Search Results

The EndoSign® Cell collection device is to be used for the collection of cells from the surface of the oesophagus for molecular, cytological and histological analyses.

The EndoSign® Cell collection device is to be used for the collection of cells from the surface of the oesophagus for molecular, cytological and histological analyses. It is a non-sterile low risk, transient use, minimally invasive, single use, oesophageal cell collection device designed for use by trained and qualified medical professionals. The device is composed of a clear, size 00 capsule made from vegetable-derived material. The capsule houses a 30mm compressed spherical sponge and is connected to a non-absorbable silicone-coated braided polyester thread, secured to a clear polycarbonate applicator. The patient swallows the capsule along with the bundled thread, and as it travels through the oesophagus, the capsule dissolves allowing the sponge to expand and release. The thread is then gently pulled to retrieve the sponge, which collects cells from the lining of the oesophagus as it is removed. The device is used to collect cell samples which are further analyzed for identification of disease biomarkers. The results of the test will be used to assess patients suspected of oesophageal pathologies such as Barrett's oesophageal cancer, eosinophilic esophagitis, and other abnormalities.

The provided FDA 510(k) summary for the EndoSign® Cell collection device (K233142) does not contain specific acceptance criteria, detailed study results, or information typically found in a clinical study report for device performance. Instead, it focuses on demonstrating substantial equivalence to a predicate device (Cytosponge™ Cell Collection Device, K181020) through bench functional testing and general performance and safety validation.

Therefore, I cannot provide the detailed information requested in the prompt based solely on the provided text. The document states:

"Performance testing for the EndoSign® Cell collection device consisted of bench functional testing, performance and safety validation, and shelf life. Functional testing included dissolution, tensile strength, biocompatibility, manufacturing accuracy, dimensional reproducibility, sampling sufficiency, and usability/human factors testing. Results of performance testing demonstrate performance equivalence for the EndoSign® Cell collection device when evaluated against the predicate device."

This is a general statement about the types of tests conducted, but it does not provide the acceptance criteria (e.g., minimum tensile strength), the reported performance metrics (e.g., actual tensile strength measured), or the methodologies (e.g., sample size, ground truth establishment) for any of these tests.

If this were a typical AI/ML medical device submission, the acceptance criteria and study details would be much more explicit, particularly regarding diagnostic performance metrics. However, this is a physical device submission where the focus is on the collection mechanism's equivalence and safety.

Based on the provided text, here is what can be inferred and what cannot be provided:

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

• Cannot provide. The document lists categories of functional testing (dissolution, tensile strength, biocompatibility, manufacturing accuracy, dimensional reproducibility, sampling sufficiency, usability/human factors testing) but does not provide specific numerical acceptance criteria or the measured performance values for these tests. It only states that the "Results of performance testing demonstrate performance equivalence."

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

• Cannot provide. The document mentions "performance testing" but does not specify sample sizes or data provenance (e.g., number of devices tested for tensile strength, origin of samples for biocompatibility). Given its focus on demonstrating equivalence for a physical device, these tests are likely lab-based bench tests rather than clinical studies with patient data.

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)

• Cannot provide. This type of information is typically relevant for diagnostic devices that rely on expert interpretation of images or data. For a cell collection device, "ground truth" would likely relate to objective measurements of physical properties (e.g., cell yield, integrity) rather than expert consensus on a diagnosis. The document does not describe such expert involvement for ground truth establishment.

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

• Cannot provide. Adjudication methods are specific to studies involving human readers or evaluators, often in cases where subjective interpretation needs to be standardized. This is not applicable to the functional bench tests described for this physical device.

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

• Cannot provide. An MRMC study is relevant for AI/ML diagnostic tools where the impact of AI on human reader performance is assessed. The EndoSign® is a physical cell collection device, not an AI diagnostic tool.

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

• Cannot provide. Standalone performance is relevant for AI/ML algorithms. The EndoSign® is a physical device, so this concept does not apply.

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

• Cannot clearly provide. For the functional tests mentioned (dissolution, tensile strength, biocompatibility, etc.), the ground truth would be objective physical measurements against engineering specifications or established standards. For "sampling sufficiency," it would likely be laboratory analysis of collected cells (e.g., cell count, viability, presence of specific markers), but the document does not specify the method or "ground truth" criteria for this.

8. The sample size for the training set

• Not applicable. This device is not an AI/ML algorithm that requires a training set.

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

• Not applicable. This device is not an AI/ML algorithm that requires a training set.

In summary, the provided document describes a 510(k) submission for a physical medical device. It focuses on demonstrating substantial equivalence through bench testing of physical and performance characteristics, rather than clinical efficacy studies or performance metrics for an AI/ML diagnostic tool. Therefore, most of the detailed information requested regarding acceptance criteria and study designs typically associated with AI/ML or extensive clinical trials is not present in this type of regulatory submission document.

