Search Results

The Tablo® Hemodialysis System and TabloCart™ is indicated for use in patients with acute and/or chronic renal failure, with or without ultration, in an acute or chronic care facility. Treatments must be administered under physician's prescription and observed by a trained individual who is considered competent in the use of the Tablo Hemodialysis System is also indicated for use in the home. Treatment types available include Intermittent Hemodialysis (IHD), Sustained Low Efficiency Dialysis (SLED/ SLEDD), Prolonged Intermittent Renal Replacement Therapy (PIRRT), and Isolated Ultrafiltration.

The Tablo® Hemodialysis System is a self-contained hemodialysis system intended for acute and chronic dialysis therapy, with or without ultrafiltration, in an acute, chronic care facility or in the home. The Tablo Hemodialysis System consists of: Tablo Console and Software, Tablo Cartridge. The TabloCart™ is an optional accessory to the Tablo Hemodialysis System that raises the height of the Tablo console and includes larger wheels that rotate and lock in more functional directions than the Tablo console without a cart, aiding in overall system mobility. When configured with a Prefiltration Drawer, the cart has replaceable, large-capacity cartridge filters (sediment and/or carbon) that serve as "prefilters" to help remove major sediment and chlorine/chloramines from supply water before it enters the Tablo console's water purification system. The cart with prefiltration also includes backflow prevention and a booster pump to transport water from the incoming water supply to the Tablo console. The TabloCart with Prefiltration Drawer consists of: Tablo Cart Wheeled Platform, Fluidics Drawer and Software.

The provided document is an FDA 510(k) Premarket Notification review letter for the Tablo® Hemodialysis System; TabloCart™ with Prefiltration Drawer (K232776). This document primarily focuses on demonstrating substantial equivalence to a predicate device (Tablo Hemodialysis System, K223248) rather than detailing specific acceptance criteria and a study proving the device meets those criteria in the context of device performance metrics (e.g., accuracy, sensitivity, specificity for an AI/algorithm-based device).

The "acceptance criteria" and "study that proves the device meets the acceptance criteria" as requested in the prompt typically refer to a device's performance against predefined metrics (e.g., clinical accuracy, diagnostic performance, or a specific functional output) which are common for AI/algorithm-based devices. However, the Tablo Hemodialysis System and its accessory cart are not an AI/algorithm-based device in the common sense (e.g., for image analysis or disease diagnosis). Instead, it's a medical device for renal replacement therapy, and the 510(k) submission focuses on demonstrating that the new accessory (the cart with prefiltration) does not alter the fundamental safety and effectiveness of the existing, cleared hemodialysis system.

Therefore, many of the specific questions in the prompt (e.g., sample size for test/training sets, number/qualifications of experts, adjudication methods, MRMC studies, standalone performance, type of ground truth) are not applicable to this type of device and submission. The "study" proving acceptance criteria here is primarily a series of bench performance tests, biocompatibility testing, electromagnetic compatibility (EMC) and electrical safety testing, and software verification and validation testing to confirm that the addition of the cart does not negatively impact the established safety and performance of the base hemodialysis system.

Here's an attempt to address the prompt based on the available information, highlighting what is applicable and what is not:

Acceptance Criteria and Study Proving Device Meets Acceptance Criteria for the Tablo® Hemodialysis System with TabloCart™ with Prefiltration Drawer (K232776)

Given that this 510(k) submission is for an accessory cart to an already cleared hemodialysis system, the "acceptance criteria" revolve around demonstrating that the modified device (system with cart) maintains the same safety and effectiveness as the predicate device (system without cart). The "study" is a compilation of various engineering and performance tests rather than a single clinical trial or AI validation study.

1. Table of Acceptance Criteria and Reported Device Performance

For this type of device and submission, the acceptance criteria are largely implied by demonstrating substantial equivalence to the predicate device. They are not typically laid out as quantitative performance metrics (like accuracy or sensitivity) as would be for an AI diagnostic device. Instead, they relate to maintaining fundamental safety, performance, and functionality.

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

• Not applicable in the context of typical AI/algorithm test sets. The "test set" here refers to the physical device and its components undergoing engineering and functional verification.
• Data Provenance: The testing was conducted by the manufacturer, Outset Medical, Inc., presumably in their facilities (San Jose, CA, USA). The studies are prospective in the sense that they were designed and executed specifically to support this 510(k) submission for the modified device.

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

• Not applicable. This is not an AI/diagnostic device where expert consensus defines a "ground truth" for disease states in a dataset. "Ground truth" for this device is based on engineering specifications, physical measurements, chemical analysis (for water purity), and functional performance verification against design requirements. The "experts" involved would be engineers, quality control personnel, and regulatory specialists within Outset Medical, Inc.

