(145 days)
The NxStage System One is indicated for treatment of renal failure or fluid overload using hemofiltration, hemodialysis and/or ultrafiltration. All treatments must be administered by a health care provider, under physician prescription.
The NxStage System One consists of the NxStage Cycler and the NxStage Cartridge Extracorporeal Blood and Fluid Circuit. The NxStage Cycler is an electro-mechanical device that interfaces with the NxStage Cartridge. The NxStage Cartridge is a single-use extracorporeal blood circuit and fluid management device that mounts integrally within the NxStage Cycler. The system is designed to deliver hemofiltration, hemodialysis and/or ultrafiltration.
The provided FDA 510(k) premarket notification for the NxStage System One does not contain specific acceptance criteria or a detailed study report with performance metrics, sample sizes, ground truth methodologies, or information about human reader studies commonly found in submissions for AI/ML-enabled medical devices.
Instead, this document focuses on demonstrating substantial equivalence to predicate devices through a qualitative comparison of technological characteristics and general performance testing. Therefore, I cannot provide a table of acceptance criteria or a detailed study description as requested for a typical AI/ML medical device submission.
Here's an analysis of what can be extracted from the document based on the provided questions:
1. A table of acceptance criteria and the reported device performance
The document does not specify quantitative acceptance criteria (e.g., sensitivity, specificity, AUC thresholds) or specific performance metrics in a tabular format. The FDA letter states: "We have reviewed your Section 510(k) premarket notification... and have determined the device is substantially equivalent... to legally marketed predicate devices." This implies the "acceptance criteria" were met by demonstrating equivalence, rather than achieving specific performance thresholds.
The "reported device performance" is summarized conceptually: "Results of the performance testing have documented that the proposed NxStage System One is substantially equivalent to the predicate devices and is suitable for the labeled indications for use." No specific performance values are given.
2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)
This information is not provided in the document. The submission mentions "Performance testing was conducted," but gives no details about the size or nature of any test sets used, the type of data, or its provenance.
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 information is not applicable and not provided. The NxStage System One is a hemodialysis system, not an AI/ML diagnostic device requiring expert interpretation for ground truth establishment. The "performance testing" likely involved engineering and clinical functional assessments, not subjective expert reviews of output.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
Not applicable and not provided, for the same reasons as point 3.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
Not applicable. The NxStage System One is a standalone medical device for renal failure treatment, not an AI system designed to assist human readers (e.g., radiologists) in interpretation. Therefore, no MRMC study or AI assistance effect size is mentioned or relevant.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
While the device operates without a human-in-the-loop for its core function (delivering hemofiltration, hemodialysis, and/or ultrafiltration), the concept of "standalone performance" as it applies to an algorithm's diagnostic or prognostic capabilities is not relevant here. The device itself is a standalone system, and its performance was evaluated against predicate devices.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The document does not detail the specific "ground truth" used for performance testing. Given the device type, "ground truth" would likely relate to objective measurements of system function, such as fluid removal rates, solute clearance, pressure monitoring accuracy, and safety parameters, compared to established medical standards and predicate device performance. It would not involve expert consensus on diagnostic images or pathology.
8. The sample size for the training set
Not applicable and not provided. The NxStage System One is not an AI/ML device that requires a "training set" in the conventional sense. Its design and validation would follow traditional engineering and clinical testing methodologies.
9. How the ground truth for the training set was established
Not applicable and not provided, for the same reasons as point 8.
In summary: The provided 510(k) summary focuses on demonstrating substantial equivalence of a hemodialysis system to existing devices through general performance testing and technological comparison. It predates the widespread regulatory focus on AI/ML devices and therefore does not contain the specific details about acceptance criteria, study designs, ground truth, or expert involvement typically associated with such submissions, as requested in your prompt.
§ 876.5860 High permeability hemodialysis system.
(a)
Identification. A high permeability hemodialysis system is a device intended for use as an artificial kidney system for the treatment of patients with renal failure, fluid overload, or toxemic conditions by performing such therapies as hemodialysis, hemofiltration, hemoconcentration, and hemodiafiltration. Using a hemodialyzer with a semipermeable membrane that is more permeable to water than the semipermeable membrane of the conventional hemodialysis system (§ 876.5820), the high permeability hemodialysis system removes toxins or excess fluid from the patient's blood using the principles of convection (via a high ultrafiltration rate) and/or diffusion (via a concentration gradient in dialysate). During treatment, blood is circulated from the patient through the hemodialyzer's blood compartment, while the dialysate solution flows countercurrent through the dialysate compartment. In this process, toxins and/or fluid are transferred across the membrane from the blood to the dialysate compartment. The hemodialysis delivery machine controls and monitors the parameters related to this processing, including the rate at which blood and dialysate are pumped through the system, and the rate at which fluid is removed from the patient. The high permeability hemodialysis system consists of the following devices:(1) The hemodialyzer consists of a semipermeable membrane with an in vitro ultrafiltration coefficient (K
uf ) greater than 8 milliliters per hour per conventional millimeter of mercury, as measured with bovine or expired human blood, and is used with either an automated ultrafiltration controller or anther method of ultrafiltration control to prevent fluid imbalance.(2) The hemodialysis delivery machine is similar to the extracorporeal blood system and dialysate delivery system of the hemodialysis system and accessories (§ 876.5820), with the addition of an ultrafiltration controller and mechanisms that monitor and/or control such parameters as fluid balance, dialysate composition, and patient treatment parameters (e.g., blood pressure, hematocrit, urea, etc.).
(3) The high permeability hemodialysis system accessories include, but are not limited to, tubing lines and various treatment related monitors (e.g., dialysate pH, blood pressure, hematocrit, and blood recirculation monitors).
(b)
Classification. Class II. The special controls for this device are FDA's:(1) “Use of International Standard ISO 10993 ‘Biological Evaluation of Medical Device—Part I: Evaluation and Testing,’ ”
(2) “Guidance for the Content of 510(k)s for Conventional and High Permeability Hemodialyzers,”
(3) “Guidance for Industry and CDRH Reviewers on the Content of Premarket Notifications for Hemodialysis Delivery Systems,”
(4) “Guidance for the Content of Premarket Notifications for Water Purification Components and Systems for Hemodialysis,” and
(5) “Guidance for Hemodialyzer Reuse Labeling.”