Ask a specific question about this device

The EsoCheck Cell Collection Device is indicated for use in the collection and retrieval of surface cells of the esophagus in the general population of adults and adolescents, 12 years of age and older.

The EsoCheck Cell Collection Device is a non-sterile, single-use disposable non-endoscopic balloon capsule catheter designed to collect and retrieve surface cells of the esophagus.

The balloon capsule is attached to a catheter and swallowed with the balloon deflated and inverted. Once positioned, the balloon is inflated and withdrawn allowing its textured surface to swab the surface of the targeted segment of the esophagus, retrieving cells in the process. The balloon is then deflated, retracting it along with the retrieved cells on its surface into the capsule, where they are protected from dilution or contamination as the capsule is fully withdrawn from the patient. The balloon is cut from the capsule and placed in the desired specimen container. The specimen is then sent for diagnostic processing and analysis.

The subject device is technologically identical to the previously-cleared predicate device (K222366). The only modification to the subject device is of its sterility, which has been modified to non-sterile (i.e., provided non-sterile and not requiring end-user sterilization before use).

The provided document does not contain information regarding acceptance criteria or studies proving device performance in the sense of clinical performance or diagnostic accuracy. Instead, it is an FDA 510(k) clearance letter and summary for a medical device, the EsoCheck Cell Collection Device.

This document focuses on demonstrating substantial equivalence to a previously cleared predicate device, rather than proving a diagnostic algorithm's performance against clinical acceptance criteria. The key point is that the only modification to the device is its sterility status (from sterile to non-sterile). Therefore, the "performance data" section in this document refers to engineering and safety performance related to this change (e.g., bioburden testing), not clinical accuracy or effectiveness in diagnosing a condition.

Therefore, I cannot fulfill the request as it pertains to the clinical performance of a diagnostic device, the establishment of ground truth, or an MRMC study.

Here's a breakdown of why and what information is present:

• No Acceptance Criteria for Diagnostic Performance: The document does not define metrics like sensitivity, specificity, or accuracy for the EsoCheck device's ability to diagnose a condition. Its function is to collect cells, not to perform a diagnosis itself.
• No Study Proving Diagnostic Performance: There is no mention of a study evaluating the device's diagnostic accuracy or comparing its performance against a ground truth for a disease.
• The "Performance Data" Section: This section specifically states, "All prior testing of the predicate device remains applicable to the subject device because sterilization status could not affect device performance (thus no new performance testing is required), and the prior sterilization method (EtO) constituted worst case test conditions for other types of testing (i.e., biocompatibility and packaging/shelf life)." The only new testing mentioned is "bioburden testing" to support the change to non-sterile status. This is a safety and manufacturing performance test, not a clinical diagnostic performance test.

To directly address your requested points based on the provided text, the answer for most will be "Not Applicable" or "No information provided," as the document's purpose is different from what your prompt assumes:

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

   • Acceptance Criteria: Not applicable for diagnostic performance. The implicit acceptance criterion for this 510(k) was that changing the sterility status to non-sterile did not negatively impact safety or essential functioning, which was demonstrated by bioburden testing.
   • Reported Device Performance:
     • Bioburden Testing: Showed "an absence of specific objectionable organisms and acceptable bioburden levels."
     • Cell Adherence: "Functionally, the ability of cells to adhere to the EsoCheck balloon surface is unimpacted by device sterility."

2. Sample sized used for the test set and the data provenance: Not applicable. No clinical test set data is provided. The bioburden testing would have involved samples from the manufactured device, not patient data.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. No clinical ground truth establishment is described.

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. This device is a cell collection tool, not an AI-powered diagnostic algorithm.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): Not applicable.

8. The sample size for the training set: Not applicable. No training set for an algorithm is mentioned.

9. How the ground truth for the training set was established: Not applicable.

In summary, the provided document is a regulatory submission for a physical medical device (cell collection device), not a document detailing the validation of a diagnostic algorithm or AI system.

Ask a specific question about this device

The PENTAX Medical Video Esophagoscope EE17-J10 is intended to provide optical visualization of (via a video monitor), and therapeutic access to, the upper gastrointestinal tract. This anatomy includes the organs, tissues, and subsystems of esophagus and gastro-esophageal junction.

This endoscope is introduced via the mouth or nose when indications consistent with the need for the procedure are observed in adult and pediatric patient populations.

The PENTAX Medical Video Esophagoscope EE17-J10 is intended to be used with a PENTAX Video Processor, video monitor, endoscopic device and other ancillary equipment for optical visualization (via a video monitor) of, and/or therapeutic access to the esophagus and Gastro-Esophageal Junction. This anatomy includes, the following organs, tissues; and subsystems: Esophagus and Gastro-Esophageal Junction.

