Search Results

The NxStage System One is indicated for the treatment of acute and chronic renal failure or fluid overload using hemofiltration, hemodialysis, and/or ultrafiltration, in an acute or chronic care facility. The NxStage System One is also indicated for hemodialysis with or without ultrafiltration in the home.

All treatments must be administered under physician's prescription, and must be observed by a trained and qualified person, considered to be competent in the use of this device by the prescribing physician.

The NxStage System One dialysis system consists of an electro-mechanical cycler and a disposable Cartridge Extracorporeal Blood and Fluid Circuit (NxStage Cartridge). The NxStage Cartridge is available with a pre-attached high permeability dialyzer, together referred to as the "NxStage Cartridge Express".

The NxStage Cartridge Express filter is made up of a fiber bundle maintained within a polyethylene terephthalate glycol (PETG) dialyzer housing. The polysulfone fiber bundle is a semipermeable, hollow fiber membrane through which water molecules and smaller molecular weight solutes pass from the blood to the dialysate, but larger molecular weight solutes (such as proteins) do not. Uremic toxins and waste products are removed from the patient's blood by means of diffusion during hemodialysis.

The NxStage System One with Cartridge Express (CAR-170-E and CAR-172-E) received a 510(k) clearance (K232803) for the treatment of acute and chronic renal failure or fluid overload using hemofiltration, hemodialysis, and/or ultrafiltration. This device is an updated version of the legally marketed predicate device, NxStage System One with Cartridge Express (K061837). The device is a gamma-sterilized, single-use device, and the dialyzer is provided with the blood pathway sterile and nonpyrogenic.

Here's an analysis of the acceptance criteria and study details:

1. Acceptance Criteria and Reported Device Performance

The submission indicates that performance testing was conducted according to ISO 8637-1 First Edition 2017-11 and the FDA's "Guidance for the Content of Premarket Notifications for Conventional and High Permeability Hemodialyzers, August 1998." All testing met predetermined acceptance criteria, demonstrating that the NxStage Cartridge Express is safe and effective for its intended use, similar to the predicate device.

Specifically, key performance indicators for dialyzers are Urea, Creatinine, and Vitamin B12 clearance. The provided table details the in vitro clearance performance data for various blood and dialysate flow rates. Additionally, ultrafiltration rate information is presented for different transmembrane pressures.

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

The document does not explicitly state the specific sample sizes for the "test set" in terms of number of devices or experimental replicates for the performance and structural integrity testing. However, it indicates these were in vitro tests using bovine blood for ultrafiltration rate measurements (Hct. 32%; Total Protein 6 gm/dL; Temperature 37° C). The data provenance is described as in vitro testing. It does not mention any specific country of origin for the data provided from the in-vitro studies.

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

Not applicable. The reported performance data appears to be based on objective, quantitative in vitro measurements, not on expert assessment of images or interpretations that would require a "ground truth" established by experts.

4. Adjudication Method for the Test Set

Not applicable, as this was not an expert-based subjective assessment.

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 medical hardware/disposable (dialysis cartridge), not an AI-powered diagnostic or assistive tool for human readers. No MRMC study was mentioned or would be relevant.

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

Not applicable. This is not an algorithm-only device.

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

The "ground truth" in this context refers to the objectively measured values from the in vitro performance and structural integrity tests of the dialyzer (e.g., measured clearance rates of specific molecules, ultrafiltration rates, integrity test results). Biocompatibility was assessed against established ISO standards.

8. The Sample Size for the Training Set

Not applicable. This device is hardware and does not utilize a "training set" in the sense of machine learning algorithms.

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

Not applicable for the reasons stated above.

Ask a specific question about this device

NxStage PureFlow Solution is indicated for use with NxStage renal replacement therapy systems that utilize sterile premixed dialysate during hemodialysis for chronic care patients.

The NxStage PureFlow Solution is a family of premixed dialysate solution formulations which are sterile, non-pyrogenic, fully constituted dialysate solutions provided in 5L single use flexible bags.

The provided text describes the 510(k) premarket notification for the NxStage PureFlow Solution, a pre-mixed dialysate for hemodialysis. However, the document does not contain information about a study involving an AI/Machine Learning device or a Multi-Reader Multi-Case (MRMC) comparative effectiveness study.

