Search Results

The PillCam™ Genius SB Capsule Endoscopy Kit with the PillCam Genius SB 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 PillCam Genius SB Capsule may be used as a tool in the detection of abnormalities of the small bowel and is intended for use in adults.

The subject device introduces the PillCam Genius Capsule Endoscopy Kit (PillCam Genius SB Capsule and the PillCam Genius Link Device), the PillCam Genius Sync Agent, and the Real Time View Application.
The PillCam Genius Link Device is a single use device that is adhered to the patient's abdomen throughout the PillCam Genius SB procedure that connects to the PillCam Genius SB Capsule. Each Genius Link Device is paired and packaged with a single PillCam Genius SB Capsule. At the end of the procedure, the Link Device is removed and returned to the clinic.
The PillCam Genius Sync Agent is software used by the healthcare provider to setup and manage PillCam Genius SB endoscopy procedures and converts data from the PillCam Genius Link Device to the workstation.
The optional Real Time View Application allows the healthcare provider to view real time images from the capsule for a short period of time during the procedure to estimate the location of the capsule in the gastrointestinal tract.
The PillCam Desktop Software and HCP Software Application have been updated to display PillCam Genius SB Capsule procedures. The HCP Software Application has also been updated to be compatible with the PillCam Genius SB System and allow for uploading multiple procedures.

This 510(k) summary does not contain information about acceptance criteria or a study demonstrating that the device meets such criteria. Specifically, it states that "No clinical testing was conducted in support of this 510(k) submission." Therefore, it's not possible to provide the requested details from the given text.

The document focuses on demonstrating substantial equivalence to a predicate device through non-clinical testing, including biocompatibility, bench testing, electrical safety, EMC, and software documentation.

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 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

The PillCam Patency System is an accessory to the PillCam video capsule and is intended to verify adequate patency of the gastrointestinal tract prior to administration of the PillCam video capsule in patients with known or suspected strictures. The PillCam Patency capsule should only be used within the specified patient age range based on the patient age of the indicated video capsule system.

Therefore, the PillCam Patency System is intended to be used:

• prior to PillCam SB capsule in adults and children from 2 years of age, or
• prior to PillCam UGI, COLON, and Crohn's capsules in adults

The PillCam Patency System is an accessory to the PillCam capsule endoscopy (CE) System and it is used for verifying the patency of the Gastrointestinal (GI) tract. The PillCam Patency System consists of the following components; The PillCam Patency capsule, the Patency scanner and TesTag (interference tester).

The Patency capsule is an ingestible and dissolvable capsule, similar in size to the PillCam CE. It is comprised of a body that surrounds a small Radio Frequency Identification (RFID) tag. The body is coated with an impermeable membrane, except for two small windows that are plugged by the Timer Plugs. The Timer plugs seal the capsule's body. If the Patency capsule is excreted structurally whole, then this confirms patency of the GI tract of the patient for objects similar in size to the capsule. However, if the capsule is retained in the GI tract, the Timer Plugs erode, allowing the penetration of body fluids into the capsule and the dissolution of the capsule's body. The remaining fragments of the capsule can pass even small orifices.

The Patency scanner may be utilized to detect RF signals from the RFID tag, to verify the PillCam Patency capsule presence in the body.

The only difference between the PillCam Patency System and the predicate device is the proposed labeling modification, to allow the use of the existing Patency capsule with the PillCam capsules that are slightly longer (PillCam COLON, Crohn's and UGI capsules). The intention of the proposed change is to offer physicians a clinical tool to evaluate the suitability of patients for CE, as an alternative to magnetic resonance enterography (MRE) or Computed Tomography (CT) which are already used in practice for this purpose.

The provided text is a 510(k) summary for the PillCam Patency System. It references a previous submission (K053639) for clinical testing data, but the details of that study, including specific acceptance criteria and detailed device performance, are not explicitly laid out in the current document. However, based on the information provided, I can construct a response with the available data and highlight where information is missing.

Here's a breakdown of the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The current document (K180171) itself does not explicitly state quantitative acceptance criteria or detailed device performance metrics in a readily digestible table. Instead, it refers to prior clinical testing (K053639) and general statements about the system's performance.

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

• Test Set Sample Size: Not explicitly stated in K180171. It refers to "patients with known strictures" in the leveraged K053639 study.
• Data Provenance: Not specified in K180171 (e.g., country of origin). The previous study (K053639) from which the data was leveraged would contain this information. The current submission is a regulatory document concerning a device from Israel (Given Imaging Ltd.).
• Retrospective or Prospective: Not explicitly stated for the leveraged K053639 study. However, the description "patients with known strictures ingested the Patency capsule and underwent periodic scanning until the capsule was excreted" suggests a prospective clinical study design.

