Search Results

The device PNEUMOCLEAR™ is a CO2 insufflator intended for use during diagnostic and/or therapeutic endoscopic procedures to distend a cavity by filling it with CO2 gas. The Standard, High Flow/Bariatric, Pediatric and Advanced Flow operating mode of the device are indicated to fill and distend a perioneal cavity with gas during a laparoscopic procedure. The Pediatric operating mode is indicated for pediatic laparoscopic procedures. The Vessel Harvest operating mode is indicated for use during endoscopic vessel harvesting procedures to create a cavity along the saphenous vein or radial artery. The TAMIS operating mode is indicated to fill and distend the rectum and colon using CO2 gas during transanal minimally invasive surgery.

The PNEUMOCLEAR™ is a microprocessor controlled device that consists of the following major components and features: a casing, a world power supply, pressure reducers, pressure sensors, venting systems, various safety valves, a suction pump, a fluid sensor and a software controlled graphical user interface (GUI) touch screen with various setting keys and display elements. The proposed device offers six operating modes: Standard, High Flow/Bariatric, Pediatric, Advanced Flow, Vessel Harvest, and TAMIS. The PNEUMOCLEAR™is not intended to enter the sterile field and cannot be sterilized. It is to be used with one of the following specially designed, single-use, sterile insufflation tube sets: (1) insufflation tube set with integrated filter, (2) insufflation tube set with integrated filter and heating wire; (3) insufflation tube set with integrated filter, heating wire and humidification media; (4) insufflation and smoke evacuation tube set with integrated filter, heating wire. and humidification media; and (5) insufflation and smoke evacuation tube set with integrated filter. When a smoke evacuation tube set is connected, the PNEUMOCLEAR™ allows for removal and filtration of CO2 and surgical smoke from the abdomen. rectum or colon during laparoscopic and transanal minimally invasive procedures and at the end of a procedure.

The provided text is a 510(k) Premarket Notification for the PNEUMOCLEAR™ device. It describes the device, its intended use, and claims substantial equivalence to a previously cleared predicate device (K170784 PNEUMOCLEAR™).

However, the document does not contain the kind of detailed information about acceptance criteria and clinical study performance typically found for AI/ML-driven devices. This is because the PNEUMOCLEAR™ is a CO2 insufflator, which is a hardware device, not an AI/ML diagnostic or assistive tool that would undergo studies involving human readers, ground truth establishment by experts, or MRMC studies.

The "Performance Data" section in the document focuses on:

• Electrical Safety and Electromagnetic Compatibility: Adherence to AAMI ANSI ES60601-1 and IEC 60601-1-2 standards.
• Packaging and Shelf-Life Testing: Compliance with various ASTM and ISO standards for packaging integrity and shelf-life.
• Software/Bench Testing: Software developed and verified according to FDA guidance and IEC 62304. Modifications to sensor sealing and gas lines for tube sets ST297 and ST298 were confirmed through submerged testing and simulated use testing, respectively. All software changes were bench-tested.

This submission is a "catch-up 510(k) submission intended to update the PNEUMOCLEAR™ record at FDA with the changes that have been implemented for the device." The changes are primarily tweaks to optional features and routine developmental updates, not fundamental changes to the device's technological characteristics or intended use. Therefore, clinical performance studies involving patient data, expert review, or complex statistical analysis for diagnostic accuracy (common for AI/ML devices) are not relevant or present in this submission.

In summary, based on the provided text, it is not possible to describe acceptance criteria and study proving device meets them in the context of an AI/ML device. The document is for a hardware medical device (CO2 insufflator) and its substantial equivalence to a predicate, focusing on engineering, safety, and performance standards relevant to its mechanical and electrical functions, not diagnostic accuracy or human-in-the-loop performance of an AI system.

Ask a specific question about this device

The ARTHRO-Pump PA304 is an arthroscopic pump intended to provide fluid distension of knee, shoulder, hip, elbow, ankle and wrist joint cavities and fluid aspiration during diagnostic and operative arthroscopic procedures.

The ARTHRO-Pump PA304 is a microprocessor controlled single roller pump that functions according to the peristaltic principle. It transports sterile irrigation fluid to distend cavities and provides fluid aspiration for arthroscopic procedures. The pump consists of the following main components: a power supply, a power switch, a touch display, a connection for the suction function, a roller wheel, a pump head and a casing. The pump has to be used with the following tube sets:

• . Standard Irrigation Tube Set (also referred to as "ST261")
• . Suction Tube Set (one connection, "I"-shape; also referred to as "ST287")
• Suction Tube Set (two connections, "Y"-shape; also referred to as "ST282") .
• Vacuum Tube Set (also referred to as "ST291"). .

