Search Results

The Dexcom G7 15 Day Continuous Glucose Monitoring (CGM) System (Dexcom G7 15 Day CGM System or G7 15 Day) is a real time, continuous glucose monitoring device indicated for the management of diabetes in persons 18 years and older.

The Dexcom G7 15 Day CGM System is intended to replace fingerstick BG testing for diabetes treatment decisions. Interpretation of the Dexcom G7 15 Day CGM System results should be based on the glucose trends and several sequential sensor readings over time. The Dexcom G7 15 Day CGM System also aids in the detection of episodes of hyperglycemia and hypoglycemia, facilitating both acute and long-term therapy adjustments.

The Dexcom G7 15 Day CGM System is also intended to autonomously communicate with digitally connected devices, including automated insulin dosing (AID) systems. The Dexcom G7 15 Day CGM System can be used alone or in conjunction with these digitally connected medical devices for the purpose of managing diabetes.

The Dexcom G7 15 Day Continuous Glucose Monitoring (CGM) System (Dexcom G7 15 Day CGM System or G7 15 Day) is an interoperable continuous glucose monitoring system intended to continuously measure the glucose in the interstitial fluid, calculate the glucose reading and make this available to the user. The Dexcom G7 15 Day CGM System is intended for single patient use at home and requires a prescription.

The G7 15 Day consists of the following primary components: a wearable, consisting of a sensor and transmitter worn on the body and a display device, which can be a G7 Mobile Application (Mobile App) on an iOS or Android OS smart device or a G7 Receiver (Receiver).

To achieve the intended functions and performance of the G7 15 Day, one sensor and at least one display device (App or Receiver) must be used together. The user must pair the display device(s) with each unique sensor to enable communication and start a sensor session. During an active session, the sensor reports new glucose data to the display device every 5-minutes. The display device then displays glucose data and provides alerts and information signals to the user. The reportable glucose range for the G7 15 Day is 40 mg/dL to 400 mg/Dl. Glucose values below this range are reported as 'LOW' and glucose values above this range are reported as 'HIGH'. The sensor has an expected wear period of up to 15 days with an extended 12-hour grace period after the sensor session. The grace period allows additional time for the user to change the sensor at a convenient time.

The Dexcom G7 15 Day CGM System is an interoperable connected device that can communicate glucose readings and other information wirelessly and securely to and from compatible electronic interfaces via the following secure wireless connections:

• Wireless communication from the transmitter directly to an interoperable device communicating through the same protocol
• The Mobile App communicates to another app on a single mobile platform
• The Mobile App communicates through the cloud to another software device
  • Dexcom Partner Web APIs: The Dexcom Partner Web APIs enable secure and reliable communication of CGM data to authorized client software intended to receive the data through the cloud. The Partner Web APIs is not intended to be used by automated insulin delivery systems (AID).

Principle of Operation:

The principles of operation for the Dexcom G7 15 Day CGM System remain the same as prior generations of Dexcom CGM Systems. The System uses a wire-type sensing mechanism that continuously measures interstitial glucose levels and uses a radio transmitter to wirelessly communicate glucose data to the display device for the user to see and use accordingly.

The provided FDA 510(k) clearance letter and summary for the Dexcom G7 15 Day CGM System outlines several acceptance criteria and the studies performed to meet them. However, it's important to note that the document primarily focuses on demonstrating substantial equivalence to a predicate device and fulfilling regulatory requirements. It does not provide the detailed numerical performance metrics typically found in a full clinical study report, nor does it specify exact numerical "acceptance criteria" in all cases, instead referring to meeting "specifications" or "special controls."

Here's an attempt to extract the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document states:

• "A clinical study was conducted to evaluate the safety and effectiveness of the Dexcom G7 15 Day CGM System... in adult (18 years and older) participants with diabetes."
• "A subsequent clinical study was performed to assess the impact of a new sensor patch intended to improve survival rate."
• "A separate clinical study was performed in adults with type 1 and type 2 diabetes to assess the data transmission reliability over the 15-day wear period."

Sample Size: The exact sample size (number of participants) for these clinical studies is not specified in the provided text.

Data Provenance:

• Country of Origin: Not specified in the document.
• Retrospective or Prospective: Clinical studies are generally prospective, especially when evaluating safety and effectiveness of a new device. The phrasing "A clinical study was conducted to evaluate..." implies a prospective study.

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

This information is not provided in the given document. For a CGM device, the ground truth for glucose measurements is typically established using a highly accurate reference method, such as a YSI glucose analyzer, rather than expert interpretation of images or observations.

4. Adjudication Method for the Test Set

Adjudication methods like "2+1" or "3+1" are typically used in studies involving subjective assessment (e.g., image interpretation by multiple readers). For a continuous glucose monitoring system, the ground truth is established by objective laboratory measurements (YSI). Therefore, an adjudication method for the test set in the traditional sense is not applicable or described.

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

An MRMC study is relevant for devices where human readers interpret data, often with or without AI assistance.

• Was an MRMC study done? No, an MRMC study was not described. The Dexcom G7 is a diagnostic device that provides quantitative glucose values, not an imaging or interpretive AI, so comparative effectiveness with human readers in the traditional MRMC sense is not relevant here.
• Effect size of human readers improvement with AI vs without AI assistance: Not applicable, as no MRMC study was conducted or described for this type of device.

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

Yes, a standalone performance assessment was done. The clinical study evaluating "safety and effectiveness of the Dexcom G7 15 Day CGM System... with respect to reference venous plasma sample YSI measurements" directly assesses the algorithm's performance without human interpretation of the CGM readings. The device is intended "to generate continuous glucose measurements and make this available to the user," and the study uses these generated measurements against a gold standard.

7. Type of Ground Truth Used

The primary ground truth for the clinical effectiveness study was:

• Reference venous plasma sample YSI measurements.
  This is a highly accurate laboratory method for measuring glucose in blood, considered the gold standard for comparing CGM performance.

8. Sample Size for the Training Set

The document focuses on the new clinical data submitted for the Dexcom G7 15 Day CGM System and refers to its substantial equivalence to the predicate "Dexcom G7 Continuous Glucose Monitoring System." The sample size for the training set (i.e., data used to develop the algorithms for the CGM) is not mentioned in this 510(k) summary. This information would typically be developed during the device's original design and development phase, not necessarily recounted in each subsequent 510(k) submission unless there were significant algorithm changes requiring new training data.

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

Similar to item 8, the process for establishing ground truth for the training set used during the development of the Dexcom G7 algorithms is not described in this document. It is highly probable that similar reference methods (like YSI venous plasma measurements) would have been used during the development and training phases as well.

Ask a specific question about this device

The Signos Glucose Monitoring System is an over-the-counter (OTC) mobile device application that receives data from an integrated Continuous Glucose Monitor (iCGM) sensor and is intended to continuously measure, record, analyze, and display glucose values in people 18 years and older not on insulin. The Signos Glucose Monitoring System helps to detect normal (euglycemic) and low or high (dysglycemic) glucose levels. The Signos Glucose Monitoring System may also help the user better understand how lifestyle and behavior modification, including diet and exercise, impact glucose excursions. This information may be useful in helping users to maintain a healthy weight.

The user is not intended to take medical action based on the device output without consultation with a qualified healthcare professional.

The Signos Glucose Monitoring System is a mobile device application that is paired, via Bluetooth®, with an over-the-counter interoperable continuous glucose monitor (iCGM). The application functions as a primary display for the iCGM by showing the user's glucose reading along with a historic trend every 15 minutes. The system is capable of backfilling missed data and supporting a grace period dictated by the iCGM.

