Search Results

The 2008 Sorbent System is intended for adult acute and chronic uremic patients in the presence of a healthcare practitioner where hemodialysis is prescribed on the order of a physician.

The 2008 Sorbent System consists of two distinct components:

• the 2008 Machine, and .
• . the SORB™ Module.

The SORB Module is a sorbent dialysate regenerative system that attaches to the 2008 Machine and replaces the machine's existing single-pass dialysate delivery system.

During treatment, used dialysate is chemically reprocessed into fresh, new dialysate and sent back to the dialyzer instead of being sent down a drain. By recirculating and regenerating the dialysate, the 2008 Sorbent System uses less than 15 liters of potable tap water per treatment compared to a standard sinqle-pass system that uses at least 120 liters of purified water during a standard 4-hour dialysis treatment.

The provided text describes a Special 510(k) submission for an updated version of a hemodialysis system, the 2008 Sorbent System. This type of submission focuses on demonstrating substantial equivalence to a predicate device (an already legally marketed device) through verification testing for modifications that do not significantly alter the device's fundamental technology, indications for use, or safety and effectiveness.

Here's an analysis based on the provided text, addressing your questions:

1. Table of Acceptance Criteria and Reported Device Performance

The submission does not explicitly state quantitative "acceptance criteria" in the traditional sense of a performance study with specific outcome measures and thresholds. Instead, it describes a "verification testing summary" aimed at demonstrating that the modified device meets its design requirements and is substantially equivalent to the predicate device.

The "performance" is implicitly defined by the successful completion of these verification activities, indicating that the modified device functions as intended and safely.

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 the context of a clinical study. The testing described is non-clinical verification testing (e.g., software testing, hardware testing, cartridge performance), not a study involving human patients. Therefore, the "sample size" would refer to the number of test runs, prototypes, or cartridges used to perform the verification, which is not detailed.
• Data Provenance: The data is likely internal to the manufacturer, Renal Solutions, Inc., and represents retrospective (or in-house) testing focusing on engineering and performance verification of the device itself, rather than prospective clinical data from patients. There is no information regarding the country of origin of data, as it's not a clinical data set.

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

This information is not applicable to this submission. The "ground truth" for non-clinical verification testing is typically established by engineering specifications, regulatory standards, and the performance characteristics of the predicate device. The experts involved would be engineers, scientists, and quality assurance personnel within Renal Solutions, Inc., responsible for design, testing, and regulatory affairs. Their specific numbers and qualifications are not detailed here, as this is not a study requiring expert clinical review for ground truth establishment.

4. Adjudication Method for the Test Set

This information is not applicable. Adjudication methods (like 2+1, 3+1) are typically used in clinical studies or studies where multiple human readers assess cases and discrepancies need to be resolved. This submission describes non-clinical verification testing of a device's functionality and performance against engineering requirements and established safety standards.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

There is no mention of an MRMC comparative effectiveness study, human readers, or AI assistance. This device is a hemodialysis system, not an imaging or diagnostic AI-powered device.

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 machine with a sorbent system. It is a physical medical device for treatment, not an algorithm or AI system for standalone performance evaluation. Its operation still requires a healthcare practitioner ("human-in-the-loop") as stated in its Indications for Use.

7. The Type of Ground Truth Used

The "ground truth" for this submission is based on:

• Engineering Specifications and Design Requirements: The device was tested to ensure it met its own defined performance parameters.
• Predicate Device Performance: The primary ground truth for demonstrating "substantial equivalence" is the established safety and effectiveness of the legally marketed predicate device (2008 Sorbent System, K093362). The modified device's performance was compared to, and intended to be equivalent to, that of the predicate.
• Regulatory Standards: Implicitly, the verification testing would also adhere to relevant industry standards and regulatory guidance for hemodialysis devices.

8. The Sample Size for the Training Set

This information is not applicable. The device is a physical hemodialysis system, not a machine learning model that requires a "training set."

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

This information is not applicable for the same reason as above (not a machine learning model).