4. Adjudication method for the test set:

• Not applicable. Adjudication methods (like 2+1, 3+1) are for resolving discrepancies in expert interpretations of data (e.g., medical images). For engineering tests, results are typically objective measurements or pass/fail criteria based on predefined specifications.

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 is not an AI-assisted diagnostic device, so MRMC studies are irrelevant.

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

• Not applicable. This device is a physical hemodialysis system with an accessory, not a standalone algorithm.

7. The type of ground truth used:

• Engineering Specifications and Physical/Chemical Standards: For example, the ground truth for water quality would be established by relevant water quality standards for hemodialysis (e.g., AAMI standards). For mechanical aspects, it would be the design specifications (dimensions, mobility, filter capacity). For software, it would be the functional requirements and safety standards.

8. The sample size for the training set:

• Not applicable. This refers to machine learning models, which is not what this device is.

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

• Not applicable. See point 8.

Ask a specific question about this device

The Tablo® Hemodialysis System is indicated for use in patients with acute and/or chronic renal failure, with or without ultrafiltration, in an acute or chronic care facility. Treatments must be administered under physician's prescription and observed by a trained individual who is considered competent in the use of the device. The Tablo Hemodialysis System is also indicated for use in the home. Treatment types available include Intermittent Hemodialysis (IHD), Sustained Low Efficiency Dialysis (SLED/ SLEDD), Prolonged Intermittent Renal Replacement Therapy (PIRRT), and Isolated Ultrafiltration.

The Tablo Hemodialysis System is a self-contained hemodialysis system intended for acute and chronic dialysis therapy, with or without ultrafiltration, in an acute, chronic care facility or in the home. The Tablo Hemodialysis System consist of:

1. Tablo Console
2. Tablo Cartridge

This appears to be a 510(k) summary for a medical device (Tablo Hemodialysis System) that has undergone a modification. The document states that the device has been found substantially equivalent to its predicate device (Tablo Hemodialysis System, K223248), specifically due to changes in the hydraulic material.

Crucially, this document is NOT a study report for a novel AI device or a device that required extensive clinical or human factors validation for its primary function. The modifications were related to material changes in the hydraulics, and the FDA determined that these changes did not impact the device's fundamental performance, safety, or effectiveness. Therefore, many of the typical acceptance criteria and study components you've listed for AI/human-in-the-loop devices are not applicable or were explicitly deemed unnecessary in this context.

I will address the questions based on the information provided, explicitly stating when a piece of information is not available or relevant to this specific submission.

Here's an analysis of the provided text in relation to your questions:

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

The document doesn't provide a direct "acceptance criteria" table in the format typically seen for novel device performance or AI algorithms. Instead, the acceptance criteria for this submission revolve around demonstrating substantial equivalence to the predicate device despite the hydraulic material changes. Performance was demonstrated through various non-clinical tests to confirm the new materials didn't negatively impact the established performance of the device.

Since this submission is about material changes validated through bench testing, the "performance" is about maintaining the original specifications rather than achieving a new performance threshold.

• Dialysate Temperature Accuracy
• Fluid Removal Accuracy
• Chemical Disinfection
• Heat Disinfection
• Related Alarms |
  | Human Factors/Usability: No negative impact on usability. | Modifications to hydraulics do not impact usability. No new Human Factors validation study deemed necessary. |
  | Clinical Performance: No need for new clinical studies. | No clinical studies were conducted as the changes were deemed not to require them for substantial equivalence. |

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

This document describes bench testing, biocompatibility testing, electrical safety/EMC analysis, and software/human factors assessments for a modification to an existing device. It's not a typical "test set" in the sense of a dataset for an AI algorithm or a patient cohort for a clinical trial.

• Sample Size for Bench Testing/Biocompatibility: The specific sample sizes for each type of bench test (e.g., number of units tested for dialysate temperature accuracy, number of samples for biocompatibility) are not provided in this 510(k) summary. These details would be in the full submission, but not in this public summary.
• Data Provenance: Not applicable in the context of patient data provenance for a test set. The tests described are laboratory-based and engineering assessments.

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. Ground truth, expert consensus, or clinical interpretation by medical experts are not detailed because this submission is about physical/material modificationsvalidated through non-clinical testing, not diagnostic performance or clinical outcomes directly assessed by experts interpreting data.

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

This is not applicable. Adjudication methods are typically used in studies where human readers or interpreters are involved in generating or confirming ground truth, such as in imaging studies. This document concerns engineering and material changes validated through bench testing.

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, an MRMC study was not conducted. This submission is for modifications to a hemodialysis system, not an AI-powered diagnostic or assistive tool where human reader performance would be a relevant metric. The document explicitly states "No clinical studies were conducted."

