Search Results

The Purema® H Hemoconcentrator - Pediatric is designed to remove excess fluid from the blood in order to maintain proper hematocrit and protein concentration during cardiopulmonary bypass and to enable reinfusion of blood remaining in the circuit after bypass.

It is intended to be used in a hospital setting, in connection with a suitable circuit for extracorporeal blood circulation and a pump that regulates its flow. There are no other accessories.

The Purema® H Hemoconcentrator - Pediatric model DP03HC is intended to be used for pediatric patients.

The Purema® H Hemoconcentrator - Pediatric is a single use hemoconcentrators containing filters composed of a hollow fiber made of polyethersulfone (PUREMA® H). The Purema® H Hemoconcentrator - Pediatric is a hemoconcentrators that can be used in treatments which require the removal of liquids that are in excess. Blood is pumped through a membrane that has high permeability, and the pressure gradient, through the transmembrane pressure (TMP) determines the passage of water and molecules with a mechanism that is similar to glomerular filtration (convective mechanism). The fraction of filtrated liquid depends on the osmotic pressure, hydrostatic transmembrane pressure, the surface, membrane permeability and patient hematocrit. The Purema® H Hemoconcentrator - Pediatric is designed to be used in a healthcare facility.

Purema® H Hemoconcentrator - Pediatric is sterilized using Ethlyene Oxide (EtO). The EtO sterilized device consists of hollow fiber made of polyethersulfone (PUREMA® H), cartridge, rings, connectors, potting (fiber closure seals), and O-rings. The EtO sterilized Purema® H Hemoconcentrator - Pediatric is available in model DP03HC.

N/A

Ask a specific question about this device

The Baxter AK 98 dialysis machine is intended to be used for intermittent hemodialysis and/or isolated ultrafiltration treatments of patients with chronic or acute renal failure or fluid overload upon prescription by a physician. The AK 98 dialysis machine is indicated to be used on patients with a body weight of 25 kg or more. The AK 98 dialysis machine is intended to be used by trained operators when prescribed by a physician, in a chronic care dialysis or hospital care environment. The Baxter AK 98 dialysis machine is not intended for Selfcare or home use.

The AK 98 Dialysis Machine is a standalone hemodialysis machine intended for use as a single patient dialysis machine to perform HD treatments of patients with renal failure or fluid overload. The Vantive AK 98 Dialysis Machine is intended to be used in a chronic dialysis or hospitale care environment for intermittent hemodialysis and/or isolated ultrafiltration treatments of patients with chronic or acute renal failure or fluid overload upon prescription by a physician. The AK 98 Dialysis Machine is intended to be used on patients with a body weight of 25 kg or more.

To perform hemodialysis therapy, the AK 98 system needs a high purity water source and the appropriate consumables for treatment, including but not limited to: cleaning products, ultrafilters, acid and base dialysate concentrates, bloodlines, and dialyzers.

In hemodialysis therapies, the AK 98 is used to pump the blood through the extracorporeal circuit and to monitor the arterial and venous pressure, but the blood directly contacts only the disposable bloodline and dialyzer, not the monitor itself.

The fluid unit of the AK 98 Dialysis Machine is used to produce the dialysis fluid (with the correct temperature, flow, and composition) from reverse osmosis water and concentrates (dry or liquid) and to transport the dialysis fluid through the dialyzer. The fluid unit offers Profiling of Ultrafiltration and/or conductivity, it also offers isolated Ultrafiltration. The fluid unit also includes "Clearance Measurement" (Diascan). The fluid unit maintains the dialysis fluid flow through the dialyzer and controls ultrafiltration. If a fault occurs, the machine enters a patient safe state, which, depending upon the fault, can include actions such as bypassing the dialyzer.

The fluid path of the AK 98 is composed of a variety of different materials, including silicone tubing.

The provided FDA 510(k) clearance letter and summary for the AK 98 Dialysis Machine (K250508) do not contain the details typically associated with Acceptance Criteria and Study to Prove Device Meets Acceptance Criteria for AI/ML-driven medical devices.

The document describes a submission for a dialysis machine, and the key changes and testing detailed focus on physical components and performance attributes of a medical device (e.g., changes in silicone tubing curing process, ultrafiltration accuracy, blood flow rate accuracy). It specifically highlights non-clinical tests rather than clinical studies with human subjects or AI-specific validation.

Therefore, many of the requested categories in the prompt (e.g., sample sizes for test and training sets, number of experts for ground truth, adjudication methods, MRMC studies, standalone AI performance) are not applicable to this type of device and submission as described in the provided text.

The information that can be extracted relates to the device's functional performance and how it maintains equivalence to its predicate.

Here's an attempt to address the prompt based only on the provided text, while noting the limitations:

Acceptance Criteria and Device Performance for AK 98 Dialysis Machine

Based on the provided 510(k) summary for the AK 98 Dialysis Machine (K250508), the device is demonstrated to be substantially equivalent to its predicate device (AK 98 Dialysis Machine, K232467). The assessment of differences focuses on ensuring the proposed device maintains similar performance and safety characteristics despite a material change in its silicone tubing.

1. Table of Acceptance Criteria and Reported Device Performance

The concept of "acceptance criteria" in this context refers to maintaining the performance specifications of the predicate device. The "reported device performance" is implicitly that the proposed device performs identically to the predicate device for all listed features, having passed non-clinical functional testing. The key change evaluated was the transition from peroxide-cured and platinum-cured tubing to solely platinum-cured tubing.

Note on Silicone Tubing Difference: The crucial "acceptance criteria" here for the tubing change was that "Performance, biocompatibility, and extractables testing demonstrates that the difference in the curing process does not impact the performance or safety of the AK 98 Hemodialysis System." The reported performance is that this testing was successfully conducted, confirming no impact.

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

The provided document describes non-clinical functional performance testing, biocompatibility testing, and extractables and leachables assessment. It does not mention a "test set" in the context of patient data or clinical trials. Therefore, sample sizes for such data are not applicable here. The data provenance would be laboratory testing results from the manufacturer.