Ask a specific question about this device

The 2008 Sorbent System is intended for adult acute and chronic uremic patients in the presence of a healthcare practitioner where hemodialysis is prescribed on the order of a physician.

The 2008 Sorbent System is intended for adult acute and chronic uremic patients in the presence of a healthcare practitioner where hemodialysis is prescribed on the order of a physician. The 2008 Sorbent System operates in a similar manner to standard hemodialysis systems currently approved for use; it is substantially equivalent to the Fresenius 2008T hemodialysis machine (K080964) and the Renal Solutions Allient® Sorbent Hemodialysis System (K070739). The significant difference between the 2008 Sorbent System and standard single-pass hemodialysis machines is that the 2008 Sorbent System utilizes a sorbent cartridge to purify dialysate made from potable tap water and then regenerates fresh dialysate from spent dialysate (like the Allient Sorbent Hemodialysis System). The 2008 Sorbent System consists of two distinct components: the 2008 Machine, and the SORB™ Module. The SORB Module is a sorbent dialysate regenerative system that attaches to the 2008 Machine and replaces the machine's existing single-pass dialysate delivery system. During treatment, used dialysate is chemically reprocessed into fresh, new dialysate and sent back to the dialyzer instead of being sent down a drain. By recirculating and regenerating the dialysate, the 2008 Sorbent System uses less than 15 liters of potable tap water per treatment compared to a standard single-pass system that uses at least 120 liters of purified water during a standard 4-hour dialysis treatment.

The provided text describes the 2008 Sorbent Hemodialysis System, focusing on its substantial equivalence to predicate devices and the verification testing performed. However, it does not include the specific details required to fully answer your request regarding acceptance criteria and a study proving the device meets those criteria, particularly for an AI-powered medical device.

The document is a 510(k) summary for a Sorbent Hemodialysis System, which is a medical device for dialysate delivery, not an AI or software-intensive diagnostic device in the sense your questions imply (e.g., test sets, ground truth, expert consensus, MRMC studies). The "software testing" mentioned is to ensure the device's control software meets its design input requirements, not for evaluating an AI algorithm's diagnostic or predictive performance.

Therefore, many of your requested items cannot be extracted from this document as they are not relevant to the type of device being described.

However, I can extract what is available:

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

The document outlines categories of testing and general objectives, implying acceptance criteria were defined for each. However, it does not explicitly state the quantitative acceptance criteria or the specific numerical performance results. Instead, it refers to "pre-defined acceptance or pass/fail criteria" and states that testing "demonstrates the device meets its performance specifications."

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 given text. The testing described is non-clinical verification testing of a physical medical device, not a study involving patient data in the context of AI performance evaluation.

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/provided. The ground truth for this type of device (a hemodialysis system) is established through engineering and performance specifications, adherence to standards, and risk analysis, not expert consensus on diagnostic interpretations.

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

This information is not applicable/provided. Adjudication methods like 2+1 are typically used in clinical studies involving multiple readers or interpretations, which is not what is described here.

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

An MRMC comparative effectiveness study was not done, as this device is a hemodialysis system and not an AI-assisted diagnostic tool for 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 "software testing" refers to the control software of the device, not a standalone diagnostic algorithm.

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

The "ground truth" for this device is based on engineering specifications, regulatory standards (e.g., IEC, ISO), and performance requirements related to the physical and functional operation of the hemodialysis system. The document lists "pre-defined acceptance or pass/fail criteria" as part of the test protocols.

8. The sample size for the training set

This information is not applicable/provided. This device is a physical medical device, not an AI model trained on a dataset.

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

This information is not applicable/provided. As above, there is no AI model or training set in the context of this device.

In summary, the provided document describes a 510(k) submission for a Sorbent Hemodialysis System, focusing on its functional, safety, and software verification to demonstrate substantial equivalence to predicate devices. It does not contain the detailed information typically associated with the evaluation of AI-powered diagnostic or predictive medical devices.

