Search Filters

Search Results

Found 2 results

510(k) Data Aggregation

    Why did this record match?
    Reference Devices :

    K103088, K090557

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The NaviCam Xpress Stomach Capsule is intended for visualization of the stomach of patients >= 6 years old with BMI =

    Device Description

    NaviCam® Xpress Stomach Capsule Endoscope System enables the operator to control the capsule endoscope inside the stomach. The capsule endoscope can be moved in any direction during examination. The direction and angulation of the capsule camera head can be adjusted in real-time, hence realizing complete control of capsule endoscope movement and attitude during examination in the X left and right, Y forward and backward, Z up and down directions as well as rotation clockwise and counterclockwise.

    AI/ML Overview

    This document (K231960) describes a 510(k) premarket notification for the NaviCam Xpress Stomach Capsule Endoscope System. The filing is an expansion of the Indications for Use for an already cleared device, primarily expanding age and BMI limitations. As such, the performance study focuses on demonstrating that the device's performance is not adversely affected by these expanded patient characteristics.

    Here's an analysis of the acceptance criteria and study information provided:

    1. Acceptance Criteria and Reported Device Performance

    The document does not explicitly state quantitative acceptance criteria in terms of metrics like sensitivity, specificity, or accuracy for a specific diagnostic task from an AI component. This is because this 510(k) notification is for an expanded indication for use of an existing device, not for the clearance of a new AI-powered diagnostic algorithm.

    The "performance data" section focuses on demonstrating that the existing device's performance is not affected by the expanded age and BMI patient populations. Therefore, the "acceptance criteria" are implicitly that the device continues to perform as intended and safely within the expanded patient population.

    Acceptance Criteria (Implied)Reported Device Performance
    Device performance is not adversely affected by increased BMI up to 65."The company provided technical data demonstrating capsule and system performance would not be affected by increasing the BMI of the patient up to the limitations stated in the report."
    Device performance is not adversely affected by lower age patients (down to 6 years old)."The clinical data demonstrate using the system on lower age patients... doesn't affect performance of the device."
    Device remains safe in expanded patient populations."This real-world evidence demonstrates the safety..." and "does not pose any new risks to the patient as demonstrated using the device in clinical settings."

    2. Sample Size and Data Provenance

    • Test Set Sample Size: The document mentions "clinical data" and "real-world evidence" but does not provide a specific sample size for a test set. This suggests that a formal, prospective, rigorously controlled "test set" in the context of an AI study was not conducted. Instead, they relied on existing clinical literature and internal reports.
    • Data Provenance: The document does not specify the country of origin. The data is described as "published in the scientific literature along with unpublished clinical reports" and "real-world evidence." This implies a mix of retrospective and possibly ongoing observational data.

    3. Number of Experts and Qualifications

    The document does not mention the number or qualifications of experts used to establish ground truth. This is expected given that the filing is not for an AI diagnostic algorithm requiring this type of ground truth establishment for its performance evaluation. The "ground truth" seems to be the continued functionality and safety of the device itself in the expanded population.

    4. Adjudication Method

    No adjudication method is mentioned, as it's not applicable to this type of device modification submission.

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

    No MRMC study was done, as this submission is not about the effectiveness of a diagnostic algorithm or how it improves human reader performance.

    6. Standalone (Algorithm Only) Performance Study

    No standalone algorithm performance study was done. This device is a capsule endoscope system, and while it has software, the submission is not for a new AI-driven diagnostic or analytical algorithm.

    7. Type of Ground Truth Used

    The "ground truth" implicitly used for this submission is clinical experience and technical (bench) data demonstrating the continued functional performance and safety of the existing device when used in the expanded age and BMI populations. It is not about diagnostic accuracy against a specific disease state.

    8. Sample Size for Training Set

    No training set sample size is mentioned. This is not a submission for a new AI/ML algorithm that would undergo a training phase.

    9. How Ground Truth for Training Set was Established

    Not applicable, as no training set for an AI/ML algorithm is discussed.

    Ask a Question

    Ask a specific question about this device

    K Number
    K140751
    Date Cleared
    2014-06-30

    (97 days)

    Product Code
    Regulation Number
    876.1300
    Reference & Predicate Devices
    Why did this record match?
    Reference Devices :

    K103088

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    The MiroCam® Capsule Endoscope System is intended for visualization of the small bowel mucosa. It may be used as a tool in the detection of abnormalities of the small bowel in adults and children from two years of age.