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

This information is not provided in the K180171 document. The document primarily focuses on the device's physical and functional characteristics and references prior clinical safety and efficacy without detailing the methodology of ground truth establishment in the studies themselves.

4. Adjudication method for the test set

This information is not provided in the K180171 document.

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

This is not applicable to the PillCam Patency System as described. The Patency System's function is to verify GI tract patency, primarily through the detection of an RFID tag or the capsule's dissolution, not through interpretation of images by human readers or AI. It's an accessory to a video capsule, but its own function doesn't involve image interpretation where "human readers improve with AI" would be a relevant metric.

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

Yes, the core function of the PillCam Patency System, as described, is a standalone process. The Patency scanner detects RF signals from the RFID tag, and the capsule's dissolution is a physical process, both occurring without direct human interpretive intervention during the patency verification itself. The "human-in-the-loop" aspect would be the physician's decision based on the outcome (intact capsule excreted or not), but the patency test itself does not involve AI or human image interpretation.

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

The ground truth for the efficacy aspect (successful patency verification) would likely be based on:

• Direct observation of capsule excretion: If the capsule is excreted whole, patency is confirmed.
• Follow-up outcomes: The success of the subsequent capsule endoscopy (e.g., no retention) after a positive patency test would serve as an outcome-based ground truth.
• Clinical assessment: The resolution or passage of the capsule (or its fragments) and the patient's clinical status.

The K180171 document states: "If the Patency capsule is excreted structurally whole, then this confirms patency of the GI tract of the patient for objects similar in size to the capsule." This indicates direct observation as a primary ground truth.

8. The sample size for the training set

The K180171 document does not mention a training set. This is because the device is a physical capsule system, not an AI/ML algorithm that requires a training set. The "design" and "performance" of the capsule are based on engineering principles and clinical testing, not model training.

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

As there is no training set for this type of device, this information is not applicable.

Ask a specific question about this device

The PillCam SBC capsule is intended for visualization of the small bowel and colonic mucosa.
• It may be used in the visualization and monitoring of lesions in the small bowel that may indicate Crohn's disease not detected by upper and lower endoscopy, and for the visualization of inflammation of the colon in patients with colonoscopy-diagnosed Crohn's disease.
• It may be used in the visualization and monitoring in the small bowel of lesions that may be a source of obscure bleeding (either overt or occult) or that may be potential causes of iron deficiency anemia (IDA) not detected by initial upper and lower endoscopy.
• The PillCam SBC capsule may be used as a tool in the detection of abnormalities of the small bowel. It is intended for use in adults.

PillCam Desktop Software 9.0 indications for use:
With PillCam SB 2/ SB 3 Capsule
The PillCam SB 2/ 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 2/ 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.

With PillCam UGI Capsule
The PillCam UGI capsule endoscopy system is intended for visualization of the upper gastrointestinal tract (esophagus, stomach, duodenum). It may be used for visualization of blood in the upper gastrointestinal tract (esophagus, stomach, duodenum) in patients who are hemodynamically stable and at least 18 years of age.

With PillCam COLON 2 Capsule
The PillCam COLON 2 capsule endoscopy system is intended to provide visualization of the colon. It may be used for detection of colon polyps in patients after an incomplete optical colonoscopy with adequate preparation, and a complete evaluation of the colon was not technically possible. In addition, it is intended for detection of colon polyps in patients with evidence of gastrointestinal bleeding of lower GI origin. This applies only to patients with major risks for colonoscopy or moderate sedation, but who could tolerate colonoscopy and moderate sedation in the event a clinically significant colon abnormality was identified on capsule endoscopy.

With PillCam SBC Capsule
The PillCam SBC capsule is intended for visualization of the small bowel and colonic mucosa.

• It may be used in the visualization and monitoring of lesions in the small bowel that may indicate Crohn's disease not detected by upper and lower endoscopy, and for the visualization of inflammation of the colon in patients with colonoscopy-diagnosed Crohn's disease.
• It may be used in the visualization and monitoring in the small bowel of lesions that may be a source of obscure bleeding (either overt or occult) or that may be potential causes of iron deficiency anemia (IDA) not detected by initial upper and lower endoscopy.
• The PillCam SBC capsule may be used as a tool in the detection of abnormalities of the small bowel. It is intended for use in adults.