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

This submission pertains to a physical medical device and primarily relies on engineering and laboratory testing for equivalence, not AI/ML-driven analysis of medical images or patient data requiring expert adjudication. Thus, this information is not applicable.

4. Adjudication Method for the Test Set

As there is no mention of a clinical test set requiring human interpretation or AI output evaluation, an adjudication method is not applicable.

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

No, an MRMC study was not done, as this device is a physical hemodialysis machine, not an AI/ML diagnostic or assistive tool for human readers.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) was Done

No, a standalone algorithm performance study was not done, as this device does not contain a discrete AI/ML algorithm whose performance is being evaluated in isolation. Its "performance" refers to the mechanical and fluid dynamic functions of the dialysis machine itself.

7. The Type of Ground Truth Used

The "ground truth" for this device's performance evaluation lies in established engineering standards, device specifications, and the performance characteristics of the legally marketed predicate device. The change in the silicone tubing's curing process required "Performance, biocompatibility, and extractables testing" to demonstrate continued safety and effectiveness. This testing serves as the "ground truth" method for verifying that the new component does not negatively impact the device's adherence to its established specifications.

8. The Sample Size for the Training Set

This concept is not applicable to the submission of this physical medical device. There is no AI/ML model being trained with a dataset.

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

This concept is not applicable as there is no training set for an AI/ML model.

Ask a specific question about this device

The 2008T BlueStar Hemodialysis Machine is indicated for acute and chronic dialysis therapy in a healthcare facility.

Additional therapy options for patients receiving hemodialysis include: Isolated Ultrafiltration, Sustained Low Efficiency Dialysis (SLED), and low volume hemodialysis (patients weighing ≥ 20kg and ≤ 40 kg). This machine accommodates the use of both low flux and high flux dialyzers. The SLED therapy option is not to be used for patients weighing ≤ 40 kg. The 2008T BlueStar Hemodialysis Machine is not to be used for plasma replacement therapies, for patients weighing less than 20 kg, or for renal therapies using substitution fluid.

The 2008T BlueStar Hemodialysis Machine is an electromechanical device. Software controls the machine during hemodialysis treatment, including fluid flow, mixing, heating, and alarms.
The 2008T BlueStar Hemodialysis Machine provides hemodialysis treatment by controlling and monitoring both the dialysate circuit and the extracorporeal blood circuit. The machine pumps blood from the patient's body through an extracorporeal circuit, one component of which is the dialyzer. The dialyzer contains a semi-permeable membrane that uses diffusion to transfer toxins and ultrafiltration to transport excess water from the blood into the dialysate circuit. In this separate dialysate circuit, the dialysate concentrates are mixed with purified water, heated, degassed, and delivered to the dialyzer. Balancing chambers control the incoming flow and outgoing flow of the dialysate fluid during ultrafiltration. During hemodialysis, the extracorporeal blood circuit is monitored for venous and arterial blood pressures as well as for the presence of air and blood.
The 2008T BlueStar Hemodialysis Machine has automation features (independent internal conductivity testing, auto priming, auto start, CDX auto on, assisted reinfusion) to minimize user workload and improve user experience. The 2008T BlueStar Hemodialysis Machine includes SLED (Sustained Low Efficiency Dialysis), Low Volume, and Isolated Ultrafiltration therapy options. The 2008T BlueStar Hemodialysis Machine also accommodates the use of the Patient Card system, a dialysis treatment information system.

Based on the provided FDA 510(k) Clearance Letter, the device in question is the 2008T BlueStar Hemodialysis Machine. This document is a Class II Medical Device submission, which means it relies on substantial equivalence to a predicate device, rather than a clinical trial proving new efficacy. Therefore, the "acceptance criteria" and "study that proves the device meets the acceptance criteria" in this context are focused on demonstrating substantial equivalence to a legally marketed predicate device, rather than establishing new clinical effectiveness benchmarks through a de novo study.

The primary study type proving the device meets the "acceptance criteria" for 510(k) clearance is a comparison to a predicate device and supporting non-clinical performance and safety testing.

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

1. Table of Acceptance Criteria and Reported Device Performance

The "acceptance criteria" for a 510(k) submission are typically related to demonstrating that the new device meets the same performance specifications as the predicate and does not raise new questions of safety or effectiveness. The reported device performance is presented as its features and specifications.

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

For a 510(k) of this nature (a hemodialysis machine), the "test set" does not refer to a clinical data set in the same way it would for an AI/ML algorithm. Instead, it refers to the units of the device that underwent various engineering and biocompatibility tests.

• Sample size for test set: Not explicitly stated as a number of specific units in a formal statistical sense, but implies a sufficient number of devices were tested to demonstrate compliance with standards and specifications for various non-clinical tests (e.g., electrical safety, EMC, performance specifications). For biocompatibility, representative materials were tested.
• Data provenance: Not directly applicable in the sense of patient data. The provenance of the testing is internal company testing (Fresenius Medical Care Renal Therapies Group, LLC). All testing is prospective in the sense that the tests were conducted specifically for this submission. The origin of the testing would be within the manufacturer's facilities or accredited testing labs.

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

This question is not applicable to this type of 510(k) submission. This clearance is for a hardware device (hemodialysis machine) with embedded software, not an AI/ML diagnostic or prognostic device that relies on expert interpretation of medical images or patient data to establish ground truth for a test set. The "ground truth" for the device's performance is established by engineering specifications, validated sensors, and calibrated measurement systems.

4. Adjudication Method for the Test Set

Not applicable. There is no "test set" of patient cases requiring adjudication by multiple experts for a hemodialysis machine clearance. Engineering tests are pass/fail based on predefined thresholds and standards.

5. 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

Not applicable. This is not an AI/ML diagnostic or imaging device. There were no human readers or AI assistance studies conducted or required for this clearance.

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

While the device contains software, it is an electromechanical device, not a standalone algorithm. Its performance is intrinsically linked to the physical machine. Therefore, a "standalone algorithm performance" study is not relevant or applicable. The software controls the machine's functions, and its performance is evaluated as part of the total system.