    The Suspected GI Bleeding Indicator (SGIB) is intended to mark frames of the video suspected of containing blood or red areas.

    Device Description

    The MiroCam® Capsule Endoscope System is comprised of the following core components:

    • MiroCam® Capsule: MC1000-B
    • MiroCam® Receiver: MR1100
    • Data Cable / Data Belt (Optional): MR1000-D / MR1000-D(M) or MR1000-D(L)
    • MiroView™ Software: MiroView™ U, MiroView™ RTV, MiroView™ RTV-i

    The general usage workflow of the MiroCam® system is as follows, the MiroCam® capsule captures images of the Gl tract, which are sent via Human Body Communication to sensor pads which are affixed to the patient body. The sensor pads are connected to the receiver by the data cables. The image data is stored on the receiver for the duration of the patient procedure. After removing the receiver set from the patient body, the receiver is connected via USB to the Commercial PC and the image data is uploaded. Following upload, the physician (Gastroenterologist) reviews the patient image data for suspected abnormalities of the small bowel.

    AI/ML Overview

    The provided text does not contain detailed information about specific acceptance criteria or an exhaustive study proving the device meets those criteria. The 510(k) summary states that "The performance testing are exactly the same as the predicate device (K123428)," implying that the current submission relies on the testing of its predicate device. This usually means that the device is shown to be substantially equivalent to the predicate through similar technological characteristics and equivalent intended use, rather than a new de novo performance study with specific acceptance criteria.

    However, based on the structure of a typical 510(k) submission, and the limited information provided, I can infer some aspects and highlight what is missing.

    Here's a breakdown of the requested information, indicating where the document provides details and where it is silent:


    1. Table of acceptance criteria and the reported device performance

    The document does not explicitly state acceptance criteria or provide a table of reported device performance for this specific submission (K140751). It states that its performance testing is "exactly the same as the predicate device (K123428)." This implies that the current device is considered to have met the performance established for its predicate. Without access to K123428's full submission, specific quantitative acceptance criteria cannot be extracted from this text.

    The closest to a performance claim is the intended function of the "Suspected GI Bleeding Indicator (SGIB) is intended to mark frames of the video suspected of containing blood or red areas." However, no metrics (e.g., sensitivity, specificity, accuracy) or acceptance criteria (e.g., >90% sensitivity for SGIB detection) are provided for this feature.

    2. Sample size used for the test set and the data provenance

    The document does not provide details about the sample size for a test set or data provenance for K140751, as it refers back to the predicate device (K123428) for performance testing.

    3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

    The document does not provide this information for K140751.

    4. Adjudication method for the test set

    The document does not provide this information for K140751.

    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

    The document does not indicate that an MRMC comparative effectiveness study was done for K140751. The device description mentions "MiroView™ U provides some kinds of Modes and Views to help the user review patient video data quickly and conveniently; however, IntroMedic Co., Ltd. recommends that the doctor review the patient video in the Normal Mode / Single View to prevent from a wrong diagnosis." This statement suggests a recommendation against relying solely on AI-assisted views for diagnosis and doesn't claim an improvement in human reader performance with AI assistance.

    6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done

    The document does not explicitly present data on standalone algorithm performance for K140751. The "Suspected GI Bleeding Indicator (SGIB)" feature could imply an algorithm-only function, but no performance metrics are given.

    7. The type of ground truth used

    The document does not provide information on the type of ground truth used for K140751.

    8. The sample size for the training set

    The document does not provide information on the sample size for any training set for K140751.

    9. How the ground truth for the training set was established

    The document does not provide information on how ground truth was established for any training set for K140751.


    Summary of what is known from the provided text for K140751:

    The submission for the MiroCam® Capsule Endoscope System (K140751) states that its "Technological Characteristics" and "Performance Testing" are "exactly the same as the predicate device (K123428)." This means that the current device is deemed substantially equivalent based on its similarity to a previously cleared device, rather than requiring new, detailed performance studies to be included in this specific 510(k) summary.

    The only specific "performance" mentioned is the Suspected GI Bleeding Indicator (SGIB), which is "intended to mark frames of the video suspected of containing blood or red areas." However, no quantitative performance metrics (e.g., sensitivity, specificity, accuracy) or acceptance criteria for this feature are provided in the document.

    To get the detailed information requested, one would need to access the full 510(k) submission for K123428, which is the predicate device for performance testing.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1