The PillCam SBC capsule endoscopy system is comprised of four main subsystems; (1) the ingestible PillCam SBC capsule, (2) the PillCam Recorder DR3, (3) the PillCam Software (a new version of the formerly branded "RAPID" software), and (4) the Workstation and/or accessories.

1. Ingestible PillCam SBC Capsule
   The disposable, ingestible PillCam SBC 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 Recorder located outside the body.
2. PillCam Recorder DR3
   The PillCam Recorder DR3 is an external receiving/recording unit that receives and stores the acquired images from the capsule.
3. PillCam Software
   The PillCam Software (previously branded as "RAPID" Software) 9.0 is a software application that is utilized to process, analyze, store, and view the acquired images collected from the PillCam 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 Desktop Software 9.0 supports PillCam capsule endoscopy of the gastrointestinal (GI) tract with all PillCam video capsules (SB, COLON, UGI and SBC).
4. Workstation and Accessories
   The Workstation is a 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 describes a 510(k) premarket notification for the PillCam SBC capsule endoscopy system and PillCam Desktop Software 9.0. It asserts substantial equivalence to predicate devices but does not contain a detailed study report with specific acceptance criteria and performance data in the format requested.

Therefore, I cannot extract the following information from the provided text:

• A table of acceptance criteria and the reported device performance: The document states that the device "meets the guidance entitled 'Class II Special Controls Guidance Document: Ingestible Telemetric Gastrointestinal Capsule Imaging System; Final Guidance for Industry and FDA' dated November 28, 2001." and that "The proposed changes in this submission do not raise new performance or safety issues." However, it does not provide specific quantitative acceptance criteria or detailed reported performance against those criteria. It lists some "Bench Testing" but without numerical results or criteria.
• Sample sizes used for the test set and the data provenance: No information is provided regarding the sample size of any test sets or whether data was retrospective or prospective, or its country of origin.
• Number of experts used to establish the ground truth for the test set and the qualifications of those experts: This information is not present in the document.
• Adjudication method for the test set: This information is not present.
• If a multi-reader, multi-case (MRMC) comparative effectiveness study was done, and the effect size of how much human readers improve with AI vs without AI assistance: No mention of an MRMC study or AI assistance is made. The software's features focus on improving user viewing experience and providing tools for analysis.
• If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: The document does not describe standalone algorithm performance studies.
• The type of ground truth used: The document does not specify the type of ground truth used for performance evaluation, beyond implying that the device's visualization capabilities are compared to existing diagnostic methods (e.g., endoscopy) as part of its intended use.
• The sample size for the training set: No information about training sets is provided.
• How the ground truth for the training set was established: No information about training sets is provided.

However, the document does contain information about performance data in a general sense:

Relevant Performance Data Mentioned:

The document mentions that the device "meets the guidance entitled 'Class II Special Controls Guidance Document: Ingestible Telemetric Gastrointestinal Capsule Imaging System; Final Guidance for Industry and FDA' dated November 28, 2001." This is the general regulatory standard the device aims to meet.

It also highlights that "The proposed changes in this submission do not raise new performance or safety issues."

Bench Testing:
The following bench tests were conducted or deemed applicable due to similarity with the predicate device (PillCam COLON 2 capsule):

• Biting test
• pH resistance test
• Optical resolution
• Optical verification including Field of View and depth of focus
• Verification of frame rate (PillCam SBC capsule, PillCam Desktop Software 9.0)
• Shelf life and battery evaluation (PillCam SBC capsule, PillCam Desktop Software 9.0)
• Color reproducibility (PillCam SBC capsule, PillCam Desktop Software 9.0)
• Image quality (PillCam SBC capsule, PillCam Desktop Software 9.0)

Software Validation:
PillCam Desktop Software 9.0 was validated and documented per FDA's software guidance document.

Optical Features:

• 4 white LEDs per optical head are used as the SBC capsule illumination source.
• The optical Field of view from the entrance pupil is 168°.
• The Effective Visibility distance is set to 30mm. (These features are identical to the PillCam COLON 2 capsule).

In summary, while the document confirms that performance testing and validation were conducted to demonstrate substantial equivalence and adherence to regulatory guidance, it does not provide the detailed, quantitative breakdown of acceptance criteria and study results requested.

Ask a specific question about this device

With PillCam SB 2 and SB 3 Capsules

The PillCam Capsule Endoscopy System with a PillCam SB 2 and SB 3 capsules is intended for visualization of the small bowel mucosa.