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

Not applicable in the context of an AI algorithm. The device is a hemodialysis system, not an AI algorithm. Its performance is inherent to its mechanical, electrical, and material properties.

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

The "ground truth" in this context refers to the established performance specifications and safety profiles of the predicate device (K223248) and the relevant regulatory standards (e.g., ISO 10993-1, FDA guidance for hemodialysis delivery systems). The studies conducted (bench testing, biocompatibility) aim to demonstrate that the modified device continues to meet these established performance and safety requirements.

8. The sample size for the training set

Not applicable. This is not an AI/machine learning device that requires a training set.

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

Not applicable. As above, this is not an AI/machine learning device.

Ask a specific question about this device

The Tablo® Hemodialysis System is indicated for use in patients with acute and/or chronic renal failure, with or without ultrafiltration, in an acute or chronic care facility. Treatments must be administered under physician's prescription and observed by a trained individual who is considered competent in the use of the device. The Tablo Hemodialysis System is also indicated for use in the home. Treatment types available include Intermittent Hemodialysis (IHD), Sustained Low Efficiency Dialysis (SLED/ SLEDD), Prolonged Intermittent Renal Replacement Therapy (PIRRT), and Isolated Ultrafiltration.

The Tablo Hemodialysis System is a self-contained hemodialysis system intended for acute and chronic dialysis therapy, with or without ultrafiltration, in an acute, chronic care facility or in the home. The Tablo Hemodialysis System consist of:

1. Tablo Console
2. Tablo Cartridge

The provided document is a 510(k) summary for the Tablo® Hemodialysis System, specifically for a new software version. This document focuses on demonstrating substantial equivalence to a predicate device (K211370), rather than a study defining acceptance criteria for AI or a detailed performance study as would be required for a novel AI device.

Therefore, the requested information regarding "acceptance criteria and the study that proves the device meets the acceptance criteria" in the context of AI performance metrics (like sensitivity, specificity, etc.) is not directly applicable to this document. The document primarily discusses verification and validation of software changes and bench performance testing to support the extension of treatment duration.

However, I can extract the relevant information from the document regarding the device's performance data and the types of studies conducted to support its substantial equivalence.

Here's a breakdown based on the provided text, reinterpreting "acceptance criteria" as the deemed "substantial equivalence" established through various tests:

1. Table of Acceptance Criteria and Reported Device Performance

As this is a 510(k) for a software update to an existing device, the "acceptance criteria" are implicitly tied to maintaining or improving the safety and effectiveness of the device as cleared under the predicate (K211370) and extending the treatment duration. The "reported device performance" is primarily about the successful completion of various tests to demonstrate this.

Information not directly applicable or available from the provided text, as it relates to AI-specific studies:

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 as the document describes a 510(k) for a software update to a hemodialysis system, not an AI/ML device with a distinct "test set" in the context of an algorithm's performance. The "test set" would implicitly be the entire system undergoing the verification and validation processes.

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 to the type of device and study described. Ground truth in this context would be defined by engineering specifications, regulatory standards, and established medical safe use practices for hemodialysis machines.

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

• Not applicable, as there's no "ground truth" derived from expert consensus for an AI algorithm's output.

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 conducted. This device is a hemodialysis system, not an imaging or diagnostic AI tool. The "Human Factors validation data" mentioned relates to the usability and safety of the system's interface for operators, not to AI-assisted interpretation by human readers.

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

• Standalone performance in the AI sense is not explicitly discussed. The device itself (Tablo Hemodialysis System) performs its function either autonomously or with user interaction, but it's not described as an AI algorithm in the context of image analysis or diagnostic support. The software performance here refers to the operating system controlling the device's functions.

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

• The "ground truth" for the performance of the hemodialysis system software and hardware would be based on engineering specifications, adherence to ISO/IEC standards, regulatory requirements, and safe operational parameters for dialysis treatment. For the extended 24-hour treatment capability, the ground truth would be the ability to maintain specified performance (e.g., fluid removal, solute clearance, alarm responsiveness) over that duration without compromise to safety.

8. The sample size for the training set

• This information is not applicable to a traditional software update for a hemodialysis machine. "Training set" typically refers to data used to train AI/ML models, which is not the subject of this 510(k). Verification and validation are performed against requirements, not a "training set" in the AI sense.

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

• Not applicable, see point 8.

Ask a specific question about this device

The Tablo® Hemodialysis System is indicated for use in patients with acute and/or chronic renal failure, with or without ultrafiltration, in an acute or chronic care facility. Treatments must be administered under physician's prescription and observed by a trained individual who is considered competent in the use of the Tablo Hemodialysis System is also indicated for use in the home.

