Search Results

BlueStar® Rx is indicated for use by healthcare providers (HCPs) and their patients – aged 18 years and older – who have type 1 or type 2 diabetes. BlueStar® Rx analyzes, and reports blood glucose test results and supports medication adherence. In addition, BlueStar® Rx provides coaching messages (motivational, and educational) based on real-time blood glucose values and trends. It includes software intended for use on mobile phones or personal computers in the home or in professional healthcare settings. The software also allows for entry of other diabetes-related healthcare information and provides educational information to aid in diabetes self-management.

· For bolus insulin users with type 1 or type 2 diabetes, BlueStar® Rx includes an insulin dose calculator to allow patients to use their prescribed regimen to calculate a dose of bolus insulin for a given amount of carbohydrates and/or blood glucose value.

• For basal insulin users with type 2 diabetes, BlueStar® Rx includes an Insulin Adjustment Program (IAP) which calculates appropriate long-acting basal insulin doses for titrating insulin levels based on configuration by a healthcare provider.

• For bolus insulin users with type 2 diabetes, BlueStar® Rx's IAP calculates appropriate dose adjustments of bolus insulin based on configuration of a healthcare provider. Qualified type 2 diabetes patients are those who are not achieving glycemic targets despite optimization of their basal insulin dose or their current bolus insulin regimen.

· For premixed insulin users with type 2 diabetes, BlueStar® Rx's IAP calculates appropriate dose adjustments of premixed insulin based on the configuration of a healthcare provider. Qualified type 2 diabetes patients are those who are not achieving glycemic targets and who do not take other types of insulin.

The algorithms for the IAP are not designed for the titration of NPH, regular human premixed insulins. The healthcare provider must activate the IAP and configure it with patient-specific parameters.

BlueStar® Rx is not intended to replace the care provided by a licensed healthcare professional, including prescriptions, diagnosis, or treatment.

Subject device (BlueStar® Rx) is a modified version of the predicate (BlueStar® Rx cleared under K193654). BlueStar® Rx maintains the basic features / functionality of the predicate and adds the titration of fast-acting bolus insulin doses and premixed insulins for qualified type 2 diabetes patients. Qualified patients are those with type 2 diabetes whose blood glucose is not adequately managed on current insulin therapies (e.g., using basal insulin) and/or non-insulin therapies.

This bolus insulin and premixed titration feature is included as part of the expanded Insulin Adjustment Program (IAP) in BlueStar® Rx. The predicate (BlueStar® Rx, K193654) is a standalone software system intended to be used by healthcare providers (HCPs) and their patients aged 18 years and older - who have type 1 or type 2 diabetes. The system is intended to assist type 1 and type 2 diabetes patients to self-manage their disease. Like the predicate, the subject device (BlueStar® Rx) is intended to provide secure capture, storage, and transmission of blood glucose data as well as other information to aid in diabetes self-management. Patients receive guidance on diabetes self-management, are encouraged to reach out to their healthcare team when needed and have access to a bolus insulin calculator. The insulin adjustment program (IAP) of the predicate (BlueStar® Rx, K193654) already includes the ability to titrate long-acting basal insulin for patients with type 2 diabetes. In this submission, fast-acting bolus insulin and premixed insulin titration features are added to the subject device's (BlueStar® Rx) IAP for patients with type 2 diabetes.

Health care providers (HCPs) will be required to initiate and manage the titration of basal, bolus and premixed insulin titration for their qualified type 2 diabetes patients using the following two interfaces:

• Web based HCP interface for use by the providers to prescribe insulin doses for the qualified type 2 diabetes patients.
• Web and mobile patient interface for use by patients to follow provider's insulin titration plan.

The IAP feature in subject device (BlueStar® Rx) provides directions to the patients based on prescription by their HCP for titrating basal, bolus and premixed insulin doses.

The document describes the BlueStar® Rx device, a modified version of a previously cleared device (K193654), which now includes expanded Insulin Adjustment Program (IAP) capabilities for fast-acting bolus insulin and premixed insulin titration for qualified type 2 diabetes patients.

The document does not provide a table of acceptance criteria and reported device performance in a numerical format. Instead, it states that "Performance testing demonstrated that the BlueStar® Rx performed as intended." The performance testing listed are:

• Software verification and validation per FDA Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices (May 11, 2005) for a Major Level of Concern.
• Cybersecurity evaluation per FDA Guidance Content of Premarket Submissions for Management of Cybersecurity in Medical Devices Guidance for Industry and Food and Drug Administration Staff, (October 2, 2014), specifically addressing Identify and Protect, Detect, Response and Recover.
• Human Factors testing conducted with intended user populations of patients and healthcare providers. The submission confirmed that the user interface was adequately validated.

Based on the information provided, here are the answers to your questions:

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

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 explicitly state the sample size for the test set or the data provenance for the software, cybersecurity, or human factors testing. It refers to human factors testing being conducted with "the intended user populations of patients and healthcare providers" but doesn't specify numbers.

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

This information is not provided in the document. For the software testing, the ground truth would likely be the expected output of the algorithms given specific inputs, which would be established during development and verified against known medical protocols, but no specifics are given regarding expert involvement in establishing this "ground truth" for the test set.

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

This information is not provided in the document.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

A multi-reader multi-case (MRMC) comparative effectiveness study was not conducted, as stated under "Clinical Tests" where it says "Not Applicable." The device is a 'Drug Dose Calculator' and primarily provides recommendations based on algorithms, rather than being an AI-assisted diagnostic tool that human readers would interpret.

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

The document implies that the performance testing (software verification and validation) for the algorithms, particularly the new bolus and premixed insulin titration features, would inherently be standalone algorithm testing. The IAP "calculates appropriate dose adjustments" (page 2), indicating the algorithm's direct output. However, the system is designed to operate under the supervision of a healthcare provider ("HCP inputs are entered and confirmed using the HCP web portal. HCP can monitor and adjust treatment plan." - page 6). So, while the calculation itself is standalone, the overall system is not without human-in-the-loop. The human factors testing would assess the interaction with the human users, but the core algorithmic performance would be tested standalone.

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

The ground truth for the algorithms is implicitly based on evidence-based titration algorithms from clinical studies (e.g., AUTONOMY study, INITIATE study, Adjust to Target in Type 2 Diabetes, Real-World Approach) as referenced in Note-2 on page 9 and the detailed comparison table (page 6). This effectively means the ground truth is derived from established clinical protocols and research outcomes.

8. The sample size for the training set:

The document does not specify a training set sample size. The BlueStar® Rx is a software medical device that uses predefined algorithms and does not appear to be a machine learning model that undergoes a typical training phase with a distinct training dataset. Its functionality is based on established clinical algorithms rather than learned patterns from a large dataset.

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

As the device uses predefined, evidence-based clinical algorithms rather than having a machine learning training set, the concept of establishing ground truth for a "training set" in the traditional AI sense is not applicable. The underlying algorithms (e.g., AUTONOMY, INITIATE) were developed and validated through prior clinical research and studies, which would have established their efficacy and safety based on patient outcomes and expert consensus in those original studies.

Ask a specific question about this device