7. The Type of Ground Truth Used

The "ground truth" for the 2008T BlueStar Hemodialysis Machine's performance is established by:

• Engineering Specifications: The design and expected performance metrics (e.g., flow rates, temperatures, accuracies) are the primary ground truth for the device's functional integrity.
• International and Industry Standards: Compliance with standards like IEC 60601-1-2 for EMC and ISO 10993-1 for biocompatibility serves as the ground truth for safety and foundational performance aspects.
• Predicate Device Performance: The underlying assumption for a 510(k) is that the predicate device's performance is the established "ground truth" for safe and effective hemodialysis delivery. The new device demonstrates equivalence to this established standard.

8. The Sample Size for the Training Set

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

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

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

Ask a specific question about this device

The 5008X Hemodialysis System is intended for use in acute and chronic hemodialysis therapy. Therapy options include hemodialysis (HD), hemodiafiltration (HDF), hemofiltration (HF), and isolated ultrafiltration (ISO).

The 5008X™ system is indicated for intermittent hemodialysis treatment for patients with acute and chronic renal failure in a healthcare facility. Therapy options for patients weighing more than 40 kg include: Hemodiafiltration (HDF), Hemodialysis (HD), Hemofiltration (HF) and Isolated Ultrafiltration.

The 5008X™ Machine is equipped with a bibag system, but it may also be used with liquid bicarbonate using the connector included with the machine. The bibag system is indicated for use in patients undergoing extracorporeal bicarbonate hemodialysis for acute and chronic renal failure. The bibag system is intended to be used as one component in the preparation of dialysate according to a physician's prescription in a 3-stream proportioning hemodialysis machine equipped with the bibag module.

The 5008X™ Machine is available equipped with a Crit-Line Clip (CLiC) Monitor System.

The optional CLiC system is used to non-invasively measure hematocrit, oxygen saturation and percent change in blood volume in real time for application in the treatment of dialysis patients with the intended purpose of providing a more effective treatment for both the dialysis patient and the dialysis technician. Based on the data that the monitor provides, the clinician/nurse, under physician direction, intervenes (i.e. increases or decreases the rate at which fluid is removed from the blood) in order to remove the maximum amount of fluid from the dialysis patient without the patient experiencing the common symptoms of dialysis which include nausea, cramping and vomiting.

The DIASAFE®plusUS is intended for the preparation of ultrapure dialysate and sterile, nonpyrogenic substitution fluid from pretreated water and is not intended to provide primary purification. Attention must still be given to the chemical and microbiological quality of water and concentrates and the maintenance of supply systems (e.g. RO system, central delivery system).

The microbiological quality (microbial count [CFU/mL] and endotoxin measurement [EU/mL]) of the incoming water should be < 200 CFU/mL and < 2 EU/mL, respectively.

The DIASAFE®plusUS can only be used with Fresenius Medical Care dialysis machines fitted for use with DIASAFE®plusUS.

The blood tubing sets are intended to be used only with the Fresenius Medical Care 5008X Hemodialysis Device, which is indicated for intermittent hemodialysis treatment for patients with acute kidney injury or chronic kidney disease in a healthcare facility. Therapy options include: hemodiafiltration (HDF), hemodialysis (HD), hemofiltration (HF), and isolated ultrafiltration.

The HDF blood tubing sets are indicated for use with a prescribed dialyzer. For use with a compatible dialyzer, as per the labeling.

The Fresenius Twister Access Flow Reversing Connector (AFRC) is indicated for use during hemodialysis to reverse the blood flow to and from the arterial and venous vascular access devices in order to obtain an access flow measurement.

The blood tubing set is intended to be used with the Crit-Line Clip Monitor System (CLiC) on the 5008X Hemodialysis Device.

The CLiC is used to non-invasively measure hematocrit, oxygen saturation, and percent change in blood volume in real time for application in the treatment of dialysis patients with the intended purpose of providing a more effective treatment for both the dialysis patient and the dialysis technician. Based on the data that the monitor provides, the clinician/nurse, under physician direction, intervenes (i.e., increases or decreases the rate at which fluid is removed from the blood) in order to remove the maximum amount of fluid from the dialysis patient without the patient experiencing the common symptoms of dialysis which include nausea, cramping and vomiting.

CitraSure is intended for thermal disinfection of the Fresenius Medical Care 5008X Hemodialysis System when delivered and diluted per the 5008X heat disinfection program.

The 5008X Hemodialysis System consists of the following:

• The 5008X Hemodialysis Machine
• Two (2) DIASAFE®plusUS Filters (hereinafter referred to as the "Diasafe filter(s)")
• The 5008X Bloodlines are available in five (5) configurations:
  • 5008X HD/HDF – Standard Blood Tubing Set (hereinafter referred to as the "HD/HDF Standard Bloodline")
  • 5008X HD/HDF – With Twister Blood Tubing Set (hereinafter referred to as the "HD/HDF Twister Bloodline")
  • 5008X HD/HDF – With CLiC Blood Tubing Set (hereinafter referred to as the "HD/HDF CLiC Bloodline")
  • 5008X HD Pre-Flush – Standard Blood Tubing Set (hereinafter referred to as the "HD Standard Bloodline")
  • 5008X HD Pre-Flush – With Twister Blood Tubing Set (hereinafter HD Twister Bloodline")
• CitraSure™ Disinfectant

The 5008X Hemodialysis Machine is an electromechanical device. Software controls the machine during hemodialysis treatment, including fluid flow, mixing, heating, and alarms.

The Diasafe filter is a non-sterile dialysis fluid filter that produces ultrapure dialysate and sterile, non-pyrogenic substitution fluid as defined in ISO 23500-5. The filter reduces microbial contaminants including endotoxins in the dialysate during hemodialysis treatment.

The 5008X Bloodlines are single-use, ethylene oxide (EO) sterilized bloodlines.

CitraSure™ disinfectant is a liquid chemical disinfectant for chemical heat disinfection of the 5008X Hemodialysis Machine.