• o PillCam Capsule Endoscopy System with PillCam SB 2 and SB 3 capsules may be used in the visualization and monitoring of lesions that may indicate Crohn's disease not detected by upper and lower endoscopy.
• PillCam Capsule Endoscopy System with PillCam SB 2 and SB 3 capsules ● 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.
• PillCam Capsule Endoscopy System with PillCam SB 2 and SB 3 capsules 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 Capsule Endoscopy System with PillCam SB 2 and SB 3 capsules 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.

With PillCam ESO 3 Capsule

The PillCam Capsule Endoscopy System with PillCam ESO 3 capsules is intended for the visualization of esophageal mucosa in adults and children from 18 years of age..

With PillCam UGI Capsule

The PillCam UGI capsule endoscopy system is intended for visualization of the upper gastrointestinal tract (esophagus, stomach, duodenum). It may be used for visualization of blood in the upper gastrointestinal tract (esophagus, stomach, duodenum) in patients who are hemodynamically stable and at least 18 years of age.

With PillCam COLON Capsule

The PillCam COLON 2 capsule endoscopy system is intended to provide visualization of the colon. It may be used for detection of colon polyps in patients after an incomplete optical colonoscopy with adequate preparation, and a complete evaluation of the colon was not technically possible. In addition, it is intended for detection of colon polyps in patients with evidence of gastrointestinal bleeding of lower GI origin. This applies only to patients with major risks for colonoscopy or moderate sedation, but who could tolerate colonoscopy and moderate sedation in the event a clinically significant colon abnormality was identified on capsule endoscopy.

The RAPID Web is a client server based version of the RAPID video review and report creation components of the cleared RAPID 8 software. The RAPID Web is designed to allow users to review and analyze videos created using the cleared RAPID software, and to create reports over a private intranet network or over a secure internet connection. The PillCam capsule studies are created at workflow-relevant locations and stored at a central repository. The RAPID Web server is installed on a central server in an intranet or internet environment with access to the study repository. After the capsule endoscopy procedure was conducted using the cleared RAPID software, Given Workstation/User PC, PillCam capsule, and DR 3 PillCam recorder, end users will use an internet browser with authorization login to access, review, and manage the studies in the repository using workstation, user PC, a laptop or an Apple™ (screen size > 9.7").

The provided text describes the 510(k) submission for RAPID Web, comparing it to its predicate device, RAPID 8.0. The core of the submission revolves around demonstrating that RAPID Web is substantially equivalent to RAPID 8.0, and thus, RAPID Web's "performance" is implicitly tied to how well it replicates the established performance of RAPID 8.0.

Here's an analysis of the acceptance criteria and study as presented in the document:

1. A table of acceptance criteria and the reported device performance

The document does not explicitly state numerical acceptance criteria in a table format for RAPID Web's diagnostic performance. Instead, it states the acceptance criterion informally as "RAPID 8.0 met the pre-specified sensitivity" in the context of a comparative performance study. The reported performance is that the analysis of "matched and un-matched pathologies" showed this criterion was met.

2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)

• Sample Size for Test Set: The document states that a "comparative performance study wherein trained professionals identified pathologies in the same video and video segments that we displayed using RAPID Web and RAPID 8.0 was performed." However, it does not specify the number of cases (videos or video segments) used in this test set.
• Data Provenance: The document does not specify the country of origin of the data or whether the data was collected retrospectively or prospectively.

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)

• The document implies that "trained professionals" were involved in identifying pathologies. However, it does not specify the number of experts used to establish the ground truth or their specific qualifications (e.g., years of experience, medical specialty). The study design appears to be a comparison of user performance with two different software versions, rather than a separate ground truth establishment phase by independent experts for the test set itself. The "ground truth" for this comparative study seems to be derived from the consensus or established interpretations of "trained professionals" using the predicate device.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set

• The document does not describe an explicit adjudication method (like 2+1 or 3+1) for the test set. The study compares "matched and un-matched pathologies," suggesting a direct comparison of findings between the two software versions, likely relying on individual assessments by the trained professionals.

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 study described is a "comparative performance study" where "trained professionals identified pathologies in the same video and video segments that we displayed using RAPID Web and RAPID 8.0." This sounds like a multi-reader, multi-case study (MRMC) in the sense that multiple readers would use the two different software versions on the same cases.
• However, this is not a study on human readers improving with AI vs. without AI assistance. RAPID Web and RAPID 8.0 are video review and analysis software. The "Suspected Blood Indicator (SBI) feature" is mentioned as "intended to mark frames of the video suspected of containing blood or red areas," which is an algorithmic assistance feature. The study assessed if this feature, within the new web-based context, maintained its performance from the predicate.
• The document does not report any effect size demonstrating improvement of human readers with either RAPID Web or RAPID 8.0 over a non-assisted reading scenario. The study aims to demonstrate substantial equivalence between the two software versions.

