(87 days)
The Glooko device system for Glooko Application is data management software intended for use in home and professional settings to aid individuals with diabetes and their health care professionals in review, analysis and evaluation of blood glucose readings to support an effective diabetes management program. The Glooko device system for Glooko Application connects to compatible FDA cleared meters and allows users to transfer their blood glucose meter results to their mobile devices running on Android Operating System.
The Glooko device system for Glooko Application is not intended to provide treatment decisions or to be used as a substitute for professional healthcare advice.
The Glooko device system for Glooko Application is used to aid individuals with diabetes in the download, review, analysis, evaluation, and communication of their blood glucose readings. The system allows users to download readings from compatible, FDA-cleared, commercial blood glucose meters to their Android Operating System mobile devices, and then share this information with healthcare professionals. It is intended for use both in home and professional settings to support an effective diabetes management program. The data may be displayed on supported devices to provide an online view of all collected data and notes from the Glooko Android Application. The system does not provide treatment decisions and cannot be used as a substitute for professional healthcare advice.
The Glooko device system for Glooko Application consists of the following components:
- The Glooko MeterSync Cable for Android
- The Glooko Application
The provided document describes the Glooko Device System for Glooko Application, which is data management software for individuals with diabetes to download, review, analyze, evaluate, and communicate their blood glucose readings. The submission is a Special 510(k) and demonstrates substantial equivalence to a predicate device (K130886). The primary difference is the operating system platform (Android vs. iOS) and the meters supported.
Here's an analysis of the acceptance criteria and study information provided:
1. Table of Acceptance Criteria and Reported Device Performance:
The document does not explicitly present a table of quantitative acceptance criteria for device performance. Instead, it states that "All test results fell within the pre-determined specification parameters." The studies focused on confirming that the device performs according to its stated intended use and specifications, particularly regarding data integrity, software features, and error handling.
| Acceptance Criteria Category | Reported Device Performance |
|---|---|
| Functional Performance | - Data Integrity Verification: Passed, all test results within pre-determined specification parameters. |
- Software Design/features Verification: Passed, all test results within pre-determined specification parameters.
- Error Handling Testing: Passed, all test results within pre-determined specification parameters. |
| Intended Use | - Device performs according to its stated intended use (aid in review, analysis, evaluation, and communication of blood glucose readings, support diabetes management program). |
| Substantial Equivalence | - Demonstrated substantial equivalence to the predicate device (K130886) in intended use, function, and technology for downloading and analyzing blood glucose data. |
2. Sample Size Used for the Test Set and Data Provenance:
The document mentions "functional testing performed pursuant to Glooko's design verification protocol" and lists categories like "Data Integrity Verification, Software Design/features Verification, and error handling testing." However, it does not specify the sample size used for these test sets (e.g., number of data transfers, number of unique meter readings, etc.).
Data Provenance: The document does not explicitly state the country of origin of the data or whether the data used for testing was retrospective or prospective. Given the nature of a software application for managing blood glucose readings, the "data" would likely refer to simulated or actual blood glucose readings downloaded from various meters.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts:
The document does not mention the use of experts to establish ground truth for the test set. The validation appears to be based on internal verification protocols and specifications. For a data management system that transfers and displays blood glucose readings, ground truth would typically involve comparing the downloaded data against the original data stored in the blood glucose meters or a reference system. This verification is usually performed by engineers and quality assurance personnel, rather than medical experts, unless the displayed interpretation itself needed clinical validation.
4. Adjudication Method for the Test Set:
The document does not describe an adjudication method for the test set. The testing appears to be based on a pass/fail criteria against pre-determined specifications, implying direct verification rather than a consensus-based 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:
A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not conducted and is not relevant for this type of device. The Glooko Device System is a data management tool for blood glucose readings; it is not an AI-powered diagnostic or interpretive tool that assists human readers (e.g., radiologists interpreting images). Therefore, there is no "human reader" component to improve or an "AI assistance" to measure an effect size against.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done:
The "standalone" performance in this context refers to the Glooko Application and MeterSync Cable's ability to accurately download, store, process (generate graphs, statistics), and display blood glucose data without human intervention beyond initiating the download and viewing the data. The documentation indicates that functional testing, including data integrity verification, software design/features verification, and error handling, was performed. This implies a standalone assessment of the software's functionality in accurately handling the data.
7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.):
For a device like the Glooko Application, the "ground truth" for the test set would be the actual blood glucose readings stored on the compatible FDA-cleared blood glucose meters. The system's performance is validated by ensuring that the data downloaded, processed, and displayed by the Glooko Application precisely matches the data from the source meters. This is a direct comparison, not based on expert consensus, pathology, or outcomes data.
8. The Sample Size for the Training Set:
The Glooko Device System is a deterministic software application for data management, not a machine learning or AI algorithm that requires a "training set." Therefore, there is no training set mentioned or implied in the document.
9. How the Ground Truth for the Training Set Was Established:
Since there is no training set for this device, a method for establishing its ground truth is not applicable.
§ 862.1345 Glucose test system.
(a)
Identification. A glucose test system is a device intended to measure glucose quantitatively in blood and other body fluids. Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus, neonatal hypoglycemia, and idiopathic hypoglycemia, and of pancreatic islet cell carcinoma.(b)
Classification. Class II (special controls). The device, when it is solely intended for use as a drink to test glucose tolerance, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 862.9.