The system's various displays, text, graphs, suggestions, and notifications serve to clearly illustrate the user's past and present glucose readings and their trend direction to assist the user in maintaining a euglycemic state.

The glucose display range is 70 mg/dL to 250 mg/dL.

The Signos System is intended for users over the age of 18 not on insulin.

The provided text is a 510(k) premarket notification letter from the FDA regarding the Signos Glucose Monitoring System. It primarily focuses on the device's substantial equivalence to a predicate device based on its intended use, technological characteristics, and non-clinical testing.

Unfortunately, the provided document does not contain the detailed information required to describe the acceptance criteria and the study that proves the device meets those criteria, specifically for performance metrics like accuracy or effectiveness related to AI/algorithm performance. The document is a regulatory clearance letter, not a detailed study report.

Here's what can be inferred from the document and what information is missing:

What the document does provide:

• Device Name: Signos Glucose Monitoring System
• Intended Use: Over-the-counter (OTC) mobile device application that receives data from an integrated Continuous Glucose Monitor (iCGM) sensor. Intended to continuously measure, record, analyze, and display glucose values in people 18 years and older not on insulin. Helps detect normal/low/high glucose levels and understand how lifestyle impacts glucose excursions. Not intended for medical action without consultation.
• Technological Characteristics: Software system, displays interstitial fluid glucose sensor data, assists in understanding lifestyle impact on glucose. Uses data from an iCGM (same as predicate). Display range: 70-250 mg/dL. Update interval: Every 15 minutes.
• Non-Clinical Testing Mentioned:
  • Software Testing: Verified that the system functions consistently with design inputs and that displayed data is the same as transmitted data. (This is a functional verification, not a performance study against specific acceptance criteria for diagnostic accuracy)
  • Cybersecurity Testing: Demonstrated no unacceptable cybersecurity risks.
  • Usability / Human Factors: Demonstrated unacceptably low risks related to use errors that could cause harm or degrade performance.

What the document does not provide, and therefore cannot be filled:

1. A table of acceptance criteria and the reported device performance: The document mentions "software requirements have been verified," but does not list specific performance acceptance criteria for glucose measurement accuracy (e.g., MARD, Clarke Error Grid analysis) or how the algorithm detects normal/low/high glucose levels beyond simply displaying the iCGM data. It states the displayed data is the same as transmitted, implying the software's role is primarily display and analysis, not independent glucose measurement.
2. Sample size used for the test set and the data provenance: Not mentioned.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable based on the information provided, as the software is stated to display data transmitted by the biosensor, not to perform independent diagnostic interpretations requiring expert ground truth.
4. Adjudication method: Not applicable.
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 and unlikely given the device's described function as a display and analysis tool for iCGM data, rather than an AI diagnostic aid for image interpretation.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The document describes "Software Testing" which confirms the software displays data correctly, but this is not a standalone diagnostic performance study using an algorithm to interpret data independently of the iCGM. The device's "algorithm" here seems to be in the display and analysis of iCGM data (e.g., trend direction, identifying dysglycemic states based on thresholds), not in generating novel glucose measurements.
7. The type of ground truth used: Not explicitly stated for any actual performance metrics. The software testing confirmed data consistency with the biosensor, implying the biosensor's output is the "truth" for the software. For general "detection of euglycemic/dysglycemic" states, presumably standard glucose thresholds would be used.
8. The sample size for the training set: Not mentioned. The document describes software verification, cybersecurity, and human factors testing, not machine learning model training and validation.
9. How the ground truth for the training set was established: Not mentioned.

Conclusion:

The provided FDA letter grants marketing clearance based on substantial equivalence, primarily asserting that the Signos Glucose Monitoring System is a mobile application that accurately displays data from a legally marketed and cleared iCGM. It emphasizes software functionality, cybersecurity, and usability rather than presenting de novo clinical performance data for an AI/algorithm that performs diagnostic interpretations. The letter likely relies on the predicate iCGM's established performance for glucose measurement, with the Signos system's "performance" being its accurate receipt, display, and basic analysis of that underlying data. Therefore, the detailed performance data and acceptance criteria typical for AI-driven diagnostic devices are not present in this regulatory clearance document.

Ask a specific question about this device

The Libre Rio Continuous Glucose Monitoring System is an over-the-counter (OTC) integrated continuous glucose monitoring (iCGM) device indicated for non-insulin using persons age 18 and older. The System detects trends and tracks patterns and aids in the detection of euglycemia, and hypoglycemia. The System is also intended to autonomously communicate with digitally connected devices.

The Libre Rio Continuous Glucose Monitoring System (herein referred to as the 'System') is an integrated continuous glucose monitoring system (iCGM) that provides continuous glucose measurements every minute to facilitate calculation of glucose values accompanied by trend information (glucose arrows) and historical glucose information (glucose graph). The System is intended for over-the-counter use in a home setting. The System consists of the following components: a Sensor which transmits via Bluetooth Low Energy (BLE), and a mobile application Libre Rio App that is downloaded to a compatible smartphone running iOS and Android operating system.

Here are the details regarding the acceptance criteria and the study that proves the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not explicitly present a table of acceptance criteria with corresponding performance metrics for the Libre Rio Continuous Glucose Monitoring System. It primarily focuses on the device's substantial equivalence to a predicate device and summarizes various performance testing categories. The "Reported Device Performance" for each category usually states that acceptance criteria were met, without detailing the specific metrics or thresholds.

However, based on the type of testing mentioned and common practices for CGM devices, we can infer some general areas where acceptance criteria would have been established and reportedly met:

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

The document does not explicitly state the sample sizes for the test sets used in the listed performance tests. It mentions "studies" and "testing" but does not quantify the number of participants or data points.

The data provenance is not explicitly mentioned for the reported tests. However, the study is for the Libre Rio Continuous Glucose Monitoring System, which appears to be a new device (or an updated version) from Abbott Diabetes Care, Inc., located in Alameda, CA, USA. This suggests the data would likely be generated in the USA, and primarily from prospective testing conducted specifically for this submission, especially for areas like human factors, bench testing for new contraindications, and software validation. The clinical performance data is stated to be derived from the predicate device (K222447), which would have its own provenance details.

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

The document does not provide information on the number of experts used or their qualifications for establishing ground truth for any of the mentioned test sets. It broadly refers to "studies" and "testing" but does not detail the methodology of ground truth establishment for specific components like software, cybersecurity, or human factors.

4. Adjudication Method for the Test Set

The document does not specify any adjudication methods (e.g., 2+1, 3+1, none) used for establishing ground truth in the performance testing.

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

No, the document does not mention a Multi-Reader Multi-Case (MRMC) comparative effectiveness study. The device is a continuous glucose monitoring system, which typically involves direct measurement and user interaction, not interpretation by multiple human readers of clinical cases. The "Human Factors" testing mentioned focuses on usability and user interface, not on comparative effectiveness with human interpretation of readings.

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

Yes, implicit in the description of the device and testing, especially for "Software Verification and Validation" and the "Sensor glucose algorithm," is that standalone algorithm performance testing was conducted. The device's "Sensor glucose algorithm" is stated to be the "ADC Glucose Algorithm established for the predicate device," which would have undergone rigorous standalone validation. The "Libre Rio App" is designed to autonomously receive and display glucose data, suggesting the algorithm operates independently of immediate human intervention for value generation. The bench testing of the sensor's compatibility with CT, MRI, and X-ray would also involve objective measurements without human interpretation in the loop to assess the sensor's function.