The provided text describes the 510(k) premarket notification for the ARTHRO-Pump PA304. This device is an arthroscopic pump, and the documentation focuses on demonstrating its substantial equivalence to a predicate device (Arthroscopy Pump A107) rather than providing detailed acceptance criteria and a study specifically designed to prove all aspects of its performance against those criteria in a typical clinical study format.

However, based on the provided information, I can infer the acceptance criteria and summarize the studies performed to demonstrate the device's safety and effectiveness for its intended use, focusing on the available performance data.

Here's an interpretation and structured presentation of the information:

Acceptance Criteria and Device Performance for ARTHRO-Pump PA304

The ARTHRO-Pump PA304 is an arthroscopic pump. The primary goal of the 510(k) submission is to demonstrate its substantial equivalence to a predicate device (Arthroscopy Pump A107) by showing that its performance does not raise new questions of safety and effectiveness. Therefore, the "acceptance criteria" are implicitly tied to meeting established safety and performance standards for arthroscopic pumps and showing comparable or superior performance to the predicate device where applicable.

1. Table of Acceptance Criteria and Reported Device Performance:

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

• Software Design Verification: Not explicitly stated, but implies comprehensive testing according to standards.
• Electrical Safety & EMC Testing: Not explicitly stated, typically involves testing representative units.
• Biocompatibility Testing: Performed on "the tube sets of both the proposed device and predicate device." Specific number of samples not given, but standard practice involves multiple samples per test (e.g., cytotoxicity, irritation, sensitization, systemic toxicity).
• Sterilization Validation: Performed on "the tube sets of both devices." Specific sample size not given, but validation processes typically involve statistically significant numbers of products run through the sterilization cycle to establish SAL and residual levels.
• Bench Performance Testing: 36 test runs were conducted.
• Data Provenance: The document refers to "The ARTHRO-Pump PA304 is designed, developed and manufactured by W.O.M. WORLD of MEDICINE GmbH" in Berlin, Germany. Therefore, the data would originate from their internal testing and validation processes. All testing appears to be retrospective bench-top and lab-based testing, performed to support the 510(k) submission, rather than prospective clinical trials.

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

• This information is not applicable in the context of this 510(k) summary. The "ground truth" here is compliance with engineering standards and specific performance metrics (e.g., pressure stability, sterilization levels, biocompatibility). These are established through validated testing methodologies and adherence to international standards, not through expert clinical consensus on a test set of patient data.

4. Adjudication Method for the Test Set:

• Not applicable. This pertains to clinical studies using human observers/experts. The tests described are laboratory-based engineering and safety validations.

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, an MRMC study was not done. This type of study is relevant for imaging devices or AI-assisted diagnostic tools where human interpretation of medical images is involved. The ARTHRO-Pump PA304 is a surgical pump; its performance is assessed through its physical characteristics, fluid dynamics, safety, and compatibility, not human interpretation of data.

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

• This question is phrased for AI/software algorithms. While the device does contain software, the "standalone" performance here refers to the pump's mechanical and fluidic operation and the correct execution of its programmed functions, which were evaluated through design verification and bench testing. The software itself was tested for compliance withIEC62304:2006. The pump's operation without human intervention (e.g., maintaining a set pressure) would be considered part of its standalone performance.

7. The type of ground truth used:

• For this device, the "ground truth" is defined by:
  • Engineering Specifications: The design parameters for pressure range, stability, fluid flow.
  • International Standards: Compliance with ISO (e.g., 10993, 11135, 11607, 14937) and IEC (e.g., 60601) standards for medical devices, electrical safety, biocompatibility, and sterilization.
  • Regulatory Guidance: Adherence to FDA guidance for software in medical devices.
  • Predicate Device Performance: Implicitly, the performance of the legally marketed predicate device (Arthroscopy Pump A107) serves as a benchmark for comparison when demonstrating substantial equivalence.

8. The sample size for the training set:

• Not applicable. This device is an arthroscopic surgical pump, not an AI/machine learning model that requires a training set. The software mentioned is likely control software for the physical pump functions, developed using standard software engineering practices rather than machine learning.