The Tablo Hemodialysis System is a self-contained hemodialysis system intended for acute and chronic dialysis therapy, with or without ultrafiltration, in an acute or chronic care facility or in the home. The device includes the:

• Tablo Console, a single module consisting of multiple fluidic systems that perform the activities of a water purification system (WPS) and a conventional dialysis delivery system (DDS), and
• Table Cartridge

The provided text is a 510(k) premarket notification summary for the Tablo® Hemodialysis System (software version 4.8). This document primarily focuses on demonstrating substantial equivalence to a predicate device, rather than presenting a detailed clinical study for a new device requiring a comprehensive performance evaluation against defined acceptance criteria.

Therefore, the information required to answer your specific questions about acceptance criteria and study details (like sample size, number of experts, adjudication methods, MRMC studies, standalone performance, ground truth types, and training set information for an AI/software device) is not present in this type of FDA submission.

This document describes a software update (version 4.8) to an existing hemodialysis system. The performance data provided is limited to bench testing, biocompatibility, electrical safety, and software verification and validation testing. The software is considered "major" level of concern, and verification and validation were conducted. However, the document does not detail specific acceptance criteria for performance metrics that would be relevant to an AI/ML-driven diagnostic device.

Here's an attempt to answer based on the limited information available in the provided text:

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

The document provides very high-level acceptance criteria for specific non-clinical tests, rather than detailed performance metrics for an AI/ML system.

For an AI/ML device, you would expect detailed performance metrics like sensitivity, specificity, AUC, F1-score, etc., with associated acceptance thresholds for "Pass." This is not present here.

2. Sample sized 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 as it is not a clinical study on patient data for an AI/ML diagnostic. The software V&V would involve testing against various scenarios and inputs, but the "sample size" in the context of patient data for AI model evaluation is not applicable here.

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. Ground truth establishment by experts is relevant for diagnostic AI/ML systems where human-annotated data is used for evaluation. This document describes a software update for a hemodialysis system, not an AI diagnostic.

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

This information is not provided, as it pertains to expert consensus on ground truth in studies of diagnostic AI/ML systems.

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 conducted or reported. The document explicitly states: "No clinical studies were conducted to support the modified device." MRMC studies are typically performed for diagnostic AI/ML tools to assess their impact on human reader performance.

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

While "Software Verification and Validation Testing" was conducted, the document does not specify standalone algorithm performance in terms of diagnostic metrics. It only states that the testing "passed" and "supports safety and effectiveness." The software's function is to control a hemodialysis system, not to perform a standalone diagnostic task.

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

This information is not provided. Ground truth in the context of this device's software V&V would relate to the correct functional behavior of the system under various conditions, not diagnostic outcomes based on expert consensus, pathology, or outcomes data.

8. The sample size for the training set

This information is not provided. Training set details are relevant for AI/ML model development. This document is about a software update for a medical device's control system, not the development of a predictive AI model.

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

This information is not provided. As above, this is relevant for AI/ML model training, which is not the focus of this 510(k) submission.

In summary: The provided document is an FDA 510(k) clearance letter and summary for a software update to an existing hemodialysis system. It demonstrates substantial equivalence to a predicate device through non-clinical testing and verification/validation of software changes. It does not contain the detailed performance study information, particularly for AI/ML-driven diagnostics, that your questions are designed to elicit. The "acceptance criteria" presented are for general device performance and regulatory compliance, not for algorithmic diagnostic accuracy.

Ask a specific question about this device

The Tablo Cartridge is a single use, disposable arterial and venous bloodline set intended to provide extra-corporeal access during hemodialysis. The Tablo Cartridge is compatible only with the Tablo Hemodialysis System.

The Tablo Cartridge is a single use blood tubing set attached to an organizer tray. The E-beam sterilized and disposable cartridge is inserted onto the front panel of the console for each dialysis treatment.

The provided document is a 510(k) summary for the Tablo Cartridge, a medical device used in hemodialysis. It outlines the performance data submitted to the FDA to demonstrate substantial equivalence to a predicate device. However, this document does not describe a study involving an AI/machine learning device, nor does it detail acceptance criteria and a study proving an AI device's performance in the way implied by the prompt's structured questions.

Specifically, the device in question is a physical "blood tubing set" for hemodialysis, and the changes discussed are related to manufacturing processes (sterilization method) and minor design improvements. The "performance data" refers to validation tests for sterilization, shelf-life, biocompatibility, and bench performance of the physical cartridge, not the performance metrics of an AI algorithm.

