Search Results

The OLYMPUS SMALL INTESTINAL CAPSULE ENDOSCOPE SYSTEM is intended for visualization of the small intestine 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 Red Color Detection Function is intended to mark frames of the video suspected of containing blood or red areas.
  The OLYMPUS SMALL INTESTINAL CAPSULE ENDOSCOPE SYSTEM may be used as a tool in the detection of abnormalities of the small intestine and is intended for use in adults only.

The OLYMPUS SMALL INTESTINAL CAPSULE ENDOSCOPE SYSTEM is a capsule imaging system used for visualization of the small intestine mucosa. This system consists of capsule endoscopes which capture images and transmit the data, an antenna unit and a recorder which are secured around the patient and receive data from the capsule, and workstation software which downloads the image data from the recorder and processes images for visualization. After the visualization, the diagnostic review (also known as reading) of images would start with user selectable OMNI mode feature. OMNI mode is an algorithm that assists the physician in reviewing the Capsule Endoscopy(CE) case data.

The provided text describes the OLYMPUS SMALL INTESTINAL CAPSULE ENDOSCOPE SYSTEM and its performance. However, it does not explicitly define specific "acceptance criteria" in a quantitative table or directly state that the device meets pre-defined acceptance criteria in all aspects. The document focuses on demonstrating substantial equivalence to a predicate device and presenting the results of a clinical study for the OMNI mode.

Based on the provided text, here's an attempt to answer your request, highlighting where information is directly available and where it's inferred or not explicitly stated:

1. Table of acceptance criteria and the reported device performance

The provided text does not contain a specific table of quantitative acceptance criteria for the entire device or the OMNI mode, nor does it explicitly state that the device "meets" acceptance criteria in a comparative table.

However, the clinical study's outcome regarding reading efficiency can be considered a performance metric and, implicitly, a criterion for the OMNI mode's improvement claim.

For other performance aspects (Software verification, Electrical safety, EMC, Radio signal communication, Radio Interference, FCC Test, Risk Management), the document states that tests were conducted "to demonstrate that the OLYMPUS SMALL INTESTINAL CAPSULE ENDOSCOPE SYSTEM performs according to specifications and functions as intended" and "Test results verified the safety and effectiveness of the devices in accordance with design specifications and applicable standards." Risk management was conducted "in accordance with established in-house acceptance criteria based on ISO 14971:2007." However, the specific quantitative acceptance criteria and their corresponding results are not detailed.

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

• Sample Size for the Test Set: Not explicitly stated as a number of cases or patients from the clinical trial description. It mentions "the cases" were reviewed, implying multiple cases, but a specific number is not provided.
• Data Provenance: Not explicitly stated (e.g., country of origin). It is described as a "multicenter, randomized trial," suggesting prospective data collection.

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

• Number of Experts: "Seven different expert CE physicians".
• Qualifications of Experts: They are described as "expert CE physicians" (CE likely stands for Capsule Endoscopy). Further specific qualifications (e.g., years of experience, board certification) are not provided.
• Ground Truth for Test Set: The study compares "Normal mode" (conventional review of all CE images) to "OMNI mode" by having experts review the cases. While "Normal mode" reading time is a baseline, the document doesn't detail how the ground truth for pathology or lesions within these cases was established. The focus of the study was on review efficiency, not diagnostic accuracy against a separate gold standard.

4. Adjudication method for the test set

• The study states, "Seven different expert CE physicians, blinded to the reading mode, reviewed the cases in randomized order." This implies that each physician independently reviewed the cases under both conditions (Normal mode and OMNI mode), and their review times were compared. There is no mention of an adjudication process among these seven experts to establish a single "ground truth" diagnosis for the cases themselves, as the primary endpoint was reading time rather than diagnostic consensus.

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

• MRMC Study: Yes, a "multicenter, randomized trial" was conducted comparing "Normal mode" (without OMNI mode assistance) and "OMNI mode" (with OMNI mode assistance) among "seven different expert CE physicians." This fits the description of a multi-reader, multi-case study.
• Effect Size of Improvement: The human readers (physicians) improved their reading efficiency with OMNI mode assistance.
  • Average review time for OMNI mode (with assistance): 27.3 minutes
  • Average review time for Normal mode (without assistance): 75.1 minutes
  • Improvement (reduction in time): 64% reduction in review time (75.1 - 27.3 = 47.8 minutes reduction). This is a substantial effect size for efficiency.

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

• No, the study described is an evaluation of the OMNI mode as an "algorithm that assists the physician" and measures the physician's review time with the assistance versus without it. There is no mention of testing the OMNI mode in a standalone capacity (i.e., automatically detecting lesions without human review) or reporting its performance metrics independent of human interaction. The "Red Color Detection Function" is described as "intended to mark frames of the video suspected of containing blood or red areas," which implies an assistive, not standalone, role.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

• The ground truth for the efficiency comparison was the measured time taken by the expert physicians to review the cases under different modes. The study's endpoint was not diagnostic accuracy or lesion detection against a separate gold standard like pathology. The OMNI mode's purpose is to "remove and store redundant images," and the study evaluates its success in improving review time.

8. The sample size for the training set

• Not provided. The document focuses on the clinical validation study of the OMNI mode. Information about the training set used to develop the OMNI algorithm (which is a form of AI/algorithm assistance) is not included in this 510(k) summary.

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

• Not provided. Since the training set sample size and details are not mentioned, the method for establishing its ground truth is also not elaborated upon in this document.

Ask a specific question about this device