7. The Type of Ground Truth Used

The document does not explicitly state the type of ground truth used for each specific test. However, based on the nature of the device and the tests:

• Clinical Performance (inherited from predicate): For CGM devices, the gold standard for ground truth is typically blood glucose measurements obtained from a laboratory reference method (e.g., YSI analyzer) at various glucose levels.
• Software Verification and Validation: Ground truth would be based on functional specifications and expected outputs for given inputs.
• Cybersecurity: Ground truth involves adherence to security protocols and identified risk mitigations.
• Human Factors: Ground truth is established through user task completion rates, error rates, and subjective feedback against predefined usability goals and safety requirements.
• Bench Testing (CT, MRI, X-ray): Ground truth would be based on physical and electrical performance standards and expected device behavior under specific environmental conditions, potentially using calibrated instruments to verify sensor output accuracy.

8. The Sample Size for the Training Set

The document does not provide information about the sample size for the training set. Given that the sensor glucose algorithm is "ADC Glucose Algorithm established for the predicate device," the training data would be associated with the development of that original algorithm, not necessarily new training for the Libre Rio specifically (unless modifications were made, which is not indicated for the algorithm itself).

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

The document does not specify how the ground truth for the training set (for the inherited "ADC Glucose Algorithm") was established. For glucose monitoring algorithms, ground truth for training data is typically established through paired comparisons with laboratory reference methods (e.g., YSI blood glucose measurements) across a diverse range of glucose values, patient populations, and physiological conditions.

Ask a specific question about this device

The Lingo Glucose System is an over-the-counter (OTC) integrated Continuous Glucose Monitor (iCGM) intended to continuously measure, record, and display glucose values in people 18 years and older not on insulin. The Lingo Glucose System helps to detect euglycemic glucose levels. The Lingo Glucose System may also help the user better understand how lifestyle and behavior modification, including diet and exercise, impact glucose excursion.

The user is not intended to take medical action based on the device output without consultation with a qualified healthcare professional.

The Lingo Glucose System (also referred to as 'System') is Abbott's latest biowearable evolution in health technology for glucose measurement. This system encourages users 18 years and older not on insulin, to understand how glucose impacts their body. The Lingo Glucose System includes the Lingo Glucose Biosensor and the Lingo App.

Lingo Biosensor: The Lingo Glucose Biosensor hardware and technology is based on the FDA-cleared FreeStyle Libre 2 (FSL2) sensor (K222447). The Biosensor is a single use disposable on-body Biosensor that incorporates a subcutaneously implanted electrochemical glucose sensor and associated electronics. The Biosensor can be worn for up for 14 days and transmits data to the Lingo App via Bluetooth Low Energy (BLE). Similar to the predicate device, a disposable Biosensor insertion device, consisting of a Biosensor Applicator and Biosensor Pack is used to assemble and apply the Biosensor to the back of the user's upper arm.

Lingo App (iOS): When downloaded on a compatible smartphone running on iOS, the Lingo App uses Near-Field Communication (NFC) to start a new Biosensor and uses BLE to receive glucose data from the Biosensor. The user can view real-time glucose value, trend arrow, and glucose graph on the app through a glucose range of 55-200 mg/dL. The Lingo App contains on-boarding materials with a self-selection questionnaire that a user must consent prior to using the device. The App does not provide any glucose or system alerts.

The Lingo Glucose System (K233655) is an over-the-counter (OTC) integrated Continuous Glucose Monitor (iCGM) intended for continuous measurement, recording, analysis, and display of glucose values in people 18 years and older not on insulin. It aims to help users detect euglycemic and dysglycemic glucose levels and understand the impact of lifestyle modifications on glucose excursions.

Here's an analysis of its acceptance criteria and the study used to demonstrate fulfillment:

1. Table of Acceptance Criteria and Reported Device Performance

The FDA clearance relies on the substantial equivalence of the Lingo Glucose System to its predicate device, the FreeStyle Libre 2 Flash Glucose Monitoring System (K222447). The clinical performance acceptance criteria for the Lingo Glucose System are tied to meeting the iCGM special controls requirements per 21 CFR 862.1355. While specific numerical acceptance criteria for accuracy (e.g., MARD percentage) are not explicitly stated in the provided text, the documentation states that the device demonstrated accuracy (clinical performance) meeting these iCGM special controls.

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

The Lingo Glucose System leverages the clinical data from the FreeStyle Libre 2 (FSL2) study (K222447). The text states: "Abbott conducted a statistical analysis to confirm that the clinical data of the FSL2 System (submitted under K222447) can be leveraged to support the Lingo Glucose System."

• Sample Size for Test Set: Not explicitly stated for the FSL2 study in this document.
• Data Provenance: Not explicitly stated in this document. Based on typical FDA submissions for iCGM devices and considering the predicate device (FreeStyle Libre 2), these trials are generally prospective and multi-center, often involving participants from various healthcare systems or regions.

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

This information is not provided in the given text. For iCGM studies, ground truth is typically established by laboratory reference methods (e.g., YSI glucose analyzer) rather than expert consensus on images or clinical assessments.

4. Adjudication Method for the Test Set

This information is not provided in the given text. Again, for iCGM studies, the reference method provides the ground truth, so expert adjudication methods (like 2+1 or 3+1 used in imaging studies) are typically not applicable to the establishment of the ground truth itself.

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

An MRMC study is not applicable to this device. The Lingo Glucose System is a continuous glucose monitor (CGM) and does not involve human "readers" interpreting medical images or data in a way that would necessitate an MRMC analysis of AI assistance. Its primary function is direct glucose measurement.

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

Yes, the clinical performance assessment of the Lingo Glucose System (by leveraging the FSL2 data) effectively represents a standalone algorithm performance study relative to the reference glucose measurements. The "system accuracy was demonstrated to meet the iCGM special controls requirements." The device continuously measures and reports glucose values, which is an algorithmic output compared against a reference standard. The user interacts with the app to view these values, but the core accuracy is an algorithmic function.

7. The Type of Ground Truth Used

The ground truth for iCGM devices is almost universally established by laboratory reference methods for glucose measurement, such as a YSI glucose analyzer, from blood samples drawn contemporaneously with the interstitial fluid measurements. The text refers to "clinical data" and "sensor performance," implying a comparison against such a gold standard.

8. The Sample Size for the Training Set

The document does not explicitly state the sample size for the training set. It mentions that "ADC Glucose Algorithm established for the predicate device" is used for the Lingo Glucose System. The development and training of such an algorithm would have involved a substantial dataset, but the specifics are not detailed here.

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

The document states that the "ADC Glucose Algorithm established for the predicate device" is used. For this type of algorithm, the ground truth for its development (training) would have been established through a combination of:

• Laboratory reference glucose measurements: From blood samples.
• Contemporaneous interstitial fluid readings: From prototype or earlier versions of the sensor.
• Extensive data collection: From a diverse population under various physiological conditions (e.g., different glucose levels, meals, exercise).

This data would be used to develop and refine the algorithm that translates the electrochemical signals from the sensor into accurate glucose readings.

Ask a specific question about this device

Libre 2 Sensor users:

The FreeStyle Libre 2 Flash Glucose Monitoring System is a continuous glucose monitoring (CGM) device with real time alarms capability indicated for the management of diabetes in persons age 4 and older. It is intended to replace blood glucose testing for diabetes treatment decisions, unless otherwise indicated.