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

• Not applicable. As stated above, there is no "training set" in the context of an AI/ML system for this device. The software was developed and verified against predefined functional requirements and engineering specifications to control the pump's operations.

Ask a specific question about this device

The GYN-Pump PH304 is a combined suction and irrigation pump for use in hysteroscopic and laparoscopic interventions. During diagnostic and operative hysteroscopy, the GYN-Pump PH304 is intended to provide liquid distension of the uterus and to monitor the volume differential between the irrigation fluid flowing into and out of the uterus. During diagnostic and therapeutic laparoscopic procedures, the GYN-Pump PH304 is intended to irrigate fluid into and remove fluid from the abdominal cavity.

The GYN-Pump PH304 is a microprocessor controlled single roller pump that functions according to the peristaltic principle. It transports sterile irrigation fluid to distend the uterus and provides fluid deficit monitoring during operative hysteroscopy. It is also used to irrigate the abdominal cavity during laparoscopy and provides fluid aspiration. The pump consists of the following main components: a power supply, a power switch, a touch display, a connection for the suction function, a roller wheel, a pump head and a casing. The proposed pump is designed to be used with the Fluid Monitoring Unit PS304 in order to assist with fluid deficit monitoring. The Fluid Monitoring Unit PS304 is a component of the GYN-Pump PH304 and together they are a medical electrical system. The pump must be used with the following tube sets: Standard Irrigation Tube Set (also referred to as "ST261"), Suction Tube Set (one connection, "I"-shape; also referred to as "ST287"), Suction Tube Set (two connections, "Y"-shape; also referred to as "ST282"), Vacuum Tube Set (also referred to as "ST291").

The medical device in question is the GYN-Pump PH304, a combined suction and irrigation pump for hysteroscopic and laparoscopic interventions.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

The document focuses on comparing the GYN-Pump PH304 to its predicate devices, rather than explicitly stating acceptance criteria in a standalone table within the performance section. However, the comparative table on page 7 and the subsequent discussion implicitly define the performance targets for the GYN-Pump PH304 by referencing the predicate devices' specifications and emphasizing improvements or equivalency.

2. Sample Sizes Used for the Test Set and Data Provenance:

The document describes bench tests for performance.

• Comparative Bench Test – Fluid Deficit Measurement: This test compared the GYN-Pump PH304 to the Aquilex Fluid Control System H112. The sample size for fluid deficit measurement is not explicitly stated in terms of number of procedures or specific data points. It mentions "fluid was dispensed through the system," implying a controlled experimental setup.
• Pressure Regulation Bench Test: This test involved connecting the GYN-Pump PH304 to a model system and cycling it through a range of flow rates and pressures. The sample size is not explicitly stated.
• Data Provenance: The studies were bench tests, conducted in a controlled laboratory environment by the manufacturer (W.O.M. World of Medicine GmbH). The country of origin for the studies would be Germany, where the manufacturer is located. The studies are prospective in nature, as they were conducted to evaluate the performance of the newly developed GYN-Pump PH304.

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

The document does not mention the involvement of experts (e.g., clinicians, radiologists) to establish ground truth for the bench tests. Ground truth for these performance tests was established through manual measurement (for fluid deficit) and continuous monitoring and recording (for pressure regulation) within the experimental setup, likely using calibrated instruments. The expertise would lie in the engineers and technicians conducting the validation tests according to established protocols and standards.

4. Adjudication Method for the Test Set:

No adjudication method (like 2+1 or 3+1) is mentioned as these were bench tests of a physical device's performance against predefined quantifiable metrics, not assessments of qualitative outputs or interpretations that would require expert consensus.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:

No MRMC comparative effectiveness study was done. The studies described are bench tests comparing device performance to predicate devices and predefined specifications, not human reader performance with or without AI assistance. Therefore, no effect size of human readers improving with AI vs without AI assistance is reported.

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

The device (GYN-Pump PH304) is a physical pump with embedded software, not an AI algorithm for diagnostic interpretation. The performance data presented is for the standalone device operating according to its design specifications in a test environment. Thus, a "standalone" performance study in the context of an AI algorithm is not applicable here, but the described bench tests effectively serve as standalone performance evaluations of the device.