The document discusses performance testing for the NxStage PureFlow Solution, which is a physical medical device (a liquid solution in a bag), not a software or AI-driven diagnostic device. Therefore, the acceptance criteria and study details requested in the prompt (e.g., sample size for test/training sets, data provenance, expert ground truth, adjudication methods, MRMC studies, standalone algorithm performance) are not applicable to the content of this document.

The performance data mentioned in the document for the NxStage PureFlow Solution are related to:

• Analytical testing: per device specifications and applicable sections of USP and EP.
• Physical testing of container (bag): per device specifications.
• Container closure integrity testing: per ISO 11607-1.
• Temperature excursion testing: per device specifications.
• Stability/Shelf-life testing: per ICH Q1A to support a 24-month shelf life.
• Ship testing: per ASTM D4169-22.
• Biocompatibility testing: in accordance with ISO 10993-1 and FDA guidance, including chemical characterization, toxicological risk assessment, cytotoxicity, sensitization, irritation, pyrogenicity, hemocompatibility, and systemic toxicity.
• Human Factors Validation Testing: in accordance with FDA guidance and AAMI/ANSI/EC 62366-1.
• Electrical Safety and EMC: Not Applicable (the device has no electronic features).
• Software Verification and Validation Testing: Not Applicable (the device has no software features).
• Animal Studies: Not Applicable.
• Clinical Studies: Not Applicable.

The conclusion states that "Verification and validation was conducted to characterize the proposed device and the predetermined acceptance criteria were met." However, the document does not enumerate specific quantitative acceptance criteria or the specific performance metrics achieved in these tests, only the types of tests conducted.

Therefore, I cannot provide the requested information about AI acceptance criteria and study details based on the provided document.

Ask a specific question about this device

The NxStage system is indicated for the treatment of acute and chronic renal failure or fluid overload using hemofiltration, hemodialysis, and/or ultrafiltration, in an acute or chronic care facility.

The system is also indicated for home hemodialysis, including home nocturnal hemodialysis and solo home hemodialysis during waking hours.

All treatments must be administered under a physician's prescription, and must be performed by a trained and qualified person, considered to be competent in the use of this device by the prescribing physician.

The VersiHD with GuideMe Software is comprised of the NxStage Cycler, an electromechanical control unit and the NxStage Cartridge (disposable) extracorporeal blood and fluid management circuit (with or without a pre-attached high permeability filter) that mounts integrally within the NxStage Cycler.

The combined system is designed to deliver hemofiltration, hemodialysis and/or ultrafiltration in an acute or chronic care facility. It is also indicated for home hemodialysis, including home nocturnal hemodialysis and solo home hemodialysis during waking hours.

Based on the provided text, the device in question is the VersiHD with GuideMe software, which is a modification to an existing hemodialysis system (specifically, a software-only modification to the graphical user interface). This submission is a 510(k) premarket notification, which focuses on demonstrating substantial equivalence to a predicate device, rather than proving novel clinical effectiveness from scratch.

Therefore, the "acceptance criteria" and "study that proves the device meets the acceptance criteria" are framed within the context of demonstrating safety, effectiveness, and non-inferiority compared to the predicate device, especially regarding the software modification and its human factors.

Here's an analysis based on your requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative "acceptance criteria" for performance metrics in a pass/fail table format, nor does it provide numerical "reported device performance" against those criteria in the way one might see for a diagnostic algorithm. Instead, it details that testing was conducted to demonstrate compliance with specifications and equivalence to the predicate.

The closest equivalent to "acceptance criteria" derived from the text are the regulatory and engineering requirements that the device must meet, and the "reported device performance" is indicated by the statement that these requirements were met.

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

• Sample Size: The document does not specify a numerical sample size for "test sets" in terms of patient data or case numbers. The testing described (simulated treatments, software V&V, system V&V, human factors validation) are engineering and usability tests, not clinical performance studies with patient cohorts.
• Data Provenance: Not applicable in the context of patient data. The origin of the testing itself would be the manufacturer (NxStage Medical, Inc.). The simulated treatments were described as "Simulated home hemodialysis treatments were performed in a simulated use environment (dialysis center/clinic or home setting)." This indicates a lab-based simulation rather than real patient data collection. The study specifically states "N/A. No clinical studies were conducted," and "N/A. No animal studies were conducted."