Therefore, many of the questions asked in the prompt, such as "Number of experts used to establish the ground truth for the test set," "Adjudication method," "MRMC comparative effectiveness study," "standalone (i.e. algorithm only without human-in-the-loop performance)," and "How the ground truth for the training set was established," are not applicable to the information provided in this 510(k) summary.

Based on the provided document, here's what can be extracted, acknowledging that it does not fit the typical AI/ML device study format requested:

Device: Tablo® Cartridge (Hemodialysis blood tubing set)
Nature of Submission: 510(k) for a modified device (change in sterilization method from Ethylene Oxide (EO) gas to E-beam radiation, and minor design changes).

Given the nature of the device and the modification, the "acceptance criteria" and "study proving the device meets the acceptance criteria" are related to the safety and performance of the physical medical device and its manufacturing process, not an AI algorithm.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not present a single table with explicit "acceptance criteria" alongside "reported device performance" values in a quantitative, pass/fail format in terms of algorithm accuracy (e.g., sensitivity, specificity, AUC). Instead, it lists various types of tests conducted to ensure the device's safety and functionality after the modification. The acceptance criteria for these tests are implied to be compliance with relevant ISO standards, USP standards, and FDA guidance documents.

Overall Conclusion: "The Tablo Cartridge (Modified Device) is substantially equivalent to the Predicate Device, and the minor difference between the Modified and the Predicate Device do not raise any new or different questions of safety or effectiveness."

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

• Sample Size: Not explicitly stated numerically (e.g., number of cartridges tested). For sterilization validation, often a statistically significant sample size based on standards like ISO 11137 is used, but the exact number isn't provided here. The same applies to shelf-life and bench performance testing.
• Data Provenance: Not specified regarding country of origin or whether it was retrospective/prospective. This is typical for device performance testing performed by the manufacturer, rather than clinical trial data.

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

• Not Applicable. This is not an AI/imaging device requiring expert interpretation for ground truth. The "ground truth" for this device would be objective measurements and laboratory test results demonstrating physical, chemical, and biological properties.

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

• Not Applicable. There's no human interpretation or subjective assessment 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:

• No. This is a physical medical device, not an AI/ML algorithm that assists human readers.

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

• Not Applicable. This is a physical medical device.

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

• For this device, the "ground truth" is established through objective laboratory testing, established chemical/biological assays, and physical performance measurements against predefined specifications and internationally recognized standards (e.g., ISO, USP). It's based on empirical measurements of device properties rather than human diagnostic interpretation.

8. The sample size for the training set:

• Not Applicable. There is no "training set" as this is not an AI/ML model.

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

• Not Applicable. There is no "training set" or corresponding ground truth establishment process in the context of AI/ML.

Ask a specific question about this device

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

The Tablo Hemodialysis System is a self-contained hemodialysis system intended for acute and chronic dialysis therapy, with or without ultrafiltration, in an acute or chronic care facility. This premarket notification is an indication expansion to include home use of the device. The product described in this submission includes:

• . Tablo Console, a single module consisting of multiple fluidic systems that perform the activities of a water purification system (WPS) and a conventional dialysis delivery system (DDS), and
• . The following accessories/components
  • Tablo Script (optional accessory software) o
  • Tablo Straws O
  • O Outset Acid Concentrate 1K, 2K and 3K
  • Outset Bicarbonate Concentrate O
  • Patient USB Stick O
• Hand Crank O
• O Locking Power Cord
• Drain Line O
• O Water Line
• Disinfectant Straw O

Here's an analysis of the acceptance criteria and supporting studies for the Tablo Hemodialysis System, based on the provided FDA 510(k) summary:

The document describes the acceptance criteria and performance for several bench performance tests and mentions a clinical study to support the device's substantial equivalence and expanded indication for home use.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Bench Performance Tests: No specific sample sizes (e.g., number of units tested) are provided for these tests within the summary.
• Clinical Study: No specific sample size (number of patients) is explicitly stated in the summary.
• Data Provenance: The clinical study is described as a "prospective, multicenter, open label, non-randomized, cross-over study." This indicates the data was collected prospectively from multiple clinical sites. The country of origin is not specified but is implicitly the US, given the FDA submission context.

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

• Bench Performance Tests: Not applicable. Ground truth for these tests is based on established engineering and regulatory standards (e.g., AAMI, USP, FDA guidance).
• Clinical Study: Not applicable in the traditional sense of expert consensus on image interpretation. The "ground truth" for the clinical study involved direct measurement of patient outcomes (adverse events, Kt/V, ultrafiltration) which are objective physiological parameters.

4. Adjudication Method for the Test Set

• Bench Performance Tests: Not applicable. These are objective tests against defined physical or chemical standards.
• Clinical Study: Not explicitly stated. For clinical trial outcome measures like adverse events and adequacy, typically events are recorded as they occur and then reviewed by study investigators and/or an independent data safety monitoring board.

