Search Results

SmartGuard technology is intended for use with compatible integrated continuous glucose monitors (iCGM), compatible Medtronic continuous glucose monitors (CGMs), and alternate controller enabled (ACE) pumps to automatically adjust the delivery of basal insulin and to automatically deliver correction boluses based on sensor glucose values.
SmartGuard technology is intended for the management of Type 1 diabetes mellitus in persons 7 years of age and older requiring insulin.
SmartGuard technology is intended for single patient use and requires a prescription.

Predictive Low Glucose technology is intended for use with compatible integrated continuous glucose monitors (iCGM), compatible Medtronic continuous glucose monitors (CGMs), and alternate controller enabled (ACE) pumps to automatically suspend delivery of insulin when the sensor glucose value falls below or is predicted to fall below predefined threshold values.
Predictive Low Glucose technology is intended for the management of Type 1 diabetes mellitus in persons 7 years of age and older requiring insulin.
Predictive Low Glucose technology is intended for single patient use and requires a prescription.

SmartGuard Technology, also referred to as Advanced Hybrid Closed Loop (AHCL) algorithm, is a software-only device intended for use by people with Type 1 diabetes for ages 7 years or older. It is an interoperable automated glycemic controller (iAGC) that is intended for use with compatible integrated continuous glucose monitors (iCGM), compatible interoperable Medtronic continuous glucose monitors (CGM) and compatible alternate controller enabled (ACE) pumps to automatically adjust the delivery of basal insulin and to automatically deliver correction boluses based on sensor glucose (SG) values.
The AHCL algorithm resides on the compatible ACE pump, which serves as the host device. It is meant to be integrated in a compatible ACE pump and is an embedded part of the ACE pump firmware.
Inputs to the AHCL algorithm (e.g., SG values, user inputs) are received from the ACE pump (host device), and outputs from the AHCL algorithm (e.g., insulin delivery commands) are sent by the algorithm to the ACE pump. As an embedded part of the firmware, the AHCL algorithm does not connect to or receive data from compatible CGMs; instead, sensor glucose (SG) values or other inputs received by the ACE pump from compatible CGMs via Bluetooth Low Energy (BLE) technology are transmitted to the embedded AHCL algorithm.
The AHCL algorithm works in conjunction with the ACE pump and is responsible for controlling insulin delivery when the ACE pump is in Auto Mode. It includes adaptive control algorithms that autonomously and continually adapt to the ever-changing insulin requirements of each individual.
The AHCL algorithm requires specific therapy settings (target setpoint, insulin-to-carb ratios and active insulin time) that need to be established with the help of a health care provider (HCP) before activation. It also requires five (5) consecutive hours of insulin delivery history, a minimum of two (2) days of total daily dose (TDD) of insulin, a valid sensor glucose (SG) and blood glucose (BG) values to start automated insulin delivery.
When activated, the AHCL algorithm adjusts the insulin dose at five-minute intervals based on CGM data. A basal insulin dose (auto basal) is commanded by the AHCL algorithm to manage glucose levels to the user's target setpoint of 100 mg/dL, 110 mg/dL or 120 mg/dL. The user can also set a temporary target of 150 mg/dL for up to 24 hours. In addition, under certain conditions the algorithm can also automatically command correction boluses (auto correction bolus) without user input.
Meal boluses are the responsibility of the user. The AHCL algorithm includes an integrated bolus calculation feature for user-initiated boluses for meals. When the user inputs their carbohydrate intake, the AHCL algorithm automatically calculates a bolus amount based off available glucose information, entered carbohydrate amount and other patient parameters.
The AHCL algorithm contains several layers of "safeguards" (mitigations) to provide protection against over-delivery or under-delivery of insulin to reduce risk of hypoglycemia and hyperglycemia, respectively.
The AHCL algorithm is a software-only device and does not have a user interface (UI). The compatible ACE pump provides a UI to the user to configure the therapy settings and interact with the algorithm. The AHCL-related alerts/alarms are displayed and managed by the pump.

Predictive Low Glucose Technology, also referred to as the Predictive Low Glucose Management (PLGM) algorithm is a software-only device intended for use by people with Type 1 diabetes for ages 7 years or older. It is an interoperable automated glycemic controller (iAGC) that is intended for use with compatible integrated continuous glucose monitors (iCGM), compatible interoperable Medtronic continuous glucose monitors (CGM) and compatible alternate controller enabled (ACE) pumps to automatically suspend delivery of insulin when the sensor glucose value falls below or is predicted to fall below predefined threshold values.
The PLGM algorithm resides on the compatible ACE Pump, which serves as the host device. It is meant to be integrated in a compatible ACE pump and is an embedded part of the ACE pump firmware.
Inputs to PLGM algorithm (e.g., sensor glucose values, user inputs) are received from the ACE pump (host device), and outputs from PLGM algorithm (e.g., suspend/resume commands) are sent by the algorithm to the ACE pump. As an embedded part of the ACE pump firmware, the PLGM algorithm does not connect to or receive data from compatible CGMs; instead, sensor glucose (SG) values or other inputs are received by the ACE pump from compatible CGMs via Bluetooth Low Energy (BLE) technology are transmitted to the embedded PLGM algorithm.
The PLGM algorithm works in conjunction with the ACE pump. When enabled, the PLGM algorithm is able to suspend insulin delivery for a minimum of 30 minutes and for a maximum of 2 hours based on current or predicted sensor glucose values. It will automatically resume insulin delivery when maximum suspend time of 2 hours has elapsed or when underlying conditions resolve. The user is also able to manually resume insulin at any time.
The PLGM algorithm is a software-only device and does not have a user interface (UI). The compatible ACE pump provides the UI to configure therapy settings and interact with the algorithm. The PLGM-related alerts/alarms are displayed and managed by the pump.

