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 is intended to provide secure capture, storage, and transmission of glucose data as well as information to aid in diabetes self-management. BlueStar Rx automatically receives insulin dose related data when connected to compatible Tempo Smart Button™ device via wireless Bluetooth® technology and has the ability to detect and mark which doses are prime and which are injected insulin. BlueStar Rx analyzes and reports glucose test results and supports medication adherence. In addition, BlueStar Rx provides coaching messages (motivational, and educational) based on real-time glucose values and trends. It includes software intended for patient use on mobile phones and software intended for healthcare provider use through computer web browsers. The software also allows for entry of other diabetes-related healthcare information and provides educational information.

• For bolus insulin users with type 2 diabetes, BlueStar Rx includes an insulin dose calculator to allow patients to use their prescribed regimen to calculate a dose of bolus insultin for a given amount of carbohydrates and/or 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 levels based on configuration by a healthcare provider. The healthcare provider must activate the IAP and configure it for patient-specific parameters.

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

BlueStar® 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 is intended to provide secure capture, storage, and transmission of glucose data as well as information to aid in diabetes self-management. BlueStar automatically receives insulin dose related data when connected to compatible Tempo Smart Button™ device via wireless Bluetooth® technology and has the ability to detect and mark which doses are prime and which are injected insulin. BlueStar analyzes and reports glucose test results and supports medication adherence. In addition, BlueStar provides coaching messages (motivational, behavioral, and educational) based on real-time glucose values and trends. It includes software intended for patient use on mobile phones and software intended for healthcare provider use through computer web browsers. The software also allows for entry of other diabetes-related healthcare information and provides educational information.

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

BlueStar® (subject device) combines the existing diabetes self-management features of the predicate (BlueStar® and BlueStar® Rx, K193654) with the automatic tracking of insulin delivery functionality of the reference InPen System (K160629). BlueStar maintains all of the features of the predicate and adds the capability to connect with compatible devices connected with insulin pens via Bluetooth wireless technology. In this submission, the predicate device is being modified such that it can receive insulin dose-related data when connected to a Tempo Smart Button™ (TSB). The TSB when attached to a disposable Tempo Pen (insulin pen), can transfer dose-related data (corresponding to the brand of insulin, dose amount, date, and time) via Bluetooth® Low Energy (Bluetooth) wireless technology.

BlueStar is a Software as a Medical Device (SaMD) intended to be used by healthcare providers (HCPs) and their patients – aged 18 years and older - who have type 1 or type 2 diabetes. BlueStar is intended to assist patients in managing their diabetes with guidance from their providers. BlueStar has two versions – BlueStar (Over the Counter, OTC) and BlueStar Rx (prescription use version).

BlueStar is comprised of the following software applications (app):

• iOS and Android based mobile apps for patients .
• web-based app (web-portal) for HCPs ●

BlueStar requires initial registration before the patient can access the software applications.

BlueStar is compatible with devices including Blood Glucose Meters (BGM), Blood Pressure Monitors, Continuous Glucose Monitors (CGM) , Tempo Smart Button™ 2, Weight Scales, Activity Trackers. Data, including blood glucose values, blood pressure, medications, carbohydrates, physical activity, weight, and sleep are entered, stored and processed in the patient software applications. Data can be entered manually or automatically via Bluetooth for compatible devices. Additionally, the mobile application for patients is capable of automatically receiving, storing, processing, and displaying insulin data from the Tempo Smart Button via Bluetooth.

The BlueStar apps for patients function as an information repository (logbook and Personal Health Record) and diabetes education resource (curriculum, articles, videos). Patients also receive in-the-moment coaching (Real Time Feedback messages), Pattern Reports and SMART Visit Reports that can be shared with their providers. Coaching messages are motivational, behavioral, and educational in nature and are based on data (and trends) including real-time blood glucose, blood pressure, and weight. Patients receive guidance on diabetes selfmanagement and are encouraged to reach out to their healthcare team when needed. Patients also receive insights based on data entered and trends detected by the app. BlueStar patient apps include a secure communication system (Message Center) as well as a medication information repository (dose and schedule). Qualified type 1 and type 2 diabetes patients have access to a bolus insulin calculator (cleared under K190013). Qualified type 2 diabetes patients have access to the Insulin Adjustment Program (IAP) to titrate long-acting basal insulin (cleared under K193654). Patients use their mobile software applications to follow their HCP's bolus insulin prescription or basal insulin titration plan. The bolus insulin calculator and basal insulin titration features are only available in BlueStar Rx for use under the direction of their HCP.

The provider can review patient information, workflows and decision support information using the web-based software application for HCP. The HCP can initiate and manage basal insulin titration (IAP) and the bolus insulin calculator prescription / parameters through the web-based software application for HCP.