The System also detects trends and tracks patterns and aids in the detection of episodes of hyperglycemia and hypoglycemia, facilitating both acute and long-term therapy adjustments. Interpretation of the System readings should be based on the glucose trends and several sequential readings over time.

The System is also intended to autonomously communicate with digitally connected devices. The System can be used alone or in conjunction with these digitally connected devices where the user manually controls actions for therapy decisions.

Libre 2 Plus Sensor users:

The FreeStyle Libre 2 Flash Glucose Monitoring System is a continuous glucose monitoring (CGM) device with real time alarms capability indicated for the management of diabetes in persons age 2 and older. It is intended to replace blood glucose testing for diabetes treatment decisions, unless otherwise indicated.

The System also detects trends and tracks patterns and aids in the detection of episodes of hyperglycemia and hypoglycemia, facilitating both acute and long-term therapy adjustments. Interpretation of the System readings should be based on the glucose trends and several sequential readings over time.

The System is also intended to autonomously communicate with digitally connected devices, including automated insulin dosing (AID) systems. The System can be used alone or in conjunction with these digitally connected devices for the purpose of managing diabetes.

Libre 3 Sensor users:

The FreeStyle Libre 3 Continuous Glucose Monitoring System is a real time continuous glucose monitoring (CGM) device with alarms capability indicated for the management of diabetes in persons age 4 and older. It is intended to replace blood glucose testing for diabetes treatment decisions, unless otherwise indicated.

The System also detects trends and tracks patterns and aids in the detection of episodes of hyperglycemia and hypoglycemia, facilitating both acute and long-term therapy adjustments. Interpretation of the System readings should be based on the glucose trends and several sequential readings over time.

The System is also intended to autonomously communicate with digitally connected devices. The System can be used alone or in conjunction with these digitally connected devices where the user manually controls actions for therapy decisions.

Libre 3 Plus Sensor users:

The FreeStyle Libre 3 Continuous Glucose Monitoring System is a real time continuous glucose monitoring (CGM) device with alarms capability indicated for the management of diabetes in persons age 2 and older. It is intended to replace blood glucose testing for diabetes treatment decisions, unless otherwise indicated.

The System also detects trends and tracks patterns and aids in the detection of episodes of hyperglycemia and hypoglycemia, facilitating both acute and long-term therapy adjustments. Interpretation of the System readings should be based on the glucose trends and several sequential readings over time.

The System is also intended to autonomously communicate with digitally connected devices, including automated insulin dosing (AID) systems. The System can be used alone or in conjunction with these digitally connected devices for the purpose of managing diabetes.

The FreeStyle Libre 3 Continuous Glucose Monitoring System (hereinafter also referred to as 'FSL3 System') and FreeStyle Libre 2 Flash Glucose Monitoring System (hereinafter also referred to as the 'FSL2 System') are integrated continuous glucose monitoring (iCGM) systems that provide continuous glucose measurements every minute to provide glucose levels, trends, and real-time alarms capability to aid in the management of diabetes. The FSL2 and FSL3 Systems also provide configurable alarms designed to warn the user of Low Glucose, High Glucose or Signal Loss. The user may make treatment decisions based in part on the sensor glucose results provided by both Systems. The FSL2 and FSL3 Systems require a prescription and are intended for home use.

The subject FSL3 System consists of a sensor (the FreeStyle Libre 3 Sensor (FSL3 Sensor) or FreeStyle Libre 3 Plus Sensor (FSL3 Plus Sensor)) and a primary display device (the FreeStyle Libre 3 Reader (FSL3 Reader) or the FreeStyle Libre App (FSL App) [iOS and Android] downloaded to a compatible phone). The FSL3 Reader and the FSL App do not interact with each other.

The subject FSL2 System consists of a sensor (the FreeStyle Libre 2 Sensor (FSL2 Sensor) or FreeStyle Libre 2 Plus Sensor (FSL2 Plus Sensor)) and a primary display device (the FreeStyle Libre 2 Reader (FSL2 Reader) or the FSL App (iOS and Android) downloaded to a compatible phone). The FSL2 Reader and FSL App do not interact with each other.

Both the FSL2 and FSL3 Systems are compatible with the Libre Data Sharing API cleared in K223537. The display device of the connected FSL2 or FSL3 Systems, which directly receives the data from the sensor, continues to serve as a primary display device for the glucose data and alarms.

This document is a 510(k) summary from Abbott Diabetes Care Inc. regarding their FreeStyle Libre 3 Continuous Glucose Monitoring System and FreeStyle Libre 2 Flash Glucose Monitoring System. It outlines the device details, indications for use, comparison to predicate devices, and a summary of performance testing.

Acceptance Criteria and Study Proving Device Meets Criteria

The provided text focuses on the substantial equivalence of the new FreeStyle Libre 2 Plus and 3 Plus sensors and updated app features to their predicate devices, rather than establishing new acceptance criteria for the entire system's glucose monitoring accuracy. The document states that clinical performance and human factors were "established in the predicate device (K223435) and are not affected by the introduction of the FSL App in this 510(k)." This implies that the glucose accuracy and user interface performance metrics (e.g., MARD, % in Zones A+B, usability outcomes) for the core glucose monitoring function were previously accepted for the predicate devices and are assumed to hold true for the current submission due to the nature of the changes being primarily related to sensor life, age ranges, and app features.

Therefore, the acceptance criteria and performance data discussed below are extrapolated from the types of performance studies conducted to demonstrate substantial equivalence for the modifications presented in this 510(k), particularly regarding safety and compatibility, and from the implied reliance on the predicate device's established clinical performance.

Please note: This response does not contain specific quantitative acceptance criteria or precise performance metrics for glucose accuracy (e.g., MARD values) as these details are explicitly referred to as having been established in the predicate device (K223435) and are not re-evaluated in this submission. The focus of this 510(k) is on the changes from the predicate.

1. Table of Acceptance Criteria and Reported Device Performance

Given the nature of this 510(k) (modifications to existing systems), the presented "acceptance criteria" are derived from the tests conducted to demonstrate that the changes do not adversely affect safety and effectiveness.

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

The document does not provide specific sample sizes for the detailed technical tests (Software V&V, Cybersecurity, Bench Testing for CT/MRI/X-ray). These types of tests typically involve controlled laboratory environments rather than human subject test sets in the traditional sense for clinical performance.

For the core clinical performance (glucose accuracy, etc.), the document explicitly states these characteristics were "established in the predicate device (K223435) and are not affected." Therefore, any sample size for these fundamental performance aspects would refer to those used in the studies for the predicate device, which are not detailed in this 510(k) summary.

Data Provenance: The document does not specify the country of origin for any testing data. The nature of the tests (Software V&V, Cybersecurity, Bench Testing) suggests they are likely conducted in a controlled environment, potentially in-house or by a certified testing facility. The "retrospective or prospective" nature is not specified, but these are typically prospective tests conducted as part of the development and verification process.

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

This type of information (number of experts, qualifications, and ground truth establishment) is typically relevant for clinical studies involving expert adjudication (e.g., for diagnostic imaging devices). Given that the 510(k) summary indicates clinical performance was "established in the predicate device" and that the current submission primarily addresses technical and software improvements/modifications, there's no mention of a new clinical study involving multiple experts to establish ground truth for this specific submission.

For the bench testing related to CT/MRI/X-ray compatibility, ground truth would be established by physical measurements and functional checks against engineering specifications, not by human experts.

