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:slim® 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 scope of this Traditional 510(k) is limited to expansion of the indications for use to include individuals 6 years of age and greater. The device is indicated for use with NovoLog or Humalog U-100 insulin. No changes have been made to the device components to accommodate the modified indications for use.

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

• 1. a software-controlled, programmable insulin infusion pump ("t:slim Pump" or "Pump");
• 2. a dedicated, disposable 3.0 mL (300 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 3 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:slim Pump is a battery operated infusion pump capable of both basal and bolus delivery of insulin. The Pump 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:slim Pump is a touch screen that displays information used to control the t:slim System. The delivery of insulin is accomplished through a micro-syringe within the head of the cartridge.

Identical to the predicate device, the t:slim cartridge is a single-use device, individually packaged and sealed, and is provided sterile. The cartridge attaches to the t:slim Pump and is designed to hold up to 3.0 mL (300 units) of insulin. Both in the predicate and in the device that is the subject of this 510(k) notice, 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.

The provided text describes a 510(k) submission for the t:slim® Insulin Delivery System, focusing on expanding its indications for use to include individuals 6 years of age and greater. This is a regulatory document rather than a study report detailing specific performance criteria and a study to prove they are met in a quantitative sense as might be expected for an AI/ML medical device.

Therefore, many of the requested elements for acceptance criteria and study details are not directly applicable or available in the provided text, as this document is about establishing substantial equivalence based on existing data and human factors testing for a wider age range, rather than presenting a novel clinical performance study with specific device metrics.

However, I can extract information related to the safety assurance case and human factors testing, as these touch upon aspects of "acceptance criteria" in a broader sense for this type of regulatory submission.

Here's an attempt to answer based on the provided text, noting where information is not available:

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

The document does not provide a table with specific quantitative acceptance criteria or reported device performance metrics in the way one would see for a diagnostic device (e.g., sensitivity, specificity thresholds). Instead, the "acceptance criteria" are framed in terms of general safety, reliability, and substantial equivalence, particularly concerning the expanded age range.

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

• Sample Size for Test Set: Not specified for the human factors testing or the peer-reviewed literature summary.
• Data Provenance: Not specified for human factors testing. The peer-reviewed literature would be drawn from various studies, likely international, but this is not detailed. The human factors testing is implied to be relevant to the U.S. market.

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 specified. This document describes a 510(k) submission for an insulin pump, not for a diagnostic device that requires expert-established ground truth for a test set in the same manner as an AI/ML imaging system. The "ground truth" here is the established safety and efficacy of CSII, and the device's equivalent performance to its predicate and suitability for a broader age range, assessed through engineering principles, human factors, and literature review.

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

• Not applicable/None specified. No adjudication method is mentioned as this is not a study involving human reader interpretations that require adjudication.

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 done. This device is an insulin pump, 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

• Not applicable/Not directly addressed in this framework. The device itself is a standalone insulin pump. The "performance" being evaluated is its safety and functionality for an expanded age range, not an algorithm's diagnostic accuracy in isolation.

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

• The "ground truth" used for this submission is multifaceted:
  • Peer-reviewed medical literature: Supporting the general efficacy and safety of CSII in pediatric populations (ages 6-11).
  • Device specifications and design verification/validation: Demonstrating the device meets its intended functional requirements.
  • Human Factors testing: Confirming that the device can be used safely and effectively by the intended user population, including the expanded pediatric group, and that updated labeling is sufficient.
  • Predicate device's established safety and performance: The t:slim System is shown to have identical technological characteristics and similar intended use to the predicate device, implying its "ground truth" is aligned with the predicate's proven track record.

8. The sample size for the training set

• Not applicable/Not specified. This document does not describe a machine learning model or a training set in the conventional sense. The "training" for the device's expanded indication relies on existing engineering documentation, human factors insights, and clinical literature.

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

• Not applicable. As there is no "training set" for a machine learning model described, this question is not relevant to the provided text.

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

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 t:slim® 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 scope of this 510(k) is limited to a new software version and minor changes to the pump component of the t:slim System.

