Search Results

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 ("780G ACE 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 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 780G Pump is an interoperable device that can communicate via a Bluetooth Low Energy (BLE) wireless electronic interface with digitally connected devices. The 780G 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 780G 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 FDA 510(k) clearance letter and summary for the MiniMed 780G Insulin Pump (K253470) do not contain the detailed information required to fill out all requested sections of the acceptance criteria and study design. This document focuses on demonstrating substantial equivalence to a predicate device and fulfilling regulatory requirements, rather than providing a detailed clinical study report suitable for assessing device performance against specific, quantifiable acceptance criteria in the manner requested.

However, based on the provided text, I can extract and infer some information, and note where specific details are missing.

Here's an attempt to answer your request based on the provided text:

Acceptance Criteria and Device Performance for MiniMed 780G Insulin Pump

The provided FDA 510(k) summary extensively references compliance with regulatory standards and performance compared to predicate devices, particularly for "Delivery Volume Accuracy" and "Bolus Delivery Accuracy" which specify numerical criteria. Other performance aspects are described more qualitatively as meeting requirements or demonstrating safety and effectiveness.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size for Test Set: Not specified in the provided document. The document refers to various "testing" and "verification activities" but does not detail the sample sizes for these tests (e.g., number of pumps, number of test cycles, number of patients, etc.).
• Data Provenance: The studies appear to be pre-market, non-clinical bench testing conducted by the manufacturer, Medtronic MiniMed, Inc. There is no indication of clinical study data or geographical origin of patient data (e.g., country of origin) as this particular submission focuses on the device and not a clinical study of its use. Many tests refer back to the predicate device (K251032).

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

• Not Applicable / Not Specified. The document describes non-clinical performance and engineering validation tests (e.g., accuracy, stability, cybersecurity, human factors). These types of tests typically rely on objective measurements against engineering specifications or regulatory requirements, rather than expert-established ground truth in the context of diagnostic interpretation. Human Factors validation involved intended users but the details about "experts" to establish a ground truth in a diagnostic sense are not present.

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

• Not Applicable / None Specified. This methodology (e.g., 2+1, 3+1 for clinical adjudication) is used for establishing ground truth in diagnostic studies, typically when evaluating algorithmic performance against human interpretation. The provided text describes engineering and regulatory compliance testing where such adjudication methods are not typically employed.

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. The provided text does not describe an MRMC comparative effectiveness study. This device is an insulin pump, not a diagnostic imaging AI system assisting human readers. The human factors validation is a separate type of study focusing on device usability and safety, not diagnostic performance improvement.

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

• Yes, implicitly for many aspects. Many of the tests described are standalone performance evaluations of the device, its firmware, and its capabilities without human intervention beyond setting up the test (e.g., Delivery Volume Accuracy, Catheter Occlusion Detection, Data Logging, Cybersecurity, Software Verification). The bolus calculator's operation within the pump would also be a standalone algorithmic function based on user input. The "Manual Mode" and "Auto Mode" imply different levels of automation, but the core technical tests are often standalone.

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

• The type of "ground truth" varies by the specific test and is generally based on objective engineering and regulatory standards and reference methods.
  • Delivery Accuracy: Ground truth is the precisely measured or theoretical ideal insulin volume/rate against which the pump's actual delivery is compared.
  • Occlusion Detection: Ground truth would be the presence or absence of an occlusion under controlled test conditions.
  • Drug Stability/Compatibility: Ground truth is the chemical stability of insulin and the integrity of pump materials under test conditions.
  • Data Logging: Ground truth is the expected logging behavior as per design specifications and regulatory requirements.
  • Cybersecurity: Ground truth is the identified vulnerabilities and presence of effective mitigations.
  • Human Factors: Ground truth is the identification of safety-critical tasks and demonstration of safe and effective completion by intended users, often against predefined success criteria.

8. The sample size for the training set

• Not Specified / Not Applicable. The document does not describe a machine learning algorithm that undergoes a "training phase" with a specific dataset in the context of the device's development or regulatory submission. While the device contains firmware and potentially algorithms (like the iAGC algorithm embedded in the pump), the text focuses on verification and validation of the device itself against engineering specifications and regulatory controls, not the training of a learning algorithm. The iAGC is described as an embedded algorithm, but its training data or methodology are not part of this 510(k) summary.