Ask a specific question about this device

The Allient Sorbent Hemodialysis System, including the SORB™ series and HISORB™ series of cartridges is to be used for the treatment of acute and chronic uremic patients where hemodialysis is prescribed by the physician.

Not Found

This document is a 510(k) clearance letter for the Allient Sorbent Hemodialysis System. It does not contain information on the acceptance criteria or a study that proves the device meets specific acceptance criteria in the format requested. The letter confirms that the device is substantially equivalent to legally marketed predicate devices, but it does not detail the technical performance data that led to this determination.

Therefore, I cannot provide the requested table or information based on the content of this document.

Ask a specific question about this device

The Allient Sorbent Hemodialysis System, including the SORB series and HISORB series of cartridges is to be used for the treatment of acute and chronic uremic patients where hemodialysis is prescribed by the Physician.

The Allient Sorbent Hemodialysis System is intended for the treatment of THE Allent Oorbont Homoutients where hemodialysis is prescribed by the ohysician. The Allient System functions as a traditional re-circulating sorbent hemodialysis system. Either single-needle or dual-needle access to the nemodialysis bystem . The system consists of the Allient hemodialysis machine, SORB™ series of sorbent cartridges, a single-use, sterile, disposable blood tubing set, a single-use disposable dialysate set, and various dialysate and infusate chemicals. The patient's blood is pumped from the access through a dialyzer and is returned to the patient.

This is a 510(k) summary for a medical device (Allient® Sorbent Hemodialysis System) and not a study describing acceptance criteria and device performance. Therefore, most of the requested information regarding acceptance criteria, study details, sample sizes, ground truth establishment, expert qualifications, adjudication methods, and comparative effectiveness studies is not available in the provided text.

The document primarily focuses on establishing substantial equivalence to a previously cleared predicate device, rather than presenting a performance study with detailed acceptance criteria and results.

Here's what can be extracted and what cannot:

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

• Not Available. The document does not describe specific acceptance criteria (e.g., performance metrics, thresholds) for the device. Instead, it asserts "substantial equivalence" to a predicate device.

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

• Not Available. There is no mention of a "test set" or any specific clinical data used to evaluate the device's performance against predefined criteria. The assessment is based on comparison to a predicate device.

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 / Not Available. Since no "test set" or performance study is detailed, there's no mention of experts establishing ground truth for such a study.

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

• Not Applicable / Not Available. No test set or adjudication method 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

• Not Applicable. This device is a hemodialysis system, not an AI-assisted diagnostic tool involving human readers. Therefore, an MRMC study is not relevant here.

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

• Not Applicable. This is a hardware medical device, not an algorithm.

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

• Not Applicable / Not Available. As no detailed performance study with a test set is described, the concept of "ground truth" in this context is not relevant. The substantial equivalence is based on similar design, operating principles, and intended use as the predicate device.

8. The sample size for the training set

• Not Applicable / Not Available. This device is not an AI/ML algorithm that would typically involve a "training set."

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

• Not Applicable / Not Available. As above, this concept doesn't apply to the reported device.

Summary of available information related to the device:

• Device Name: Allient® Sorbent Hemodialysis System
• Intended Use: Treatment of acute and chronic uremic patients where hemodialysis is prescribed by the Physician.
• Predicate Device: Allient Sorbent Hemodialysis System K043572 (or K043574 as cited later, which appears to be the same predicate).
• Basis for Equivalence:
  • Same indicated use.
  • Same operating principles.
  • Same basic system design.
  • Incorporates the same accessories and generic materials, manufactured, packaged, and sterilized using the same processes.
• Regulatory Classification: Class II, Product Code FKT, Regulation Number 21 CFR §876.5600 (Sorbent regenerated dialysate delivery system for hemodialysis).

In conclusion, the provided text is a regulatory submission for a 510(k) clearance, which aims to demonstrate substantial equivalence to an already legally marketed device rather than providing a detailed performance study with acceptance criteria and results as typically seen for novel diagnostic or AI devices.