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. Given that no clinical studies or animal studies were conducted, and the device is a software modification (GUI change) to an existing system, the "ground truth" would likely relate to engineering specifications, safety standards, and usability engineering principles, rather than clinical diagnostic ground truth established by experts.

4. Adjudication Method for the Test Set

This information is not provided in the document. Adjudication methods (e.g., 2+1, 3+1) are typically used in clinical imaging studies to establish ground truth from multiple expert reads. Since no clinical studies were performed with patient data, such a method would not be relevant here.

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

• Was it done?: No. The document explicitly states: "N/A. No clinical studies were conducted." MRMC studies are clinical studies involving human readers interpreting cases.
• Effect Size of Human Readers Improvement with AI vs. without AI assistance: Not applicable, as no MRMC study was performed. The "GuideMe" software appears to be an instructional aid, not an AI for diagnostic interpretation.

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

• Was it done?: This concept isn't directly applicable in the same way it would be for a diagnostic AI algorithm. The "GuideMe" software is described as a "new optional 'Guide Me' feature in which step-by-step instructions are available for users if they press the 'Guide Me' button on the updated user interface." It assists the human operator, rather than performing an independent task that could be evaluated in isolation like a diagnostic algorithm.
• The software's performance was verified and validated as part of the overall system and human factors testing, demonstrating its functionality and safety within the human-in-the-loop context.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

The "ground truth" relevant to this submission is primarily:

• Engineering specifications and pre-determined performance specifications: For software and system verification and validation.
• International standards (e.g., IEC 60601 series): For electrical safety and EMC.
• FDA Human Factors guidance: For usability and safe interaction.

There is no mention of clinical ground truth derived from expert consensus, pathology, or outcomes data, as no clinical studies were conducted.

8. The Sample Size for the Training Set

• Not applicable / Not provided. This device is not described as a machine learning or AI model trained on a data set in the typical sense for image interpretation or diagnosis. The "GuideMe" feature is a software modification providing step-by-step instructions. Therefore, there wouldn't be a "training set" like for a deep learning model.

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

• Not applicable / Not provided. As there's no mention of a training set for an AI/ML model, the establishment of ground truth for such a set is irrelevant here. The software's functionality and content (the "Guide Me" instructions) would have been developed based on existing procedural knowledge for operating the hemodialysis system and validated through engineering and human factors testing.

Ask a specific question about this device

The NxStage System One is indicated for the treatment of acute and chronic renal failure or fluid overload using hemofiltration, hemodialysis, and/or ultrafiltration, in an acute care facility.

The NxStage Cartridge Express with Speedswap is an optional accessory device to be used exclusively with the NxStage System One for facilitating the removal and replacement of a flow-compromised filter during to acute and chronic renal failure or fluid overload. The device would be used when hemodialysis, and /or ultrafiltration may become disrupted.

All treatments must be administered under a physician's prescription and must be observed by a trained and qualified person, considered to be competent in the use of this device by the prescribing physician.

The NxStage Cartridge Express with Speedswap is a single use extracorporeal blood circuit and fluid management device with a pre-attached detachable high permeability hollow-fiber. The proposed feature, "Speedswap" is a feature in the cartridge design that will allow the user to exchange the filter that is becoming clotted or clogged with a new filter that has been manually primed.

A kit will be required to perform the filter exchange. The proposed optional kit will consist of a filter with tubing connections for manual priming along with a waste bag to collect used saline. The nurse has the option of using the proposed cartridge without using the Speedswap feature. The functionality of the proposed cartridge is the same as the predicate Cartridge. Exchanging a used filter is optional and the facility can choose to dispose of the entire cartridge instead of exchanging the Filter.

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

Device: NxStage Cartridge Express with Speedswap

1. Table of Acceptance Criteria and Reported Device Performance:

The document primarily focuses on demonstrating substantial equivalence to a predicate device rather than presenting specific, quantitative performance acceptance criteria with numerical targets. However, the testing performed implicitly aims to meet the regulatory and safety standards expected for such a device.

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

The document does not explicitly state the sample sizes for the individual performance, biocompatibility, or human factors tests. It refers to "testing" and "studies" but doesn't quantify the number of units or participants.

