Search Results

Ask a specific question about this device

Asahi AM-BIO Series Dialyzers are intended for use for hemodialysis treatment of patients who have chronic renal failure or acute renal failure. Asahi AM-BIO Series Dialyzers must be used in accordance with the instructions of a physician familiar with hemodialysis and familiar with the conditions of the patient. Asahi AM-BIO Series-Dialyzers have been tested in vitro and in confirmatory clinical studies under single or initial use and under reprocessing and reuse conditions for up to 15 reuse cycles. Based on the results from these evaluations, Asahi AM-BIO Series Dialyzers may be reprocessed for reuse on the same patient. If reprocessing and reuse is practiced, it is recommended that the reuse be done under the conditions as existed in the in vitro and confirmatory clinical studies as recommended immediately below. It is noted that the Asahi AM-BIO Series Dialyzers have not been tested for reuse when reprocessed with agents and/or processes other than these, and the performance of the dialyzers under other conditions are not known and cannot be recommended. Accordingly: 1. The reprocessed dialyzer may be used only if the residual Total Cell Volume (TCV) is at least 80% of the original TCV and if such dialyzer otherwise meets the acceptance criteria of these instructions for use and the instructions of the reprocessing system utilized. Furthermore, the policies, instructions, and criteria of the institution for reuse (e.g., concerning dialyzer performance, residual blood, and/or dialyzer leakage or damage) should be followed. 2. The reprocessing agent may be either (1) 4% formaldehyde (also known as formalin) in conjunction with the Seratronics Dialyzer Reprocessing Systems for Dialyzer Reprocessing and Preparation (DRS4" and DPS4"), manufactured by Seratronics, Inc., or (2) Renalin® in conjunction with the Renatron® Dialyzer Reprocessing System (RS 8300), manufactured by Renal Systems, Inc. 3. The instructions provided by the manufacturer of the chosen reprocessing agent must be followed in reprocessing the dialyzer. 4. The reprocessed dialyzer may be used only on dialysis systems equipped with volumetric ultrafiltration controllers.

The line of Asahi AM-BIO Series Dialyzers is a family of hemodialysis membranes, or hollow fiber dialyzers developed to provide safe and effective hemodialysis over ranges of dialyzer patient treatment requirements. The device is intended for use in patients who have chronic renal failure or acute renal failure, for both single or initial use and when reprocessed for reuse for a maximum of 15 reprocessing reuse cycles on the same patient. The membrane fibers are made of modified cellulose (i.e., alkyl ether polymer grafted cellulose), derived from cuprammonium rayon. The cuprammonium rayon is manufactured to have a thin layer of modified cellulose exposed to blood contact surfaces. The modification to the cellulose yields the fiber more compatible to the patient's blood, manifested through lower complement activation (C3, and C5,) when compared to regular cellulose membrane dialyzers. The membranes are housed within a plastic casing of styrene butadiene block polymer. Nonremovable casing end caps are also made of styrene butadiene block polymer. The potting material (sealant) is polyurethane and the port caps (stoppers) are made of hydrogenated styrene butadiene block polymer. The AM-BIO Series Dialyzers will be offered for sale in both a "wet" model and a "dry" model. The wet and dry dialyzers are identical to each other except that the wet models are filled at the factory with a fluid to facilitate priming by the user and the dry models are not filled. The use of a wet or dry dialyzer is a matter of user preference. The fluid in wet dialyzers is made of water containing 600 ppm sodium pyrosulfite and 300 ppm sodium carbonate. All Asahi AM-BIO Series Dialyzers are sterilized before shipment by gamma radiation (y-rays). The dialyzer is no longer sterile after it is accessed for the initial use.

Here's a breakdown of the acceptance criteria and the study details for the Asahi AM-BIO Series Dialyzers, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set (Clinical Study):

  • Sample Size: 12 patients per clinical site. The study aimed for each patient to be treated 36 consecutive times, reusing the dialyzer up to 15 times on each subject.
  • Data Provenance: Prospective, from two clinical sites (country of origin not explicitly stated, but the company is Japanese and the submission to the FDA, suggesting US or international involvement).