Ask a specific question about this device

The Allient® Sorbent Hemodialysis System, including the SORB™ series and HISORB™ series of cartridges, is to be used for the treatment of acute and chronic uremic patients where hemodialysis is prescribed by the physician.

The Allient Sorbent Hemodialysis System (Allient System) is intended for the treatment of acute or chronic uremic patients where hemodialysis is prescribed by the physician. The system consists of the Allient hemodialysis machine, SORB™ series of Sorbent cartridges, a single-use, sterile, disposable blood tubing set, a singleuse disposable dialysate set, and various dialysate and infusate chemicals. The system is recommended for use with a variety of dialyzers, access needles or access cannulae, which will be supplied by other manufacturers. The Allient System operates in a similar manner to standard hemodialysis systems currently approved for use. The only significant differences between the Allient System and standard hemodialysis machines are as follows: The Allient System utilizes a Sorbent cartridge to purify dialysate made from potable water. After passing through the dialyzer, the dialysate is recirculated to the dialyzer instead of being disposed of. The Allient System utilizes the Pulsar™ air-activated pump in contrast to the roller-activated pump commonly employed in traditional hemodialysis systems. The Pulsar blood pump is a dual-chamber pneumatically operated pump. All other aspects of Renal Solutions' Allient Sorbent Hemodialysis System process are identical to those employed in the standard "single pass" method of dialysis: there are no significant differences in the technology employed in Sorbent dialysis therapy between the Allient System and traditional methods. The Allient System functions as a traditional recirculating Sorbent hemodialysis system, similar to the REDY 2000 System. Either single-needle or dual-needle access to the patient is permitted. The patient's blood is pumped from the access through a dialyzer and is returned to the patient. Heparin is administered via a flow-controlled heparin pump capable of delivering rates of 0 to 3 milliliter per hour (mL/hr) in 0.5 mL/hr increments as well as an initial bolus of 0 to 10 mL. Blood-flow rates are settable in 10 milliliter per minute (mL/min) increments in the range of 200 to 400 mL/min in the dual-needle mode and 200 to 300 mL/min in the singleneedle mode. The dialysate delivery system consists of a container for dialysate. Sorbent regenerative cartridges, chemical infusion system to replace chemicals removed by the Sorbent cartridges, and an ultrafiltrate control system. The dialysate delivery system operates in a batch recirculating mode and continuously recirculates the dialysate through the cartridge. The cartridge removes dialyzed toxins from the dialysate and buffers the sodium and bicarbonate levels in the dialysate to maintain normal levels in the patient. The Acute mode of operation is intended for use in a hospital, acute or chronic-care facility, or dialysis clinic where the patient is continually monitored. The Acute mode of operation allows the clinician or dialysis technician to enter prescription parameters and machine operating parameters for each patient. The Allient System incorporates a Graphical User Interface (GUI) comprised of a touch-screen display, which controls the System software. The GUI is used to select the mode of operation of the Allient System and enter prescription data and machine control parameters during setup. This information is stored for future reference and verification prior to subsequent treatments. Treatment status and progress, in addition to machine status, is continually collected and displayed on the GUI screen to support treatment. The GUI's touch-screen technology also provides ease of use for Home patients. The Allient System incorporates a control system that contains a number of safety features and audible and visible alert and alarm functions to warn the operator or patient of unsafe conditions.

The provided document describes the "Allient® Sorbent Hemodialysis System" and its substantial equivalence to a predicate device, the REDY 2000. It focuses on the device's specifications and compliance with various domestic and international standards, rather than a clinical study with acceptance criteria in the typical sense of accuracy, sensitivity, or specificity for a diagnostic or AI-driven device.

However, I can extract the relevant information from the document to construct an answer regarding acceptance criteria based on performance specifications and the study that "proves" (or verifies, in this context) the device meets them.

