Search Results

The t:slim® Insulin Delivery System is indicated for the subcutaneous delivery of insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin, for individuals 6 years of age and greater. The device is indicated for use with NovoLog® or Humalog® U-100 insulin.

The t:flex™ Insulin Delivery System is indicated for the subcutaneous delivery of insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin, for individuals 12 years of age and greater. The device is indicated for use with NovoLog® or Humalog® U-100 insulin.

The Tandem® Device Updater™ System consists of software which allows for communication between a computer and a t:slim® or t:flex™ Insulin Delivery System. It allows for remote software installation and update of a Tandem Insulin Delivery System.

The t:slim® and t:flex™ Insulin Delivery Systems facilitate the subcutaneous delivery of insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin.

The accessory Tandem Device Updater™ System is comprised of a personal computer application. a web server, an embedded firmware application, and a Tandem pump (t:slim or t:flex). The goal of the Tandem Device Updater System is to provide a secure process for software installation and update.

This document is regarding a 510(k) premarket notification for an insulin delivery system and its updater. It primarily focuses on demonstrating substantial equivalence to predicate devices, rather than presenting a study with specific acceptance criteria and detailed performance data in the typical sense of a diagnostic or screening device.

The "acceptance criteria" and "device performance" in this context are related to the regulatory process of demonstrating safety and effectiveness for substantial equivalence, particularly for software verification/validation and hardware changes.

Here's an attempt to extract and interpret the information based on the provided text, acknowledging that it's a regulatory submission for device changes and not a clinical study report for AI performance.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria with corresponding device performance metrics in a quantitative format typical for a diagnostic study. Instead, "acceptance criteria" are implied by successful completion of various verification and validation activities. The "reported device performance" is a statement that these tests were performed and supported substantial equivalence.

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

• Test Set Sample Size: Not explicitly stated for any specific test. The document refers to "testing" and "studies" but does not quantify the number of devices or participants used for each.
• Data Provenance: Not explicitly stated as country of origin. The studies were conducted by Tandem Diabetes Care, Inc. for submission to the FDA (USA). The nature of most tests described (software V&V, hardware verification, human factors) suggests a mix of in-house testing and possibly external human factors studies. The document does not specify if the human factors studies were prospective or retrospective, but typically, these are prospective.

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

There is no mention of "experts" in the context of establishing a ground truth for a test set, as this is not a diagnostic device relying on expert interpretation for its output. The "ground truth" for the device's function is its ability to correctly deliver insulin as programmed and function safely according to its specifications.

4. Adjudication Method for the Test Set

Not applicable. This is not a study requiring adjudication of expert interpretations or clinical outcomes.

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 an insulin delivery system and its updater, not an AI-assisted diagnostic or screening tool. Therefore, MRMC studies and "human reader improvement with AI" are not relevant to this submission.

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

The "Tandem® Device Updater™ System" consists of software, and "Software verification and validation testing" was performed. This implies standalone testing of the software component, although the details of such testing are not provided beyond the statement that it was done per FDA guidance. The insulin delivery systems themselves are hardware-software integrated devices, so "standalone" in the AI sense isn't directly applicable.

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

The ground truth for this device's performance is based on:

• Engineering Specifications: Successful operation within pre-defined hardware and software specifications.
• Safety Standards: Compliance with relevant safety standards (e.g., electrical safety, EMC, hazard analysis).
• User Performance: Demonstrated ability of users (including pediatric users) to safely and effectively interact with the device as assessed through human factors studies.
• Regulatory Guidance: Adherence to FDA guidance documents for infusion pumps and software V&V.

8. The Sample Size for the Training Set

Not applicable. This document describes a medical device undergoing 510(k) clearance, not a machine learning or AI model that typically requires a "training set" in the computational sense. The software is part of an embedded system, thoroughly tested for compliance with specifications, rather than "trained" on data.

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/ML model for this device's clearance.

Ask a specific question about this device

The t:slim® Insulin Delivery System is indicated for the subcutaneous delivery of insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin, for individuals 12 years of age and greater. The device is indicated for use with NovoLog or Humalog U-100 insulin.

The t:flex™ Insulin Delivery System is indicated for the subcutaneous delivery of insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin, for individuals 12 years of age and greater. The device is indicated for use with NovoLog or Humalog U-100 insulin.

The Tandem® Device Updater™ System consists of software which allows for communication between a computer and a t:slim® or t:flex™ Insulin Delivery System. It allows for remote software installation and update of a Tandem Insulin Delivery System.

The t:slim® and t:flex™ Insulin Delivery Systems facilitate the subcutaneous delivery of insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin.

The accessory Tandem Device Updater™ System consists of software which allows for communications between a computer and a Tandem Diabetes Care. Inc. Insulin Delivery System. The Tandem Device Updater™ allows for software installation and update.