The data provenance is industrial testing, likely conducted in a laboratory setting by the manufacturer (NxStage Medical, Inc. in Lawrence, MA), and is therefore considered retrospective to the submission date. There is no information about country of origin for specific test data beyond the manufacturer's location.

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

This type of information is not applicable to the studies described. The "ground truth" here is based on engineering specifications, regulatory standards (e.g., ISO, ASTM), and established biological/chemical safety protocols, rather than expert interpretation of medical images or patient outcomes.

4. Adjudication Method for the Test Set:

Not applicable. The tests described are objective measurements against defined criteria (e.g., pass/fail for leak tests, adherence to ISO standards, or clear results for biocompatibility). There is no ambiguity or subjective interpretation that would require an adjudication method.

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 medical accessory for a hemodialysis system, not an AI-powered diagnostic or interpretive tool. Therefore, MRMC studies related to human reader performance with or without AI assistance are irrelevant to this submission.

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

Not applicable. This is a physical medical device, not a standalone algorithm.

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

The "ground truth" for the various tests relies on established scientific principles, engineering standards, and regulatory guidelines:

• Engineering Specifications: For integrity, kink resistance, priming volume, chemical resistance, and system performance.
• International Standards (e.g., ISO 8638:2010): For performance testing.
• Biocompatibility Standards (e.g., ISO 10993 series implicitly): For cytotoxicity, sensitization, reactivity, pyrogenicity, genotoxicity, hemocompatibility, etc.
• Risk Analysis and Usability Engineering Principles: For human factors validation.

8. The sample size for the training set:

Not applicable. This device is not an AI/ML product that undergoes a training phase with a dataset.

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

Not applicable, as there is no training set for this type of device.

Ask a specific question about this device

The NxStage Connected Health System is for use by chronic hemodialysis patients remotely in combination with the NxStage System One and a variety of devices such as blood pressure monitor and weight scale upon the prescription of a licensed physician or healthcare practitioner. The Connected Health System serves as the data repository and communication link to the server software which is utilized by the healthcare facility. The healthcare facility may include the physician or licensed healthcare practitioner, other clinicians, or a disease management center.

The purpose of the system is to collect, accumulate, store and transmit medical information such as flowsheet data, vital signs, blood pressure, weight and dialysis data from the patient and transmit these results to their healthcare practitioner at another facility. The system also provides online labeling, treatment status, trending and supports education and messaging.

The device is not intended to provide time sensitive data or alarms and does not control the System One Cycler. This system may not be used as a substitute for direct medical intervention or emergency care.

Interpretation of the information collected and transmitted requires clinical judgment by an experienced medical professional.

The NxStage Connected Health system collects, stores, and transmits medical information such as flowsheet data, vital signs, blood pressure, weight, and dialysis treatment data from the patient and transmits these results to their healthcare practitioner at another facility. The system also provides online labeling, treatment status, trending and supports education, has the ability to add picture attachments through the notes in a flowsheet, and the ability for the Clinician to remotely access snapshots of patient's treatment data while the treatment is taking place.

The internet server receives the patient data from the home setting or remote location where it is made available to the healthcare facility to track, graph, trend, note variances, set alert criteria, and receive alerts when parameters are outside the criteria set.

The provided documentation is a 510(k) Premarket Notification for the NxStage Connected Health System. This type of submission focuses on demonstrating substantial equivalence to a predicate device, rather than providing detailed clinical study results often seen in PMA (Premarket Approval) submissions. Therefore, the information regarding acceptance criteria and performance studies is primarily related to non-clinical verification and validation testing, and does not involve AI or human reader studies.

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

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

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

The document describes non-clinical verification and validation testing, not a clinical study involving a "test set" of patient data in the sense of a dataset for AI evaluation.

• Sample size: Not applicable in the context of a "test set" of patient data for AI. The testing involved various software verification tests, simulated use scenarios, and design validation activities rather than a sample of patient data.
• Data provenance: Not applicable. The testing is described as internal verification and validation of software and system functionalities by the manufacturer.

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)

This is not applicable as the document describes non-clinical software and system validation, not a study requiring expert-established ground truth for a diagnostic AI.

• Design Validation Testing (for "Link" and "Remote View" functionalities) involved "Clinicians at Dialysis Clinics and NxStage Technical Support personnel." Specific numbers or detailed qualifications are not provided beyond "Clinicians" and "Technical Support personnel."