The provided FDA 510(k) clearance letter and summary for the 5008X Hemodialysis System pertains to a medical device for renal treatment. The document does not describe an AI/ML device, a comparative effectiveness study (MRMC), or a standalone AI algorithm performance study. Therefore, sections of your request related to those topics (e.g., sample size for test/training sets, data provenance, number of experts, adjudication methods, ground truth types, human reader improvement with AI) are not applicable and cannot be extracted from this document.

However, I can provide the acceptance criteria and a summary of the performance testing conducted to prove the device meets these criteria based on the provided text for the various components of the 5008X Hemodialysis System.

Acceptance Criteria and Device Performance Summary for 5008X Hemodialysis System

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document lists "Key Performance Specifications/Characteristics" which serve as the acceptance criteria for each component. The "Reported Device Performance" column summarizes the claims made in the document regarding the device meeting these specifications through various tests.

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

As this is not an AI/ML device, the concept of "test set" in the context of diagnostic AI algorithms (e.g., patient images or clinical data) is not directly applicable. The performance data presented refers to engineering and quality assurance tests on the physical devices/systems.

• Sample Size for Physical Device Testing: The document does not specify exact sample sizes for each individual engineering performance test (e.g., how many bloodlines were tested for structural integrity, how many machines for fluid flow accuracy). It generally states "Testing performed" or "Testing conducted."
• Data Provenance: Not applicable in the context of patient data provenance (e.g., country of origin, retrospective/prospective). These are laboratory and simulated use tests on hardware components.

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

Not applicable. The "ground truth" for the performance of a hemodialysis system is based on direct physical measurements against defined engineering specifications and regulatory standards (e.g., flow rates, pressure tolerances, material properties, sterility levels), not expert interpretation of complex data like medical images.

4. Adjudication Method for the Test Set

Not applicable for a medical device's engineering performance testing. Adjudication methods like 2+1 or 3+1 typically refer to resolving discrepancies in expert interpretations (e.g., radiologists reviewing medical images for ground truth labeling in AI studies).

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

No. The document explicitly states: "No clinical studies were performed for the 5008X Hemodialysis System." MRMC studies inherently involve human readers (clinicians) assessing cases, often with or without AI assistance, to measure diagnostic performance and comparative effectiveness. This type of study was not conducted as this is not an AI-assisted diagnostic device.

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

No. The device described is a physical hemodialysis system, not a standalone AI algorithm. While it contains software, the performance evaluation is for the integrated system, and there is no mention of a standalone AI algorithm being assessed.

7. The Type of Ground Truth Used

For the various performance tests, the "ground truth" is defined by:

• Engineering Specifications and Standards: Numeric values for flow rates, pressures, temperatures, accuracies, dimensions, and material properties derived from established engineering principles and relevant international standards (e.g., ISO 8637-2:2018 for bloodlines, ISO 23500-5 for dialysate quality, IEC 60601-1-2 for EMC).
• Regulatory Requirements: Compliance with FDA guidance documents and regulations (e.g., for biocompatibility, sterility, software verification and validation, human factors).
• Absence of Failure: Demonstrating that components do not break, kink, leak, or fail under specified conditions (e.g., blood pump endurance, simulated use).

8. The Sample Size for the Training Set

Not applicable. This is not an AI/ML device that requires a training set. The software for the 5008X Hemodialysis Machine would have undergone development, verification, and validation, but this is distinct from AI model training.

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

Not applicable. As there is no AI training set, there is no ground truth established in this context.

Ask a specific question about this device

The intended indications for use of the PICO 14 is for individuals with mild to moderate pain associated with carpal tunnel syndrome. It is designed to provide support and compression to the wrist, helping to alleviate discomfort and promote healing.

A very compact and versatile smart plug with Wi-Fi connectivity, energy monitoring, and scheduling capabilities.

The provided text describes the FDA clearance for the DBB-06 PRO Hemodialysis Delivery System. However, it does not contain detailed information regarding acceptance criteria for specific device performance metrics (e.g., sensitivity, specificity, accuracy) nor does it describe specific studies that prove the device meets such criteria in the context of an AI/algorithm-driven medical device.

The document focuses on:

• Safety and Performance of a Physical Hemodialysis Machine: It outlines various engineering specifications, material compatibility, sterilization validation, electrical safety, and software verification for a hemodialysis delivery system.
• Substantial Equivalence: The primary goal of the 510(k) submission is to demonstrate that the DBB-06 PRO is substantially equivalent to predicate devices (DBB-06 Hemodialysis Delivery System and 2008T Bluestar Hemodialysis Machine).
• General Performance Testing: The "Performance – Bench Testing" section lists various types of tests conducted (e.g., "System Level Performance Testing," "Disinfection Validation Testing," "Bacterial Retention Testing"), but it does not provide acceptance criteria for these tests nor the specific performance results in a way that would allow for the population of the requested table for an AI model.

Therefore, most of the requested information cannot be extracted from this document, as it pertains to a physical medical device (hemodialysis machine) rather than an AI-driven diagnostic or prognostic algorithm. Specifically, sections 1-7 of your request are not applicable as presented because there is no AI/algorithm being evaluated for diagnostic or prognostic performance with associated metrics like sensitivity, specificity, or reader studies.

The document does mention "Software controls the machine during hemodialysis treatment" and "Software Verification and Validation Testing," indicating software components are present, but these are for controlling the machine's operation, not for diagnostic interpretation or prediction in an AI context.

Here's what can be extracted, and where limitations exist:

1. Table of Acceptance Criteria and Reported Device Performance

• Limitation: The document provides "Key Performance Characteristics" (Table 1) for various mechanical and electrical aspects of the hemodialysis machine. These are specifications (e.g., "Flow rate accuracy: Set value ±10%") rather than acceptance criteria for an AI model's diagnostic/prognostic performance (like sensitivity, specificity, AUC). No reported performance results against specific acceptance criteria for AI are available.

