• For the core device performance, information on adjudication from the predicate studies is not provided in this document.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• No, a MRMC comparative effectiveness study was not done for this submission. The submission is primarily focused on demonstrating substantial equivalence for a labeling change (remote administration) based on existing device performance. There is no mention of human readers improving with or without AI assistance, as the "AI" component here (SBI feature) is already part of the predicate and not being newly evaluated in a comparative effectiveness study against human readers.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

• The document refers to the "Suspected Blood Indicator (SBI) feature" which "is intended to mark frames of the video suspected of containing blood or red areas." This feature, while part of the software, is an assistive tool for human readers.
• The document does not report a standalone performance study (i.e., algorithm only without human-in-the-loop performance) for the SBI feature or any other automated detection capability. Its performance is implicitly considered acceptable through its inclusion in the predicate device.

7. Type of Ground Truth Used

• For remote administration usability: Ground truth was established through observing and recording user performance and errors in simulated use, likely against pre-defined success criteria for the procedure steps.
• For remote administration safety: Ground truth was the absence of reported complications in real-world clinical use.
• For core device performance (e.g., lesion detection): This information would be in the predicate device submissions and is not provided in this document. Typically for such devices, ground truth might involve endoscopic findings, histological confirmation (pathology), or clinical follow-up/outcomes data.

8. Sample Size for the Training Set

• The document does not provide any information on the sample size used for training any algorithms within the PillCam Software 9.0E, including the SBI feature. This is likely because the software itself (including the SBI feature) existed in the predicate device.

9. How the Ground Truth for the Training Set Was Established

• As no information on a training set is provided, the method for establishing its ground truth is also not available in this document.

Ask a specific question about this device