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

• Not Applicable. As no training set is described for a machine learning algorithm, the method for establishing its ground truth is not relevant to this document.

Ask a specific question about this device

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, and of Type 2 diabetes mellitus in persons 18 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, and of Type 2 diabetes mellitus in persons 18 years of age and older requiring insulin.

Predictive Low Glucose technology is intended for single patient use and requires a prescription.

SmartGuard technology

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, ages 7 years or older, and by people with Type 2 diabetes, ages 18 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

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, ages 7 years or older, and by people with Type 2 diabetes, ages 18 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 summary concern the Medtronic SmartGuard Technology (Advanced Hybrid Closed Loop algorithm, AHCL) and Predictive Low Glucose Technology (Predictive Low Glucose Management algorithm, PLGM). The document details the devices' descriptions, indications for use, comparison to predicate devices, and summaries of non-clinical and clinical performance data.

However, it's important to note that this document primarily focuses on establishing substantial equivalence to previously cleared predicate devices and does not explicitly state specific acceptance criteria (performance targets) for clinical efficacy metrics (e.g., specific HbA1c reduction percentages or time in range targets needed for clearance) and does not present the study results in a direct "acceptance criteria vs. reported performance" table format for those specific targets. Instead, it highlights that the clinical data "confirmed the safety and effectiveness" and "demonstrated improved glycemic outcomes" or "non-inferiority," and that "the results also confirm that use...was associated with improved glucose control."

The document also provides details about the clinical studies without explicitly labelling them as "the study that proves the device meets the acceptance criteria" in the way a clinical trial protocol would specify primary and secondary endpoints and their statistical targets. Instead, it justifies substantial equivalence through the provided study data.

Therefore, the response below will extract the most relevant information based on your request, presenting the outcomes demonstrated by the studies as "reported device performance" where specific metrics are given, and noting the absence of explicit, pre-defined acceptance criteria targets in the clearance letter itself.

Acceptance Criteria and Study to Prove Device Meets Criteria

The FDA 510(k) summary for Medtronic's SmartGuard Technology and Predictive Low Glucose Technology establishes substantial equivalence to predicate devices. While the document asserts the safety and effectiveness, it does not explicitly define quantitative "acceptance criteria" for specific performance metrics in a pass/fail sense within this summary. Instead, it relies on demonstrating improved or non-inferior clinical outcomes compared to baseline or predicate performance. The clinical studies described confirm the safety and effectiveness and demonstrate associations with improved glucose control, which implicitly means the performance was deemed acceptable by the FDA for substantial equivalence.

Here's a breakdown of the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

As explicit quantitative acceptance criteria (e.g., "HbA1c must reduce by X%") are not stated in this 510(k) summary, the table below presents the demonstrated clinical outcomes as "Reported Device Performance" highlighting the positive findings that supported clearance.

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

The primary "test sets" for clinical effectiveness and safety were the patient cohorts in the described clinical studies.

• AHCL with Simplera Sync CGM (Type 1 Diabetes): The sample size details for this study (originally in K251217) are not explicitly provided in this 510(k) summary. However, it confirmed safety and effectiveness in Type 1 Diabetes patients.
• AHCL with Simplera Sync CGM & Guardian 4 CGM (Type 2 Diabetes) (P160017/S124):
  • Phase 1 (Guardian 4 CGM): N = 95 subjects.
  • Phase 2 (Simplera Sync sensor): N = 302 subjects (66 "transition", 236 "naive").
  • Data Provenance: Multi-center, single-arm study. The document does not specify countries but implies clinical trial settings. Given the general nature of FDA submissions, it would typically involve US-based and possibly international sites. Clinical data is generally considered prospective for such trials.
• AHCL with Guardian 4 CGM and Lyumjev Insulin (Type 1 Diabetes) (P160017/S125):
  • ITT Population: N = 101 (Age 7-17 Years), N = 110 (Age 18-80 Years).
  • Data Provenance: Single-arm, multi-center, home clinical investigation. The document does not specify countries but implies clinical trial settings. Prospective.
• AHCL with Guardian 4 CGM and Fiasp Insulin (Type 1 Diabetes) (P160017/S125):
  • ITT Population: N = 107 (Age 7-17 Years), N = 116 (Age 18-80 Years).
  • Data Provenance: Global multi-center, single-arm study. Countries mentioned: Australia, Canada, United States. Prospective.
• PLGM Algorithm: Evaluated for safety in a multi-center, single-arm, in-clinic study of the MiniMed 640G System. The sample size for this study (originally in K251217) is not explicitly provided in this 510(k) summary.