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

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This type of study is typically used for diagnostic imaging devices where human readers interpret medical images. The Tablo Hemodialysis System is a medical device for therapy, not diagnosis.

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

A "standalone" performance evaluation in the context of an AI algorithm is not applicable here. The Tablo Hemodialysis System is a physical medical device that interacts directly with patients, albeit with software control. Its performance is evaluated through its direct physical and physiological effects, not through an algorithm's interpretive ability. The software reliability improvements mentioned refer to the device's operational software, not an AI diagnostic algorithm.

7. Type of Ground Truth Used

• Bench Performance Tests: Regulatory and engineering standards (e.g., ANSI/AAMI, USP, FDA guidance for reprocessing).
• Clinical Study: Objective physiological measurements of patient outcomes:
  • Safety: Adverse event rates.
  • Adequacy: Weekly standardized Kt/V (a measure of dialysis efficacy).
  • Ultrafiltration: Achievement of ultrafiltration goals.

8. Sample Size for the Training Set

• Software Verification and Validation: No specific sample size (e.g., lines of code, test cases) is provided for the "training set" of the software. Instead, the summary states that "Software verification and validation testing were conducted and passed for the incremental software changes," following FDA guidance for "major" level of concern software. This implies a comprehensive testing process, but not a "training set" in the machine learning sense.
• Clinical Study: Not applicable; the clinical study evaluated the device's performance, it did not "train" a model.

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

• Software Verification and Validation: Not applicable in the context of a machine learning "training set." The "ground truth" for software validation would be the defined functional and non-functional requirements and specifications against which the software's behavior is tested.
• Clinical Study: Not applicable.

Ask a specific question about this device

The Tablo® Hemodialysis System is indicated for use in patients with acute and/or chronic renal failure, with or without ultrafiltration, in an acute or chronic care facility. Treatments must be administered under physician's prescription, with a trained individual available as needed who is considered competent in the use of the prescribing physician.

The Tablo® Cartridge is a single use, disposable arterial and venous bloodline set intended to provide extra-corporeal access during hemodialysis. The Tablo Cartridge is compatible only with the Tablo Hemodialysis System.

The Tablo Hemodialysis System is a self-contained hemodialysis system intended for acute and chronic dialysis therapy, with or without ultrafiltration, in an acute or chronic care facility. The system's innovative design includes the:

• . Tablo Console, a single module consisting of multiple fluidic systems that perform the activities of a water purification system (WPS) and a conventional dialysis delivery system (DDS), and
• Tablo Cartridge, a single use blood tubing set attached to an organizer tray. The ethylene oxide (EO) sterilized and disposable cartridge is inserted onto the front panel of the console for each dialysis treatment (Figure 1).
• . Tablo Script, an accessory software to the Tablo Console, is designed for use by medical professionals to a) prepare, update and verify patient dialysis prescriptions b) view and export dialysis treatment information and billing activities and c) set and modify Tablo Console settings. Note: Tablo Script is optional, patient prescriptions can still be created or changed directly on the Tablo Console.

Here's a breakdown of the acceptance criteria and study findings for the Tablo Hemodialysis System and Tablo Cartridge, based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