The EE17-J10 is composed of the following main parts: an insertion portion, control body and PVE connector. The insertion is inserted into the body cavity of patient. The insertion portion includes the distal end and bending section. The objective lens, light guide, instrument channel and air/water nozzle are located on the distal end of the insertion portion. The control body is held by the user's hand. The control body includes the angulation control knob, angulation lock knob/lever, air/water cylinder, suction cylinder, remote button, and instrument channel inlet. The air/water feeding valve is attached to the air/water cylinder, and the suction control valve is attached to the suction cylinder. The inlet seal is attached to the instrument channel inlet. The PVE connected to the video processor via electrical contacts.

The bending section is bent by the angulation control knob to operate the endoscope angulation. The angulation lock knob/lever is used to adjust the rotation torque of the angulation control knob.

The air/water feeding system is used to deliver the air and water to the objective lens from the air/water nozzle. When the hole at the top of air/water feeding valve is covered, the air is delivered. When the air/water feeding valve is pushed, the water is delivered. The suction control system is used to suction the fluid and air in body cavity from the instrument channel. When the suction control valve is pushed, the fluid and air are suctioned.

The remote button is used to operate the functions of the video processor and any external device from the control body, as necessary.

Endoscopic devices such as biopsy forceps are inserted from the instrument channel Inlet into the body cavity through the instrument channel.

The light guide of the distal end is used to illuminate the body cavity by light which is carried through the light carrying bundle. The light carrying bundle guides the light from light guide plug which is connected to the light source inside the Video Processor. The CCD built into the distal end receives reflected light (image data) from the body cavity, and sends the image data to the Video Processor through the video cable. The image data are converted into the image signal by the Video Processor, and the image inside the body cavity is displayed on the monitor.

The PENTAX Medical Video Processors EPK-i7010 and EPK-3000 are compatible with PENTAX Medical Video Esophagoscope EE17-J10.

The PENTAX Medical Video Esophagoscope EE17-J10 is provided with the following accessories:

• Inlet Seal - prevents suctioned fluid from coming out of the instrument Channel Inlet during the use of suction function. During reprocessing, it seals the instrument Channel Inlet in order to fill the chemical solution inside the channel.
• Bite Block - prevents patients from biting the endoscope insertion tube during an endoscopic examination.
• Suction Control Valve - intended to control suction.
• Air/Water Valve - intended to control air and water feeding.

Additional accessories for reprocessing are provided with the device. These include a Cleaning Adapter, Soaking Cap, Ventilation Cap, Endoscope Cleaning Brush Kits, and replacement O-Rings.

The provided text does not contain detailed acceptance criteria or a comprehensive study report for the device's clinical performance. Instead, it focuses on non-clinical performance data and a brief mention of a "clinical image capture study."

Here's an analysis based on the information available:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not provide a table specifying distinct acceptance criteria for clinical performance and corresponding reported device performance metrics. It mainly lists validation studies for non-clinical aspects and states that "All acceptance criteria were satisfied" for reprocessing validation.

For the "Optical Performance" and "Clinical Image Capture Study," it claims equivalence or demonstration of capability rather than specific quantitative performance against acceptance criteria.

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

• Clinical Image Capture Study: The document states that "A clinical image capture study was performed," but it does not specify the sample size (e.g., number of patients or cases) used for this test set nor the data provenance (e.g., country of origin, retrospective or prospective nature).

3. Number of Experts and Qualifications for Ground Truth

• The document does not mention the number of experts used to establish ground truth for the clinical image capture study, nor their qualifications.

4. Adjudication Method

• The document does not specify any adjudication method used for the clinical image capture study's ground truth.

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

• No information is provided about a multi-reader multi-case (MRMC) comparative effectiveness study. The document does not discuss human reader improvement with or without AI assistance, as the device described is an esophagoscope and not an AI-powered diagnostic tool in the typical sense that would involve such a study.

6. Standalone (Algorithm Only) Performance

• This question is not applicable as the device is an esophagoscope, a medical instrument for direct visualization, not an algorithm for standalone diagnostic performance.

7. Type of Ground Truth Used

• For the "Clinical Image Capture Study," the document states it was performed "to demonstrate the maneuverability of the EE17-J10 endoscope and its ability to capture images at each of the pre-determined anatomical areas when used in a clinical setting." This suggests the ground truth was based on the successful visualization and image capture of anatomical areas by a clinician, rather than expert consensus on a diagnosis, pathology, or outcomes data.

8. Sample Size for the Training Set

• This question is not applicable as the device is an esophagoscope and does not appear to involve a "training set" in the context of machine learning or AI algorithms. The "reference device" EG17-J10 (K210177) is used for comparison in performance, not as a training set for the current device's development.

9. How Ground Truth for the Training Set Was Established

• This question is not applicable for the same reason as point 8; there is no mention of a "training set" with established ground truth for this medical device's clearance.