The provided FDA 510(k) clearance letter and supporting documentation detail the acceptance criteria and the studies conducted to prove that Medtronic's SmartGuard Technology and Predictive Low Glucose Technology meet these criteria.

It's important to note that the provided text focuses on demonstrating substantial equivalence to a predicate device, as is typical for 510(k) submissions, rather than establishing de novo acceptance criteria for an entirely novel device. The "acceptance criteria" here refer to the performance benchmarks that demonstrate safety and effectiveness comparable to the predicate and compliance with regulatory special controls.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Acceptance Criteria and Device Performance

The acceptance criteria are generally implied by the comparative data presented against the predicate device (Control-IQ Technology) and the compliance with "iAGC Special Controls requirements defined in 21 CFR 862.1356." The clinical study primarily aims to demonstrate non-inferiority or beneficial outcomes in key glycemic metrics compared to baseline (run-in period).

Table of Acceptance Criteria and Reported Device Performance

Given that this is a 510(k) submission showing substantial equivalence, the "acceptance criteria" are largely derived from the performance of the predicate device and clinical guidelines (e.g., ADA guidelines for Time Below Range). While specific numerical thresholds for acceptance are not explicitly listed as "acceptance criteria" in a table format within the provided text, the results presented serve as the evidence that these implicit criteria are met.

For the purpose of this response, I will synthesize the implied performance targets from the "Pivotal Study Observed Results" and "Supplemental Clinical Data" sections and present the device's reported performance against them.

Table 1: Implied Acceptance Criteria (via Predicate Performance/Clinical Guidelines) and Reported Device Performance for SmartGuard Technology (AHCL Algorithm)

Table 2: Implied Acceptance Criteria and Reported Device Performance for Predictive Low Glucose Technology (PLGM Algorithm)

Study Details

1. Sample Sizes and Data Provenance

Test Set (Clinical Studies):

• SmartGuard Technology (AHCL Algorithm) - Pivotal Study:

  • Adults (18-80 years): 110 subjects enrolled (105 completed).
  • Pediatrics (7-17 years): 112 subjects enrolled (107 completed).
  • Total: 222 subjects enrolled (212 completed).
  • Provenance: Multi-center, single-arm study conducted across 25 sites in the U.S. This implies prospective data collection, specifically designed for this regulatory submission. Home-setting study.

• Predictive Low Glucose Technology (PLGM Algorithm) - Clinical Testing:

  • Adults (14-75 years): 71 subjects. In-clinic study.
  • Pediatrics (7-13 years): 105 subjects. In-clinic evaluation.
  • Total: 176 subjects.
  • Provenance: Multi-center, single-arm, in-clinic studies. Location not explicitly stated but part of a US FDA submission, implying US or international sites adhering to FDA standards. Prospective data.

Training Set:

• SmartGuard Technology & Predictive Low Glucose Technology (Virtual Patient Model):
  • Sample Size: Not explicitly stated as a number of "patients" but referred to as "extensive validation of the simulation environment" and "virtual patient (VP) model."
  • Data Provenance: In-silico simulation studies using Medtronic Diabetes' simulation environment. This is synthetic data generated by computational models, validated against real patient data.

2. Number of Experts and Qualifications for Ground Truth (Test Set)

The clinical studies for both SmartGuard and PLGM technologies involved direct measurement of glucose values via CGM and blood samples (YSI for PLGM study, and HbA1c for SmartGuard study). These are objective physiological measures, not subjective interpretations requiring external expert consensus for "ground truth."

• For SmartGuard Technology: Glucose values were measured by the Simplera Sync CGM and HbA1c by laboratory tests. These are considered objective measures of glycemic control.
• For Predictive Low Glucose Technology: Hypoglycemia induction was monitored with frequent sample testing (FST) and frequent blood sampling for glucose measurements (likely laboratory-grade methods like YSI [Yellow Springs Instrument]).
• Expert involvement: While healthcare professionals (investigators, study coordinators, endocrinologists, nurses) were undoubtedly involved in conducting the clinical studies, managing patient care, and interpreting results, their role was not to establish "ground truth" through consensus or adjudication in the sense of image review. The ground truth was physiological measurements.

3. Adjudication Method for the Test Set

Not applicable in the typical sense of subjective clinical assessments (e.g., radiology image interpretation). Ground truth was established by direct physiological measurements (CGM data, HbA1c, YSI/FST blood glucose). The clinical studies were single-arm studies where subject outcomes were measured, not comparative assessments where multiple readers adjudicate on decisions.