7. The Type of Ground Truth Used:

• Bench Tests (Fluid Deficit Measurement): Ground truth was established through manual measurement of the fluid deficit. This involved a direct and objective physical measurement to compare against the device's computed deficit.
• Bench Tests (Pressure Regulation): Ground truth was established through continuously monitored and recorded pressure data from the model system, likely using highly accurate pressure transducers or sensors.

8. The Sample Size for the Training Set:

The GYN-Pump PH304 is a hardware device with embedded software logic, not an AI/machine learning system that requires a "training set" of data in the conventional sense. The software development, testing, and verification followed standards like IEC 62304, which involves rigorous development and testing phases, but not a "training set" of patient data as understood in AI/ML.

9. How the Ground Truth for the Training Set was Established:

As there is no "training set" in the context of an AI/ML algorithm for this device, this question is not applicable. The software's "ground truth" or correct functioning is established through comprehensive software verification and validation activities (unit testing, integration testing, system testing) against its design specifications and requirements, as per IEC 62304.

Ask a specific question about this device

The Aquilex® Fluid Control System AQL-100S is intended to provide fluid distension of the uterus during diagnostic and operative hysteroscopy and to monitor the volume differential between the irrigation fluid flowing into and out of the uterus.

The Aquilex® Fluid Control System AQL-100S is a modified version of the primary predicate device, Aquilex Fluid Control System H112 (K112642). The proposed device is a microprocessor-controlled device that consists of the following two main components: (1) an irrigation pump unit including suction pumps (AQL-110P) and (2) and fluid monitoring unit (AQL-100CBS) that are to be placed on a roller stand. The irrigation pump unit (AQL-110P) of the Aquilex® Fluid Control System AQL-100S is a microprocessor-controlled device that functions according to the peristaltic principle and consists of the following components: (1) a casing. (2) a power switch, (3) a power supply, (4) mains cable, (5) a roller wheel, (6) a pump head, (7) suction pumps, (8) various setting keys and (9) display elements. The irrigation pump unit (AQL-110P) is to be used with specially designed single use irrigation and outflow tube sets that are delivered sterile (AQL-110 and AQL-111). In addition, the suction pumps of the irrigation pump unit are to be used with specially designed non-sterile vacuum tube sets (AQL-114). The fluid monitoring unit (AQL-100CBS) consists of the following main components: (1) two scale units, (2), a bag holder, (4) a bag deflector, (5) a container holder, and (6) a roller wheel base. The irrigation pump unit of the proposed device is only operational in conjunction with the fluid monitoring unit.

The provided document in the prompt relates to a 510(k) premarket notification for a medical device called the "Aquilex® Fluid Control System AQL-100S." This document describes the device, its intended use, comparison to predicate devices, and a summary of performance data collected to demonstrate substantial equivalence.

However, the document does not contain specific acceptance criteria tables nor detailed results from a clinical study proving the device meets those criteria. Instead, it provides a summary of various bench tests and compliance with standards (electrical safety, EMC, software, biocompatibility, sterilization, shelf life) to support its substantial equivalence claim, rather than a clinical study with acceptance criteria for device performance in a real-world or simulated clinical setting.

Therefore, many of the requested details about acceptance criteria, study design, sample sizes, expert involvement, and ground truth cannot be extracted directly from this document in the manner typically associated with studies demonstrating performance against specific clinical or diagnostic metrics.

Based on the available information, here's what can be inferred and what cannot:

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

The document mentions "Bench testing was performed to demonstrate that the fluid deficit determination...is substantially equivalent...in terms of accuracy." However, it does not provide a specific table of acceptance criteria for this accuracy or the reported numerical performance values (e.g., mean accuracy, standard deviation, or specific thresholds).

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

• Test Set Sample Size: Not specified for any of the performance tests. The bench testing refers to "fluid deficit determination" but doesn't quantify the number of measurements or conditions.
• Data Provenance: The tests (electrical safety, EMC, software verification/validation, biocompatibility, sterilization, shelf life, bench testing) are described as performed by "independent laboratories" or internally. No information on country of origin of data or whether it was retrospective or prospective is given, as these are typically laboratory/bench tests, not clinical studies.

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 performance tests described are laboratory-based and do not involve human interpretation or subjective assessment that would require "experts to establish ground truth" in the clinical sense.

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

Not applicable. There's no human adjudication involved in the described bench and standard compliance tests.

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 fluid control system, not an AI or imaging diagnostic device that would involve human readers or MRMC studies.