In summary, the provided text details non-clinical performance evaluations (reprocessing, biocompatibility, software/cybersecurity, electrical safety, system performance, optical performance) focused on establishing substantial equivalence to a predicate and reference device. However, it lacks specific details regarding quantitative clinical performance, acceptance criteria, sample sizes, expert involvement, or ground truth establishment for a clinical study that would directly address device effectiveness in a diagnostic or therapeutic context. The "Clinical Image Capture Study" is mentioned as merely demonstrating the device's ability to capture images in clinical settings.

Ask a specific question about this device

The EsoCheck Cell Collection Device is indicated for use in the collection and retrieval of surface cells of the esophagus in the general population of adults and adolescents, 12 years of age and older.

The EsoCheck Cell Collection Device is a sterile single-use disposable non-endoscopic balloon capsule catheter designed to collect and retrieve surface cells of the esophaqus. The balloon capsule is attached to a catheter and swallowed with the balloon deflated and inverted. Once positioned, the balloon is inflated and withdrawn allowing its textured surface to swab the surface of the targeted segment of the esophagus, retrieving cells in the process. The balloon is then deflated, retracting it along with the retrieved cells on its surface into the capsule, where they are protected from dilution or contamination as the capsule is fully withdrawn from the patient. The balloon is cut from the capsule and placed in the desired specimen container. The specimen is then sent for diagnostic processing and analysis.

The provided text describes the EsoCheck Cell Collection Device, but it does not contain specific acceptance criteria or performance metrics in a table format, nor does it detail a study that defines such criteria and measures the device's performance against them.

The "Performance Data" section in the document refers to a GLP animal study that supported the expansion of the device's indications for use to include adolescents. However, this study focused on safety (successful esophageal deployment and no significant injuries) rather than specific performance metrics like sensitivity, specificity, or cell collection efficiency which would typically be associated with acceptance criteria for such a device.

Here's an analysis based on the information provided, and what is missing:

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

• Missing. The document does not provide a table with acceptance criteria or quantitative performance metrics for cell collection, diagnostic accuracy, or similar. The "performance data" discussed is related to safety for expanded use in adolescents.

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

• The only study mentioned is a GLP animal study in a porcine model.
• Sample size: Not specified.
• Data provenance: Prospective (animal study).

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. The animal study was for safety (lack of injury), not for establishing diagnostic ground truth requiring expert interpretation of collected samples.

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

• Not applicable. The animal study focused on physical outcomes (esophageal deployment, injury assessment), not diagnostic interpretation requiring adjudication methods.

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

• No. This device is a cell collection device, not an AI-assisted diagnostic tool.

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

• No. This device does not have an AI algorithm.

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

• For the animal study related to the expanded indication, the "ground truth" was the absence of significant injuries and successful deployment observed during evaluations after the procedure. This would be based on direct veterinary assessment or pathological examination of the animal tissues.

8. The sample size for the training set

• Not applicable. The device is a physical cell collection device; there is no mention of a training set for an algorithm.

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

• Not applicable. (No training set for an algorithm).

Summary of what is available regarding performance for the expanded indication:

The document states: "The animal study found that the EsoCheck Cell Collection Devices demonstrated successful esophageal deployment, and evaluations after the EsoCheck procedure found no significant injuries in the test population." This is the reported performance for the specifically mentioned study designed to support the expanded indication for adolescents. It focuses on the safety and mechanical functionality in an adolescent-representative model.

Ask a specific question about this device

The gathering and recovery of cells and cellular material from the mucosa in the esophagus for cytological and histological analyses.

The EsophaCap® Swallowable Cellular Retrieval Device is a non-sterile, non-endoscopic, singleuse Esophageal cell sampling device. The EsophaCap® is composed of an open-cell polyether polyurethane foam sphere attached to a polyester tether cap. The open-cell foam sphere ranging in diameter sizes from 20 mm to 35mm is compressed and encapsulated within a vegetable (hypromellose (HPMC)) capsule. When swallowed the EsophaCap® capsule dissolves releasing the foam sphere. The foam sphere expands to form a cytology and cellular retrieval device that allows a circumferential "bottle brush" collection using the expanded "open cell" foam sphere. The radiopaque polyester tether/stylus is used to slowly withdraw the foam sphere through the esophagus and then to subsequently retrieve the foam sphere with the cellular sample.

The provided text describes the EsophaCap® Swallowable Cellular Retrieval Device, its intended use, and its equivalence to predicate devices, but it does not contain information about acceptance criteria and a study proving the device meets those criteria from an AI/ML perspective. The document focuses on regulatory clearance (510(k)) based on substantial equivalence to existing devices.