• Test Set (In vitro study):

  • Sample Size: Not explicitly stated as a number of individual dialyzers, but involved "the smallest wet model (AM-BIO-50) and the largest wet model (AM-BIO-100)" tested with 15 reprocessing cycles.
  • Data Provenance: Used "outdated human blood from a blood bank".

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

The document does not explicitly state the number of experts or their qualifications for establishing ground truth within the clinical or in-vitro tests conducted for this 510(k) submission. Clinical measurements were taken, and general "established dialysis practices" were followed at the institutions. However, the overall "ground truth" for product safety and effectiveness in K983720 is based on substantial equivalence to predicate devices, which themselves would have been cleared based on existing medical consensus on hemodialysis.

4. Adjudication Method for the Test Set

The document does not mention a formal adjudication method (like 2+1 or 3+1 consensus) for the clinical study's outcomes. Clinical measurements (Kur, removal rates, complement activation) were likely gathered and analyzed according to the study protocol.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size

No, an MRMC comparative effectiveness study was not done. This device is a medical device (dialyzer) for organ support, not an AI or imaging diagnostic software that typically involves human reader performance.

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

Yes, the performance of the dialyzer itself (the "algorithm" in this context) was evaluated in standalone in-vitro and clinical studies without human-in-the-loop performance influencing its function. Humans operate the reprocessing systems and dialysis machines, but the device's efficacy (filtration, biocompatibility) is an intrinsic property.

7. The Type of Ground Truth Used

• For in-vitro testing: Measured physical and chemical parameters (Kur, clearances for urea, creatinine, B12) using standard laboratory methods, established as "ground truth" through direct measurement.
• For clinical testing:
  • Performance: Clinical measurements of Kur, removal rates for urea, creatinine, and albumin, which serve as direct, objective "ground truth" for the device's function in a patient setting.
  • Safety/Biocompatibility: Monitoring of complement activation (C3a and C5a) and characterization of patient effects over 36 treatments provide "ground truth" for the device's safety profile.
  • Overall: Substantial equivalence to predicate devices, meaning the "ground truth" for overall safety and effectiveness is largely benchmarked against well-established and legally marketed hemodialyzers.

8. The Sample Size for the Training Set

The concept of a "training set" is not applicable here, as this is a medical device (dialyzer), not an AI algorithm. The device's design and manufacturing process are based on established engineering principles and prior research, not a machine learning training paradigm.

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

Not applicable, as there is no "training set" in the context of an AI algorithm. The design of the dialyzer and its membrane material (modified cellulose) were engineered to achieve specific performance characteristics and enhanced hemocompatibility, likely based on R&D, material science, and prior knowledge of hemodialysis.

Ask a specific question about this device

Hemoflow dialyzers are designed for use in acute or chronic hemodialysis therapies as either single use or multiple use.

Fresenius Polysulfone Hemodialyzers

The provided documents are a letter from the FDA regarding a 510(k) premarket notification and an "Indications for Use" statement for Fresenius Polysulfone Hemodialyzers. These documents are from 1998 and pertain to medical devices (dialyzers), not an AI-powered diagnostic device.

Therefore, the information required to describe the acceptance criteria and the study proving an AI device meets those criteria (such as detailed performance metrics, sample sizes, expert qualifications, ground truth methods, or MRMC studies) is not present in the provided text.

The documents confirm that the specified Fresenius Hemoflow Dialyzers were found "substantially equivalent" to predicate devices for use in acute or chronic hemodialysis. This substantial equivalence determination by the FDA is the "acceptance criteria" in this context, rather than specific performance metrics detailed in a study report for an AI device.