• Water from the Post RO sample port meets ISO 23500 electrolyte concentration limits when prepared from water with hardness of 150 mg/L. | Pass |
  | 17. Water Treatment System (Bench Performance Testing) | The system shall meet requirements for a water treatment system. | Pass |
  | 18. Dialysate flow and Conductivity Monitoring (Bench Performance Testing) | The system shall meet requirements for dialysate flow, temperature, volume, and conductivity monitoring. | Pass |
  | 19. Air-In-Line (Bench Performance Testing) | The system shall meet requirements related to the system's purging and detection of air bubbles in the extracorporeal circuit. | Pass |
  | 20. Pre-Treatment Mode (Bench Performance Testing) | The system shall meet requirements for pre-treatment mode. | Pass |
  | 21. Post-Treatment Mode (Bench Performance Testing) | The system shall meet requirements for post-treatment mode. | Pass |
  | 22. Blood Pump and Pinch Valve Control, and Saline Delivery Performance (Bench Performance Testing) | The system shall meet requirements for operation, performance, and control of the peristaltic blood pump. | Pass |
  | 23. Heat Disinfection Mode (Bench Performance Testing) | The system shall meet requirements for heat disinfection mode. | Pass |
  | 24. Chemical Disinfection Mode (Bench Performance Testing) | The system shall meet requirements for chemical disinfection mode. | Pass |
  | 25. Ultrafiltration Accuracy (Bench Performance Testing) | The system shall provide a treatment fluid removal accuracy of +/- 100 mL per hour of the treatment time. | Pass |
  | 26. Maintenance and Service User (Bench Performance Testing) | The system shall meet requirements for maintenance and service user. | Pass |
  | 27. Maintenance and Service User (Mock Treatments) (Bench Performance Testing) | The system shall allow the user to run mock treatments in Service Interface without the need of a Patient USB. | Pass |
  | 28. Heat and Chemical Disinfection Effectiveness (Bench Performance Testing) | Disinfection validation was performed on n=3 consoles per organism, totaling n=6 consoles to demonstrate that chemical and heat disinfection cycles reduce vegetative bacterial species (e.g., Pseudomonas aeruginosa) by six logs and non-tuberculous Mycobacterium species (e.g., Mycobacterium terrae) by three logs. | Pass |
  | 29. External Disinfectant Chemical Compatibility Testing (IEC 60601-2-16 Test) (Bench Performance Testing) | The system and its accessories shall be capable of withstanding daily cleaning, using specified chemicals (70% Isopropyl Alcohol, 10% bleach, PDI Super Sani Cloth Germicidal Wipes, CaviWipes, CaviWipes1 Disinfecting Wipe, Oxivir 5, Oxivir TB Wipes) over the service life of the device per the chemical manufacturer instructions. | Pass |
  | 30. Bring Your Own Concentrate Conductivity Test (Bench Performance Testing) | The system shall be compatible with dialysis fluid concentrates intended for a 45X-proportioning ratio. When mixed at a 45X ratio, the acid concentrate should comply with the following labeled formulation range: Sodium 100 mEq/L, Potassium 0 - 4 mEq/L, Calcium 0 - 3.5 mEq/L, Acetate 4 mEq/L. | Pass |
  | 31. Human Factors Validation (Bench Performance Testing) | The system shall be assessed for usability with representative users (i.e., nurses and patient care technicians in clinical settings and acute-care facilities) in accordance with its intended use/indications for use. | Pass |

The document states that "Non-clinical testing supports the safety and effectiveness of the Tablo Hemodialysis System and Tablo Cartridge. The bench testing demonstrates that the device systems comparably to the predicate device and is substantially equivalent to the legally marketed device." This implies that all listed acceptance criteria were met.

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

• Test Set Sample Size: The document does not explicitly state a general "test set" sample size for all performance tests. Specific sample sizes are mentioned for certain tests:
  • Shelf Life and Sterilization Testing: The specifics of how many cartridges were subjected to accelerated aging are not detailed, but it's implied that the testing was sufficient to justify a 12-month shelf life.
  • Heat and Chemical Disinfection Effectiveness: n=3 consoles per organism, totaling n=6 consoles for disinfection validation.
• Data Provenance: The data is from non-clinical bench performance testing and biocompatibility testing. It is not patient-derived data. The country of origin is not specified but implicitly refers to testing performed by or for Outset Medical, Inc., a U.S. company. The studies are prospective in the sense that they were designed and executed to evaluate the device.

3. Number of Experts and Qualifications for Ground Truth

• Ground Truth for Biocompatibility: Not applicable in the sense of expert consensus on qualitative data. The ground truth here is derived from standardized laboratory tests and their established pass/fail criteria (e.g., cytotoxicity, sensitization, hemocompatibility). Interpretation of these results would be done by qualified laboratory personnel and toxicologists. The specific number and qualifications are not detailed.
• Ground Truth for Performance Testing: Not applicable. Performance tests (e.g., flow rates, pressures, temperatures, disinfection efficacy, ultrafiltration accuracy) are measured against predefined engineering and regulatory specifications and standards (e.g., IEC standards, AAMI standards). The ground truth is the objective measurement comparing the device's output to these quantitative standards.
• Ground Truth for Human Factors Validation: The "ground truth" here is the assessment of usability in accordance with intended use. While representative users (nurses and patient care technicians) are involved, the document does not specify the number of experts (e.g., human factors engineers) who established the protocol or interpreted the findings, nor their specific qualifications.

4. Adjudication Method for the Test Set

The concept of an "adjudication method" (like 2+1, 3+1) typically applies to studies where human readers are interpreting ambiguous data (e.g., medical images, clinical diagnoses) and discrepancies need to be resolved. This is not applicable to the non-clinical, objective functional and safety performance tests described for the Tablo Hemodialysis System. The results are based on direct measurements and adherence to engineering and biological standards.

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

No. A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. This type of study typically evaluates the diagnostic performance or interpretative accuracy of humans (with or without AI assistance) on a set of cases. The studies presented are non-clinical engineering and safety performance tests of a medical device.