The "Testing Performance Data" section mentions "bench testing, biocompatibility testing and user input" and lists specific bench tests like "dissolution testing, and tether /stylus tensile testing, and tether/stylus length test." These are engineering and material performance tests, not clinical studies demonstrating performance against diagnostic or other clinical acceptance criteria that would typically be associated with an AI/ML device.

Therefore, I cannot provide the requested information, specifically:

1. A table of acceptance criteria and the reported device performance.
2. Sample size used for the test set and data provenance.
3. Number of experts used to establish ground truth and their qualifications.
4. Adjudication method for the test set.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done.
6. If a standalone (algorithm only) performance was done.
7. The type of ground truth used.
8. The sample size for the training set.
9. How the ground truth for the training set was established.

This device, as described, is a physical medical device (cellular retrieval device), not an AI/ML diagnostic or predictive tool, and thus the typical metrics and study designs for AI/ML devices are not applicable or reported in this document.

Ask a specific question about this device

The EsoCheck Cell Collection Device is indicated for use in the collection and retrieval of surface cells of the esophagus in the general population of adults, 22 years of age and older.

The EsoCheck Cell Collection Device is a sterile single-use disposable non-endoscopic balloon capsule catheter designed to collect and retrieve surface cells of the esophagus. The balloon capsule is attached to a catheter and swallowed with the balloon deflated and inverted. Once positioned, the balloon is inflated and withdrawn allowing its textured surface to swab the surface of the targeted segment of the esophagus, retrieving cells in the process. The balloon is then deflated, retracting it along with the retrieved cells on its surface into the capsule, where they are protected from dilution or contamination as the capsule is fully withdrawn from the patient. The balloon is cut from the capsule and placed in the desired specimen container. The specimen is then sent for diagnostic processing and analysis.

This version of the device is a modification to the predicate EsoCheck CCD Cell Collection Device that was cleared under K183262. The minor changes made to the device include minor changes to the secondary packaging design change (addition of a tether) to increase tensile stiffness of the catheter during removal. In addition, the previous version of the device utilized 2 syringes, a 20cc syringe and a 5cc syringe, to complete the procedure. The modified device will utilize a single 20cc syringe to streamline the process and the syringe will have markings printed on its surface indicating different volumes.

Here's an analysis of the provided text regarding the acceptance criteria and supporting study for the EsoCheck Cell Collection Device.

Important Note: The provided document is a 510(k) summary for a device (EsoCheck Cell Collection Device), not an AI algorithm. Therefore, many of the typical AI/ML-related questions (e.g., ground truth for training/test sets, expert adjudication, MRMC studies, standalone algorithm performance) are not applicable to this submission. The "study" mentioned here refers to device validation tests, not a clinical performance study involving AI.

Acceptance Criteria and Device Performance (Based on Device Modifications)

The document primarily discusses the validation of modifications to an already cleared device, not the initial clearance of a novel device. The "acceptance criteria" are implied by the nature of the tests performed to ensure the modified device remains safe and effective and is substantially equivalent to its predicate.

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document only states that these tests were performed and implies successful completion, leading to the conclusion of substantial equivalence. It does not provide specific metrics or thresholds (e.g., "sterility assurance level X achieved," "packaging passed drop test Y," "95% of users found the device easy to use").

2. Sample Size and Data Provenance

Since this is a device modification validation and not a clinical study on patient data for an algorithm, the concepts of "sample size for the test set" and "data provenance" (country, retrospective/prospective) as they relate to AI/ML clinical performance are not directly applicable or reported in this document. The "tests" refer to laboratory and engineering validations.

3. Number of Experts and Qualifications for Ground Truth

Not applicable. Ground truth for AI/ML performance is irrelevant here as it's a device. The "experts" would be the engineers and quality control personnel conducting the validation tests, but their number and qualifications are not specified nor relevant in the context of AI ground truth.

4. Adjudication Method for the Test Set

Not applicable. There is no "test set" in the sense of clinical data requiring expert adjudication, as this is a device validation.

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

Not applicable. This is not an AI-assisted diagnostic tool; it is a cell collection device. Therefore, no MRMC study, human reader improvement, or effect size is relevant.

6. Standalone Algorithm Performance

Not applicable. There is no algorithm here whose standalone performance would be measured.

7. Type of Ground Truth Used

The "ground truth" for these device validation tests would be:

• Sterilization: Regulatory standards (AAMI TIR 28:2016) and passing criteria for sterility.
• Packaging: Engineering specifications and industry standards for package integrity.
• Shelf-Life: Material degradation limits and functional requirements over time.
• Usability: User feedback and task completion rates against predefined usability goals.
• Bench Performance: Engineering specifications and functional requirements of the device (e.g., aspiration volume, balloon inflation/deflation, tether tensile strength).

The document does not detail the specific metrics for these.

8. Sample Size for the Training Set

Not applicable. This is a physical medical device, not an AI model requiring a training set of data.

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

Not applicable. See point 8.