To answer your specific questions:

1. A table of acceptance criteria and the reported device performance: Not applicable/not provided. The acceptance was based on substantial equivalence to predicate devices, not on specific performance metrics of an AI model against predefined acceptance criteria.
2. Sample size used for the test set and the data provenance: Not applicable/not provided. This is a medical device approval based on substantial equivalence, not an AI model validation study.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable/not provided. Ground truth for an AI model is not relevant here.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set: Not applicable/not provided.
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/not provided. This is not an AI device.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: Not applicable/not provided. This is not an AI device.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not applicable/not provided.
8. The sample size for the training set: Not applicable/not provided.
9. How the ground truth for the training set was established: Not applicable/not provided.

Ask a specific question about this device

Hemoflow dialyzers are designed for acute and chronic hemodialysis. Hemoflow dialyzers are also appropriate for single or multiple use when reprocessed with 1.5% Citric Acid/95℃.

The submission describes a procedure and components used in the reprocessing of Fresenius polysulfone hemodialyzers with 95°C/1.5% citric acid. This involves using radiant heat (moist or dry) at 95°C for 24 hours with the addition of 1.5% citric acid solution.

The provided text is related to a 510(k) submission for a hemodialyzer reprocessing procedure using 95°C/1.5% citric acid. It focuses on demonstrating the substantial equivalence of this new reprocessing method to existing ones. The information required for acceptance criteria and study details is largely based on sterilization and disinfection effectiveness, as well as material compatibility and performance for the reprocessed dialyzers.

Here's an analysis based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Microbial Reduction (Disinfection/Sterilization):

  • Test dialyzers were selected after exposure to blood in "at least 10 reprocessing procedures."
  • For kill effectiveness, "10X blood contacted reprocessed F80 dialyzers biologically seeded with approximately 1,000,000 B. stearothermophilus spores" were used.
  • "Three test runs were conducted."
  • A single run was done at 90°C.
  • "24 dialyzers were seeded with the test organism B. stearothermophilus" for a subsequent growth observation test.
  • Data Provenance: The studies were conducted by Fresenius Medical Care, suggesting internal, prospective experimental data. The country of origin is not explicitly stated but implies US-based submission context.

• Toxicity Testing:

  • "Dialyzer samples that were reprocessed a minimum of 15 times" were used. The exact number of samples is not specified beyond "samples."
  • Data Provenance: Internal, prospective experimental data.

• In Vitro Performance:

  • "Each membrane family of Fresenius polysulfone dialyzers; low (F4, F6 and F8), mid (F60M and F80M) and high flux (F60 and F80)" were evaluated. The specific number of dialyzers per family/reprocessing condition is not detailed.
  • Data Provenance: Internal, prospective experimental data.

• In Vivo Product Performance:

  • "All Fresenius polysulfone membrane configurations" were compared. The specific number of devices tested is not detailed.
  • Data Provenance: Internal, prospective experimental data (possibly animal or human surrogate studies, but the text doesn't specify which, just "in vivo product performance").

• In Vivo Clinical Data:

  • "Patients dialyzed with hemodialyzers reprocessed with 1.5% formaldehyde and 40℃ incubation who were then transferred to dialyzers heat reprocessed with 95°C/1.5% citric acid." The number of patients is not specified.
  • Data Provenance: Clinical study data, likely prospective given the "transferred" description and follow-up.

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

The text does not provide information on the number or qualifications of experts used to establish a "ground truth" in the traditional sense related to a diagnostic or AI device. The ground truth for the device's performance here is based on objective measurements (e.g., microbial counts, temperature, flux rates, toxicity assays, patient monitoring). The regulatory body (FDA) and Fresenius's internal scientists (e.g., Director, Product Development) are involved in reviewing and generating the data, respectively, but not in establishing a subjective "ground truth" through consensus for a test set.

4. Adjudication Method for the Test Set

This concept is not relevant to the type of device and study described. Adjudication methods (like 2+1, 3+1) are typically used for establishing ground truth in diagnostic studies involving human interpretation or subjective assessments. Here, the studies involve objective, measurable outcomes (e.g., sterilization effectiveness, physical performance, toxicity) that don't require such adjudication.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size

No, an MRMC comparative effectiveness study was not done. MRMC studies are typically used to assess the performance of diagnostic imaging devices or algorithms where human readers interpret medical images or data, and their performance is compared with and without AI assistance. This submission describes an industrial reprocessing procedure for a medical device (hemodialyzer), not an AI-enabled diagnostic tool.