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

No, an MRMC comparative effectiveness study was not described. The clinical studies were single-arm (evaluating the device's performance in a standalone setting against a baseline or predefined safety/efficacy metrics) and did not involve human readers interpreting data from the device to make clinical decisions and then comparing human performance with and without AI assistance. Instead, the AI (algorithm) directly controlled insulin delivery and was evaluated based on patient physiological outcomes.

5. Standalone (Algorithm Only) Performance

Yes, the core of the evaluation is the standalone performance of the algorithms (SmartGuard AHCL and PLGM) in managing glucose, as they are "software-only devices" that reside on the ACE pump firmware. The clinical studies directly measured the physiological impact of the algorithm's actions on glucose levels, HbA1c, and safety parameters in a human population.

6. Type of Ground Truth Used

• Clinical Studies (SmartGuard & PLGM): Objective Physiological Measurements

  • Sensor Glucose (SG) values: From compatible CGMs (Simplera Sync CGM, Guardian 4 CGM)
  • HbA1c: Laboratory measurements of glycosylated hemoglobin.
  • Frequent Sample Testing (FST) / Blood Glucose (BG) values: Clinical laboratory measurements (e.g., YSI) to confirm hypoglycemia during PLGM induction.
  • Adverse Events (AEs): Clinically reported and documented events.
  • These are considered the definitive "ground truth" for evaluating glycemic control and safety.

• In-Silico Simulation Studies: Virtual Patient Model Outputs

  • The "ground truth" for these simulations is the metabolic response of the validated virtual patient models. This computational modeling is used to extend the clinical evidence to various parameter settings and demonstrate equivalence to real-world scenarios.

7. Sample Size for the Training Set

The document does not explicitly state a numerical "sample size" for a distinct "training set" of patients in the traditional machine learning sense for the algorithms themselves. The algorithms are likely developed and refined using a combination of:

• Physiological modeling: Based on established understanding of glucose-insulin dynamics.
• Historical clinical data: From previous similar devices or general diabetes patient populations (though not specified in this document for algorithm training).
• Clinical expertise: Incorporated into the algorithm design.
• The "Virtual Patient Model" itself is a form of simulated data that aids in development and testing. The validation of this model is mentioned as "extensive validation" and establishment of "credibility," implying a robust dataset used to verify its accuracy against real patient responses.

It's typical for complex control algorithms like these to be developed iteratively with physiological models and potentially large historical datasets, but a specific "training set" size for a machine learning model isn't detailed.

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

As noted above, a distinct "training set" with ground truth in the conventional sense of labeling data for a machine learning model isn't described. The development of control algorithms often involves:

• Physiological Simulation: The ground truth for this is the accurate metabolic response as modeled mathematically.
• Clinical Expertise & Design Principles: The ground truth is embedded in the scientific and medical principles guiding the algorithm's control logic.
• Validation of Virtual Patient Model: The "equivalency was demonstrated between Real Patients (RPs) and Virtual Patients (VPs) in terms of predetermined characteristics and clinical outcomes." This suggests that real patient data was used to validate and establish the "ground truth" for the virtual patient model itself, ensuring it accurately mirrors human physiology. This validated virtual patient model then serves as a crucial tool for in-silico testing.

Ask a specific question about this device

The MiniMed 780G insulin pump is intended for the subcutaneous delivery of insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin.

The MiniMed 780G insulin pump is able to reliably and securely communicate with compatible, digitally connected devices, including automated insulin dosing software, to receive, execute, and confirm commands from these devices.

The MiniMed 780G insulin pump contains a bolus calculator that calculates an insulin dose based on user-entered data.

The MiniMed 780G insulin pump is indicated for use in individuals 7 years of age and older.

The MiniMed 780G insulin pump is intended for single patient use and requires a prescription.

The MiniMed 780G insulin pump is an alternate controller enabled (ACE) pump intended for the subcutaneous delivery of insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin. It can reliably and securely communicate with compatible digitally connected devices, including an integrated continuous glucose monitor (iCGM), interoperable Medtronic continuous glucose monitor (CGM), and interoperable automated glycemic controller (iAGC). The pump is intended to be used both alone and in conjunction with compatible, digitally connected medical devices for the purpose of drug delivery.

The MiniMed 780G insulin pump is an ambulatory, battery-operated, rate-programmable micro-infusion pump that contains pump software and houses electronics, a pumping mechanism, a user interface, and a medication reservoir within the same physical device. The pump also contains a bolus calculator that calculates an insulin dose based on user-entered data. It is comprised of several discrete external and internal components including a pump case made of a polycarbonate blend, an electronic printed circuit board assembly stacks and a drive motor system.

The MiniMed 780G insulin pump is an interoperable device that can communicate via a Bluetooth Low Energy (BLE) wireless electronic interface with digitally connected devices. The MiniMed 780G insulin pump is a host device for the iAGC and integrates iAGC algorithm into the pump firmware. The pump is then able to receive, execute, and confirm commands from an iAGC to adjust delivery of insulin. The pump receives sensor glucose (SG) data via BLE interface from a compatible iCGM or a compatible interoperable Medtronic CGM and transmits these CGM data to the embedded iAGCs.