Summary of the Device and its Modifications:

The EsoCheck Cell Collection Device is a sterile, single-use, disposable, non-endoscopic balloon capsule catheter designed to collect surface cells from the esophagus. The procedure involves swallowing the deflated capsule, inflating the balloon once positioned, and then withdrawing it to swab the esophageal surface. Cells are then retracted into the capsule and protected during withdrawal.

The modified device, K210137, has minor changes compared to its predicate (K183262):

• Minor changes to the secondary packaging design (addition of a tether to increase tensile stiffness during removal).
• Changed from using two syringes (20cc and 5cc) to a single 20cc syringe with printed volume markings to streamline the process.

The "Performance Data" section lists the types of tests performed to validate these minor modifications: Sterilization Validation, Packaging Validation, Shelf-Life Testing, Usability Confirmation Testing, and Bench Performance Testing. The conclusion is that these tests demonstrate the modified device is as safe and effective as the predicate and is substantially equivalent.

Ask a specific question about this device

The CMOS Video Esophagoscope SSU is intended to provide visualization of nasal sinuses, larynx, esophagus and gastroesophageal junction during diagnostic procedures.

The E-Box serves as an adaptor for operating the flexible single-use videoscope on the compatible CCU.

The CMOS Video Esophagoscope SSU System includes three main components: (1) the CMOS Video Esophagoscope SSU (091370-01), (2) E-Box adaptor (TP010) and (3) the CCU. CMOS Video Esophagoscope SSU is compatible with two KARL STORZ CCUs: C-HUB and C-MAC. CMOS Video Esophagoscope SSU is provided sterile single-use.

The provided document describes the Karl Storz SE & Co. KG CMOS Video Esophagoscope SSU, a flexible video endoscope intended for visualization during diagnostic procedures of nasal sinuses, larynx, esophagus, and gastroesophageal junction. The document focuses on demonstrating substantial equivalence to a predicate device, rather than proving device performance against specific acceptance criteria for a new clinical claim. Therefore, much of the requested information regarding clinical study design, performance metrics (like sensitivity, specificity, AUC), expert adjudication, and effect sizes of AI assistance is not available in this filing.

Here's a breakdown of the available information and an explanation of the missing components:

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

The submission does not define specific clinical acceptance criteria (e.g., sensitivity, specificity, AUC) for the CMOS Video Esophagoscope SSU's diagnostic performance, as no clinical study was conducted for this purpose to demonstrate substantial equivalence. Instead, the acceptance criteria are related to technical performance and safety, assessed through non-clinical testing against recognized standards, and direct comparison of technological characteristics to the predicate device.

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

Not Applicable. The document explicitly states: "Clinical testing was not required to demonstrate the substantial equivalence to the predicate device. Non-clinical bench testing and labeling were sufficient to establish the substantial equivalence of the modifications." Therefore, there is no clinical test set, sample size, or data provenance from clinical trials to report.

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

Not Applicable. As no clinical study was conducted for performance evaluation using a test set requiring ground truth, this information is not available.

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

Not Applicable. No clinical test set means no adjudication method was used.

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. This device is an endoscope for "visualization" during diagnostic procedures. It is not an AI-powered diagnostic algorithm or an AI-assisted device. Therefore, no MRMC study, AI assistance, or related effect sizes are relevant or present in the submission.

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

Not Applicable. This device is directly operated by a human. It is not a standalone algorithm.

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

Not Applicable. No clinical study was performed to establish diagnostic performance, therefore no ground truth was established through external means like expert consensus, pathology, or outcomes data. Ground truth in this context typically refers to a definitive diagnosis or finding against which a device's diagnostic output is compared.

8. The sample size for the training set

Not Applicable. This device is a medical instrument (hardware with internal software), not a machine learning model that requires a "training set" in the context of AI/ML development. The software for the device underwent standard software verification and validation, but not in the framework of a training set for an AI algorithm.

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

Not Applicable. As there is no training set for an AI/ML model, this question is not applicable.

Ask a specific question about this device

The EsoCheck CCD Cell Collection Device is indicated for use in the collection and retrieval of surface cells of the esophagus in the general population of adults, 22 years of age and older.

The Lucid Diagnostics EsoCheck™ CCD Cell Collection Device is a sterile single-use disposable non-endoscopic balloon capsule catheter designed to collect and retrieve surface cells of the esophagus. The balloon capsule is attached to a catheter and swallowed with the balloon deflated and inverted. Once positioned, the balloon is inflated and withdrawn allowing its textured surface to swab the surface of the targeted segment of the esophagus, retrieving cells in the process. The balloon is then deflated, retracting it along with the retrieved cells on its surface into the capsule, where they are protected from dilution or contamination as the capsule is fully withdrawn from the patient. The balloon is cut from the capsule and placed in the desired specimen container. The specimen is then sent for diagnostic processing and analysis.