Acceptance Criteria and Device Performance based on provided specifications:

1. Table of Acceptance Criteria and Reported Device Performance

For a medical device like a hemodialysis system, "acceptance criteria" are more about meeting technical specifications and safety standards rather than diagnostic performance metrics (like sensitivity/specificity). The document details various operating parameters, flow rates, and safety features as the de facto acceptance criteria. The "reported device performance" is implicitly stated by saying the system "meets its specifications" and various standards.

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

The document does not explicitly state a "sample size" for a test set in the traditional sense of a clinical trial with patient data. The "testing" referred to is engineering verification and validation against technical specifications and recognized standards. This typically involves testing multiple units of the device and its components in a controlled laboratory environment.

• Test Set Sample Size: Not specified as a number of patients or cases. It would refer to the number of devices or components tested.
• Data Provenance: The testing is internal (by Renal Solutions Inc.) for verification and validation against engineering specifications and international standards (e.g., IEC, ISO, AAMI). This is a technical validation, not clinical data provenance.

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

This concept is not applicable to the type of device and study described. For a hemodialysis machine, the "ground truth" is defined by the physical laws of operation and the engineering specifications that ensure safety and effectiveness. Experts (e.g., engineers, quality control personnel) would be involved in designing, measuring, and verifying these specifications against established benchmarks and regulatory requirements. There is no "ground truth" established by clinical experts reading or interpreting output in the way one would for an AI-driven diagnostic device.

4. Adjudication Method for the Test Set

This concept is not applicable. Adjudication methods (like 2+1, 3+1) are used in clinical trials or studies where there is subjective interpretation (e.g., image reading) and a need to resolve disagreements among multiple experts to establish a definitive ground truth. For the Allient System, performance is measured against objective, quantifiable engineering specifications.

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

No, an MRMC comparative effectiveness study was not done, and the document does not mention any clinical trials comparing human performance with and without AI assistance. This type of study is typically for evaluating diagnostic accuracy or decision support systems, which the Allient System is not.

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

The Allient System is a physical medical device, not an algorithm or AI system. Its performance is inherent in its electromechanical and chemical operations. Therefore, the concept of "standalone" performance for an algorithm is not applicable here. Its operation is standalone in the sense that it performs its function (dialysis) according to its design.

7. The Type of Ground Truth Used

The "ground truth" for the Allient System is based on:

• Engineering Specifications: Quantifiable parameters and tolerances for flow rates, temperatures, leak detection, etc.
• Compliance with Recognized Standards: Adherence to established domestic and international standards for medical devices (e.g., ANSI/AAMI, IEC, ISO) which define safety, electrical, biological, and sterilization requirements.
• Predicate Device Performance: The predicate device, REDY 2000, serves as a benchmark for "substantial equivalency," implying its established safety and effectiveness forms part of the "ground truth" or acceptable performance standard.

8. The Sample Size for the Training Set

This concept is not applicable. The Allient System is not an AI/ML algorithm that requires a "training set" of data. Its design and operational parameters are determined through engineering principles, bench testing, and adherence to established medical device standards.

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

This concept is not applicable as there is no "training set" for this type of medical device. The "ground truth" for its design and verification is established through a combination of engineering design principles, regulatory requirements, and established industry standards for hemodialysis systems.

Ask a specific question about this device

The SORB+ and HISORB+ Cartridges are to be used only with Renal Solutions' REDY Sorbant Dialysis systems for the treatment of acute and chronic uremic patients where hemodialysis is prescribed by the physician.

Sorbent (or regenerative) dialysis systems use the chemical action of a sorbent cartridge to remove urea and other waste materials from the dialysate and return the fresh dialysate to the dialysate holding tank. This fresh dialysate then passes through a dialyzer, removes additional waste material, and re-circulates through the sorbent cartridge to continue the process. This contrasts to traditional "single pass" dialysis, which uses purified water passing across the dialysate side of a dializer membrane in a single flow-through system to remove urea and other waste materials from the dialysis patient's bloodstream. Wastewater is routed to a drain and not recirculated. By re-circulating and refreshing the dialysate, the Renal Solutions' REDY System uses 6L of water per dialysis treatment. A traditional single pass dialysis system uses at least 120L of purified water during the typical 4 hour dialysis session.