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

• The document does not describe a standalone algorithm-only performance study. The performance evaluation is explicitly framed as a "comparative performance study wherein trained professionals identified pathologies," indicating human-in-the-loop performance. The SBI feature is an algorithm, but its performance is assessed within the context of human review.

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

• The ground truth for the "pathologies" identified in the comparative study appears to be based on the interpretations of "trained professionals" themselves, as they "identified pathologies." The comparison is between the findings obtained using RAPID Web and those obtained using RAPID 8.0, with RAPID 8.0's established performance serving as the reference. There is no mention of an independent, higher-standard ground truth like biopsy/pathology reports or long-term clinical outcomes data being used to validate the accuracy of these identified pathologies in this particular comparative study. The study's goal is equivalence, not re-proving clinical accuracy against an external gold standard for the new platform.

8. The sample size for the training set

• The document does not provide any information about a training set or its sample size. This submission is for a new version of existing software (RAPID Web being a client-server version of RAPID 8.0), not necessarily a new AI model that would require a distinct training phase described in the submission. The "Suspected Blood Indicator (SBI) feature" is part of the established functionality from the predicate device, not a new AI algorithm being introduced or trained for RAPID Web.

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

• As no training set is described in the document, there is no information on how ground truth for a training set was established.

Ask a specific question about this device

The ManoScan System provides mapping of pressures and, optionally, impedance within organs of the human gastrointestinal tract. These include the pharynx, upper esophageal sphincter (UES), esophageal sphincter (LES), stomach, Sphincter of Oddi, small bowel, colon, duodenum and anorectal organs. It is used in a medical clinical setting to acquire pressures and then store the corresponding data for visualization and analysis. The real-time data as well as the analysis information can be viewed by trained personnel for diagnostic and analytic purposes. The ManoScan HRM modules provide high-resolution mapping of the pressure and impedance data. The ManoScan CLT module provides conventional line trace mapping of the pressure data.

The ManoScan System provides hardware and software for performing gastrointestinal (GI), sphincter of Oddi, and colorectal manometry. The ManoScan System comprises two sub-systems: the ManoScan HRM System and the ManoScan CLT System. The ManoScan HRM modular series is a high resolution manometry system used for GI manometry. The base system includes a manometric catheter probe, a ManoScan HRM module (A120 module), and software for data acquisition and analysis. Various probe configurations are available depending on the application (esophageal or anorectal manometry), size (regular or small), and catheter diameter. The ManoScan A200 module enables measuring pressure and impedance data using different dedicated catheters. The ManoScan A300 module is used for high-definition 3D catheters which pass pressure data through to the ManoScan A120 module. When enabled, the optional ManoScan A400 module will enable video acquisition through video inputs that originate in typical medical imaging equipment. The ManoScan 3.0 software supports display of video from the ManoScan A400 module (or other video input) and displays it concurrently with pressure (and impedance if enabled) to allow for improved physiological review of the esophageal or anorectal motility function. The ManoScan CLT series is a conventional line trace system used for GI manometry. The system includes a manometric catheter probe, the ManoScan CLT module (A550), and software for data acquisition and analysis. The system is supplied as an integrated cart system consisting of: a cart, manometric catheter, ManoScan CLT A550 module, Computer, monitor and computer peripherals (keyboard, mouse, etc.), power isolation station, ManoScan 3.0 and ManoView CLT software. The ManoScan CLT A550 module acquires pressure data from three catheter types: water-perfused, solid state, and air-charged, manufactured by specific vendors. Each catheter type is connected to the ManoScan CLT A550 module by means of corresponding transducer cable.

The provided document, a 510(k) summary for the ManoScan® System, focuses on demonstrating substantial equivalence to predicate devices rather than presenting a standalone study with detailed acceptance criteria and performance data for the current device. Therefore, much of the requested information regarding specific acceptance criteria, sample sizes, expert involvement, and ground truth types for a study proving device performance is not explicitly available in this document.

However, based on the information provided, here's what can be extracted and inferred:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not present a formal table of acceptance criteria with corresponding performance data in the same way a clinical trial report might. Instead, it focuses on demonstrating equivalence through technical specifications and verification against standards.

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

The document describes bench testing for hardware and pressure mapping.