Regarding AI/Algorithm-Specific Questions (2-7):

The provided text does not contain any information related to an AI/algorithm for diagnostic or prognostic purposes, and therefore, these questions cannot be answered from the given document. The software mentioned "controls the machine during hemodialysis treatment" rather than performing analytical or interpretive tasks characteristic of AI in medical imaging or diagnostics.

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. This is a physical device, not a diagnostic AI.
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.
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.
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.

Regarding Training Set Information (8-9):

The document mentions "Software Verification and Validation Testing" but does not describe a "training set" in the context of machine learning or AI. The software is for controlling the hemodialysis machine's functions.

8. The sample size for the training set: Not applicable. The software performs control functions for the machine, not an AI model that requires a training set of data.
9. How the ground truth for the training set was established: Not applicable for the same reasons as above. The software is validated against functional requirements and design specifications, not against a "ground truth" for a learned AI task.

Ask a specific question about this device

The hemoconcentrators are intended for use in cardiopulmonary bypass circuits for hemoconcentration and consequent restoring of patient physiological hematocrit. The choice of hemoconcentrator depends on the protocol being used and required filtration speed. The device is intended to be used for six hours or less.

DHF and SH Hemoconcentrators are single-use, non-toxic and nonpyrogenic fluid path devices; they are supplied sterile and individually packaged. The devices are made of plastic materials and are recommended for use in cardiopulmonary bypass circuits for hemoconcentration and consequent restoring of patient's physiological hematocrit: The choice of hemoconcentrator depends on the protocol being used and required filtration rate. The device can be used up to 6 hours.

The DHF and SH hemoconcentrators are the modified version of the disposables currently marketed in the Dideco DHF hemoconcentrators (K021732) and the SH 14 hemoconcentrators (K081313).

The provided FDA 510(k) clearance letter for the DHF and SH Hemoconcentrators does not describe a study that proves the device meets specific acceptance criteria in the manner of an AI/ML algorithm or diagnostic device.

Instead, this document details a change to an existing, cleared medical device (hemoconcentrators used in cardiopulmonary bypass circuits). The core of the 510(k) submission is to demonstrate substantial equivalence to previously cleared predicate devices, not to establish performance against new, quantitative clinical acceptance criteria as one would find for a novel diagnostic or AI-powered system.

The "study" described here is a non-clinical performance evaluation focused on demonstrating that a material change (from Santoprene to Silicone for O-rings) does not introduce new questions of safety or effectiveness.

Therefore, many of the specific questions you've asked (e.g., sample size for test set, number of experts for ground truth, MRMC study, standalone performance) are not applicable to this type of device clearance.

Here's an analysis based on the provided document, highlighting what is (and isn't) present:

Analysis of Acceptance Criteria and Device Performance for DHF and SH Hemoconcentrators

The information provided describes a 510(k) clearance for hemoconcentrators, which are physical medical devices, not an AI/ML or diagnostic software. The "acceptance criteria" and "study" are therefore framed around demonstrating substantial equivalence to existing predicate devices, particularly after a material change to a component, rather than performance metrics for a diagnostic algorithm.

This document explicitly states: "No clinical testing was conducted in support of the DHF and SH hemoconcentrators, as the indications for use and technical characteristics are unchanged with respect to those of the predicate devices, which have been on the market for several years with proven safety and efficacy of use."

The "study" instead focuses on non-clinical performance data to ensure that the device still complies with applicable standards and performs as expected after the specified design change.

1. Table of Acceptance Criteria and Reported Device Performance

For this type of device and submission, acceptance criteria are generally met through compliance with recognized standards and demonstrating that the device's fundamental characteristics and performance are maintained despite the change. The document does not list specific quantitative performance criteria in a table format, but rather states compliance.

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

• Test Set Sample Size: Not explicitly stated as a number of "cases" or "patients" because this was non-clinical performance testing (e.g., bench testing of prototypes or manufacturing samples), not a clinical study on patient data.
• Data Provenance: The testing was conducted by Sorin Group Italia S.R.L. and is "non-clinical," implying laboratory or bench testing. The country of origin would be Italy (where Sorin Group Italia S.R.L. is located). It is not retrospective or prospective in the sense of a clinical trial; it is product performance verification.

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

Not Applicable. This is a physical device, and the testing involved demonstrating compliance with engineering and safety standards, not establishing a "ground truth" for diagnostic purposes by human experts.

4. Adjudication Method for the Test Set

Not Applicable. There was no human adjudication process involved in assessing diagnostic performance. The evaluation was based on engineering and performance testing.

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

No, an MRMC study was NOT done. This type of study is relevant for diagnostic devices (especially imaging-based AI) to assess how human readers perform with and without AI assistance. This device is a hemoconcentrator, not an imaging or diagnostic AI system.

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

Not Applicable. This is not an algorithm. Performance was assessed for the physical device itself.

7. The Type of Ground Truth Used

The "ground truth" for this device's performance is established by engineering specifications, recognized national and international standards (e.g., for dialyzers), and performance parameters (e.g., filtration rates, material integrity, biocompatibility, sterility assurance). It is not based on expert consensus, pathology, or outcomes data from patients in the context of a new diagnostic claim. The "ground truth" is that the device, with the new material, still meets the same performance and safety requirements as the predicate device.

8. The Sample Size for the Training Set

Not Applicable. This device is not an AI/ML algorithm, so there is no concept of a "training set."

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

Not Applicable. As there is no AI/ML algorithm or training set, this question is not relevant.

Ask a specific question about this device

FX CorAL HD dialyzers are intended for hemodialysis (HD), hemodiafiltration (HDF), hemofiltration (HF), and isolated ultrafiltration in patients, including pediatric patients, with acute kidney injury or chronic kidney disease when conservative therapy is judged to be inadequate.

Consider body and dialyzer surface area, blood flow, body weight and extracorporeal blood volume when selecting dialyzers for use with pediatric patients.

The FX CorAL dialyzers are high-flux, single-use, steam-sterilized hemodialyzers. The dialyzers are provided blood pathway sterile and non-pyrogenic. The dialyzers allow for the transfer of water and solutes between blood and dialysate using semipermeable, hollow fiber membranes.