The provided text describes the 510(k) premarket notification for the EsoCheck CCD Cell Collection Device. While it outlines the device's purpose, design, non-clinical tests conducted (verification and validation), and its substantial equivalence to predicate devices, it does not contain information regarding the acceptance criteria for device performance, nor details of a study that proves the device meets specific performance criteria related to diagnostic accuracy (e.g., sensitivity, specificity, or human reader improvement with AI assistance).

The document focuses on:

• Device Description: How the EsoCheck CCD Cell Collection Device works to collect esophageal cells.
• Intended Use: For collection and retrieval of surface cells of the esophagus from adults 22 years and older.
• Substantial Equivalence: Comparison to previously cleared predicate devices (Brandt Cytology Balloon, Cytosponge, Hobbs Medical Cytology Brush) based on intended use, population, anatomical location, design, principles of operation, and single-use disposition.
• Nonclinical Tests: Lists various verification (e.g., visual inspection, balloon inflation/deflation, tensile tests) and validation (biocompatibility, sterilization, shelf life, user validation) tests. These are primarily engineering and safety tests rather than performance tests for diagnostic accuracy.

Therefore, I cannot fulfill your request for the following information based solely on the provided text:

1. A table of acceptance criteria and the reported device performance: The document lists non-clinical tests but does not provide specific performance metrics (e.g., cell yield, diagnostic accuracy) or their acceptance criteria.
2. Sample size used for the test set and the data provenance: Not mentioned.
3. Number of experts used to establish the ground truth and their qualifications: Not mentioned, as no diagnostic performance study is detailed.
4. Adjudication method for the test set: Not applicable based on the provided information.
5. MRMC comparative effectiveness study: Not conducted or mentioned. The device is a cell collection tool, not an AI-assisted diagnostic tool.
6. Stand-alone (algorithm only) performance: Not applicable, as it's a physical device, not an algorithm.
7. Type of ground truth used: Not mentioned.
8. Sample size for the training set: Not applicable, as there's no mention of an algorithm requiring a training set.
9. How ground truth for the training set was established: Not applicable.

The "user validation" listed under validation testing (page 5) might imply some form of study involving users, but the details (methodology, sample size, outcome metrics, acceptance criteria) are not provided in this regulatory letter and 510(k) summary. This submission is for a cell collection device based on substantial equivalence, not a novel diagnostic method requiring extensive clinical performance studies for de novo clearance or PMA.

Ask a specific question about this device

The Strome-Blitzer Cytology Balloon device is indicated for use in the 4-quadrant collection and retrieval of surface cells from the esophagus in adults (22 years of age or older). The device may be delivered transorally under direct endoscopic visualization.

The Strome-Blitzer Cytology Balloon is an inflatable biopsy platform. It consists of a catheter with a silicone balloon at its distal end. The balloon has 6 collection pleats on its surface. Inside each pleat are 2 cytology collection strips for specimen collection. While the balloon is uninflated, the strips are covered by the balloon pleats. When inflated, the strips are exposed. The balloon inflates and deflates with the use of a syringe and attached catheter, and is a sterile, single-use device. There are 4 location indicator dots on the proximal balloon surface for orientation during esophagoscopy.

The provided text describes a medical device, the "Strome-Blitzer Cytology Balloon," and its 510(k) premarket notification to the FDA. The information focuses on demonstrating substantial equivalence to a predicate device, rather than proving the device meets specific acceptance criteria in the context of an AI/ML algorithm. Therefore, many of the requested details, such as the effect size of human reader improvement with AI assistance, sample sizes for training sets of AI, or ground truth for AI model development, are not present in this document.

However, I can extract the acceptance criteria and study details related to the device's performance as described in the provided text.

Acceptance Criteria and Reported Device Performance (Device-Specific, not AI/ML):

Study Details:

1. Sample size used for the test set and the data provenance:

   • Test Set Sample Size: 6 swine.
   • Data Provenance: Not explicitly stated (e.g., country of origin), but the study was an "Animal Study," implying prospective data collection specifically for this evaluation.

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

   • The document implies that "cytologic examination" was performed to evaluate the samples. However, it does not state the number of experts used, nor their specific qualifications, for establishing the ground truth of "diagnostically useful cytology samples of high cellularity" or "morphologically comparable."

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

   • The document does not describe any adjudication method for the evaluation of cytology samples from the animal study.

4. 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:

   • No. This was a study comparing a new medical device (a cytology balloon) to a reference device (a cytology brush) in an animal model, not an AI/ML algorithm requiring human reader performance improvement metrics.

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

   • No. This is a physical medical device, not an algorithm.

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

   • The ground truth appear to be based on cytologic examination of the collected samples, which implies expert evaluation (likely by pathologists or cytotechnologists). The document states "cytologic examination... resulted in diagnostically useful cytology samples of high cellularity that were morphologically comparable..." This suggests an expert assessment of the cellular quality and morphology.