4. Adjudication Method for the Test Set

Adjudication methods (e.g., 2+1, 3+1) are typically used in clinical studies, particularly for diagnostic accuracy where multiple human readers interpret data. As explained above, this 510(k) focuses on technical and software changes, and refers back to the predicate device for clinical performance. Therefore, no information on an adjudication method for a test set is provided or expected in this context.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done

No, an MRMC comparative effectiveness study was not done, and it is not typically relevant for a CGM device. MRMC studies are primarily conducted for diagnostic imaging devices to assess how AI assistance impacts human reader performance (e.g., radiologists interpreting scans). CGM devices provide quantitative glucose measurements, and their performance is evaluated directly against a reference method (e.g., laboratory glucose measurements), not through human reader interpretation of complex images or cases.

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

Yes, for the core glucose algorithm, a standalone performance evaluation is inherent to a CGM device. The document explicitly states:

• Glucose Algorithm: "ADC Glucose Algorithm"
• Location of Glucose Algorithm: "FSL2 System: Receiver", "FSL3 System: Sensor"

This implies that the algorithm processes the sensor's raw electrical signals to calculate a glucose value and trend independently. The clinical performance of this algorithm (e.g., MARD against a reference method) would have been part of the studies for the predicate device (K223435). This 510(k) does not present new data for this, but rather relies on the predicate's established performance, stating that ADC (Abbott Diabetes Care) Glucose Algorithm is the "Same" for the subject device.

7. The Type of Ground Truth Used

For Continuous Glucose Monitoring (CGM) devices, the ground truth for establishing accuracy is typically obtained from laboratory reference methods for blood glucose concentration, such as:

• YSI analysis (Yellow Springs Instrument): This is a widely accepted laboratory reference method for measuring glucose in blood or plasma samples.

While not explicitly stated in this 510(k) summary for the ground truth method, it is the standard for CGM accuracy studies which would have been performed for the predicate device to which this submission refers for clinical performance.

8. The Sample Size for the Training Set

The document does not provide a sample size for the training set of the glucose algorithm. This information would typically be detailed in the original predicate device's submission which established the clinical performance. The current 510(k) refers to the "ADC Glucose Algorithm" as being the same as the predicate, indicating no retraining or significant algorithm changes that would necessitate reporting new training data.

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

Similar to the sample size, the specifics of how the ground truth was established for the training set would have been detailed in the original submission for the predicate device. For CGM algorithms, this involves comparing the sensor's raw electrical signals to paired blood glucose values obtained from a highly accurate laboratory reference method (like YSI), collected over time from a cohort of study participants under various glycemic conditions. This establishes the true glucose concentration against which the algorithm learns to convert sensor signals into accurate glucose readings.

Ask a specific question about this device

The Dexcom G7 Continuous Glucose Monitoring System (Dexcom G7 CGM System or G7) is a real time, continuous glucose monitoring device indicated for the management of diabetes in persons 2 years and older.

The Dexcom G7 CGM System is intended to replace fingerstick BG testing for diabetes treatment decisions. Interpretation of the Dexcom G7 CGM System results should be based on the glucose trends and several sequential sensor readings over time. The Dexcom G7 CGM System also aids in the detection of episodes of hyperglycemia and hypodlycemia, facilitating both acute and long-term therapy adjustments.

The Dexcom G7 CGM System is also intended to autonomously communicate with digitally connected devices, including automated insulin dosing (AID) systems. The Dexcom G7 CGM System can be used alone or in conjunction with these digitally connected medical devices for the purpose of managing diabetes.

The Dexcom G7 Continuous Glucose Monitoring System) is an interoperable continuous glucose monitoring (CGM) system intended to continuously measure the interstitial fluid, calculate the qucose reading and make this available to the user. The G7 System is intended for single patient use at home and requires a prescription.

The G7 System comprises the following primary components: a wearable, consisting of a G7 sensor and transmitter worn on the body and a display device, which can be a G7 Mobile App) on an iOS or Android OS smart device, or a G7 Receiver (Receiver).

To achieve the intended functions and performance of the G7 System, one sensor and at least one display device (App or Receiver) must be used together. The user must pair the display device(s) with each unique sensor to enable communication and start a sensor session. During an active session, the sensor reports new glucose data to the display device every 5-minutes. The displays glucose data and provides alerts and information signals to the user. The reportable glucose range for the G7 System is 40 mg/dL to 400 mg/dL. Glucose values below this range are reported as 'LOW' and glucose values above this range are reported as 'HIGH'. The sensor has an expected wear period of up to 10 days with an extended 12-hour grace period after the sensor session. The grace period allows additional time for the user to change the sensor at a convenient time.

The G7 is an interoperable connected device that can communicate glucose readings and other information wirelessly and securely to and from compatible electronic interfaces via the following secure wireless connections:

• Wireless communication from the transmitter directly to an interoperable device communicating through the same protocol

· The Mobile App communicates to another app on a single mobile platform

· The Mobile App communicates through the cloud to another software device

o Dexcom Partner Web APIs: The Dexcom Partner Web APIs enable secure and reliable communication of CGM data to authorized client software intended to receive the cloud. The Partner Web APIs is not intended to be used by automated insulin delivery systems (AID).

Principle of Operation:

The principles of operation for the Dexcom G7 System renain the same as prior generations of Dexcom CGM System uses a wire-type sensing mechanism that continuously measures interstitial glucose levels and uses a radio transmitter to wirelessly communicate glucose data to the display device for the user to see and use accordingly.

The provided text is a 510(k) summary for the Dexcom G7 Continuous Glucose Monitoring System. It states that the device is substantially equivalent to a previously cleared Dexcom G7 Continuous Glucose Monitoring System (K234133). The key difference between the subject device and the predicate device is limited to "BLE communication and associated labeling updates." Crucially, it explicitly states: "No design change was required to support the extended BLE communication." and "No clinical data was necessary to determine substantial equivalence."

Therefore, the only acceptance criteria and study that proves the device meets the acceptance criteria mentioned in this document pertain to this specific change:

Acceptance Criteria and Study for Dexcom G7 Continuous Glucose Monitoring System (K240902)

Given that the submission is for an updated version of an already cleared device (Dexcom G7 K234133) and the only difference noted is related to BLE communication and associated labeling updates, with no design change, the acceptance criteria and study detailed here are specific to proving the extended BLE communication functionality.

1. Table of Acceptance Criteria and Reported Device Performance:

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

The document states, "No design change was required to support the extended BLE communication." and "No clinical data was necessary to determine substantial equivalence." This implies that the testing for the BLE communication range was likely a non-clinical bench top or engineering test.

• Sample Size: Not specified in the provided text, but it would pertain to the number of devices or test repetitions used in the communication range testing.
• Data Provenance: Not specified, but generally, non-clinical engineering tests would be controlled laboratory environments. It is implicitly prospective testing conducted specifically for this regulatory submission.

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

• This information is not applicable for the specific testing described. The acceptance criteria for BLE communication range would be met through quantitative measurements (e.g., signal strength, data transmission success rate over distance) against a pre-defined engineering specification, not through human expert assessment or ground truth establishment in the traditional sense for medical device diagnostics.

4. Adjudication Method for the Test Set:

• This information is not applicable for the specific testing described. Adjudication methods are typically used in clinical studies or image review settings involving human interpretation. The BLE communication range testing would rely on automated data collection and comparison to a specification.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and what was the effect size of how much human readers improve with AI vs without AI assistance:

• This information is not applicable. This submission is for a continuous glucose monitoring system, not an AI-assisted diagnostic imaging device. The document explicitly states, "No clinical data was necessary to determine substantial equivalence."