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

The document refers to "clinical data" and "multi-center, single-arm studies" involving patients. For automated glycemic control devices, the "ground truth" for glucose values is typically established by laboratory reference methods (e.g., YSI glucose analyzer) performed by trained clinical staff as part of the study protocol, not by experts determining a ground truth in the interpretative sense. The efficacy endpoints (HbA1c, Time in Range, hypoglycemia) are derived from objective measurements, not subjective expert assessment of an image or signal.

There is no mention of "experts" in the context of establishing ground truth for glucose values or clinical outcomes. Clinical trials are monitored by clinical investigators (physicians, endocrinologists) and their teams, who ensure data integrity and protocol adherence, but they are not establishing a "ground truth" in the way radiologists might for AI image analysis.

4. Adjudication Method for the Test Set

Adjudication methods (e.g., 2+1, 3+1) are typically used in studies where subjective interpretation is involved, such as in reading medical images. For automated glycemic control devices, clinical outcomes are based on objective measurements (e.g., sensor glucose, lab-measured HbA1c). Therefore, the concept of an adjudication method as described does not directly apply to the clinical performance data presented here. Device-related adverse events would be reported and reviewed by the study investigators and likely an independent Data Safety Monitoring Board (DSMB), but this isn't an "adjudication method" for the primary clinical endpoints. The document does not explicitly describe an adjudication method for the objective clinical endpoints.

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

No, an MRMC comparative effectiveness study was not done. MRMC studies are typically used to evaluate the performance of diagnostic devices or AI algorithms that assist human readers (e.g., radiologists interpreting images). The SmartGuard and PLGM technologies are automated insulin delivery algorithms, not diagnostic tools that human readers interpret. Therefore, the concept of "how much human readers improve with AI vs without AI assistance" does not apply here. The studies evaluate the algorithm's direct impact on glycemic control in patients.

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

Yes, the core of the evaluation involves the "standalone" or "algorithm-only" performance in controlling glucose levels. The AHCL algorithm automatically adjusts basal insulin delivery and delivers correction boluses. The PLGM algorithm automatically suspends insulin delivery. While these systems require user input for meal boluses and setup, and interaction with alerts/alarms, the "SmartGuard technology" and "Predictive Low Glucose technology" themselves are software algorithms that function autonomously based on sensor glucose values to manage insulin delivery. The clinical studies assess the efficacy and safety of these algorithms in action within the device system (pump + CGM).

7. Type of Ground Truth Used

The ground truth for evaluating device performance in these studies is based on objective clinical measurements and patient outcomes. Specifically:

• Continuous Glucose Monitoring (CGM) sensor values: These are the primary input to the algorithm. While not explicitly stated as the ground truth for the algorithm's inputs, the accuracy of these values is critical and would have been established independently for the compatible CGMs.
• Laboratory-measured HbA1c: A standard clinical biomarker for average blood glucose over 2-3 months.
• Time-in-Range (TIR): Percentage of time spent with sensor glucose values within a target range (e.g., 70-180 mg/dL), derived from CGM data.
• Time-below-range (TBR): Percentage of time spent with sensor glucose values below a predefined threshold (e.g., <70 mg/dL), derived from CGM data.
• Adverse Events (AEs) and Serious Adverse Events (SAEs): Collected during clinical trials to assess safety.

These are physiological and clinical outcome data, not expert consensus or pathology reports in the typical sense.

8. The Sample Size for the Training Set

The document does not provide details on the sample size used for training the algorithm. This 510(k) summary focuses on the clinical data for validation of the finalized algorithms. The training set would be data used during the development phase of the algorithms, which is typically proprietary and not disclosed in 510(k) summaries. It would likely involve a large dataset of glucose profiles and insulin delivery patterns.