The FX CorAL dialyzers are high-flux, sterile devices designed for single-use acute and chronic hemodialysis. The dialyzers are configured to connect to a bloodline set which connects to a patient's vascular access system when used with a hemodialysis machine equipped with ultrafiltration control. During hemodialysis, blood is pumped from the patient's body through an extracorporeal circuit, one component of which is the dialyzers contain semipermeable membranes that allow for diffusion and/or ultrafiltration to transport toxins and excess fluid from the blood compartment (fiber lumen) to the dialysate compartment. Dialyzers utilize a counter-current flow in which dialysate and blood flow in opposite directions in the dialyzer. The counter-current flow maintains the concentration gradient across the membrane for waste and fluid removal.

The document describes the FX CorAL 40 and FX CorAL 50 dialyzers and their substantial equivalence to predicate devices, focusing on performance, materials, and intended use. There is no information provided in the document regarding acceptance criteria or performance of an AI/ML device.

The provided text describes a medical device clearance (K242053) for FX CorAL 40 and FX CorAL 50 dialyzers, which are high permeability hemodialysis systems. While the request asks about acceptance criteria and study details for an AI/ML device, the document focuses on the performance data of these physical medical devices. Therefore, much of the requested information regarding AI/ML specifics (like effect size of AI assistance, standalone algorithm performance, training set details, expert qualifications for ground truth) is not applicable to this submission.

However, I can extract the relevant information pertaining to the tests conducted for these dialyzers, which function as "acceptance criteria" for a physical device.

Here's a breakdown based on the provided document:

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

The document lists performance tests conducted and states that "All testing met predetermined acceptance criteria." It does not explicitly list numerical acceptance criteria values for each test but provides typical performance results for urea clearance.

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

• Performance Testing (in vitro): Sample size for each specific in vitro test (e.g., clearance, integrity) is not explicitly stated, but it's implied that multiple samples were tested to generate the "typical" values and ensure criteria were met.
• Clinical Studies (retrospective):
  • Sample Size: Fourteen (14) pediatric ESRD patients
  • Data Provenance: Retrospective clinical data analysis. The country of origin is not specified.

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

This is not applicable as the document describes a physical medical device (dialyzer), not an AI/ML diagnostic tool requiring expert interpretation for ground truth establishment. The "ground truth" for the dialyzer's performance is established through well-defined physical and chemical measurements following international standards (e.g., ISO 8637-1).

4. Adjudication method for the test set:

Not applicable. For physical device performance, the results are typically quantitative measurements against defined specifications, not subjective interpretations requiring adjudication.

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 this is not an AI-assisted diagnostic device.

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

Not applicable, as this is not an AI/ML device.

7. The type of ground truth used:

• In vitro Performance Tests: Ground truth is based on established physical and chemical measurement standards (e.g., ISO 8637-1 First Edition 2017-11) and direct laboratory measurements of parameters like clearances, sieving coefficients, ultrafiltration rates, and pressure drops.
• Biocompatibility Testing: Ground truth is established through standardized biological evaluation tests as per FDA guidance and ISO 10993-1.
• Clinical Studies: "Adequate clearance" (demonstrated by spKt/V values) and patient tolerance serve as clinical outcomes demonstrating the device's effectiveness in a real-world setting.

8. The sample size for the training set:

Not applicable, as this is not an AI/ML device and thus does not have a "training set" in that context.

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

Not applicable.

Ask a specific question about this device

The FX CorAL hemodialyzers are intended for single use only for extracorporeal blood purification during intermittent renal replacement therapies hemodialysis (HD), hemodiafiltration (HDF) using pre-, post or mixed-dilution modes, and isolated ultrafiltration for patients suffering from renal insufficiency.

The FX CorAL hemodiafilters are intended for single use only for extracorporeal blood purification during intermittent renal replacement therapies hemodialysis (HD), hemodiafiltration (HDF) using pre-, post or mixed-dilution modes, and isolated ultrafiltration for patients suffering from renal insufficiency.

The FX CorAL dialyzers are high-flux, single-use, steam-sterilized hemodialyzers. The dialyzers are provided blood pathway sterile and non-pyrogenic. The dialyzers allow for the transfer of water and solutes between blood and dialysate using semipermeable, hollow fiber membranes. The FX CorAL dialyzers are high-flux, sterile devices designed for single-use acute and chronic hemodialysis. The dialyzers are configured to connect to a bloodline set which connects to a patient's vascular access system when used with a hemodialysis machine equipped with ultrafiltration control. During hemodialysis, blood is pumped from the patient's body through an extracorporeal circuit, one component of which is the dialyzers contain semipermeable membranes that allow for diffusion and/or ultrafiltration to transport toxins and excess fluid from the blood compartment (fiber lumen) to the dialysate compartment. Dialyzers utilize a counter-current flow in which dialysate and blood flow in opposite directions in the dialyzer. The counter-current flow maintains the concentration gradient across the membrane for waste and fluid removal.

This document is an FDA 510(k) clearance letter for a medical device called FX CorAL hemodialyzers. It primarily discusses the substantial equivalence of the new device to a previously cleared predicate device, rather than presenting a detailed study proving the device meets specific acceptance criteria through a clinical or algorithmic performance study often seen with AI/ML devices.

Therefore, the information required to answer your questions regarding acceptance criteria and study details (especially for AI/ML performance, experts, ground truth, and sample sizes for training/test sets) is not present in the provided text. The document explicitly states:

• "No clinical studies were performed." (Page 8, Section 1.8.6)
• "Not applicable. The FX CorAL dialyzers do not contain software." (Page 8, Section 1.8.4 - implying no software verification/validation testing as would be done for an AI/ML device)
• "No animal studies were performed." (Page 8, Section 1.8.5)

The clearance is based on the new devices being identical to the predicate devices in manufacturing, design, sterilization method, and materials, with only labeling changes. The performance data for the predicate device (K220721) is deemed applicable.

However, I can extract the general type of performance metric mentioned: Urea clearance.