The MiniMed 780G insulin pump can operate in one of two modes: Manual Mode or Auto Mode (also referred to as "SmartGuard Mode"). The pump provides the user with keypad pump controls, as well as a data screen for configuring therapy settings and viewing continuous real-time glucose values, glucose trends, alerts, alarms, and other information. The user interface and alerts provide the user with the ability to interact with the pump delivery system and digitally connected devices.

The provided text is a 510(k) clearance letter and summary for a medical device, specifically an insulin pump. It details the device's characteristics, intended use, comparison to predicate devices, and a summary of non-clinical performance data.

However, it does not contain the information requested regarding acceptance criteria and a study proving a device meets these criteria in the context of an AI/Machine Learning device for image analysis or diagnostics.

The request asks for details like:

• A table of acceptance criteria and reported device performance (which is present in a limited form for the pump's mechanical performance, but not for AI performance).
• Sample size for the test set and data provenance.
• Number of experts and their qualifications for ground truth.
• Adjudication method for the test set.
• MRMC study details and effect size.
• Standalone performance.
• Type of ground truth used.
• Sample size for the training set.
• How ground truth for the training set was established.

These specific points are highly relevant to the validation of AI/ML-enabled medical devices, particularly those that interpret or analyze data (like images) to aid in diagnosis or treatment decisions. The MiniMed 780G insulin pump, while having advanced software and interoperability, is primarily an infusion pump with a bolus calculator, not an AI/ML diagnostic or image analysis tool. Its software functions relate to pump control, communication, and basic dose calculation, not complex pattern recognition or inference typically associated with AI in medical devices that would require the detailed validation described in the prompt.

Therefore, I cannot extract the requested information from the provided text because the text describes a different type of medical device and its associated validation. The validation methods mentioned (Delivery Volume Accuracy, Occlusion Detection, Drug Stability, Cybersecurity, Human Factors) are appropriate for an insulin pump but do not align with the AI/ML-specific validation criteria outlined in your prompt.

Ask a specific question about this device

The InPen System is a home-use reusable pen for single-patient use by people with diabetes under the supervision of an adult caregiver, or by a patient aged 7 and older for the self-injection of a desired dose of insulin. The pen injector is compatible with Lilly Humalog® U-100 3.0 mL cartridges, Novo Nordisk Novolog® U-100 3.0 mL cartridges, and Novo Nordisk Fiasp® U-100 3.0 mL cartridges and single-use detachable and disposable pen needles (not included). The pen Smart Insulin pen allows the user to dial the desired dose from 0.5 to 30 units in one-half (1/2) unit increments.

The InPen dose calculator, a component of the InPen app, is indicated for the management of diabetes by people with diabetes under the supervision of an adult caregiver, or by a patient aged 7 and older for calculating an insulin dose or carbohydrate intake based on user entered data.

For an insulin dose based on amount of carbohydrates, a healthcare provide patient-specific target blood glucose, insulin-to-carbohydrate ratio, and insulin sensitivity parameters to be programmed into the software prior to use.

For an insulin dose based on fixed/variable meal sizes, a healthcare provide patient-specific fixed doses/ meal sizes to be programmed into the software prior to use.

The InPen App is a software application with versions that are compatible with mobile phones running the iOS or Android operating system. The App is a component of the InPen system and is used with the InPen Smart Insulin pen for the management of insulin-requiring diabetes. The InPen App communicates with the InPen Smart Insulin pen to communicate doses that are delivered by the user. The InPen App is also compatible for use with blood glucose (BG) meters, Medtronic Continuous Glucose Monitors (CGMs), and the Dexcom CGMs. The InPen App includes a dose calculator that can calculate and recommend a dose for the user to review and consider as part of following the treatment plan prescribed by the healthcare provider. The dose calculator features in the App require that a healthcare professional provide patient-specific values for various therapy settings for programming into the App prior to use by the patient. These therapy settings include glucose target(s), duration of insulin action time, insulin sensitivity factor(s), and insulin-to-carbohydrate ratio(s) or fixed insulin doses for meal types and sizes. The dose calculator feature is unavailable to the user until these patient-specific values, provided by the healthcare professional, are programmed and an InPen has been paired to the App. A healthcare provider may also provide long-acting insulin settings to be programmed into the InPen App. The App includes a logbook feature that displays the patient's recent activity related to BG values, meal types and sizes, dose calculations, doses by insulin type (rapid- or long-acting), cartridge replacement and priming. The App also provides reminders and alerts that can notify the user to check their glucose, dose insulin (for potential missed meals, correction doses, and longacting insulin doses) and log doses according to schedule, replace a cartridge, or if the insulin pen has been exposed to very low or very high temperatures. The App can generate a supplemental summary report of recent therapy information for review by the patient or healthcare professional (HCP).