• Sample Size for Test Set: Not explicitly stated. The nature of bench testing typically involves testing a representative number of units or datasets to cover operational ranges and functionalities, but specific numbers are not provided.
• Data Provenance: This would be retrospective in the sense that physical devices and software were tested in a controlled bench environment, rather than prospective clinical data collection. The location is not explicitly stated beyond Given Imaging's location in Israel, implying the testing was performed internally or by a contracted lab.

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

This information is not provided in the document. For bench testing of hardware and software, "ground truth" would typically be established by comparing measurements to known physical standards, specifications, or the performance of a predicate device/golden standard, rather than expert consensus on medical images or diagnoses.

4. Adjudication Method for the Test Set

This information is not provided. Given the nature of bench testing against standards and predicate devices, a formal adjudication method like "2+1" (which implies multiple human reviewers) is unlikely to have been used. Verification would be against objective technical criteria.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done or reported in this 510(k) summary. The document focuses on technical equivalence and safety rather than comparative clinical effectiveness with human readers. Therefore, an effect size of human improvement with AI assistance is not applicable here.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

The device is a Gastrointestinal Motility Monitoring System that acquires pressure and impedance data for visualization and analysis by trained personnel. It is not an AI algorithm intended for standalone diagnostic performance without human interpretation. Therefore, a standalone "algorithm only" performance study in the sense of an AI diagnostic tool is not applicable or reported for this device. The software performs data processing and visualization, not autonomous diagnostic decisions.

7. The Type of Ground Truth Used

For the bench testing, the ground truth would be:

• Technical Specifications/Standards: For electrical safety and EMC.
• Predicate Device Performance: For pressure mapping equivalence, the performance of the Polygraf ID module served as a reference. This is a form of measurement comparison rather than clinical ground truth like pathology or outcomes data.

8. The Sample Size for the Training Set

This information is not applicable/not provided in the context of this 510(k) submission. The ManoScan® System is described as a data acquisition, visualization, and analysis system, not a machine learning or AI system that requires a "training set" to learn patterns for diagnostic prediction. The software is developed through traditional software engineering processes, not machine learning model training.

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

This information is not applicable, as there is no "training set" for an AI/ML model for this device.

Ask a specific question about this device

The PillCam COLON 2 capsule endoscopy system is intended to provide visualization of the colon. It may be used for detection of colon polyps in patients after an incomplete optical colonoscopy with adequate preparation, and a complete evaluation of the colon was not technically possible, In addition, it is intended for detection of colon polyps in patients with evidence of gastrointestinal bleeding of lower Gl origin. This applies only to patients with major risks for colonoscopy or moderate sedation, but who could tolerate colonoscopy and moderate sedation in the event a clinically significant colon abnormality was identified on capsule endoscopy.

The Given PillCam Endoscopy system is comprised of four main subsystems; (1) the ingestible PillCam capsule, (2) the DR 3 PillCam Recorder, (3) the RAPID software, and (4) the Given Workstation and Accessories.

1. Ingestible PillCam Capsule The disposable, ingestible PillCam Capsule is designed to acquire video images during the natural propulsion through the GI tract. The capsule transmits the acquired images via a RF communication channel to the PillCam Recorder located outside the body.
2. DR 3 PillCam Recorder Recorder is an external The DR 3 PillCam receiving/recording unit that receives and stores the acquired images from the capsule. The Sensor Array/belt receives data from the PillCam capsule and transfers the data to the PillCam Recorder.
3. RAPID Software The RAPID Software is a software application that is utilized to process, analyze, store, and view the acquired images collected from the PillCam Recorder to create a RAPID video of the images. The software also includes a reporting function to create detailed clinical reports, inservice training videos, and patient instruction forms.
4. Given Workstation and Accessories The Workstation is a modified standard personal computer that is the operational platform for the RAPID software. Other accessories include a flat panel LCD monitor, a highcapacity mass storage device, and a high-capacity USB portable storage device.

This document is a 510(k) summary for the PillCam COLON 2 Capsule Endoscopy System. It requests an expanded indication for use for detection of colon polyps.

Based on the provided text, the device itself (PillCam COLON 2 Capsule Endoscopy System) is identical to a previously cleared device (DEN 120023). No new clinical testing was performed or relied upon for this specific 510(k) submission for the expanded indication. The submission relies on the substantial equivalence of the existing device and its performance against "special controls for colon capsule imaging systems, as described in 21CFR 876.1330."

Therefore, the input does not provide information about a new study directly demonstrating the device meets specific acceptance criteria for this expanded indication. Instead, it states that the device's technological characteristics and optical features are the same as the predicate device (DEN 120023).