Here's a breakdown of what can be inferred from the document and what cannot:

Acceptance Criteria & Device Performance:

The document doesn't explicitly state "acceptance criteria" in the format of a clinical trial endpoint or AI/ML performance metric. Instead, it refers to "Key Performance Specifications/Characteristics" for urea clearance (Table 2, Page 6). It also states that "FMCRTG uses sodium clearance as a marker for urea clearance because sodium and urea exhibit similar movement across the membrane."

Table of Performance (Inferred from "Typical Urea Clearance"):

Regarding the Study Details for AI/ML Performance:

Based on the provided text, the device is a physical medical device (hemodialyzer), not an AI/ML software device. As such, answers to most of your specific questions related to AI/ML study design are not applicable or the information is not provided.

1. Sample size for the test set and data provenance: Not applicable in the context of an AI/ML test set. The performance data mentioned (Table 2) is in vitro (bench testing), not from a patient test set, and its specific provenance (country, retrospective/prospective) is not detailed.
2. Number of experts used to establish ground truth: Not applicable. This refers to the ground truth for an AI/ML device, which is not what this document is about.
3. Adjudication method: Not applicable for this type of device and study.
4. MRMC comparative effectiveness study: Not applicable. The device does not involve human readers or AI assistance in diagnostic interpretation.
5. Standalone (algorithm only) performance: Not applicable. The device is a physical hemodialyzer, not an algorithm.
6. Type of ground truth used: For urea clearance, the ground truth would be based on in vitro laboratory measurements, likely chemical assays measuring concentrations before and after filtration, rather than expert consensus, pathology, or outcomes data.
7. Sample size for the training set: Not applicable. There is no AI/ML model for which a training set would be required.
8. How the ground truth for the training set was established: Not applicable, as there is no training set for an AI/ML model.

Summary of what is available in the text:

• Device Type: Hemodialyzers (physical medical devices).
• Performance Metrics: In vitro urea clearance (sodium clearance typically used as a marker).
• Study Type: Substantial equivalence a new device to a predicate device, noting that the new device is "identical" to the predicate, and hence the previous predicate's data applies.
• Clinical Studies: None performed for this 510(k) submission.
• Software/AI Component: None. The device "does not contain software."
• Animal Studies: None performed.

Ask a specific question about this device

SC+ Hemodialysis Device/ Dialysate Cartridge:

The SC+ Hemodialysis System is indicated for use in patients with acute and/or chronic renal failure, with or without ultrafiltration, in an acute or chronic care facility. Treatments must be administered under physician's prescription, by a trained clinician who is competent in the use of the device. The SC+ Hemodialysis System is also indicated for use in the home by trained patients in tandem with a trained care partner.

Blood Tube Set

The SC+ Blood Tube Set is a single use, disposable arterial and venous bloodline set intended to provide extracorporeal access during hemodialysis. The Blood Tubeset is compatible only with the SC+ Hemodialysis System.

The SC+ is a haemodialysis delivery system intended for the provision of acute and chronic dialysis therapy, with or without ultrafiltration. The SC+ system utilises incoming Dialysis Water from an external source, with industry standard dialysis concentrate consumables, to manufacture the dialysis fluid used to deliver the treatment. The SC+ system is for use in patients with arteriovenous (AV) fistulas or central venous catheter access.

The SC+ system consists of the SC+ Machine, a single use disposable Dialysate Cartridge, and a sterile, single use, disposable Blood Tubeset.

The SC+ Machine consists of a water circuit (heater, de-aeration module, etc) blood leak detector, air in blood detector, a pneumatic interface for the dialysate cartridges, a peristaltic blood pump and various other sensors. The dialysate cartridge contains the following: conductivity monitors, interfaces for pressure and temperature measurement. membrane pumps to perform mixing/proportioning in order to produce dialysis fluid and the controlled removal of fluid from a patient with acute and/or chronic renal failure based on a physician's prescription. The dialysate fluid is manufactured using dialysis water purified externally by reverse osmosis that is heated to approximately 37℃ and subsequently deaerated within the machine before entering the cartridge.

The SC+ Blood Tubeset is a single use, sterile device consisting of an arterial line, a venous line, connections to a standard dialyzer, a saline line, three pressure transducer pods integrated into a single unit, a venous drip chamber, and a line for heparin infusion.

The provided text is a 510(k) summary for the Quanta Dialysis Technologies SC+ Hemodialysis Device, Dialysate Cartridge, and Blood Tube Set. The core of this submission is to expand the indications for use of the SC+ Hemodialysis System to include home use.

This document does not include information about AI/ML device performance, interpretation by human readers, or specific quantitative acceptance criteria for features like accuracy, sensitivity, or specificity. Instead, it describes acceptance criteria related to safety and effectiveness for a medical device in a new use environment (home healthcare) and for new user groups (patients and caregivers).

Therefore, a table of acceptance criteria and reported device performance (in the context of AI metrics) cannot be extracted directly from this document. Similarly, details on sample sizes for test sets in an AI context, expert ground truth establishment, MRMC studies, or standalone algorithm performance are not applicable to the information provided.

However, I can extract the information related to the clinical study supporting the new indication for use, which serves as the "study that proves the device meets the acceptance criteria" in the context of this device.

Here's a breakdown of the relevant information from the document:

Study That Proves the Device Meets the Acceptance Criteria:

The study conducted to support the expansion of indications to home use was the HOME RUN clinical trial (G200362).