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

Not applicable. The description refers to internal verification and validation testing with predetermined pass/fail criteria, not a clinical study with an adjudication process for ground truth establishment.

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 MRMC study was done. This submission is for a data collection and communication system, not an AI-powered diagnostic device. The device does not involve "human readers" or "AI assistance" in the diagnostic context.

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

Not applicable. The device is a system for collecting, storing, and transmitting medical information, not a standalone diagnostic algorithm. It explicitly states it is "not intended to provide time sensitive data or alarms and does not control the System One Cycler" and "Interpretation of the information collected and transmitted requires clinical judgment by an experienced medical professional."

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

Not applicable in the context of diagnostic ground truth. The "ground truth" for the verification and validation described here would be the pre-defined product specifications and requirements that the system was tested against. The software functionality was verified to meet these specifications.

8. The sample size for the training set

Not applicable. This device is not an AI/ML algorithm that requires a "training set." It is a data collection and communication system.

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

Not applicable. As noted above, there is no training set for this type of device.

Ask a specific question about this device

The NxStage System One is indicated for the treatment of acute and chronic renal failure or fluid overload using hemofiltration, hemodialysis, and/or ultrafiltration, in an acute or chronic care facility. The System is also indicated for home hemodialysis, including home nocturnal hemodialysis and solo home hemodialysis during waking hours. All treatments must be administered under physician's prescription, and must be performed by a trained and qualified person, considered to be competent in the use of this device by the prescribing physician.

The NxStage System One is comprised of the NxStage Cycler, an electromechanical control unit; the NxStage Cartridge, a sterile, single-use extracorporeal blood and fluid management circuit (with or without a pre-attached high permeability filter) that mounts integrally within the NxStage Cycler. The combined system is designed to deliver hemofiltration, hemodialysis and/or ultrafiltration in an acute or chronic care facility. The NxStage System One is also indicated for home hemodialysis, including home nocturnal hemodialysis.

The provided text describes a 510(k) premarket notification for the NxStage System One, an hemodialysis system. The submission focuses on expanding the indications for use to include "solo home hemodialysis during waking hours." The study conducted is a Patient Preference Information (PPI) survey to support this indication expansion, not a typical performance study of an AI/ML device.

Therefore, many of the requested elements for describing the acceptance criteria and the study that proves an AI/ML device meets those criteria are not applicable to this document. This document is about a medical device (hemodialysis system) and an expansion of its usage, supported by patient preference data, not an AI/ML algorithm.

However, I will attempt to extract what is relevant and indicate where information is not present or not applicable based on this specific document.

Analysis of the Provided Document for AI/ML Device-Specific Criteria:

This document is a 510(k) summary for the NxStage System One, a hemodialysis device. The study described is a patient preference information (PPI) survey, not a study of an AI/ML device's performance. Therefore, many of the requests about AI/ML specific acceptance criteria, ground truth, expert adjudication, MRMC studies, standalone performance, and training sets are not applicable to the content of this document.

The "acceptance criteria" here refer to the willingness of patients to accept certain risk profiles for solo home hemodialysis.

Here's an attempt to answer the questions based on the provided text, highlighting what is (and isn't) present:

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

The "acceptance criteria" in this context are thresholds of risk tolerance for solo home hemodialysis based on patient preferences. The 'performance' is indicated by the percentage of patients willing to choose Solo HHD under varying risk scenarios.

Note: The "acceptance criteria" here are patient thresholds, not device performance metrics in a traditional sense. The 'performance' is how many patients still opt for Solo HHD at various risk levels.

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

• Sample Size: 142 evaluable responses from patients.
• Data Provenance: All dialysis centers and patients were located in the United States of America.
• Study Design: This was a prospective survey conducted electronically with current HHD patients.

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. This study is a patient preference survey, not a study evaluating a medical image or diagnostic output that would require expert ground truth. The "ground truth" here is the patient's stated preference regarding risk tolerance.

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

Not applicable. There was no expert adjudication in this patient preference survey. Patient responses were the direct data.

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 was not an MRMC study and did not involve human readers evaluating AI assistance.

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

Not applicable. This study did not involve an algorithm with standalone performance.