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

• The primary "performance" discussed for this specific 510(k) is the extended BLE communication range. This would be assessed as a "standalone" technical capability of the device's communication module, without direct human intervention in the communication process itself. However, it's not an "algorithm only" performance assessment in the sense of AI diagnostics.

7. The Type of Ground Truth Used:

• For the BLE communication range, the "ground truth" would be the engineering specification for the extended communication range itself, against which the measured performance of the device's BLE module is compared. It's a quantitative, pre-defined target.

8. The Sample Size for the Training Set:

• This information is not applicable. There is no mention of a "training set" as this is not an AI/machine learning model where a distinct training phase is described.

9. 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 Stelo Glucose Biosensor System is an over-the-counter (OTC) integrated Continuous Glucose Monitor (CCGM) intended to continuously measure, record, analyze, and display glucose values in people 18 years and older not on insulin. The Stelo Glucose Biosensor System helps to detect normal (euglycemic) and low or high (dysglycemic) glucose levels. The Stelo Glucose Biosensor System may also the user better understand how lifestyle and behavior modification, including diet and exercise, impact glucose excursion.

The user is not intended to take medical action based on the device output without consultation with a qualified healtheare professional.

The Stelo Glucose Biosensor system (Stelo System) is an over-the-counter (OTC) interoperable continuous glucose monitoring (iCGM) system.

The Stelo Glucose Biosensor system (Stelo System) is an interoperable connected device that measures and displays estimated glucose values for people who are not on insulin. The Stelo System consists of the following components: the Glucose Sensing Subsystem (GSS) and the Mobile Application Subsystem (MAS). The GSS is comprised of the sensor applicator and on-body wearable, which includes a Bluetooth Low Energy (BLE) molded transmitter, adhesive patch and sensor. The sensor is a small and flexible wire, which is inserted by the applicator into subcutaneous tissue where it converts glucose into electrical current. The transmitter's onboard algorithm converts these measurements into estimated glucose values and calculates the glucose rate of change which are sent every 5 minutes to the MAS is an app that can be downloaded to a compatible smart device and that presents glucose readings and qlucose trend to the user every 15 minutes. As such, the most recent displayed glucose value might be up to 15 minutes old. Each sensor session lasts up to 15 days with an extended 12-hour grace period. The grace period allows additional time for the user to change the sensor at a convenient time.

The proposed Stelo System is based on the same mode of operation and mechanism of reaction as the predicate G7 CGM System (K231081), which uses a wire type sensing mechanism that continuously measures interstitial fluid qlucose levels and a BLE enabled radio transmitter to wirelessly communicate CGM data to compatible display devices at regular 5-minute intervals. These data are also able to be reliably and securely transmitted to other digitally connected devices, excluding insulin pens and Automated Insulin Dosing (AID) systems.

The Stelo System uses the same hardware design as the predicate G7 CGM System. The Stelo GSS firmware is designed to support a factory-calibrated only device (without calibration inputs), to extend the sensor wear duration from 10 to 15 days while maintaining the accuracy of the device, and to connect to authorized display devices only (i.e., Stelo MAS). The Stelo MAS includes a redesigned user interface (UI) tailored to the Stelo System's user population to simplify the use of the device. The UI includes an app onboarding specific to the Stelo MAS design and its intended use, the most recent glucose value and trend graph which are updated every 15 minutes, a narrowed glucose range display from 70 mg/dL, and an "Insights" feature providing the time in range percentage with suggestions to help users improve their time in range. The Ul does not provide any glucose or system alerts.

The Dexcom Stelo Glucose Biosensor System is a continuous glucose monitoring (CGM) device intended for over-the-counter (OTC) use by adults aged 18 and older who are not on insulin. The device continuously measures, records, and displays glucose values, helping to detect normal, low, or high glucose levels and allowing users to understand the impact of lifestyle modifications on glucose excursion.

Here's a breakdown of the acceptance criteria and study information:

1. Table of Acceptance Criteria and Reported Device Performance:

The document explicitly states that the device meets the iCGM special controls for clinical performance set forth in 21 CFR 862.1355. While specific numerical acceptance criteria (e.g., MARD values, percentages of readings within certain zones) are not provided in the summary, the general umbrella acceptance criterion is:

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

The document states: "A clinical study was conducted to evaluate the safety and effectiveness of the Stelo Glucose Biosensor System. The effectiveness of the device was evaluated with respect to reference venous plasma sample YSI measurements across the measuring range throughout a 15-day wear duration with a 12-hour grace period in adult (18 years and older) participants with diabetes."

• Test Set Sample Size: The exact number of participants is not specified, but it refers to "adult (18 years and older) participants with diabetes."
• Data Provenance: Prospective clinical study data. The country of origin is not explicitly stated in the provided text.

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

The ground truth for the clinical study was established using "reference venous plasma sample YSI measurements." This usually refers to laboratory-based glucose analysis performed by trained technicians, not "experts" in the context of interpretation (like radiologists). The number and qualifications of technicians are not mentioned.

4. Adjudication Method for the Test Set:

Not applicable, as the ground truth was established through laboratory reference measurements (YSI) of venous plasma samples, which are generally considered the gold standard and do not typically require adjudication.

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

No, an MRMC comparative effectiveness study was not done. The study evaluated the standalone performance of the Stelo Glucose Biosensor System against reference measurements. The document does not mention any human readers or human-AI interaction in the context of this study.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done:

Yes, a standalone study was done. The clinical study evaluated the Stelo Glucose Biosensor System's effectiveness by comparing its glucose measurements to reference venous plasma YSI measurements, implying an assessment of the device's algorithmic and sensing accuracy without human intervention for interpretation beyond what the user does with the displayed values.

7. The Type of Ground Truth Used:

The ground truth used was laboratory reference measurements ("reference venous plasma sample YSI measurements").

8. The Sample Size for the Training Set:

The document does not provide any information about the training set size for the algorithms within the Stelo Glucose Biosensor System. This information is typically not included in a 510(k) summary unless the submission is for an AI/ML SaMD where the training data characteristics are a primary focus. Given that the Stelo System uses the "same hardware design as the predicate G7 CGM System" and its GSS firmware is designed to support a "factory-calibrated only device (without calibration inputs)," it suggests that the core algorithms might have been trained previously and validated, or leveraged from the predicate device's development.

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

This information is not provided in the document.

Ask a specific question about this device

The Dexcom G7 Continuous Glucose Monitoring System (Dexcom G7 CGM System or G7) is a real time, continuous qlucose monitoring device indicated for the management of diabetes in persons 2 years and older.

The Dexcom G7 CGM System is intended to replace fingerstick BG testing for diabetes treatment decisions. Interpretation of the Dexcom G7 CGM System results should be based on the glucose trends and several sequential sensor readings over time. The Dexcom G7 CGM System also aids in the detection of episodes of hyperglycemia and hypodlycemia, facilitating both acute and long-term therapy adjustments.

The Dexcom G7 CGM System is also intended to autonomously communicate with digitally connected devices, including automated insulin dosing (AID) systems. The Dexcom G7 CGM System can be used alone or in conjunction with these digitally connected medical devices for the purpose of managing diabetes.

The Dexcom G7 Continuous Glucose Monitoring System (G7 System) is an interoperable continuous glucose monitoring (CGM) system intended to continuously measure the glucose in the interstitial fluid, calculate the glucose reading and make this available to the user.The G7 System is intended for single patient use at home and requires a prescription.