The InPen Cloud includes a therapy report component that the user and the health care provider (HCP) can view and print to assess the overall diabetes control and treatment plan. The report displays data based upon user and HCP-defined inputs, such as glucose, insulin and carb trended information, during the defined period, as well as dose calculator usage and alerts and reminders. The Insulin Notification Service (INS) is a subcomponent of the InPen Cloud that can receive Medtronic CGM sensor glucose measurements from the CareLink Cloud. The INS includes two algorithms that assess "real time" sensor glucose measurements to identify whether a user has missed a dose or if their glucose is rising and a correction dose is needed. If either of these conditions exist, a silent notification is sent by the INS to the InPen App. The InPen App confirms the data and can provide and visual alert to the user. The user can act on the alert by assessing their glucose levels followed by calculating a dose utilizing the InPen App dose calculator.

The provided text is a 510(k) summary for the Medtronic MiniMed InPen System. It describes the device, its indications for use, and a comparison to a predicate device to establish substantial equivalence. However, the document does not contain the specific details about acceptance criteria, the study design (including sample size, data provenance, expert ground truth establishment, or adjudication methods), or performance data in the way requested in the prompt.

The "Performance Data" section (Page 10) broadly states that "Software verification and validation testing was performed in accordance with the FDA's Guidance..." and mentions "unit level testing, integration level testing, and systems testing." It also notes "Cybersecurity Testing" and "risk management activities." Finally, it mentions an "additional assessment of the changes to the InPen Cloud occurred through a summative usability evaluation" where "patients...used the InPen Cloud to perform a series of critical tasks involving the use of the InPen App and Cloud, including the additional alerts and reminder."

Therefore, it is not possible to fill in most of the requested information based on the provided text. The document focuses on regulatory arguments for substantial equivalence rather than detailed clinical or technical study results that would typically include such specifics.

Here's a breakdown of what can be extracted and what cannot:

Information that CANNOT be extracted from the provided text:

1. A table of acceptance criteria and the reported device performance: This detail is not present. The document focuses on showing the device is substantially equivalent to a predicate, not on specific performance metrics against pre-defined acceptance criteria.
2. Sample sizes used for the test set and the data provenance: No specific sample sizes for particular tests (e.g., test sets for algorithms) are mentioned, nor is the data provenance (country, retrospective/prospective). The "summative usability evaluation" is mentioned, but without sample size or details about the data used.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not mentioned.
4. Adjudication method (e.g. 2+1, 3+1, none) 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: Not mentioned. This type of study is more common for diagnostic imaging AI, whereas this device is an insulin management system with a dose calculator.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: While the InPen App has an algorithm for dose calculation and the InPen Cloud has algorithms for notifications, the document doesn't provide performance data for these algorithms in isolation. The "summative usability evaluation" implies human-in-the-loop testing.
7. The type of ground truth used (expert concensus, pathology, outcomes data, etc): Not explicitly stated how the accuracy of the dose calculations or alert effectiveness was verified as "ground truth." The "summative usability evaluation" likely involved checking if users performed tasks correctly, but the underlying ground truth for algorithm accuracy isn't detailed.
8. The sample size for the training set: Not mentioned.
9. How the ground truth for the training set was established: Not mentioned.

Information that CAN be extracted or inferred from the provided text:

• Device Type: Insulin management system (reusable pen, app with dose calculator).
• Regulatory Class: Class II (Product Code: NDC).
• Software Level of Concern: Major.
• Key Software Features: Dose calculator (insulin dose based on carbohydrates or fixed/variable meal sizes), logging, reminders, alerts (missed dose, high glucose).
• New Features (compared to predicate):
  • Two new algorithms in the InPen Cloud (Insulin Notification Service) to identify and send "silent notifications" to the InPen App for missed insulin doses or rising glucose.
  • Two new visual and audible alerts in the InPen App for missed insulin doses or high glucose, for users with a Medtronic CGM.
  • Improved existing Long-Acting Reminder to include both audible and visual alerts.
• Performance Data (General Statement): "Software verification and validation testing was performed in accordance with the FDA's Guidance for Industry and FDA Staff, "Content of Premarket Submissions for Device Software Functions'', and FDA's guidance "General Principles of Software Validation". Verification and validation activities included software testing consisting of unit level testing, integration level testing, and systems testing of the InPen App and InPen Cloud. Cybersecurity Testing was performed... Risk management activities... were undertaken... Additional assessment of the changes to the InPen Cloud occurred through a summative usability evaluation."

In summary, the provided document is a regulatory submission focused on substantial equivalence, not a detailed technical report of study results with specific performance metrics and study methodologies.

Ask a specific question about this device

MiniMed Reservoir- This Reservoir is indicated for the subcutaneous infusion of medication, including insulin, from compatible Medtronic insulin pumps and infusion sets. Refer to your Medtronic insulin pump user guide for compatibility.

Extended Reservoir- The Extended Reservoir is indicated for the subcutaneous infusion of medication, including insulin, from compatible Medtronic insulin pumps and infusion sets. Refer to the Medtronic insulin pump user guide for a list of compatible insulins and infusion sets.