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

The "ground truth" for this study was patient preference information (PPI), specifically their stated willingness to choose solo home hemodialysis given varying hypothetical risk profiles (death, needle dislodgement).

8. The sample size for the training set

Not applicable. This study did not involve a machine learning model with a separate training set. It was a survey to gather patient preference data.

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

Not applicable. As there was no training set for a machine learning model, this question is not relevant to the described study.

Ask a specific question about this device

The NxStage System One Plus is indicated for the treatment of acute and chronic renal failure or fluid overload using hemofiltration, hemodialysis, and/or ultrafiltration, in an acute or chronic care facility.

The System is also indicated for home hemodialysis, including home nocturnal hemodialysis.

All treatments must be administered under physician's prescription, and must be performed by a trained and qualified person, considered to be competent in the use of this device by the prescribing physician

The NxStage System One Plus is comprised of the NxStage Cycler, an electromechanical control unit; the NxStage Cartridge, a sterile, single-use extracorporeal blood and fluid management circuit (with or without a pre-attached high permeability filter) that mounts integrally within the NxStage Cycler. The combined system is designed to deliver hemodialysis and/or ultrafiltration in an acute or chronic care facility. The NxStage System One Plus is also indicated for home hemodialysis, including home nocturnal hemodialysis.

The provided document is a 510(k) premarket notification for a medical device called "NxStage System One Plus," a hemodialysis system. It details the device's substantial equivalence to a predicate device, its indications for use, and a summary of non-clinical testing.

However, the document does not contain the information requested regarding acceptance criteria related to device performance based on a study comparing it to a ground truth, especially for an AI/ML-based device. The tests listed are primarily related to general electrical safety, software verification, and mechanical performance for a hardware device, not the type of performance evaluation typically seen for AI/ML devices involving ground truth and human reader comparisons.

Therefore, I cannot fulfill the request using only the provided text. The requested information such as a table of "acceptance criteria and reported device performance" (in the context of AI/ML metrics like sensitivity, specificity, or image quality), sample sizes for test/training sets, expert qualifications for ground truth, adjudication methods, MRMC studies, standalone performance, and ground truth types are not present in the provided document.

It appears the request is tailored for an AI/ML device approval, while the document describes a traditional hardware-based medical device (hemodialysis system).

Ask a specific question about this device

The NxStage System One is indicated for the treatment of acute and chronic renal failure, or fluid overload using hemofiltration, hemodialysis, and/or ultrafiltration, in an acute or chronic care facility.

The System is also indicated for home hemodialysis, including home nocturnal hemodialysis.

All treatments must be administered under physician's prescription, and must be performed by a trained and qualified person, considered to be competent in the use of this device by the prescribing physician.

The NxStage System One is comprised of the NxStage Cycler, an electromechanical control unit; the NxStage Cartridge, a sterile, single-use extracorporeal blood and fluid management circuit (with or without a preattached high permeability filter) that mounts integrally within the NxStage Cycler. The combined system is designed to deliver hemofiltration, hemodialysis and/or ultrafiltration in an acute or chronic care facility. The NxStage System One is also indicated for home hemodialysis, including home nocturnal hemodialysis.

This document is a 510(k) Premarket Notification for the NxStage System One, a high permeability hemodialysis system. It seeks to demonstrate substantial equivalence to a previously cleared predicate device (K141752).

Based on the provided document, here's an analysis regarding acceptance criteria and supporting studies:

1. Table of Acceptance Criteria and Reported Device Performance

The document presents a comparison of technological characteristics between the proposed device and the predicate device in Table 1. However, this table does not directly state acceptance criteria in terms of performance metrics (e.g., minimum accuracy, maximum allowable deviation) against which the proposed device was tested. Instead, it states that the "Proposed Device (NxStage System One)" is "Same" for most parameters compared to the "Predicate Device (NxStage System One)".

The closest the document comes to defining acceptance criteria is under "Effluent Volume Accuracy" for the predicate device, where specifications for different software versions are provided. However, it only states that the proposed device is "Same," implying it meets these same specifications without explicitly presenting the proposed device's performance against them.

Therefore, a table of acceptance criteria and reported device performance cannot be fully constructed from the provided text as the explicit acceptance criteria and quantitative performance results for the proposed device are not detailed, beyond stating they were "met."