The G7 System comprises the following primary components: a wearable, consisting of a G7 sensor and transmitter worn on the body and a display device, which can be a G7 Mobile App) on an iOS or Android OS smart device, or a G7 Receiver (Receiver).

The proposed G7 CGM System is modified to allow users to display glucose data directly from the transmitter on compatible iOS smartwatches.

To achieve the intended functions and performance of the G7 System, one sensor and at least one display device (App or Receiver) must be used together. The user must pair the display device(s) with each unique sensor to enable communication and start a sensor session. During an active session, the sensor reports new glucose data to the display device every 5-minutes. The displays glucose data and provides alerts and information signals to the user. The reportable glucose range for the G7 System is 40 mg/dL to 400 mg/dL. Glucose values below this range are reported as 'LOW' and glucose values above this range are reported as 'HIGH'. The sensor has an expected wear period of up to 10 days with an extended 12-hour grace period after the sensor session. The grace period allows additional time for the user to change the sensor at a convenient time.

The G7 is an interoperable connected device that can communicate glucose readings and other information wirelessy and securely to and from compatible electronic interfaces via the following secure wireless connections:

• · Wireless communication from the transmitter directly to an interoperable device communicating through the same protocol
• · The Mobile App communicates to another app on a single mobile platform
• · The Mobile App communicates through the cloud to another software device o Dexcom Partner Web APIs: The Dexcom Partner Web APIs enable secure and reliable communication of CGM data to authorized client software intended to receive the data through the cloud. The Partner Web APIs is not intended to be used by automated insulin delivery systems (AID).

Principle of Operation:

The principles of operation for the Dexcom G7 System renain the same as prior generations of Dexcom CGM System uses a wire-type sensing mechanism that continuously measures interstitial glucose levels and uses a radio transmitter to wirelessly communicate glucose data to the display device for the user to see and use accordingly.

I am sorry, but the provided text does not contain the specific information required to describe the acceptance criteria and the study that proves the device meets those criteria, especially regarding a table of acceptance criteria and reported device performance, sample size for test and training sets, data provenance, expert involvement for ground truth, adjudication methods, MRMC studies, or standalone algorithm performance.

The document is a 510(k) premarket notification letter from the FDA to Dexcom Inc. for their G7 Continuous Glucose Monitoring System, confirming its substantial equivalence to a predicate device. It briefly mentions non-clinical testing performed to establish performance characteristics related to the "Direct to Watch (DTW) feature" (EMC, communication range, human factors, software V&V, cybersecurity) and states that these tests demonstrate the system meets "pre-defined acceptance criteria." However, it does not detail what those acceptance criteria are or present the performance results against them. It also explicitly states, "No clinical data was necessary to determine substantial equivalence."

Therefore, I cannot fulfill your request for the detailed information as the source text does not provide it.

Ask a specific question about this device

The t:slim X2 Insulin Pump with Interoperable Technology (the pump) is intended for the subcutaneous delivery of insulin, at set and variable rates, for the management of diabetes melliting insulin. The 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 pump is intended for single patient, home use and requires a prescription. The Pump is indicated for use in individuals 2 years of age and greater.

The t:slim X2 Insulin Pump with Interoperable Technology is an ambulatory, battery operated, rate-programmable infusion pump designed for the subcutaneous delivery of insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin.

The t:slim X2 insulin pump includes a disposable cartridge with a 300 unit reservoir which is filled with insulin by the user with the use of the syringe and needle. The cartridge needs to be changed every 48-72 hours depending on the type of insulin used.

The pump is motor driven to deliver patient programmed basal rates and boluses through an infusion set into subcutaneous tissue. The desired timing and quantity of insulin delivery (bolus or basal) is programmed by the patient based on their healthcare provider's recommendations.

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

The t:connect mobile app enables a user to connect a smartphone to the pump using Bluetooth® wireless technology to display pump information and perform some pump functions on the smartphone as well as display pump notifications. The t:connect mobile app can transmit pump and therapy data from the pump to the cloud as long as the user's smartphone is connected to the internet.

The pump is designed to be able to receive and display alerts and alarms to users based on information received from other interoperable devices.

The pump is compatible with Interoperable Automated Glycemic Controllers, such as Basal-IQ Technology (K193483) and Control IQ Technology (K200467) to aid in diabetes management. The latter is being submitted concurrently.

In addition, the Subject Device is compatible with iCGM systems cleared under K223931 21 CFR 862.1355.

The provided text describes the 510(k) summary for the Tandem Diabetes Care t:slim X2 Insulin Pump with Interoperable Technology (K232380). This submission focuses on a change to the age indication for the device, lowering it to individuals 2 years of age and greater.

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

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of specific quantitative acceptance criteria (e.g., minimum accuracy percentages, specific error rates) for the device's performance in relation to the expanded age indication. Instead, it makes a general statement about safety and effectiveness.

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

The document mentions "clinical testing was performed to support the expanded age indication" and "the clinical testing provided in this 510(k) demonstrate that the t:slim X2 Insulin Pump with Interoperable Technology is the same as the predicate device in safety and effectiveness."

• Sample Size for Test Set: Not explicitly stated.
• Data Provenance: Not explicitly stated as retrospective or prospective, nor the country of origin. However, the nature of "clinical testing" for an expanded age indication typically implies a prospective clinical study involving the new patient population.

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

This information is not provided in the document. The text does not describe a process of expert review or establishing ground truth in the context of the clinical testing.

4. Adjudication Method for the Test Set

This information is not provided in the document.

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

This information is not provided in the document. The study described is a clinical evaluation of the device itself rather than a comparison of human readers with and without AI assistance.

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

The device is an insulin pump, which is a physical medical device that delivers insulin. While it has interoperable technology and can communicate with automated insulin dosing software, the "performance data" mentioned pertains to the overall device in a clinical setting with human interaction (patient programming, healthcare provider recommendations). Therefore, a "standalone algorithm only" performance study as typically understood for AI/CAD devices is not directly applicable or explicitly described in this context. The focus is on the device's safety and effectiveness for insulin delivery in the expanded age group.

7. The Type of Ground Truth Used

The "ground truth" for the clinical testing would be the actual physiological responses and outcomes of the pediatric patients using the insulin pump, as assessed by healthcare professionals. This would include parameters like blood glucose levels, incidence of hypoglycemia/hyperglycemia, and adverse events. The document refers to "safety and effectiveness," which points to clinical outcomes.

8. The Sample Size for the Training Set

The document describes a clinical study to support an expanded age indication for an existing device. This implies that the device's core algorithm and functionality were developed and "trained" (in a non-AI sense, meaning designed and validated) prior to this specific submission. The text does not provide information regarding a training set for an AI/algorithm, as this submission is not about the initial development or a new AI component. If the "interoperable technology" involves AI, the training data for that specific AI component is not detailed here.

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

Given that this submission is for an expanded age indication of an existing device, and not a new AI model, the concept of a "training set" and its ground truth establishment, as typically understood for AI/ML, is not applicable or described in this document. The device's fundamental insulin delivery mechanism and safety profile would have been established through prior design, testing, and regulatory submissions. The current clinical testing validates the device's safety and effectiveness for a younger population.

Ask a specific question about this device

The Dexcom G7 Continuous Glucose Monitoring (CGM) System is a real time, continuous glucose monitoring device indicated for the management of diabetes in persons 2 years and older.