6. Standalone Performance Study (Algorithm Only)

The term "standalone" performance usually refers to the algorithm's performance without human intervention, particularly in the context of AI/software. While "Software Verification and Validation Testing" was performed for the Tablo system, the documentation doesn't describe it as an isolated algorithm performance study in the way an AI diagnostic tool would be evaluated. The software is an integrated component controlling the physical device, and its validation is part of the overall system's functional assessment. Therefore, a standalone algorithm performance study, as typically understood for AI, was not explicitly detailed as such.

7. Type of Ground Truth Used

The ground truth used for these studies is primarily:

• Established industry standards and regulatory guidelines: Examples include ISO 10993-7, ANSI/AAMI ST72, ES 60601-1, IEC 60601-2-16, ANSI/AAMI 13959:2014, ANSI/AAMI 11663:2014, and ISO 23500.
• Engineering specifications and design requirements: These define the expected performance of various components and the system as a whole (e.g., maximum power, dialyzer compatibility dimensions, ultrafiltration accuracy of +/- 100 mL/hr, specified concentrate parameters).
• Biological and chemical pass/fail criteria: For biocompatibility, sterilization, and disinfection effectiveness tests, which are based on scientific principles and regulatory limits.

There are no mentions of expert consensus, pathology, or outcomes data being directly used to establish the ground truth for these specific non-clinical tests.

8. Sample Size for the Training Set

Not applicable. This document describes the performance testing of a physical medical device (hemodialysis system and cartridge), not an AI algorithm that requires a "training set" of data. The software within the device underwent verification and validation, but this is distinct from machine learning model training.

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

Not applicable. As mentioned above, this is not an AI algorithm document where a training set and its ground truth would be relevant.

Ask a specific question about this device

The Tablo™ System is indicated for use in patients with acute and/or chronic renal failure, with or without ultrafiltration, in an acute or chronic care facility. Treatments must be administered under physician's prescription, with a trained individual available as needed who is considered competent in the use of the prescribing physician.

The Tablo™ Console is a self-contained hemodialysis system (Console) intended for acute and chronic dialysis therapy with or without ultrafiltration, in an acute or chronic care facility. The console consists of fluidic systems that perform the activities of a Water Purification System (WPS) and a conventional Dialysis Delivery System (DDS). Since the original 510(k) clearance, the Tablo Console has incorporated design and corresponding labeling updates whose purpose was to improve ease of manufacturing, increase reliability, simplify the design, and optimize performance.

This document is a 510(k) summary for the Tablo Console, a hemodialysis system. The primary purpose of this submission is to describe expanded wireless communication capabilities and other design updates.

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

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of "acceptance criteria" in the typical sense of quantitative thresholds for a specific diagnostic performance metric. Instead, it details various types of performance testing against established standards and internal requirements. The "reported device performance" is a general statement of compliance rather than specific numerical results.

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

The document does not specify a "test set" in the context of diagnostic performance involving patient data. The various tests performed (biocompatibility, electrical safety, EMC, software, system performance) would have used devices or components of the device as the test "samples." No information is provided regarding the specific number of devices tested for each type of engineering or software verification test.

Since no clinical studies were performed, there is no patient data, and therefore no information on country of origin or whether data was retrospective or prospective.

3. Number of Experts Used to Establish Ground Truth and Their Qualifications

Not applicable. This submission concerns device modifications and engineering verification, not a diagnostic algorithm requiring ground truth established by medical experts from patient data.

4. Adjudication Method

Not applicable, as there is no diagnostic algorithm performance evaluation against ground truth from patient data.

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

No. The document explicitly states: "No clinical studies were performed in support of the modifications." Therefore, no MRMC study or assessment of human reader improvement with AI assistance was conducted.

6. Standalone Performance Study

Yes, in a sense. The entire submission focuses on the standalone performance of the device and its modified components (hardware, software, wireless capabilities) against engineering and safety standards. There is no AI component that would have distinct "standalone algorithm performance" versus "human-in-the-loop performance." The device itself is the "algorithm" in terms of its operational functionality.

7. Type of Ground Truth Used

The "ground truth" for the various performance tests was based on:

• Established international and national standards (e.g., IEC 60601 series).
• Internal functional and performance requirements for software and system operation.
• Design specifications for hardware and fluidic systems.

8. Sample Size for the Training Set

Not applicable. This device is not an AI/ML algorithm that requires a training set of patient data. The "training" for the device would be its initial design, development, and iterative testing/refinement phases.

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

Not applicable, as there is no AI/ML training set in the context of this device. The "ground truth" for the device's design and functionality would stem from engineering principles, medical device regulatory requirements, and user needs for hemodialysis.

Ask a specific question about this device