The MiniMed family of reservoirs (MMT-326A, MMT-342, MMT-342, MMT-342G) (herein referred to as "reservoirs" or "subject devices") are sterile medication containers designed for single use. The reservoirs are a component of the Medtronic Insulin Pump Delivery System used by patients with diabetes mellitus, requiring the subcutaneous administration of insulin to maintain acceptable blood glucose levels. The reservoirs are indicated for the subcutaneous infusion of medication, including insulin, from compatible Medtronic insulin pumps (i.e., Paradigm pumps and NGP pumps) and infusion sets. Refer to the Medtronic insulin pump user guide for a list of compatible insulins and infusion sets. The reservoirs have the same principle of operation as the predicate devices (MMT-326A, MMT-332A, MMT-342, MMT-342G) and are designed to mechanically connect to compatible infusion sets. Reservoirs are connected to the infusion set via the tubing connector (H-Cap), which enables insulin infusion from the reservoir through a fluid path into the subcutaneous tissue.

This document describes a 510(k) premarket notification for Medtronic MiniMed's Extended Reservoir and MiniMed Reservoir. The purpose of the submission is to qualify an additional sterilization site and an optimized ethylene oxide (EO) sterilization cycle for these devices.

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

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

The document does not explicitly present a table of acceptance criteria with corresponding performance metrics in a pass/fail format. Instead, it states that "The test results demonstrate the subject devices met all the product requirements and specifications of the predicate devices." and "Medtronic concludes the reservoirs can be sterilized at the additional facility using the optimized parameters for EO sterilization cycle."

The acceptance criteria are implicitly defined by the product requirements and specifications of the predicate devices. The performance reported is that the subject devices met these predicate device requirements/specifications.

The relevant performance data from the text is summarized as follows:

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 states: "The testing was performed on MMT-332A since the subject devices have the same hardware design, materials, and attributes as the predicate device."

• Sample Size: The document does not specify the exact sample size (number of units) used for the verification testing. It only mentions that the testing was performed on "MMT-332A" (a 3.0mL MiniMed Reservoir).
• Data Provenance: The document does not explicitly state the country of origin of the data or whether it was retrospective or prospective. Given that it's "verification testing," it would typically be prospective data generated by Medtronic as part of the submission process. Medtronic MiniMed is located in Northridge, CA, USA, and the contract manufacturer and one sterilization site are in Puerto Rico, so the data likely originated from these locations.

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 this submission. The device is an infusion pump accessory, and the testing focuses on the impact of a sterilization process change on the device's physical, chemical, and functional attributes, as well as its sterility. It does not involve human interpretation or diagnostic performance where experts establish a "ground truth" in the diagnostic sense. The "ground truth" here is the established product requirements and specifications of the predicate devices.

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

This is not applicable. Adjudication methods like 2+1 or 3+1 are typically used in clinical studies involving interpretation of medical images or diagnostic results, where multiple experts provide opinions that may need to be reconciled to establish a ground truth. The testing described here is engineering and sterilization validation, which does not involve such an adjudication process.

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 not applicable. An MRMC study is relevant for AI-powered diagnostic or screening devices where human readers (e.g., radiologists) interpret cases with and without AI assistance. The Medtronic reservoirs are physical medical devices, and the submission is about a sterilization process change, not an AI diagnostic tool.

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

This is not applicable. The device is not an algorithm or software. It is a physical medical device (reservoir) for insulin delivery.

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

The "ground truth" for this submission is the established product requirements and specifications of the predicate devices (MiniMed Reservoir 1.8mL (MMT-326A), MiniMed Reservoir 3.0mL (MMT-332A), and Extended Reservoir (MMT-342, MMT-342G)). The verification testing aimed to demonstrate that the subject devices, after the sterilization change, still meet these existing, validated performance standards.

8. The sample size for the training set

This is not applicable. This is not a machine learning or AI device that requires a training set. The submission concerns changes to a manufacturing process (sterilization) for an existing medical device.

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

This is not applicable, as there is no training set for this type of device submission.

Ask a specific question about this device

The Extended Reservoir is indicated for the subcutaneous infusion including insulin, from compatible Medtronic insulin pumps and infusion sets. Refer to your Medtronic insulin pump user guide for a list of compatible insulins and infusion sets.

Extended Reservoir (herein referred to as "EWR" or "MMT-342") is a sterile medication container designed for single use. The Extended Reservoir (MMT-342) is a component of the Medtronic Insulin Pump Delivery System used by patients with diabetes mellitus, requiring subcutaneous administered insulin, to maintain acceptable blood glucose levels. The Extended Reservoir (subject device) is indicated for the subcutaneous infusion of medication, including insulin, from compatible Medtronic insulin pumps and infusion sets. Refer to your Medtronic insulin pump user guide for a list of compatible insulins and infusion sets.

The provided text describes a 510(k) premarket notification for an "Extended Reservoir" (MMT-342) by Medtronic MiniMed, Inc. The primary purpose of this notification is to demonstrate substantial equivalence to a predicate device (Medtronic MiniMed Paradigm Reservoir MMT-332A, K032005) while extending the duration of use from 3 days to 7 days.

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

Acceptance Criteria and Reported Device Performance

The core acceptance criterion is to demonstrate that extending the duration of use for the reservoir from 3 days to 7 days does not negatively impact the safety and effectiveness of the device. Since there are no changes in hardware design, materials, manufacturing, packaging, sterilization processes, fluid capacity, insulin compatibility, or reservoir assembly, the acceptance criteria are implicitly tied to maintaining the performance characteristics of the predicate device over the extended duration.