The Dexcom G7 CGM System is intended to replace fingerstick BG testing for diabetes treatment decisions. Interpretation of the Dexcom G7 CGM System results should be based on the glucose trends and several sequential sensor readings over time. The Dexcom G7 CGM System also aids in the detection of episodes of hyperglycemia and hypoglycemia, facilitating both acute and long-term therapy adjustments.

The Dexcom G7 CGM System is also intended to autonomously communicate with digitally connected devices, including automated insulin dosing (AID) systems. The Dexcom G7 CGM System can be used alone or in conjunction with these digitally connected medical devices for the purposes of managing diabetes.

The Dexcom G7 Continuous Glucose Monitoring System) is an interoperable connected device that measures and displays estimated dlucose values for people with diabetes. The G7 System consists of the following components: the Glucose Sensing Subsystem (GSS), the Mobile Application Subsystem (MAS), the Receiver Subsystem (RVS), The GSS is comprised of the sensor applicator and on-body wearable, which includes a Bluetooth Low Energy (BLE) transmitter, adhesive patch and sensor. The sensor is a small and flexible wire, which is inserted by the applicator into subcutaneous tissue where it converts glucose into electrical current. The sensor has an expected wear period of up to 10 days with an extended 12-hour grace period after the sensor session. The grace period allows additional time for the user to change the sensor at a convenient time.

The transmitter is pre-connected to the sensor and is cradled into the applicator needle inside the applicator housing. The applicator external housing consists of a cap and shroud which utilize a threaded cap and seal to create the sterile barrier system. A deployment lock mechanism prevents insertion of the on-body wearable until the applicator is pressed against the insertion site. The insertion is then completed with a single button press vertical spring deployed mechanism, which introduces the sensor via the subcutaneous tissue while also placing the embedded wearable onto the body. The wearable adheres to the skin via an adhesive patch.

After deployment, the transmitter initiates automatic wakeup and session start. The sensor's small and flexible wire converts qlucose to electrical current and the transmitter samples the electrical current produced by the sensor. The transmitter's onboard algorithm converts these measurements into estimated qlucose values and calculates the glucose rate of change; the data are sent every 5 minutes to the MAS and/or the RVS. The MAS and RVS are display devices that present the current ducose reading and glucose trend to the user. Both display devices alert the user when glucose levels are outside of a target zone and when specific system states occur. The G7 System is designed to communicate to one or both display devices simultaneously.

The G7 System is also designed to communicate estimated glucose values, trend and system information to other compatible electronic interfaces via the following secure wireless connections:

• . Wireless communication from the transmitter directly to an interoperable device communicating through the same protocol
• . The app communicates to another app on a single mobile platform
• The app communicates through the cloud to another software device ●
  • Dexcom Partner Web APIs: The Dexcom Partner Web APIs enable secure and o reliable communication of CGM data to authorized client software intended to receive the data through the cloud. The Partner Web APIs is not intended to be used by automated insulin delivery systems (AID).

The proposed G7 CGM System uses the same mode of operation and mechanism of reaction as the predicate G7 CGM System (K213919). The proposed G7 CGM System uses an alternate GSS wearable adhesive.

The provided text describes a 510(k) premarket notification for the Dexcom G7 Continuous Glucose Monitoring (CGM) System. The submission is for a modification to an already cleared device, specifically changing the adhesive patch.

Since this is a submission for a modification, the document frequently refers to the "predicate device" (K213919), which is essentially the previous version of the Dexcom G7. The current submission argues that the modified device is "substantially equivalent" to this predicate. As such, the performance data presented (or referenced indirectly) in this document likely refers to the performance of the predicate device, which the modified device is claimed to match.

Here's an analysis of the acceptance criteria and study information, extracting what's available and noting what is not explicitly stated in this particular document:

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

The document states: "The proposed Dexcom G7 CGM System was verified and validated according to Dexcom's internal design control process and in accordance with special controls for integrated continuous glucose monitoring systems. This testing demonstrated that the proposed system performed according to its specifications; and the proposed system has met its technological and performance criteria which have not changed from the predicate device."

This statement asserts that the device meets its performance criteria and specifications, and that these criteria have not changed from the predicate device. However, the exact quantitative acceptance criteria (e.g., specific MARD values, accuracy at different glucose ranges) and the reported device performance against those criteria are not explicitly provided in this document. This information would typically be found in the full 510(k) submission not included here, likely in the sections detailing the clinical study for the original device clearance (K213919).

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

This document explicitly states it is a modification to a previously cleared device. It only mentions that the "proposed Dexcom G7 CGM System was verified and validated according to Dexcom's internal design control process and in accordance with special controls for integrated continuous glucose monitoring systems."

Therefore, the specific sample size, data provenance (country of origin), and whether the study was retrospective or prospective are not provided in this document. This information would be crucial for the original submission (K213919) that established the performance of the Dexcom G7.

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)

Given that this is a Continuous Glucose Monitoring (CGM) system, the "ground truth" for glucose measurements is typically established using a reference laboratory blood glucose analyzer, not human experts. Therefore, the concept of "number of experts" is not applicable in the context of establishing ground truth for glucose values in this type of device.

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

Since the ground truth is established by a laboratory analyzer, there is no adjudication method involving human experts for the glucose values themselves.

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

The Dexcom G7 is a standalone medical device that measures glucose; it is not an AI-assisted diagnostic imaging device that involves human readers interpreting images. Therefore, a multi-reader multi-case (MRMC) comparative effectiveness study with human readers assisting AI is not applicable to this device.

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

This document describes the Dexcom G7 CGM System as "a real time, continuous glucose monitoring device." Its core function is to measure and display estimated glucose values. The device includes a "transmitter's onboard algorithm" that "converts these measurements into estimated glucose values and calculates the glucose rate of change." It also states, "The Dexcom G7 CGM System is intended to replace fingerstick BG testing for diabetes treatment decisions." This strongly implies that the device is intended for standalone performance in providing glucose measurements that can be used directly for treatment decisions, without requiring human interpretation of raw sensor data or assistance from human operators to derive the glucose values themselves.

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

The ground truth for a CGM device is established by comparison with a highly accurate reference method for measuring blood glucose, typically a laboratory-grade blood glucose analyzer (e.g., YSI analyzer) measuring venous blood samples. This is mentioned implicitly by the nature of CGM device testing.

8. The sample size for the training set

This document pertains to a 510(k) submission for a modified device, specifically a change in adhesive. While the device (and its underlying algorithm) would have been developed using training data, the size of that training set is not provided in this specific document. It would have been part of the original K213919 submission.

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

Similar to the ground truth for the test set, the ground truth for any training data used for the algorithm in a CGM device would have been established by comparison with a highly accurate reference method for measuring blood glucose, usually a laboratory blood glucose analyzer. This information is not explicitly provided in this document but is standard practice for CGM development.

In summary:

This 510(k) submission for the Dexcom G7 focuses on demonstrating substantial equivalence of a modified device (specifically, a new adhesive) to a previously cleared predicate device. It asserts that the modifications do not change the intended use or fundamental scientific technology, and that the device continues to meet its performance specifications. However, the detailed performance data, study design, and sample sizes for the original clinical validation (which would contain the answers to many of these questions) are not included in this summary document. This document emphasizes that "the proposed G7 CGM System uses the same mode of operation and mechanism of reaction as the predicate G7 CGM System (K213919)" and its "technological and performance criteria ... have not changed from the predicate device."

Ask a specific question about this device