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

Similarly, the document does not describe how the ground truth for the training set was established. For algorithms predicting glucose or controlling insulin, development and training would typically rely on:

• Retrospective or prospective real-world glucose and insulin data: Collected from individuals with diabetes using CGMs and insulin pumps, potentially under controlled conditions or in free-living settings.
• Validated glucose measurements: Such as YSI or other reference laboratory methods for blood glucose, and accurate CGM data.
• Clinical expert knowledge: Incorporating understanding of diabetes physiology, insulin pharmacokinetics/pharmacodynamics, and desired glycemic targets.
• Mathematical models of glucose metabolism: To simulate physiological responses and generate synthetic data for training.

The ground truth would be the actual glucose values and the physiological responses to insulin delivery, enabling the algorithm to learn patterns and predict future glucose trends or optimal insulin dosing.

Ask a specific question about this device

The MiniMed Go app is indicated for people with diabetes or their caregivers. The indicated patient population varies based on the combination of connected CGM and injector.

• Simplera sensor only: Diabetes patients ages 18 years and older
• InPen smart insulin pen only: Diabetes patients ages 7 years and older, or younger patients under the supervision of an adult caregiver
• Simplera sensor and InPen smart insulin pen: Diabetes patients ages 18 years and older
• Instinct sensor and InPen smart insulin pen: Diabetes patients ages 7 years and older, or patients ages 2 to 6 years under the supervision of an adult caregiver

The dose calculator of the MiniMed Go app is indicated for the management of diabetes by people with diabetes for calculating an insulin dose based on user entered data, most recent glucose value and active insulin.

To calculate a recommended insulin dose, a healthcare professional must provide patient-specific therapy settings including glucose target, insulin-to-carbohydrate ratio, and insulin sensitivity parameters to be programmed into the software prior to use.

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

When connected to a CGM, the app supports display of Sensor Glucose (SG) values and trend arrows. When connected to the InPen smart insulin pen, the app supports automatic logging of insulin doses, tracking of active insulin, and a dose calculator. The app also supports alerts or reminders for low glucose, high glucose, and insulin doses.

The MiniMed Go App is a software-only mobile application intended to connect with compatible Continuous Glucose Monitors (CGMs) – including the Simplera Sensor and Instinct Sensor, and the InPen smart insulin injector. The App enables people with diabetes to manage their therapy through data visualization, insulin dose calculation, and event logging. The App can be installed on compatible mobile devices, enabling users to effectively manage their diabetes. The compatible devices include the user's Android/iOS mobile phones or the App Manager, a compatible display device configured to host Medtronic MiniMed applications.

The App functions as the primary display and control interface for the InPen and connected CGM systems, consolidating device management, data visualization, and alert functions within a single software platform. It replaces the standalone CGM applications and serves as the central interface through which users manage connected devices and receive CGM, InPen and other system notifications. This integration provides a unified platform that supports diabetes therapy management and improves the overall user experience through consolidated device interaction.

N/A

Ask a specific question about this device

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.

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 the sample size for individual tests. The tests performed are engineering/mechanical verification, biocompatibility, and usability evaluations, not clinical studies with a "test set" in the context of patient data. The data provenance is internal to Medtronic MiniMed, and the tests are prospective, conducted on the device itself.

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

This is not applicable to the type of device and testing described. "Ground truth" in this context would refer to established engineering standards, material science properties, and biocompatibility guidelines. The "experts" involved would be engineers, material scientists, and toxicologists conducting and evaluating the tests. No specific number or qualifications are mentioned for this section of the submission. A "Usability Evaluation" was performed, which would involve users, but details on "experts" for ground truth are not provided.

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

This is not applicable. Adjudication methods are typically for clinical trials or diagnostic studies where there might be disagreement in expert opinions on patient data. The tests described are objective engineering and biocompatibility evaluations.

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. The device is a mechanical introducer, not AI software or a 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 a mechanical device with a human user performing the insertion.

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

The "ground truth" for the performance data in this submission aligns with:

• Established engineering standards: For tests like Cocking Force, Trigger Force, Life Cycle testing, Drop Test, etc., the ground truth is based on predefined engineering specifications and internal standards.
• International standards and regulatory guidance: For biocompatibility testing, the ground truth is based on standards such as ISO 10993-1, -5, -10, -18 and FDA #G95-1 guidance.
• Industry standards: For tasks like Ship Test (ASTM D4169) and Cleaning studies (AAMI TIR12, TIR30).

8. The sample size for the training set

This is not applicable. The device is a mechanical product, not a machine learning model that requires a training set.

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

This is not applicable for the reasons stated above.

Ask a specific question about this device