(351 days)
The MiroCam® Capsule Endoscope System 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.
It may be used as a tool in the detection of abnormalities of the small bowel and this device is indicated for adults only.
The Suspected GI Bleeding Indicator (SGIB) is intended to mark frames of the video suspected of containing blood or red areas.
The MiroCam® Capsule Endoscope System is comprised of the following core components:
- MiroCam® Capsule: MC2000-B
- MiroCam® Receiver: MR2000
- Data Cable / Data Belt (Optional): MR1000-D / MR1000-D(S) or MR1000-D(M) or MR1000-D(L)
- MiroView™ Software: MiroView™ U 4.0
The MiroCam® capsule captures images of the GI 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.
The MiroCam® Capsule Endoscope System is intended for visualization of the small bowel mucosa and can be used to visualize and monitor lesions related to Crohn's disease, obscure bleeding, and iron deficiency anemia (IDA) not detected by upper and lower endoscopy. It can also detect other small bowel abnormalities in adults. The Suspected GI Bleeding Indicator (SGIB) marks frames suspected of containing blood or red areas.
Here's an analysis of the acceptance criteria and the study proving the device meets them:
1. Table of Acceptance Criteria and Reported Device Performance
The provided document does not explicitly present a table of "acceptance criteria" with numerical targets. Instead, it describes performance testing conducted to demonstrate that modifications to the device (MC2000-B capsule and MiroView™ U 4.0 software) do not diminish the safety or effectiveness compared to its predicate (MiroCam® Capsule Endoscope System K143663 and Given® PillCam® SB3 K123864). The "reported device performance" is largely framed as equivalency or improvement over the predicate, rather than meeting specific quantitative thresholds.
However, based on the comparative effectiveness section, we can infer some performance aspects that were evaluated.
| Feature/Characteristic | Acceptance Criteria (Inferred from Predicate/Equivalency) | Reported Device Performance (Subject Device: MiroCam® MC2000-B) |
|---|---|---|
| Capsule Operation Time | At least 12 hours (K143663, K123864 predicate) | 12 Hours (Performance and Bench Test proved no problem) |
| Capsule Shelf Life | 18 months (K143663 predicate) | 12 months (Performance and Bench Test proved no problem) |
| Ingestion Ease (Capsule Size) | Comparable to or smaller than predicate | Smaller (30.1mm x Ø10.8mm) than reference device K123666 (31.5mm x Ø11.6mm), and comparable to K143663 (24.5mm x Ø10.8mm) in diameter. |
| Image Quality (Optical System) | Same as K143663 predicate | Uses the same optical system (Sensor, LED, Lens) as K143663, improved with two image sensors for bi-directional shooting. |
| Real-Time View (RTV) | Functional RTV (via USB/WiFi for K143663; LCD for K123864) | Displays RTV on LCD on the receiver (similar to K123864 predicate) |
| Software Functionality | Comparable to predicate MiroView™ U 3.0 | New features added (Compatibility with new receiver, UI for dual tip capsule, H.264 Codec, Express Play 3.0, Supplementary Play) |
| Safety (EMC, Electrical) | Compliant with relevant safety standards (implied, as stated for predicates) | Safety and EMC tests conducted to verify both devices (K143663 and subject) are safe. |
| Bite Resistance | Adequate (implied for capsule integrity) | Bite testing conducted. |
| Water Proofing | Adequate (implied for capsule integrity) | Water proof testing conducted. |
| pH Resistance | Safe in pH 2-8 (K143663, K123864 predicate) | pH resistance testing conducted; Safe in pH=2 ~ pH=8. |
2. Sample Size Used for the Test Set and Data Provenance
The document does not explicitly state the specific sample sizes for each performance test. It mentions tests like MTF Measurement, Minimum Distinguishable Contrast Value and Depth of Field, Geometric distortion, Field of View, Color Reproduction, Optical spectra of the light source, Intensity change during shelf life, Bite testing, Water proof testing, pH resistance testing, MR1100 and MR2000 Equivalent Performance Comparison testing, and Shelf life testing.
The data provenance is implied to be from internal lab testing and comparisons, conducted by IntroMedic Co., Ltd. The study appears to be retrospective in the sense that it compares features and performance against already cleared predicate devices. There is no information provided about prospective clinical trials or country of origin for specific data sets, except that the manufacturer is from Korea.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and the Qualifications of those Experts
This document describes a medical device submission focusing on substantial equivalence of hardware and software features, along with physical performance tests. It does not mention any human expert review or ground truth establishment by clinical experts for the purpose of validating image-based diagnostic performance or the "Suspected GI Bleeding Indicator (SGIB)" functionality in the context of this submission. The SGIB is stated to be "intended to mark frames... suspected of containing blood or red areas," but no details are provided on its validation or ground truth.
4. Adjudication Method for the Test Set
As no human expert review or ground truth establishment by experts for specific diagnostic performance is mentioned, there is no adjudication method provided for an expert-based test set.
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 describe a Multi Reader Multi Case (MRMC) comparative effectiveness study. The device described is a capsule endoscope system with an "indicator" function (SGIB) for potential bleeding, not an AI diagnostic system designed to assist human readers in interpretation or to quantify improvement in human performance.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done
The document mentions the "Suspected GI Bleeding Indicator (SGIB)" as an "intended to mark frames... suspected of containing blood or red areas." This suggests an algorithmic function. However, the document does not provide any data on the standalone performance of this SGIB algorithm (e.g., sensitivity, specificity, accuracy) using a defined ground truth. Its presence is mentioned as a feature, not a validated diagnostic tool in this submission.
7. The Type of Ground Truth Used
For the physical and functional performance tests (e.g., bite testing, water resistance, pH resistance, optical system, operation time), the ground truth is derived from engineering specifications, physical measurements, and direct observation against established standards or predicate device performance. For the SGIB feature, no specific ground truth type (e.g., expert consensus, pathology, outcomes data) for its performance validation is described in this submission.
8. The Sample Size for the Training Set
This document concerns a capsule endoscopy system, not a machine learning model requiring a training set in the typical sense. While the SGIB feature might use some form of internal algorithm, no information on the sample size of a training set is provided.
9. How the Ground Truth for the Training Set Was Established
As no training set for an AI model is explicitly mentioned or detailed, no method for establishing ground truth for a training set is provided.
§ 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.”