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

The performance tests are essentially standalone for the device, as they assess its functional capabilities (e.g., electrical safety, fluid deficit accuracy) without human intervention in the primary measurement. However, this is not an "algorithm only" study in the context of AI, but rather a functional characterization of hardware and software.

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

For the bench testing related to "fluid deficit determination," the ground truth would likely be established by highly accurate reference measurement systems (e.g., precise scales or flow meters) that are calibrated and traceable to known standards. This is inherent in laboratory bench testing. The document doesn't explicitly state the specifics of this ground truth.

8. The sample size for the training set:

Not applicable. This is not an AI-driven device requiring a training set in the typical machine learning sense. The software development and testing, while mentioned (IEC 62304), refers to traditional software verification and validation, not machine learning model training.

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

Not applicable, as there is no training set for an AI model.

Summary of available information:

The document primarily relies on demonstrating compliance with recognized standards (IEC 60601-1, IEC 60601-1-2, IEC 62304, ISO 10993 series, ISO 11135, ISO 14937, ISO 11607-1, ASTM-F1980) and bench testing indicating functional equivalence to a predicate device for its 510(k) clearance, rather than reporting detailed clinical study results with explicit acceptance criteria often found for diagnostic or treatment efficacy devices.

Ask a specific question about this device

The LAP-Pump PP110 is a suction and irrigation pump intended for use during diagnostic and or therapeutic laparoscopic procedures to irrigate fluid into and remove fluid from the abdominal cavity.

The LAP-Pump PP110 is a suction and irrigation pump for use during laparoscopic procedures. The irrigation and suction functions are used to facilitate the removal of debris and fluids during laparoscopy. The pump consists of the following main components: : (1) a power supply, (2) a power switch, (3), a START/STOP button for the irrigation function, (4), a START/STOP button for the suction function, (5) a roller wheel, (6) a pump head, (7) suction pump and (8) a casing. The pump is a microprocessor controlled single roller pump that functions according to the peristaltic principle and is to be used with specially designed sterile, single use irrigation tube sets with or without hand piece, a sterile outflow tube set and a vacuum tube set. The pump is designed to be mounted on a pole/tripod, or can be placed in an equipment rack.

This is a 510(k) premarket notification for the LAP-Pump PP110, a suction and irrigation pump for laparoscopic procedures. The document asserts substantial equivalence to predicate devices based on similar intended use, basic technological characteristics, and performance testing.

Here's an analysis of the provided text in relation to your request about acceptance criteria and the study that proves the device meets them:

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

The document does not explicitly present acceptance criteria in a table format with specific quantitative thresholds. Instead, it states that "Test results demonstrate that the proposed device conforms to the above standards" and "Design verification testing of the LAP-Pump PP10 demonstrates that the device performs as intended and that the performance does not raise new questions of safety and effectiveness."

The "performance data" section focuses on compliance with various international standards for medical devices and sterility.

Here's a summary of the reported device performance in relation to the standards it aims to meet:

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

The document does not provide information on the sample size for any specific test sets. It mentions "Design verification testing," "ETO sterilization validation," "Package and product integrity" testing, and "Biocompatibility testing," but not the number of units or samples used for these tests.

The data provenance is implied to be prospective testing conducted by the manufacturer and independent laboratories to demonstrate compliance with standards for the specific device being submitted. There is no mention of country of origin of the data beyond the standards themselves being international.

There is no mention of any clinical study involving a "test set" of patients or data in the context of diagnostic accuracy or clinical outcomes. The performance data is focused on engineering, safety, and sterilization validation.

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

This information is not applicable and not provided in the document. The performance data presented relates to engineering and safety testing, not to the establishment of ground truth by clinical experts for diagnostic or treatment outcomes.

4. Adjudication method for the test set

This information is not applicable and not provided. Adjudication methods are typically used in clinical studies or studies involving human interpretation of data, which are not described here.

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

There is no mention of an MRMC study, AI involvement, or human readers/assistants in the document. This is a submission for a physical medical device (pump for laparoscopy), not an AI-powered diagnostic or decision support system.

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

This is not applicable. The device is a physical pump, not an algorithm, so the concept of standalone algorithmic performance is irrelevant here.

7. The type of ground truth used

For the various engineering and safety tests, the "ground truth" implicitly refers to the specifications and requirements defined by the referenced international standards (e.g., AAMI ANSI ES60601-1 for electrical safety, ISO 11135-1 for sterilization). The device's performance is measured against these established engineering and safety benchmarks.