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

1. a software-controlled, programmable insulin infusion pump ("t:slim Pump" or "Pump");
2. a dedicated, disposable 3mL (300 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 Becton Dickenson 3mL sterile syringe (K941562) and 26 gauge sterile needle, or equivalently cleared syringe and 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:slim Pump is a battery operated infusion pump capable of both basal and bolus delivery of insulin. It utilizes a motor-driver 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:slim Pump is a capacitive touch screen that displays information used to control the t:slim System. The delivery of insulin is accomplished through a micro-syringe within the head of the cartridge.

The t:slim cartridge is a single-use device. individually packaged and provided sterile. The cartridge attaches to the t:slim Pump and is designed to hold up to 3 mL, or 300 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:slim Insulin Delivery System, specifically for a new software version and minor hardware changes. As such, it focuses on demonstrating substantial equivalence to a predicate device rather than presenting a de novo study with explicit acceptance criteria and device performance tables in the format typically used for novel AI/ML devices.

Therefore, much of the requested information regarding acceptance criteria, study details, and ground truth establishment, particularly in the context of an AI/ML device, is not directly available or applicable within this specific 510(k) summary.

However, I can extract information related to the performance data as described for this modified insulin pump.

Here's a breakdown of the available information based on your request:

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

This document does not provide a table of acceptance criteria and reported device performance in a quantitative manner as you might expect for an AI/ML imaging device. Instead, it states that:

• "Hardware changes were supported by verification testing per previously established acceptance criteria."
• "The new software version and minor changes to the pump component of the t:slim System were verified and/or validated per Tandem's design control process and shown to meet design requirements."

The document focuses on the types of testing performed rather than specific quantitative performance metrics against acceptance criteria.

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

The document mentions "human factor formative and summative studies" for verifying the user interface. However, it does not specify:

• The sample size used for these studies.
• The data provenance (e.g., country of origin, retrospective or prospective).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience):

This information is not provided in the document. For an insulin pump, "ground truth" would likely refer to clinical outcomes or accurate insulin delivery, but the document doesn't detail how this was established or by whom for the purpose of testing the modifications.

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

This information is not provided in the document.

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 type of study is relevant for AI/ML diagnostic tools. The t:slim Insulin Delivery System is an infusion pump, not a diagnostic imaging AI/ML device. Therefore, an MRMC comparative effectiveness study is not applicable and was not performed in this context.

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

The device is an insulin pump with human interaction. The "software-controlled, programmable insulin infusion pump" operates based on user input. While the software has standalone functions (e.g., controlling insulin delivery rates), the overall system performance is inherently with human-in-the-loop. The document confirms "Tandem completed verification of the t:slim System's user interface through a series of human factor formative and summative studies," indicating that human interaction was part of the testing.

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

The document does not explicitly state the "type of ground truth" used for performance assessment in terms of a single, definitive reference standard. For an insulin pump, performance is assessed through various engineering and functional tests:

• Verification and validation testing: Ensures the device meets design requirements.
• Hardware changes supported by verification testing: implies comparison against expected device behavior and specifications.
• Software verification and validation testing: per FDA guidance document for infusion pumps.
• Other specific tests: mechanical, environmental conditioning, water ingress, simulated aging testing, electrical safety, and electromagnetic compatibility testing.

The "ground truth" for these tests would be the established specifications, regulatory standards, and expected physical/electrical behavior of the device.

8. The sample size for the training set:

The document describes a modification to an existing device, not the development of an AI/ML model that typically involves a distinct "training set." Therefore, a "training set sample size" in that context is not applicable and not provided.

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

As above, this concept of "training set" and its ground truth establishment is not applicable to this type of device modification submission.