The Tandem Device Updater System is comprised of a personal computer application, a web server (HAL), an embedded firmware application (Homer), and a Tandem pump (t.slim or t.flex). The goal of the Tandem Device Updater System is to provide a process for the user to perform updates to the firmware components of a Tandem pump. The Tandem Device Updater System provides communication security consisting of message authentication and encryption, two commonly used methods to secure communication protocols (i.e. USB). Communication between the pump and the Tandem Device Updater System can only occur while the pump is connected to a computer via USB cable.

The HAL Web Server (HAL) is a web server that is responsible for storing and delivering the firmware components of a pump.

The Homer Firmware Application (Homer) is a software application which is part of Tandem Device Updater System that runs on the main MCU incorporated in the pump. Homer is used to update the Bootloader Software in each MCU, essentially rewriting the contents in the flash memory of the MCU. In addition to updating the Bootloader Software, Homer will provide an interface for the secure exchange of security keys during the enabling of communication security. Homer authenticates critical messages received from the PC application.

The Tandem pumps (i.e., t.flex and t:slim described above) incorporate three separate microcontroller units (MCUs), and each MCU runs two separate pieces of firmware, known as the Bootloader Software, and Application Software. The Application Software running on the main MCU, utilizes a graphics library to generate the screens for the pump display. The Tandem Device Updater downloads files from Tandem and installs them on the pump. All binary images for use on the pump transmitted by the Tandem Device Updater are encrypted.

The software components on the pump that may be updated by the Tandem Device Updater System include: the Bootloader Software stored in each MCU, the Application Software stored in each MCU, and the graphics library files stored in the nonvolatile flash memory module.

The software version of the t:slim and t:flex Insulin Delivery Systems for this submission is version 4.3.5.1. The software version of the Tandem Device Updater System for this submission is version 1.0.

This document is a 510(k) summary for the Tandem® Insulin Delivery Systems and the Tandem® Device Updater™ System. It discusses the substantial equivalence to predicate devices and provides performance data primarily in the form of assurance cases and verification/validation testing. However, it does not provide specific numerical acceptance criteria or reported device performance in the format of a table as requested. It also lacks details about specific studies with sample sizes, ground truth establishment, or expert involvement as typically found in diagnostic device evaluations.

Here's an attempt to answer your questions based only on the provided text, but please note the significant limitations due to the nature of this type of submission (a 510(k) for an infusion pump system, not a diagnostic device with specific performance metrics like sensitivity/specificity).

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

The document does not provide a table of numerical acceptance criteria or detailed reported device performance in the context of diagnostic metrics (e.g., sensitivity, specificity, accuracy). The performance data cited are primarily related to safety risks and compliance with guidance documents for infusion pumps.

The "acceptance criteria" are implied by the stated goals of the assurance cases:

• "The safety risk resulting from use of t:slim/t:flex pump is reduced to acceptable levels and is As Low As Reasonably Practicable (ALARP) through use of mitigating technologies and the risks are substantially equivalent to the predicate device."
• "The safety risk resulting from use of Tandem Device Updater is reduced to acceptable levels and is As Low As Reasonably Practicable (ALARP) through use of mitigating technologies and the risks are substantially equivalent to the predicate device."

Reported device performance focuses on successful verification and validation testing, risk mitigation, and substantial equivalence to predicate devices. Specific quantitative results (e.g., "device achieved X% accuracy") are not present.

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

The document does not specify a "test set" sample size in the context of diagnostic performance. It refers to "Software verification and validation testing" and "Hardware changes were supported by verification testing." These are likely internal engineering tests, and details on sample sizes or data provenance (country, retrospective/prospective) are not provided. "Human factor formative and summative studies" were conducted for the Tandem Device Updater System's user interface, but details on participant numbers, data type, or provenance are not given.

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 in the context of this document. The device is an insulin pump system and a software updater, not a diagnostic tool where expert ground truth establishment for a test set is typically required. The "ground truth" for these types of devices is typically compliance with technical specifications, safety standards, and functional requirements, established through engineering and quality assurance processes, not expert review of medical images or patient data.

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

This is not applicable. There is no mention of a "test set" requiring adjudication in the diagnostic sense within this document. The testing described is verification and validation, which would follow established engineering protocols rather than adjudication by medical experts.

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 such study was done or is mentioned. This is an insulin pump system, 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

While the device's software components (including the Tandem Device Updater) operate "standalone" in the sense of executing code, the performance is evaluated in the context of its function within the medical device system. Standalone "algorithm only" performance in the diagnostic sense (e.g., classifying images) is not relevant or described here. Instead, software verification and validation testing was performed on the device's software.

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

The concept of "ground truth" in the diagnostic sense (e.g., pathology, outcomes data) is not applicable to this submission. For an insulin pump and its updater, the "truth" against which performance is measured is its adherence to design specifications, safety requirements, and proper functionality as determined by engineering tests and regulatory standards. For example, for software, "truth" would be its adherence to specified algorithms and absence of critical bugs.