For the flow rate, the ground truth is simply the stated flow rate of 3 l/min, which is compared to the predicate device.

8. The sample size for the training set

This is not applicable. The device is a physical pump, not a machine learning algorithm. Therefore, there is no concept of a "training set" in the context of this 510(k) submission.

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

This is not applicable for the same reason as point 8.

Ask a specific question about this device

The HD-Camera HDC1000 is intended to be used during diagnostic and operative endoscopic procedures to provide illumination and visualization of body cavities, hollow organs and to allow for image recording and documentation. The HD-Camera HDC1000 is indicated for use with compatible rigid or flexible endoscopes and other video equipment and endoscopic accessories.

The HD-Camera HDC1000 is a video-management system that consists of a camera, an integrated light source and a capture module for storing and compressing video and still images. It is used in conjunction with an endoscope or microscope, a light cable and other endoscopic accessories to illuminate surgical sites and to view the surgical sites on video monitors during diagnostic and operative endoscopic procedures. The camera of the proposed device consists of a camera control unit (CCU), a coupler, and a camera head with an integral cable that connects to the camera control unit (CCU). The optical image is transferred from the surgical site to the camera head by compatible rigid and flexible endoscopes that are attached to the camera head using an optical coupler. The camera head including camera cable and the coupler are reusable devices and must be sterilized using the STERRAD ® advanced sterilization process or may be used with a sterile cover or sleeve. The camera control unit (CCU) is not intended to enter the sterile field, and cannot be sterilized.

This document describes the regulatory submission for the HD-Camera HDC1000, a medical device intended for diagnostic and operative endoscopic procedures to provide illumination, visualization, image recording, and documentation. The submission focuses on demonstrating substantial equivalence to a predicate device, the OVS1 Video System.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state "acceptance criteria" for the device's technical specifications in a table format. Instead, it describes performance testing conducted to demonstrate conformance to standards and substantial equivalence to a predicate device. The performance data section refers to various standards that the device conforms to, which implicitly represent the acceptance criteria for those specific aspects.

Based on the information provided, here's a summary of the performance claims and an attempt to infer "acceptance criteria" from the comparative bench testing with the predicate device, where the implied criterion is comparability.

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

The document states that "comparative bench testing was performed." However, it does not specify any sample size for this test set (e.g., number of devices tested, number of images/videos analyzed).
The data provenance is not explicitly mentioned but can be inferred as arising from bench testing conducted by independent laboratories. There is no indication of patient data or clinical studies; it is likely an engineering/technical evaluation.

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

This information is not provided in the document. The comparative bench testing described here appears to be a technical comparison against a predicate device and industry standards, rather than an evaluation requiring expert clinical interpretation to establish a ground truth.

4. Adjudication Method for the Test Set

This information is not provided and is not applicable given the nature of the described testing (bench testing against technical standards and a predicate device). No human-based adjudication for ground truth is mentioned.

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 multi-reader multi-case (MRMC) comparative effectiveness study was not done. This device is a camera system for endoscopic visualization, not an AI diagnostic tool. The document focuses on the camera's technical performance and equivalence to a predicate device.

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

This question is not applicable as the device is an HD-Camera, a hardware system for image and video capture, not an algorithm or AI system for standalone performance evaluation.

7. The Type of Ground Truth Used

For the safety, EMC, software, cleaning, sterilization, and general design verification tests, the "ground truth" implicitly refers to the requirements specified in the respective international standards (e.g., IEC 60601-1, IEC 60601-1-2, IEC 60601-2-18, IEC 62304, AAMI/ANSI/ISO 14937, AAMI TIR12) and conformity to FDA guidance documents.

For the comparative bench testing (SNR, resolution, latency, shading correction accuracy, white balance accuracy, maximum light source intensity), the "ground truth" is likely derived from measured technical specifications of both the proposed device and the predicate device, with the aim to demonstrate substantial equivalence. It refers to objective, measurable physical properties rather than subjective clinical diagnoses or pathology.

8. The Sample Size for the Training Set

This information is not applicable. The HD-Camera HDC1000 is a hardware device for image acquisition, not a machine learning or AI model that requires a training set.

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

This information is not applicable for the same reason as above; there is no training set for this type of device.

Ask a specific question about this device