Inference of Acceptance Criteria (from Predicate Device Specifications as implied by "Same"):

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

The document states: "No Clinical testing was conducted." All testing mentioned is "Non-Clinical Test/Performance Testing - Bench."

• Sample Size: Not explicitly stated for bench testing. The document refers to "Simulated treatments" but does not give a number of simulations or samples used.
• Data Provenance: Not applicable as no clinical data was used. All testing appears to be in-house bench testing.

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

Not applicable. Since no clinical testing was conducted and all testing was "Non-Clinical Test/Performance Testing - Bench," there was no need for expert ground truth establishment in a clinical context. The "ground truth" for bench testing would be established by the engineering specifications and validated test methods.

4. Adjudication Method for the Test Set

Not applicable, as no clinical testing with human subjects or expert review was performed.

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 a 510(k) for a medical device (hemodialysis system), not an AI-powered diagnostic or interpretive device that would involve human readers.

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

Not applicable in the context of an "algorithm only" performance that would typically compare to human clinicians. This device is a treatment system. The "Non-Clinical Test/Performance Testing - Bench" can be considered a form of standalone performance assessment against engineering specifications, but it's not "algorithm only" in the sense of a software-as-a-medical-device (SaMD) context. It's the performance of the integrated electromechanical control unit with its software and cartridge.

7. The Type of Ground Truth Used

For the non-clinical bench testing, the "ground truth" would be established by:

• Engineering specifications and design requirements: The device's performance was measured against these predefined technical standards and parameters (e.g., flow rates, pressure monitoring ranges, accuracy for effluent volume).
• Physical measurements and simulated conditions: The testing simulates treatment conditions and measures the device's output against expected physical and chemical outcomes.

8. The Sample Size for the Training Set

Not applicable. This device is not an AI/ML model that requires a "training set" in the conventional sense. The "training" for a traditional medical device involves its design, development, and iterative testing/refinement against engineering principles and specifications.

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

Not applicable, as there is no "training set" for an AI/ML model. The "ground truth" for the device's design and development (analogous to a training process for an AI) comes from established medical standards for hemodialysis, regulatory requirements, risk analysis, and engineering principles.

Ask a specific question about this device

The NxStage TPE Cartridge is indicated for use only with the NxStage System One for therapeutic plasma exchange in a clinical environment. All treatments must be administered under a physician's prescription, and must be observed by a trained and qualified person considered to be competent in the use of this device by the prescribing physician.

The NxStage TPE Cartridge provides therapeutic plasma exchange therapy when used with a commercially available TPE filter. The blood tubing set is the NxStage TPE Cartridge. The TPE Cartridge is a single use extracorporeal blood circuit and fluid management device available without a pre-attached filter. Therapeutic plasma exchange requires the use of a commercially available Therapeutic Plasma Exchange filter such as such as the Asahi Plasmaflo OP-05W (A) wet filter (PMA P820033 S005 approved on March 16, 2010).

The provided document describes the NxStage Therapeutic Plasma Exchange (TPE) Cartridge and its path to 510(k) clearance. The focus of the study is to demonstrate substantial equivalence to a predicate device, not to prove clinical efficacy through a comparative effectiveness study involving human readers or standalone AI performance.

Therefore, many of the requested categories are not applicable to this submission.

Here's the information that can be extracted from the provided text:

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

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

The document specifies "The following tables outline the testing performed on the CAR-510-C to support the determination of substantial equivalence to the predicate device." However, specific sample sizes for each test within the performance and functional tables (Table 2 and Table 3) are not explicitly stated. The testing described appears to be laboratory-based engineering and material testing, not patient data trials. Therefore, data provenance such as country of origin or retrospective/prospective is not applicable in the context of this device.

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

This point is not applicable. The "ground truth" for the tests described relates to engineering specifications and material properties, not diagnostic interpretations from experts. The testing involved measuring physical properties and verifying performance against predefined technical requirements.

4. Adjudication method for the test set

This point is not applicable. Adjudication methods (like 2+1, 3+1) are typically used for establishing ground truth in clinical studies involving expert interpretation of medical images or patient outcomes. The tests in this document are technical performance evaluations.

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 point is not applicable. This submission is for a medical device (a TPE Cartridge) and is not an AI/CADe/CADx device that involves human readers or AI assistance.