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 t:slim™ 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 scope of this Special 510(k) is limited to changes to the cartridge configuration of the t:slim System.
The t:slim System with the modified cartridge, like the predicate device, consists of the following components and accessories:

• 1. a software-controlled, programmable insulin infusion pump ("t:slim Pump" or "Pump"),
• 2. a dedicated, disposable 3mL (300 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 Becton Dickenson 3mL sterile syringe and 26 gauge sterile needle, or equivalently cleared syringe and needle, as well as an AC power supply with USB for charging the Pump's internal battery, cartridge Instructions for Use, and User's Guide.
     The t:slim 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:slim Pump is a capacitive touch screen that displays information used to control the t:slim System. The delivery of insulin is accomplished through a micro-syringe within the head of the cartridge.
     The t:slim cartridge is a single-use device, individually packaged and sealed, and provided sterile. The cartridge attaches to the t:slim Pump and is designed to hold up to 3 mL, or 300 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 510(k) submission (K133593) is for a Special 510(k) notice regarding changes to the cartridge of the t:slim™ Insulin Delivery System. The primary focus of the performance data and acceptance criteria is to ensure that the modifications to the cartridge materials do not negatively impact the device's safety and effectiveness compared to the predicate device.

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not explicitly state specific sample sizes for each test mentioned (e.g., for bond strength, leak testing, flow accuracy, etc.). It refers generally to "testing" and "evaluation". Given the nature of a Special 510(k) for material and supplier changes, the testing would typically involve a statistically relevant number of units to demonstrate equivalence to the previously cleared predicate device.

The data provenance is not explicitly stated as country of origin but is implicitly domestic, as the submitter, Tandem Diabetes Care, Inc., is based in San Diego, CA, USA, and the submission is to the U.S. FDA. The data is retrospective in the sense that it's based on internal verification and qualification testing performed by the manufacturer to support the safety and effectiveness of the modified device before market introduction. It is not clinical trial data involving patients.

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

This type of submission (Special 510(k) for material changes) does not typically involve a "test set" with "ground truth" established by external experts in the same way clinical studies for diagnostic devices might. The "ground truth" here is adherence to pre-defined engineering specifications, regulatory standards (like ISO 10993-1), and the performance characteristics of the predicate device. The experts involved would be the manufacturer's internal R&D, engineering, quality, and regulatory personnel responsible for designing, testing, and verifying the changes, along with potentially external lab specialists for specific tests like biocompatibility or extractables/leachables. Their qualifications would be relevant scientific and engineering degrees and experience in medical device development and testing. The document does not specify the number or detailed qualifications of these individuals.

4. Adjudication Method for the Test Set

Not applicable in the context of this Special 510(k). Adjudication methods like "2+1" or "3+1" are typically used in clinical studies or image-based diagnostic device evaluations where multiple human readers interpret data to establish a consensus ground truth. Here, the "ground truth" is defined by established engineering specifications and compliance with validated test methods.

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 submission is for modifications to an insulin pump cartridge, not an AI-powered diagnostic or assistive technology. Therefore, no MRMC study or AI-related effectiveness assessment was performed or is relevant.

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

Not applicable. This device is an insulin pump, not an algorithm. Performance is tested for the physical device components and their functionality.

7. The Type of Ground Truth Used

The ground truth used in this context is primarily:

• Engineering Specifications and Design Requirements: The performance of the modified cartridge must meet or exceed the original design specifications for the predicate device.
• Regulatory Standards: Compliance with relevant international standards, e.g., ISO 10993-1 for biocompatibility.
• Predicate Device Performance: The modified device must demonstrate substantial equivalence to the predicate device, meaning its performance, safety, and effectiveness are comparable.
• Validated Test Methods: The results are derived from validated test methods and protocols.

8. The Sample Size for the Training Set

Not applicable. This device does not have an "algorithm" in the sense of a machine learning model that requires a training set. The "training" here refers to the development and manufacturing processes which are subject to qualification (IQ/OQ/PQ) and ongoing quality control.

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

Not applicable for the reasons stated in point 8.

Ask a specific question about this device

The t:slim™ 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, for individuals 12 years of age and greater.