8. The sample size for the training set

The document does not mention a "training set." This type of submission does not involve machine learning algorithms that typically require training sets. The software development likely follows traditional software engineering paradigms, including design, coding, verification, and validation.

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

As there is no mention of a "training set," this question is not applicable.

Ask a specific question about this device

The t:flex™ Insulin Delivery System is indicated for the subcutaneous delivery of insulin at set and variable rates, for the management of diabetes mellitus in persons requiring insulin, for individuals 12 years of age and greater.

The t:flex™ Insulin Delivery System is intended for the subcutaneous delivery of insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin.

The t:flex System, like the predicate device, consists of the following components and accessories:

• 1. a software-controlled, programmable insulin infusion pump ("t:flex Pump" or "Pump");
• 2. a dedicated, disposable 4.8 mL (480 unit) insulin cartridge ("cartridge");
• 3. an UnoMedical Comfort™ Infusion Set (K051264), or an equivalently FDA cleared infusion set ("infusion set"); and
• 4. accessories, including a 5 mL sterile syringe and 26 gauge sterile needle, as well as an AC power supply and DC car adapter power supply with USB for charging the Pump's internal battery, cartridge Instructions for Use, and User's Guide.

The t:flex Pump is a battery operated infusion pump capable of both basal and bolus delivery of insulin. It utilizes a motor-driven mechanism to deliver insulin from within a disposable cartridge, through an infusion set, into a patient's subcutaneous tissue. As with current insulin infusion pumps on the U.S. market, the desired timing and quantity of the insulin delivery is programmed by the user (i.e., the patient). The graphical user interface ("GUI") of the t:flex Pump is a capacitive touch screen that displays information used to control the t:flex System. The delivery of insulin is accomplished through a micro-syringe within the head of the cartridge.

The t:flex cartridge is a single-use device, individually packaged and sealed, and is provided sterile. The cartridge attaches to the t:flex Pump and is designed to hold up to 4.8 mL, or 480 units of insulin. The delivery of insulin is accomplished through a micro-syringe within the head of the cartridge. The Pump has a pressure measurement sensor to estimate the volume of insulin in the insulin reservoir by measuring air pressure in the cartridge. This information is used to provide feedback to the software to determine the insulin volume, detect occlusions and cartridge removal.

This document is a 510(k) premarket notification for the t:flex Insulin Delivery System, an insulin infusion pump. It outlines the device's technical characteristics, intended use, and substantial equivalence to a predicate device. However, the provided text does NOT contain specific acceptance criteria or the detailed results of a study that proves the device meets those criteria.

While it mentions that "Hardware changes were supported by verification testing per previously established acceptance criteria" and outlines the types of testing performed (pump software, aged mechanical, water ingress, current consumption, battery runtime, EMC, electrical safety, cartridge verification, mechanical, package, and distribution testing, and human factors studies), it does not provide the actual acceptance criteria (e.g., "accuracy within X%," "occlusion detection time less than Y seconds") nor does it present a table of reported device performance against those criteria.

Therefore, I cannot fulfill your request for:

1. A table of acceptance criteria and the reported device performance: This information is not present in the document.
2. Sample size used for the test set and the data provenance: This information is not explicitly stated for individual tests.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: This is not mentioned. Human factors studies are mentioned, but details about expert involvement or qualifications are absent.
4. Adjudication method for the test set: Not mentioned.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance: This is an insulin pump, not an AI diagnostic imaging device, so an MRMC study is not applicable and not mentioned.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The device is an insulin pump, not an AI algorithm in the typical sense of standalone performance evaluation.
7. The type of ground truth used: Not explicitly stated for specific tests. For mechanical or electrical tests, ground truth would be established by reference standards or direct measurement.
8. The sample size for the training set: This is not an AI/machine learning device in the context of training data, so this concept is not applicable and information is not present.
9. How the ground truth for the training set was established: Not applicable.

What the document does provide regarding testing:

• Types of tests performed:
  • Software verification and validation
  • Aged mechanical verification
  • Pump aged water ingress
  • Average current consumption testing
  • Battery runtime verification
  • EMC testing
  • Electrical safety testing
  • Cartridge verification testing
  • Mechanical testing (for cartridge)
  • Package and distribution testing (for cartridge)
  • Human factor formative and summative studies (for user interface)
• Guidance followed: FDA's guidance document, "Guidance for Industry and FDA Staff - Total Product Life Cycle: Infusion Pump - Premarket Notification [510(k)] Submissions Draft Guidance," issued on April 23, 2010.

In summary, while the document confirms various tests were conducted to support substantial equivalence, it lacks the specific, quantitative details requested regarding acceptance criteria, study methodologies, and performance outcomes.

Ask a specific question about this device