• Type of Ground Truth Used: Clinical outcomes data (mean standardized weekly Kt/V for effectiveness, and rate of AEs for safety).
• Sample Size Used for the Test Set (Clinical Study):
  • Evaluable Population: n = 32 subjects. This included all subjects who were enrolled in the study and successfully completed at least 75% of their dialysis treatments.
• Data Provenance:
  • Country of Origin: Multi-center study in the US (13 sites).
  • Retrospective or Prospective: Prospective.
• Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts: Not applicable in the context of "ground truth" for an AI model. However, an Independent Safety and Clinical Ethics Committee (SCEC) was created to oversee trial safety.
  • Qualifications of Experts: Comprised nephrologists with experience of hemodialysis, one of whom had significant experience in home hemodialysis.
• Adjudication Method for the Test Set: The SCEC was blinded to whether AEs occurred in the in-clinic or in-home phase and had the authority to recommend changes to the trial. Details on specific adjudication rules for AEs (e.g., 2+1, 3+1) are not provided, but the SCEC served an oversight and review role.
• 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 is not an AI/ML device in the context of diagnostic interpretation. The study compared device performance (safety and effectiveness) in two settings (in-clinic vs. in-home).
• If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. This is a medical device, and its performance is the "algorithm" in action (the hemodialysis process). The study evaluated its use by human users (patients/caregivers/clinicians).
• The Sample Size for the Training Set: Not applicable. This document describes a clinical trial for device efficacy and safety, not an AI model requiring a training set.
• How the Ground Truth for the Training Set was Established: Not applicable.

Acceptance Criteria and Reported Device Performance (as related to the clinical study):

The acceptance criteria for the expanded indication were based on demonstrating comparable safety and effectiveness in the home setting as in the clinic, considering the new use environment and user groups.

In summary, this FDA clearance document primarily focuses on the clinical validation and human factors validation required to expand the intended use of a hemodialysis device to a home setting, rather than AI/ML performance metrics. The "acceptance criteria" here relate to demonstrating equivalent safety and effectiveness in the new use environment.

Ask a specific question about this device

The Moda-flx Hemodialysis System™ is indicated for use in patients with acute and/or chronic renal failure, with or without ultrafiltration, in an acute, post-acute, or chronic care facility. Treatments must be administered under a physician's prescription, by a trained person who is considered competent in the use of the device.

Treatment types available include: Intermittent Hemodialysis (IHD), Sustained Low Efficiency Dialysis (SLED/ SLEDD), and Prolonged Intermittent Renal Replacement Therapy (PIRRT).

The Moda-flx Hemodialysis System™ Cartridge is a single use, disposable arterial and venous bloodline set, with dialysate tubing, intended to provide extracorporeal access during hemodialysis. The Moda-flx Hemodialysis System™ Cartridge is compatible only with the Moda-flx Hemodialysis System TM.

The Moda-flx Hemodialysis System™ is a transportable hemodialysis system that consists of three parts: Hemodialysis Delivery (HD) Device. Dialysate Generator (DG) Device, and a single use Moda-flx Hemodialysis System™ Cartridge that provides extracorporeal access during hemodialysis. The Moda-flx Hemodialysis System™ Cartridge is only compatible with the Modaflx Hemodialysis System™. The system creates purified water from tap water; from this purified water and chemical concentrates, the system creates dialysate in real time. The chemicals used to create the dialysate are standard 45X concentrates.

Ultrafiltration is achieved by controlling the dialysate going in and coming out of the dialyzer independently, using pumps on the HD Device to control fluid flow from both the inlet and outlet of the dialyzer. An external bag of saline is used to provide solution infusions to combat hypotensive episodes. Saline is also used to prime the Moda-flx Hemodialysis System™ Cartridge prior to use.

Prescribed blood flow rate is generated by a peristaltic pump, while heparin is administered to prevent blood coagulation. All fluid pathways are disposable and easily installed and replaced. Once installed, the device will check the connections of the fluid pathways and the system will automatically prepare itself for treatment.

This document is a 510(k) summary for the Moda-flx Hemodialysis System and Cartridge. It outlines the device's indications for use, its description, and a comparison to predicate devices, but does not provide the acceptance criteria or results of a study designed to prove the device meets specific acceptance criteria related to its clinical performance.

The "Performance Data" section lists various tests conducted, such as biocompatibility, electrical safety, software verification, and bench performance (including clearance, transport, and dialyzer integrity testing). It explicitly states that "no clinical studies were required to support this submission." This indicates that the FDA's substantial equivalence determination for this device was based on non-clinical performance data and comparison to predicate devices, rather than a clinical study demonstrating specific efficacy or clinical performance acceptance criteria.

Therefore, I cannot provide the requested information about acceptance criteria and a study proving the device meets them, as such a study (specifically a clinical one with performance metrics) is stated as not being required and thus not provided in this document.

However, based on the information provided, here's what can be inferred about the types of performance criteria and tests performed, even if specific numerical acceptance values aren't given:

Inferred Information from the Document:

While specific clinical acceptance criteria are not detailed (as no clinical study was required for this submission), the document does list various performance data provided in support of substantial equivalence. These imply underlying performance criteria for safety and technical functionality.

1. Table of Acceptance Criteria and Reported Device Performance: This information is not provided in the document for clinical performance. The document only lists categories of tests performed.

2. Sample size used for the test set and the data provenance: This information is not provided in the document for any of the listed performance tests. The provenance (e.g., country of origin, retrospective/prospective) is also not provided.

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/provided, as no clinical study with "ground truth" established by experts is mentioned. For the non-clinical tests (e.g., bench testing, software V&V), the "ground truth" would be the engineering specifications and regulatory standards.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set: This information is not applicable/provided, as no clinical study requiring adjudication is described.

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 information is not applicable/provided. The device is a hemodialysis system, not an AI-assisted diagnostic tool involving human readers.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: This information is not applicable/provided. The device is a medical system, not an AI algorithm in the typical sense of "standalone performance" for diagnostic or predictive tasks. Performance was likely evaluated for the integrated system.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): For the non-clinical tests mentioned (biocompatibility, electrical safety, software V&V, bench performance, etc.), the "ground truth" would be established by relevant engineering standards, regulatory requirements, and internal specifications for the device's functional performance. No clinical ground truth (like pathology or outcomes data) was used or required for this submission according to the document.

8. The sample size for the training set: This information is not applicable/provided. As no clinical study requiring "training data" for an AI model is described, this question is not relevant to the provided text.

9. How the ground truth for the training set was established: This information is not applicable/provided for the same reasons as point 8.

Ask a specific question about this device