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

This question is not applicable as the device is a reprocessing procedure, not an algorithm or AI system. The "standalone performance" of the reprocessing procedure itself (i.e., its ability to disinfect, maintain performance, and be non-toxic) was demonstrated through the various tests described (microbial reduction, in vitro/in vivo performance, toxicity).

7. The Type of Ground Truth Used

The "ground truth" in this context refers to the verifiable outcomes against which the reprocessing procedure's effectiveness is measured. The types of ground truth used include:

• Microbial Counts: Direct measurement of viable organisms (e.g., B. stearothermophilus) to establish log reduction, indicating disinfection/sterilization.
• Physical/Chemical Measurements: Temperature readings (thermocouples), pH measurements, and quantitative assessment of membrane flux rates.
• Laboratory Assays: USP antimicrobial effectiveness test, ISO 10993-1 guidelines for toxicity, indicating specific biological and chemical properties.
• Clinical Observations/Outcomes Data: Monitoring patient parameters and intradialytic episodes (hypotension, reactions) in clinical use.

8. The Sample Size for the Training Set

This question is not applicable. The context is the validation of a reprocessing procedure for a medical device, not a machine learning algorithm. Therefore, there is no "training set" in the sense of data used to train an AI model. All described studies are essentially "test sets" or validation experiments for the reprocessing method itself.

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

This question is not applicable as there is no training set for an AI/algorithm in this submission.

Ask a specific question about this device

Hemodialysis with these dialyzers is indicated for patients with acute or chronic renal failure when conservative therapy is judged to be inadequate. It may also be indicated in the treatment of patients intoxicated with poisons or drugs. This dialyzer is indicated for single use or reuse. If the dialyzer is reused on the same patient, the reuse procedure and disinfectant specified in the Direction Insert must be followed. No other reuse procedure or disinfectant has been evaluated for clinical acceptability.

Models CA-90, CA-110, CA-130, and CA-150 Hemodialyzers

The provided text describes a 510(k) summary for the CA® Cellulose Acetate Hollow Fiber Dialyzer. The information focuses on the device's equivalence to a predicate device and its compliance with various standards and regulations. However, it does not contain the specific details required to answer your questions about acceptance criteria, device performance from a test set, ground truth establishment, or studies showing performance metrics as typically expected for AI/ML device evaluations.

This document is for a medical device (hemodialyzer) from 1997, which predates many of the standardized evaluation methodologies common for AI/ML-driven devices. Therefore, the information you're requesting regarding "acceptance criteria and reported device performance" (with specific metrics like sensitivity, specificity), "sample size for test set," "data provenance," "number of experts for ground truth," "adjudication methods," "MRMC studies," "standalone performance," "type of ground truth," "sample size for training set," and "how ground truth for training set was established" is not present in the provided text.

The closest analogue to "acceptance criteria" and "device performance" in this document refers to how the device meets biological requirements, sterilization levels, residue limits, pyrogen testing, particle limits, and functional testing against manufacturing specifications, rather than performance in detecting a condition or making a diagnosis. The study mentioned, "Clinical data was collected according to the FDA Guidance for Hemodialyzer Reuse Labeling," is focused on the reuse aspect, not on a diagnostic or AI-driven performance metric.

Given the nature and age of the document, it's not possible to extract the information you've requested in the format applicable to modern AI/ML device evaluations.

Ask a specific question about this device

Hemodialysis with these dialyzers is indicated for patients with acute or chronic renal failure when conservative therapy is judged to be inadequate. It may also be indicated in the treatment of patients intoxicated with poisons or drugs. These dialyzers are indicated for single use or reuse. If the dialyzer is reused on the same patient, the reuse procedure and disinfectant specified in the Direction Insert must be followed. No other reuse procedure or disinfectant has been evaluated for clinical acceptability.