7. The sample size for the training set:

   • Not applicable. This is a physical device, not an AI/ML algorithm requiring a training set.

8. How the ground truth for the training set was established:

   • Not applicable. As above, this is a physical device, not an AI/ML algorithm.

Ask a specific question about this device

The PrimeSight™ UNITY 9000 Series Video Processors, when used in conjunction with a Cogentix Medical flexible videoscope, are indicated for the display and management of video and images during trans-nasal esophagoscopy, cystoscopy, bronchoscopy and nasopharyngoscopy procedures.

The PrimeSight™ UNITY 9000 and PrimeSight™ UNITY 9100 Video Processors (herein referred to as "UNITY 9000", "UNITY 9000 Processor" or "UNITY 9000 Series Video Processors") are video processing units designed to work exclusively with the Cogentix Medical TNE-5000, CST-5000, CST-5000i. BRS-5100 and ENT-5000 models of flexible videoscopes (herein referred to as "5000 Series Videoscopes") to display images and videos during endoscopic procedures. The UNITY 9000 Processor consists of two modules which are physically connected with a hinge mechanism. The all-inone computer (AIO PC) unit is used for the presentation and display of images and includes a large 19'' wide screen display with an integrated touchscreen. The Camera Interface Module (CIM) base unit allows for the connection of a videoscope or camera to the Processor, as well as any endoscopic peripherals being used during the procedure, as well as image processing.

There are two different model configurations available for the UNITY 9000. These models are offered specific to the type of endoscopic procedure being performed. The Base Configuration model (UVP-9000) supports urology and bronchoscopy applications, while the Airway Configuration model (UVP-9100) offers an integrated air pump for trans-nasal esophagoscopy and a stroboscopy interface for use during Ear, Nose, and Throat (ENT) stroboscopy examinations.

The provided document, a 510(k) summary for the PrimeSight™ UNITY 9000 Series Video Processors, describes the device's functional performance and compliance with various standards. However, it explicitly states that clinical data was not used to demonstrate substantial equivalence because the subject device and predicate device are considered very similar in design and functionality. This means the study did not involve human readers, ground truth establishment, or multi-reader multi-case comparative effectiveness.

Therefore, many of the requested details about acceptance criteria related to clinical performance metrics and associated study parameters (like sample size for test sets, data provenance, number of experts for ground truth, adjudication methods, or MRMC studies) are not applicable or provided in this document.

The acceptance criteria mentioned are primarily focused on functional performance, compliance with electrical safety and electromagnetic compatibility standards, software requirements, environmental testing, and usability.

Here's a breakdown of the available information:

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

Since the document focuses on demonstrating substantial equivalence through non-clinical testing, specific quantitative acceptance criteria for clinical performance (e.g., sensitivity, specificity, accuracy) are not stated, nor is there reported clinical device performance in terms of these metrics.

Instead, the "acceptance criteria" are implied by the successful completion and positive results of the various engineering and regulatory compliance tests. The "reported device performance" is that the device meets these criteria and is "safe and effective and performs in a manner making it substantially equivalent to its predicate device."

2. Sample size used for the test set and the data provenance:
Not applicable for this type of non-clinical testing. The "test set" consisted of the physical device and its components undergoing various engineering, software, and regulatory compliance tests. There is no mention of a "data provenance" in the clinical sense (e.g., country of origin, retrospective/prospective).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
Not applicable. Ground truth, in the context of clinical studies, refers to definitive diagnoses or findings. This document describes engineering and regulatory compliance testing. Usability evaluation (TR 013-18) was performed, which likely involved human users, but details on the number or qualifications of "experts" to establish a clinical ground truth are not provided because it's not a clinical study.

4. Adjudication method for the test set:
Not applicable. Adjudication methods (like 2+1, 3+1) are used in clinical studies to resolve disagreements among human readers or evaluators when establishing ground truth. This document does not describe such a study.

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:
No, a MRMC comparative effectiveness study was not done. The device is a video processor for endoscopes, not an AI-powered diagnostic tool, and the document explicitly states that "Clinical data was not used to demonstrate substantial equivalence."

6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
Not applicable. This device is a video processor, which is inherently a "standalone" piece of hardware and software designed to display and manage images from endoscopes for human interpretation, not an algorithm providing diagnostic output on its own.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):
Not applicable in the clinical sense. The "ground truth" for the various engineering and regulatory compliance tests would be the established specifications, standards, and documented requirements that the device needed to meet.

8. The sample size for the training set:
Not applicable. There is no mention of a "training set" as this is not an AI/machine learning device requiring a dataset for model training.

9. How the ground truth for the training set was established:
Not applicable, as there was no training set.

Ask a specific question about this device