The t:slim™ Insulin Delivery System ("t:slim System") consists of the following components and accessories:

1. a software-controlled, programmable insulin infusion pump ("t:slim Pump" or "Pump").
2. a dedicated, disposable 3mL (300 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 Becton Dickenson 3mL sterile syringe and 26 gauge sterile needle, or equivalently cleared syringe and needle, as well as an AC power supply with USB for charging the Pump's internal battery, cartridge Instructions for Use, and User's Guide.
   The t:slim 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 end user (i.e., the patient). The graphical user interface on the t:slim Pump is a capacitive touch screen that is overlaid on an organic light emitting diode ("OLED") screen that displays information used to control the t:slim System. The delivery of insulin is accomplished through a micro-syringe within the head of the cartridge.
   Cartridges are individually packaged and sealed, and provided sterile. The cartridge attaches to the t:slim Pump and is designed to hold up to 3 mL, or 300 units, of insulin. The cartridge has been tested for insulin compatibility with two types of rapid-acting U-100 insulin (Humalog® and NovoLog®) and determined to be insulin compatible as demonstrated by the performance data submitted in this 510(k) application.

The provided text describes the t:slim™ Insulin Delivery System and its path to 510(k) clearance. Here's a breakdown of the acceptance criteria and study details based on the input:

1. Table of Acceptance Criteria and Reported Device Performance:

The document doesn't explicitly state numerical acceptance criteria or performance metrics for each test, but it broadly claims the device "functioned as intended and testing results observed were as expected." The performance data is presented as a list of validated and verified activities.

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

• Human Factors Summative Study:

  • Sample Size: 53 patients
  • Data Provenance: Prospective, non-randomized, multicenter study. (Country of origin is not specified, but typically for 510(k) in the US, it would be within the US.)

• For other performance tests (e.g., pump flow rate, bolus accuracy, cartridge performance), the document does not specify sample sizes for individual tests. It broadly mentions "appropriate validation and verification activities."

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

The document does not explicitly state the number of experts used to establish ground truth or their specific qualifications for any of the tests. The Human Factors study involved patients, and the assessment of whether "critical errors" occurred was likely based on pre-defined criteria associated with potential harm, but expert involvement for ground truth establishment beyond this is not detailed.

4. Adjudication Method for the Test Set:

The document does not describe any specific adjudication method (e.g., 2+1, 3+1) used for establishing ground truth or evaluating the results of the performance studies.

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

No, an MRMC comparative effectiveness study was not done. This device is an insulin pump, and the studies described are related to its functional performance, safety, and user interface, not comparative effectiveness with human readers using an AI.

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

The "standalone" concept, as typically applied to AI algorithms, doesn't directly apply here since the t:slim system is a physical device that requires human interaction for its intended use (programming insulin delivery). However, the document does describe extensive device-centric standalone testing for various components and functions of the pump and cartridge (e.g., Pump Flow Rate Accuracy, Bolus Accuracy, Cartridge Performance Validation, Occlusion Alarm Test). These tests evaluate the device's inherent performance characteristics independent of a human user's specific performance in a clinical setting, although they are part of a system intended for human use.

7. The Type of Ground Truth Used:

• Human Factors Study: The ground truth for this study was established against pre-defined safety criteria and the absence of "critical errors that could lead to user harm" during patient tasks. This is essentially ground truth based on safety and functional criteria defined by experts/engineers in the context of user interaction.
• Other Performance Tests (e.g., flow rate, bolus accuracy): The ground truth would have been established against engineered specifications and established physical/chemical principles. For example, a flow rate test would compare the delivered insulin volume against a precisely measured or expected volume based on pump programming. Insulin compatibility would be measured against pre-defined chemical stability parameters.

8. The Sample Size for the Training Set:

The document does not explicitly mention a "training set" in the context of machine learning. The studies described are verification and validation activities for a medical device's physical and software performance. Therefore, there is no direct equivalent of a "training set" as understood in AI/ML development.

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

As there is no "training set" in the AI/ML sense, this question is not applicable. The device's design and functionality would be based on engineering principles and regulatory requirements, and its performance verified and validated through the studies described.

Ask a specific question about this device