In summary, the provided text does not contain the information requested in your prompt regarding acceptance criteria and a study proving the device meets those criteria, because the submission claims substantial equivalence without new clinical testing.

However, given the constraint to describe the acceptance criteria and the study that proves the device meets the acceptance criteria, I will extract what is explicitly stated in the document about general performance data and and the basis for the approval.

Here's a breakdown of the available information:

1. A table of acceptance criteria and the reported device performance

The document does not provide a specific table of acceptance criteria and reported device performance for this expanded indication. It only states that the "device meets the special controls for colon capsule imaging systems, as described in 21CFR 876.1330."

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. The document explicitly states: "No clinical testing was performed or relied on for a determination of substantial equivalence."

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 no new clinical testing was performed for this submission.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

Not applicable, as no new clinical testing was performed for this submission.

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, as no new clinical testing was performed for this submission. This device is not an AI-assisted device in the context of this submission.

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

This would not apply to a capsule endoscopy system. The system provides visualization, and a human (physician) interprets the images.

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

Not applicable, as no new clinical testing was performed for this submission.

8. The sample size for the training set

Not applicable, as no new clinical testing was performed for this submission, and the device is not described as involving a machine learning algorithm that undergoes a "training set" in the context of this approval.

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

Not applicable.

Conclusion based on the provided text:

The submission for the expanded indication of the PillCam COLON 2 Capsule Endoscopy System relies on the substantial equivalence to a predicate device (DEN 120023). The document explicitly states: "No clinical testing was performed or relied on for a determination of substantial equivalence." The acceptance criteria are broadly described as meeting "the special controls for colon capsule imaging systems, as described in 21CFR 876.1330," rather than specific performance metrics from a new clinical study.

Ask a specific question about this device

The PillCam UGI capsule endoscopy system is intended for visualization of the upper gastrointestinal tract (esophagus, stomach, duodenum). It may be used for visualization of blood in the upper gastrointestinal tract (esophagus, stomach, duodenum) in patients who are hemodynamically stable and at least18 years of age.

The Given PillCam Endoscopy system is comprised of four main subsystems; (1) the ingestible PillCam capsule, (2) the DR 3 PillCam Recorder, (3) the RAPID software, and (4) the Given Workstation and Accessories.

1. Ingestible PillCam Capsule: The disposable, ingestible PillCam Capsule is designed to acquire video images during the natural propulsion through the GI tract. The capsule transmits the acquired images via a RF communication channel to the PillCam Recorder located outside the body.
2. DR 3 PillCam Recorder: DR 3 PillCam Recorder is an external The receiving/recording unit that receives and stores the acquired images from the capsule.
3. RAPID Software: The RAPID Software is a software application that is utilized to process, analyze, store, and view the acquired images collected from the PillCam Recorder to create a RAPID video of the images. The software also includes a reporting function to create detailed clinical reports, inservice training videos, and patient instruction forms. RAPID 8.0 supports PillCam capsule endoscopy of the GI tract with all PillCam video capsules. In addition, RAPID 8.0 supports PillCam Recorder DR 2C and PillCam Recorder DR 3.
4. Given Workstation and Accessories: The Workstation is a modified standard personal computer that is the operational platform for the RAPID software. The PillCam Recorder is an external receiving/recording unit that receives acquired images from the capsule. The Sensor Array receives data from the PillCam capsule and transfers the data to the PillCam Recorder. Other accessories include a flat panel LCD monitor, a highcapacity mass storage device, and a high-capacity USB portable storage device.

This document describes the Given PillCam UGI capsule endoscopy system. The provided text outlines the device's indications for use, general description, technological characteristics, and a brief statement on how it meets guidance. However, it does not contain specific details from a study proving the device meets acceptance criteria, nor does it provide a table of acceptance criteria with reported device performance.

Therefore, I cannot fulfill your request for:

• A table of acceptance criteria and the reported device performance.
• Sample size used for the test set and data provenance.
• Number of experts used to establish ground truth for the test set and their qualifications.
• Adjudication method for the test set.
• Whether a multi-reader multi-case (MRMC) comparative effectiveness study was done, or its effect size.
• Whether a standalone performance study was done.
• The type of ground truth used.
• The sample size for the training set.
• How the ground truth for the training set was established.