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

This point is not applicable. This device is a Therapeutic Plasma Exchange Cartridge, not an algorithm or AI system.

7. The type of ground truth used

The "ground truth" for the various performance and functional tests (e.g., pressure leak, endurance, tensile strength, priming volume, hemocompatibility, packaging integrity) was based on pre-defined engineering specifications, regulatory standards, and manufacturing tolerances. For biocompatibility, it was based on accepted biological evaluation standards (ISO 10993).

8. The sample size for the training set

This point is not applicable. This device does not involve a training set as it is not an AI/machine learning device.

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

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

Ask a specific question about this device

The NxStage System One is indicated for the treatment of acute and chronic renal failure, or fluid overload using hemofiltration, hemodialysis, and/or ultrafiltration, in an acute or chronic care facility.
The System is also indicated for home hemodialysis, including home nocturnal hemodialysis.
All treatments must be administered under physician's prescription, and must be performed by a trained and qualified person, considered to be competent in the use of this device by the prescribing physician.

The NxStage System One is comprised of the NxStage Cycler, an electromechanical control unit; the NxStage Cartridge, a sterile, single-use extracorporeal blood and fluid management circuit (with or without a preattached high permeability filter) that mounts integrally within the NxStage Cycler. The combined system is designed to deliver hemofiltration, hemodialysis and/or ultrafiltration in an acute or chronic care facility. The NxStage System One is also indicated for home hemodialysis, including home nocturnal hemodialysis.

This document describes the NxStage System One, a hemodialysis system. The FDA 510(k) clearance (K141752 dated December 19, 2014) indicates that the device is substantially equivalent to a previously cleared NxStage System One (K140526).

Here's an analysis of the provided information regarding acceptance criteria and the study that proves the device meets those criteria:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly defined by the chosen "primary effectiveness endpoint" and "primary safety endpoint" of the pivotal clinical study.

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

• Sample Size: A total of 58 End Stage Renal Disease (ESRD) patients participated in the clinical study. 39 completed the study period, and 19 discontinued.
• Data Provenance: The study was a US prospective, multi-center clinical study.

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

This information is not explicitly provided in the document. The "ground truth" for the clinical study was based on patient outcomes, delivered therapy volumes, and reported adverse events during the observational clinical trial. The study was conducted "under physician's prescription," implying medical oversight, but specific details about expert adjudication for individual patient data points are not detailed.

4. Adjudication Method for the Test Set

This information is not explicitly provided. The clinical study collected data on delivered therapy and adverse events. The assessment of these outcomes would have been part of the clinical trial protocol, but there is no specific mention of an independent adjudication committee for all events or for the effectiveness endpoint.

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 question is not applicable to the provided document. The NxStage System One is a hemodialysis device, not an AI-powered diagnostic or interpretive tool that would involve human readers or AI assistance in the interpretation of medical images or data. The study compared two different treatment regimens (Nocturnal Hemodialysis vs. Daily Hemodialysis) using the same device, not human performance with and without AI.

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

This question is not applicable. The device is a hemodialysis system, not an algorithm, and it always involves a human-in-the-loop (trained and qualified person, prescribing physician, and patient). The "effectiveness" measurement was based on the system's ability to deliver therapy, not an independent algorithmic output.

7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)

The ground truth for the clinical study was based on patient outcomes data, specifically:

• Effectiveness: Measured by the actual delivered volume of therapy compared to the prescribed volume.
• Safety: Measured by the occurrence and rates of intradialytic and interdialytic adverse events.

8. The Sample Size for the Training Set

The document does not describe a "training set" in the context of machine learning or AI. For the clinical study, the patients (all 58 of them) effectively served as the "test set" for evaluating the performance of the device in the two different treatment regimens. If "training set" refers to data used for initial device development and non-clinical testing, that information is not detailed here beyond "System Verification and Software Validation" and "Simulated dialysis treatments."

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

As there is no explicit "training set" described in the context of a machine learning or AI algorithm, this question is not fully applicable. For the non-clinical testing (System Verification and Software Validation, Regression testing, etc.), the ground truth would have been established through engineering specifications, validated test protocols, and simulated conditions to ensure the device performs as designed.

Ask a specific question about this device