The SORB+ and HISORB+ Cartridges are intended to be used in a Renal Solutions REDY Sorbent Hemodialysis System as the chemical agents that absorb the urea and other waste material from the dialysate stream.

Here's an analysis of the provided text to extract the acceptance criteria and study information:

Acceptance Criteria and Device Performance Study for SORB+ and HISORB+ Cartridges

This document describes the 510(k) summary for the SORB+ and HISORB+ Cartridges, which are sorbent-regenerated dialysate delivery systems for hemodialysis. The focus is on demonstrating substantial equivalence to predicate devices (K811170 - SORB 3160 and K812869 - HISORB 3260).

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly list "acceptance criteria" with quantitative targets for each test, but rather states that the device "Pass"ed the tests by conforming to specified standards or predicate device performance. The de facto acceptance criterion for each test was a "Pass" result, indicating conformance.

2. Sample Size for the Test Set and Data Provenance

The document does not specify exact sample sizes for the "test set" (i.e., the number of cartridges tested for each validation). It mentions "various weights [of REDY Chem™ dialysate] used individually and in combination" which hints at a testing regime, but no specific numbers.

The studies were in-vitro testing and "simulated patient use conditions." This suggests the tests were laboratory-based, not involving human patients directly. The provenance is not explicitly stated as retrospective or prospective due to the nature of the in-vitro testing. It would be considered prospective for the specific in-vitro tests conducted. There's no indication of country of origin for the data provided in this summary, but the submitter's address is in Oklahoma City, USA.

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

This type of information is generally not applicable to the validation of a medical device like a sorbent cartridge, which relies on chemical and physical performance measurements rather than expert interpretation of images or clinical outcomes. The "ground truth" would be established by objective measurements against predefined chemical and physical standards or specifications, rather than expert consensus.

4. Adjudication Method for the Test Set

Adjudication methods (e.g., 2+1, 3+1) are typically used in studies involving human interpretation or clinical events requiring consensus. For these device performance tests, the outcome is objective (e.g., meeting a chemical purity threshold, acceptable biocompatibility levels). Therefore, no adjudication method as described would be relevant or used in these validation tests. The results would be a direct measurement against a standard.

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

No MRMC comparative effectiveness study was done as this device is not an AI diagnostic tool and does not involve human readers for interpretation. The device's performance is measured directly (e.g., chemical capacity, purification levels).

6. Standalone Performance Study (Algorithm Only Without Human-in-the-Loop Performance)

This question is not applicable in the context of this device. The device itself is a cartridge, not an algorithm. Its performance is inherently standalone (i.e., the cartridge's chemical and physical function) in that it performs its intended function independently of direct human intervention during the purification process. The "human-in-the-loop" would be the physician prescribing its use and monitoring the patient, but not directly interacting with the cartridge's internal chemical processes. The validation tests (e.g., capacity, biocompatibility) directly assessed the cartridge's standalone performance.

7. The Type of Ground Truth Used

The ground truth used for these tests was primarily:

• Objective Chemical and Physical Standards: Conformance to AAMI/ANSI standards for water purity, endotoxin/bacteria removal.
• Biocompatibility Standards: Conformance to ISO 10993.
• Manufacturer's Published Specifications: Sorb Technologies' published capacity specifications for urea-nitrogen removal.
• Predicate Device Performance: Comparison to the performance of the previously cleared SORB and HISORB Cartridges.

8. The Sample Size for the Training Set

This concept is not applicable. The device is a physical product (sorbent cartridge), not a machine learning model that requires a "training set." The development of the cartridges would have involved R&D, but the validation described herein does not fit the training/testing paradigm of AI/ML.

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

As noted above, the concept of a "training set" is not applicable for this type of device.

Ask a specific question about this device

Ask a specific question about this device