The document primarily focuses on establishing substantial equivalence to predicate devices, discussing:

• Device Name: Given PillCam UGI capsule endoscopy system
• Intended Use: Visualization of the upper gastrointestinal tract (esophagus, stomach, duodenum), including visualization of blood, in hemodynamically stable patients at least 18 years of age.
• Components: Ingestible PillCam capsule, DR 3 PillCam Recorder, RAPID software, and Given Workstation and Accessories.
• Technological Characteristics: Similar to predicate devices (ESO 2, ESO 3, COLON 2 capsules). Modifications include prolonged operation time and adaptive frame rate (35 fps for 10 minutes, then 18 fps for 80 minutes) to achieve better upper GI tissue coverage. optical features include 4 white LEDs, 172° field of view, and 0-30mm effective visibility distance.
• Bench Testing: Biting test and pH resistance test from the COLON 2 capsule (predicate) are applicable due to identical external components and technology. Optical resolution testing showed pH environments do not affect optical performance.
• Compliance: The device meets the "Class II Special Controls Guidance Telemetric Gastrointestinal Capsule Imaging System; Final Guidance for Industry and FDA dated November 28, 2001."

The document concludes that the modifications "do not raise new performance or safety issues" and that the system is substantially equivalent to predicate devices. This implies that the performance is considered acceptable based on its similarity to previously approved devices, rather than through a dedicated performance study with specific acceptance criteria detailed in this summary.

Ask a specific question about this device

The PillCam COLON 2 Capsule Endoscopy System is indicated to provide visualization of the colon. It is intended to be used for detection of colon polyps in patients after an incomplete optical colonoscopy with adequate preparation, and a complete evaluation of the colon was not technically possible.

The PillCam® COLON 2 capsule endoscopy system includes a single-use ingestible capsule designed to acquire video images during natural propulsion through the digestive system. It is specifically designed to visualize the complex anatomy of the colon. The PillCam COLON 2 capsule is designed to withstand the mechanical forces and chemical environment of the digestive system. The system is comprised of four main subsystems; (1) the ingestible PillCam COLON 2 capsule, (2) the DR 3 PillCam® Recorder, (3) the RAPID® software, and (4) the Given® Workstation.

1. A table of acceptance criteria and the reported device performance

Note: The document does not explicitly state numerical acceptance criteria values, but rather presents the study's performance characteristics as part of the overall demonstration of effectiveness. The table above reflects the reported performance that supports the device's acceptance.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Sample Size for Effectiveness Analysis: 700 subjects successfully completed an investigation with both CCE and OC and were included in the effectiveness analysis.
• Data Provenance: Prospective, multi-center study.
• Country of Origin: 11 enrollment sites in the US and 6 in Israel.

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)

The document states that a "central reader" interpreted the CCE results. For the optical colonoscopy (OC) results, "colonoscopists" evaluated their findings. The number and specific qualifications (e.g., years of experience) of these experts are not explicitly stated in the provided text.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

The document mentions an initial phase where "colonoscopists were blinded to CCE results when evaluating their OC findings." Following this, if a polyp detected on CCE was not identified by the initial colonoscopy, "the results of the CCE evaluation were unblinded and the colonoscopy was repeated in a second attempt to identify the polyp identified on CCE." This suggests a form of sequential adjudication or unblinding with repeat examination rather than a consensus-based adjudication (like 2+1 or 3+1). The "reference OC polyp chosen for the final determination was the one that was in favor of the device" when there were multiple equally large polyps, which implies a specific rule for handling discrepancies.

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 study was a "multi-center study" comparing CCE (the device) with optical colonoscopy (OC). It primarily evaluated the standalone performance of the CCE system against OC as the ground truth. There is no information provided about a Multi-Reader Multi-Case (MRMC) comparative effectiveness study involving human readers with and without AI assistance. The focus is on the device's ability to detect polyps, not on enhancing human reader performance using the device as an AI assistant.

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

Yes, a standalone performance evaluation was conducted. The study "compared CCE with optical colonoscopy (OC) for agreement on absence or presence of colon polyps." The CCE system, including its RAPID software for video viewing and report generation, functions as an algorithm-driven system that outputs video for interpretation. The performance metrics (positive and negative percent agreement) specifically refer to the CCE as a device, implying standalone performance in detecting polyps. The "centralized reader" interpreted the CCE results, but the CCE itself is the classification device.

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

The ground truth used was Optical Colonoscopy (OC) findings, specifically the identification and sizing of colon polyps (≥6 mm or ≥10 mm). OC is considered a clinically acceptable alternative structural imaging method.

8. The sample size for the training set

The provided document does not specify the sample size for a training set. The clinical study described is for evaluating the performance of the already developed device, not for training it.

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

Since no information on a training set is provided, how its ground truth was established is not detailed in this document.

Ask a specific question about this device