The text does not provide a specific table of quantitative acceptance criteria for parameters like insulin delivery accuracy, occlusion detection, or material degradation. Instead, it states that "The test results demonstrate that MMT-342 (subject device) met all the product requirements and specifications of MMT-332A (predicate device)." This implies that the performance over 7 days matches the established performance standards of the 3-day predicate.

The reported device performance, in summary, is that the Extended Reservoir (MMT-342) successfully maintains the same safety and effectiveness as the predicate device (MMT-332A) when used for up to 7 days.

Study Details

1. Sample size used for the test set and the data provenance:
   The document states: "Medtronic performed verification testing to support extending the duration of the reservoirs use (from up to 3 days to up to 7 days)." However, the specific sample size for this verification testing is not provided in the extracted text.
   The provenance of the data is not explicitly mentioned (e.g., country of origin, retrospective/prospective). It is implied to be internal testing conducted by Medtronic.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
   This information is not provided in the extracted text. The verification testing described is likely technical performance testing rather than human expert assessment of a medical condition.

3. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
   This information is not applicable as the document describes technical verification testing, not a clinical study involving adjudication of clinical observations.

4. 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 information is not applicable. The device is an insulin reservoir, not an AI-assisted diagnostic tool.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
   This information is not applicable. The device is a physical medical device (insulin reservoir), not a software algorithm.

6. The type of ground truth used (expert concensus, pathology, outcomes data, etc.):
   For mechanical/material performance, the "ground truth" would be established engineering specifications and validated test methods (e.g., for infusion accuracy, material integrity, sterility maintenance). The document indicates that the subject device "met all the product requirements and specifications of MMT-332A." This implies the predicate device's established performance standards serve as the ground truth.

7. The sample size for the training set:
   This information is not applicable as the device is a physical medical device, not a machine learning model.

8. How the ground truth for the training set was established:
   This information is not applicable for the same reason as above.

Ask a specific question about this device

The MiniMed Quick-serter is indicated to use as an aid for inserting compatible devices. It is for use by a single patient. It is not for use by multiple patients.

The modified MiniMed Quick-serter (MMT-305) is a non-sterile, single patient, multi-use, hand held accessory product designed to be used as an insertion aid for compatible devices, including specific infusion sets. It is used to insert the introducer needle and cannula through the skin and into the subcutaneous tissue. The MiniMed Quick-serter is intended to be used by a patient or clinician as a means to insert an infusion set with minimum discomfort and technique dependency.

The MiniMed Quick-serter consists of a plastic barrel containing a stainless steel spring and a handle. The device user places and securely seats the infusion set into the MiniMed Quick-serter is loaded and locked by pulling the handle (compressing the spring) until it clicks/locks into place. The serter is placed in contact with the insertion site and fired to release the infusion set. This is done by depressing the green side buttons to release the spring, which drives the infusion set forward and the insertion needle and cannula are inserted into the user's subcutaneous tissue. The release button on the top of the device is then pressed to ease the release of the infusion set from the serter.

The provided text describes a 510(k) submission for the "MiniMed Quick-serter" (MMT-305) and compares it to a predicate device (MMT-395). This device is a syringe needle introducer, and the submission is focused on demonstrating substantial equivalence, not necessarily on detailing a study proving the device meets acceptance criteria in the way one would for a novel AI/software medical device.

Therefore, the information I can extract will be specific to the type of device and submission, which involves engineering and biocompatibility testing rather than clinical study protocols for diagnostic accuracy or comparative effectiveness with human readers.

Here's the breakdown based on the provided text:

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

The document lists performance testing that was conducted to verify the device's mechanical properties and functions. The "acceptance criteria" are implied by the statement "Results from performance testing indicate that the product meets the established performance requirements." Specific numerical acceptance criteria are not explicitly detailed for each test in this summary, but the reported device performance for some characteristics is given in the comparison table.

Ask a specific question about this device

MiniMed Connect is intended to provide a secondary display of continuous glucose monitoring and/or insulin pump data on a suitable consumer electronic device to care partners and users of a MiniMed 530G system or Paradigm REAL-Time Revel system for the purpose of passive monitoring.

MiniMed Connect system is not intended to replace the real-time display of continuous glucose monitoring and/or insulin pump data on the primary display device (i.e. the sensor-augmented pump). All therapy decisions should be based on blood glucose measurements obtained from a blood glucose meter.

The MiniMed Connect is not intended to analyze or modify the continuous glucose monitor data and/or insulin pump data that it receives. Nor is it intended to control any function of the connecting continuous glucose monitor system and/or insulin pump. The MiniMed Connect is not intended to serve as a replacement for a primary display device for the continuous glucose monitoring system and/or insulin pump data. The MiniMed Connect is not intended to receive information directly from the sensor or transmitter of a continuous glucose monitoring system.

MiniMed® Connect is a secondary display of continuous glucose monitor and/or insulin pump data on a suitable consumer electronic device for insulin pump patients and their care partners. This system is designed as an optional accessory to compatible sensor-augmented pump systems.