Model CAHP-90 Hemodialyzer

The provided text describes specific acceptance criteria and the study that proves the device meets those criteria.

1. Table of acceptance criteria and the reported device performance:

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

The document does not explicitly state the sample size for a "test set" in the context of device performance. The clinical data was collected "according to the FDA Guidance for Hemodialyzer Reuse Labeling," which suggests a prospective clinical study, though the exact nature (e.g., number of patients) is not provided. The origin of the clinical data is not specified. Other tests, like pyrogen testing, refer to JMHW Notification (Japanese) and Japanese Pharmacopeia, implying that some testing relates to Japanese regulatory standards, but doesn't specify if the samples themselves were from Japan.

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 provided in the document. The document describes compliance with established standards and guidelines (e.g., USP, AAMI, FDA guidance, Japanese Pharmacopeia) for device testing, rather than a system where human experts establish ground truth for a discrete test set.

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

This information is not applicable and not provided. The document outlines a typical regulatory submission for a medical device involving adherence to performance standards and safety guidelines, not a comparative study relying on expert adjudication of a test set.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This device, a hemodialyzer, is a piece of medical equipment, not an AI or imaging diagnostic tool that would typically involve human readers or AI assistance in interpretation.

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

This concept is not applicable to the device described. The hemodialyzer is a physical device used in treatment, not an algorithm.

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

The "ground truth" for this device's performance is established by adherence to documented performance standards and regulatory guidelines rather than a clinical ground truth like pathology or outcomes data in the typical sense of diagnostic devices. For example:

• Biological safety: Compliance with USP XXI Class VI materials.
• Sterility: Achieved SAL of 1 x 10-6 validated by AAMI guidelines.
• Pyrogenicity: Meeting standards of JMHW Notification and Japanese Pharmacopeia.
• Particle limits: Comparison to USP 23 and ASTM F25-68.
• Functional integrity: Conformance to manufacturing specifications.
• Clinical performance: Demonstrated by "In Vivo and In Vitro performance data" and compliance with "FDA Guidance for Hemodialyzer Reuse Labeling."

8. The sample size for the training set:

Not applicable. The CAHP™ Hemodialyzer is a physical medical device, not a machine learning model that requires a training set.

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

Asahi AM-R Series Dialyzers are intended for use for hemodialysis treatment of patients who have chronic renal failure or acute renal failure.

Asahi AM-R Series Dialyzers have been tested in vitro and in confirmatory clinical studies under reprocessing and reuse conditions for up to 15 reuse cycles. Based on the results from these evaluations, Asahi AM-R Series Dialyzers may be reprocessed for reuse on the same patient. If reprocessing and reuse is practiced, it is recommended that the reuse be done under the conditions as existed in the in vitro and confirmatory clinical studies as recommended immediately below. It is noted that the Asahi AM-R Series Dialyzers have not been tested for reuse when reprocessed with agents and/or processes other than these, and the performance of the dialyzers under other conditions are not known and cannot be recommended.. Accordingly:

• (1) The reprocessed dialyzer may be used only if the residual Total Cell Volume (TCV) is at least 80% of the original TCV and if such dialyzer otherwise meets the acceptance criteria of the instructions for use and the instructions of the reprocessing system utilized. Furthermore, the policies, instructions and criteria of the institution for reuse (e.g., concerning dialyzer performance, residual blood, and/or dialyzer leakage or damage) should be followed.
• (2) The reprocessing agent may be either (1) 4% formaldehyde (also known as formalin ) in conjunction with the Seratronics Reprocessing Systems for Dialyzer Reprocessing and Preparation (DRS4TM and DPS4TM), manufactured by Seratronics, Inc., or (2) Renalin® in conjunction with the Renatron® Dialyzer Reprocessing System, manufactured by Renal Systems, Inc.
• The instructions provided by the manufacturer of the chosen reprocessing (3) agent must be followed in reprocessing the dialyzer.
• The reprocessed dialyzer may be used only on dialysis systems equipped with (4) volumetric ultrafiltration controllers.