MiniMed® Connect consists of a MiniMed® Connect app (for a local secondary display), the CareLink® Connect module of CareLink® Personal (for a remote secondary display), and the MiniMed® Connect uploader (for data transmission to the local app).

The MiniMed® Connect uploader is a small, battery-powered, ambulatory device that is carried with the patient in near proximity to the insulin pump. Its rechargeable battery is charged as needed (approximately once a day) using a USB Charger that accompanies the device.

The MiniMed® Connect uploader receives continuous glucose monitor and/or insulin pump data from the sensor-augmented insulin pump using a proprietary 916.5 MHz RF, and then converts it into a 2.4 GHz Bluetooth Low Energy (BLE) format. This BLE formatted data can then be read by the MiniMed® Connect app installed on a compatible consumer electronics device with BLE capabilities.

The MiniMed® Connect app reads the BLE data transmission and displays it on the patient's compatible consumer electronic device. The MiniMed® Connect app then uploads the continuous glucose monitor and/or insulin pump data to CareLink® Connect, the remote monitoring module of CareLink® Personal. Authorized care partners can access CareLink® Connect to view the patient's continuous glucose monitor and/or insulin pump data through an Internet-enabled consumer electronic device for the purpose of passive monitoring.

Accessories associated with this system include:

• USB Charger (for charging the MiniMed® Connect uploader) .

I am sorry, but the provided text does not contain the specific information required to answer your request regarding the acceptance criteria and the study that proves the device meets them. The document is an FDA 510(k) summary for the MiniMed Connect device, which primarily focuses on establishing substantial equivalence to a predicate device.

Specifically, the text states under "PERFORMANCE DATA [807.92(b)] VII.":

"Results of the verification and validation testing indicate that the product meets established performance requirements, and is safe and effective for its intended use."

However, it does not provide:

• A table of acceptance criteria and reported device performance.
• Details about the sample size, data provenance, number of experts, their qualifications, or adjudication methods for a test set.
• Information about MRMC comparative effectiveness studies, effect sizes, or standalone algorithm performance.
• The type of ground truth used, training set sample size, or how ground truth for the training set was established.

The document confirms that verification and validation testing was done and that the device met performance requirements, but it does not elaborate on what those requirements were or present the results of such testing.

Ask a specific question about this device

The Paradigm Insulin Pump system is indicated for the continuous delivery of insulin, at set and variable rates for the management of diabetes mellitus in persons requiring insulin.

Medtronic MiniMed Paradigm Insulin Pumps (Model No. MMT-512); Medtronic MiniMed Paradigm Insulin Pumps (Model No. MMT-712); Medtronic MiniMed Paradigm Insulin Pumps (Model Nos. MMT-515, MMT-715)

I am sorry, but the provided text does not contain information about the acceptance criteria and the study that proves the device meets those criteria. The document is a 510(k) clearance letter from the FDA for a Medtronic MiniMed Paradigm Insulin Pump System, outlining its substantial equivalence to predicate devices and general regulatory information. It does not include details on specific performance criteria or a study describing how those criteria were met.

Ask a specific question about this device

The Sof-set and Polyfin families of infusion sets are indicated for the subcutaneous infusion of medication, including insulin, from a Medtronic MiniMed infusion pump and reservoir.

Not Found

This document is a 510(k) clearance letter from the FDA for a medical device called the "Polyfin Infusion Set" and related models. It explicitly states that the FDA has determined the device is "substantially equivalent" to legally marketed predicate devices.

A 510(k) clearance evaluates substantial equivalence, meaning the new device is as safe and effective as a legally marketed predicate device. This process does not typically involve detailed studies to establish new acceptance criteria or quantify device performance against specific metrics in the way a PMA (Premarket Approval) or a clinical trial for a novel device would. The provided text does not contain the acceptance criteria or a study that proves the device meets specific acceptance criteria as you've requested.

The information you are asking for, such as sample size, ground truth establishment, expert qualifications, and specific performance metrics, is usually found in detailed scientific reports, clinical trial summaries, or design validation documents that are submitted to the FDA as part of the 510(k) but are not typically included in the public-facing clearance letter itself.

Therefore,Based on the provided text, I cannot describe the acceptance criteria and the study that proves the device meets those criteria because this information is not present. The document is an FDA 510(k) clearance letter, which confirms substantial equivalence to a predicate device, rather than providing detailed performance data against new acceptance criteria.

The information you've requested typically comes from the technical documentation and studies submitted to the FDA, which are not included in this summary letter.

Ask a specific question about this device

The Medtronic MiniMed Paradigm Model MMT-512, MMT-712, MMT-515 and MMT-715 insulin infusion pumps are indicated for the continuous delivery of insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin.

Not Found

The provided document is a 510(k) clearance letter for an insulin infusion pump. It does not contain information on acceptance criteria, device performance, study details, ground truth, or sample sizes related to a medical device's performance in a study. The letter primarily confirms that the device is substantially equivalent to legally marketed predicate devices and is thus cleared for marketing.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study proving the device meets them based on the provided text.

Ask a specific question about this device