The AM-R Series Dialyzers are a family of hemodialyzers developed to provide safe and effective hemodialysis over ranges of dialyzer patient treatment requirements. The performance of these dialyzers, when new for single or initial (first) use and when reprocessed for reuse, have been documented through laboratory (in vitro) testing and confirmatory clinical testing. Assahi AM-R Series Dialyzers are constructed of hollow fiber membranes of cuprammonium rayon housed within a plastic casing of styrene butadiene block polymer. Asahi AM-R Series Dialyzers are sterilized before shipment by gamma radiation (y-rays). The dialyzer is no longer sterile after its sterile package is opened for the initial (first) use.

This document describes the Asahi AM-R Series Dialyzers and their approval for reuse after reprocessing. The acceptance criteria and supporting studies are detailed below.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Non-clinical (In Vitro) Testing:
  • Biocompatibility: The largest model (AM-R-90U) was subjected to 15 reprocessing cycles.
  • Performance (Kuf, Urea, Creatinine, Vitamin B12 clearances): The smallest model (AM-R-50M) and the largest model (AM-R-90U) were tested in vitro for initial use and up to 15 reuse cycles. Outdated human blood from a blood bank was used.
• Clinical Testing:
  • The largest model (AM-R-90U) was tested in confirmatory clinical studies for initial use and up to 15 reuse cycles.
  • Sample Size: Minimum of 12 patients enrolled at each of two clinical sites. A minimum of 50% of these patients reused the dialyzer 15 times.
  • Data Provenance: The study was a prospective clinical study conducted at two clinical sites that utilized both formalin and Renalin® reprocessing agents. The country of origin of the data is not explicitly stated, but it refers to typical US dialysis practices and FDA guidance, suggesting a US context.

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

The document does not explicitly state the number of experts used to establish ground truth or their specific qualifications for the clinical studies. However, it mentions that "dialysis sessions were conducted and patients were managed in accordance with established dialysis practices for the respective institutions," implying that qualified medical professionals (e.g., nephrologists, dialysis nurses) were involved in managing patient care and assessing outcomes.

4. Adjudication Method for the Test Set

The document does not explicitly detail an adjudication method (e.g., 2+1, 3+1) for the test set. Clinical outcomes were assessed by comparing reprocessed device performance against initial use performance within each patient, following established clinical protocols at the participating institutions.

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

No MRMC comparative effectiveness study was done. The study focuses on the device's performance with and without reuse, not on the improvement of human readers with AI assistance, as this is a medical device (dialyzer) and not an AI diagnostic tool.

6. Standalone Performance

A standalone performance evaluation was conducted in both non-clinical (in vitro) and clinical settings. The device's performance metrics (biocompatibility, ultrafiltration coefficient, clearances, and removal rates) were measured directly, independent of human interpretation beyond typical clinical monitoring.

7. Type of Ground Truth Used

• Non-clinical (In Vitro) Testing:
  • Biocompatibility: Standardized laboratory tests for cytotoxicity, sensitization, irritation, systemic toxicity, genotoxicity, hemocompatibility, and pyrogenicity, which have established scientific ground truths.
  • Performance (Kuf, Urea, Creatinine, Vitamin B12 clearances): In vitro measurements using outdated human blood, with ground truth established by laboratory analytical methods.
• Clinical Testing:
  • Performance (Kuf, Urea, Creatinine, Albumin removal rates): In vivo measurements in patients with chronic renal failure or acute renal failure. The "ground truth" for clinical performance was the patient's own initial dialysis session results, serving as a baseline for comparison with subsequent reused sessions. Outcome data included physiological measurements and patient stability.

8. Sample Size for the Training Set

The document does not explicitly describe a separate "training set" in the context of machine learning, as this is a medical device (dialyzer) evaluation, not an AI model development. The reported studies evaluate the device's performance directly.

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

As there is no "training set" in the machine learning sense, this question is not applicable to the information provided. The evaluations are direct performance assessments of the dialyzer, not data used to train an algorithm.

Ask a specific question about this device