The SMART Visit Report includes data summary, analysis, and decision support for treatment as well as psychosocial issues identified by patient survey responses within the app. The SMART Visit Report can be sent by the patient to his/her HCP from the mobile app. The HCP can also generate SMART Visit Reports from their web portal.

The provided text is a 510(k) summary for the Welldoc BlueStar® and BlueStar® Rx devices. It details the device description, indications for use, comparison to predicate devices, and performance testing. However, it explicitly states "Not Applicable" under "Clinical Tests," indicating that the submission did not include a clinical study to prove the device meets specific acceptance criteria based on human subject data.

Therefore, I cannot fulfill your request for:

• A table of acceptance criteria and the reported device performance: This would typically come from a clinical study with predefined endpoints and success metrics.
• Sample size used for the test set and the data provenance: Clinical test sets were not used.
• Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable as a clinical test set with ground truth established by experts was not described.
• Adjudication method for the test set: Not applicable.
• 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 applicable.
• If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: Not applicable for a clinical study context. The performance testing section mentions "Software verification and validation," which would assess the algorithm's functionality, but not in the format of a standalone clinical performance study to meet specific acceptance criteria.
• The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not applicable as there was no explicit clinical study described to establish ground truth for a test set.
• The sample size for the training set: The document briefly states that the device integrates existing features and technologies, implying the underlying algorithms (like the insulin dose calculator or IAP) were previously validated, but it does not specify a training set size for the current device's development.
• How the ground truth for the training set was established: Not described.

Summary of what the document does provide regarding "performance criteria" and "proof":

The acceptance criteria and proof of performance for this 510(k) submission are based on bench testing and software verification/validation, rather than a clinical study with human patients and explicitly defined performance metrics in the way you've outlined.

The document indicates the following performance testing was performed to support substantial equivalence:

• Software verification and validation: Per the FDA Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices (May 11, 2005) for a Major Level of Concern. This means the software was tested to ensure it functions as designed and meets its specifications.
• Cybersecurity: Evaluated per the 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).
• Human Factors: Evaluation conducted with intended user populations (patients and healthcare providers). The human factors information confirms the user interface was adequately validated per labeling.

The conclusion states: "Performance testing demonstrated that the BlueStar Rx performed as intended. The differences between the predicate and the subject device do not raise any new or different questions of safety or effectiveness."

In essence, the "acceptance criteria" appear to be met by demonstrating the device's functional integrity, cybersecurity, and usability through these non-clinical tests, and by showing substantial equivalence to a previously cleared predicate device, rather than by a de novo clinical study with quantitative performance metrics against a defined ground truth.

Ask a specific question about this device

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

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. The BlueStar® Rx is intended to provide secure capture, storage, and transmission of blood glucose data as well as information to aid in diabetes self-management. The BlueStar® Rx analyzes and reports blood glucose test results and supports medication adherence. In addition, the BlueStar® Rx provides coaching messages (motivational, behavioral, 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.
For bolus insulin users with type 1 and 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 knowledgeable in the care and management of diabetes. The healthcare provider must activate the Insulin Adjustment Program and configure it for patient-specific parameters.
The BlueStar® Rx is not intended to replace the care provided by a licensed healthcare professional, including prescriptions, diagnosis, or treatment.

BlueStar Rx is a modified version of the primary predicate (WellDoc BlueStar Rx cleared under K190013). BlueStar Rx maintains all of the features of the primary predicate and adds the titration of long-acting basal insulin doses for qualified type 2 diabetes patients who are not using bolus insulin. This long-acting basal insulin titration feature is included as part of the Insulin Adjustment Program (IAP) in BlueStar Rx. WellDoc BlueStar® as cleared under K190013, is a stand-alone 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. Patients receive guidance on diabetes selfmanagement and are encouraged to reach out to their healthcare team when needed. There are two versions of the primary predicate WellDoc BlueStar® (cleared under K190013) -BlueStar® (OTC version) and BlueStar® Rx (prescription only) applications. In this submission, Welldoc does not propose to change the OTC version of BlueStar application. Like the bolus insulin dose calculator already included in the primary predicate (BlueStar Rx), the new long-acting basal insulin titration feature is also limited to the prescription use (Rx) version. The bolus insulin calculator feature will be disabled in patients using long-acting basal insulin titration feature in the BlueStar Rx. Health care providers (HCPs) will be required to initiate and manage the basal 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 long-acting basal insulin doses for the qualified type 2 diabetes patients.
• Web and mobile patient interface for use by patients to follow provider's basal insulin titration plan.
  The IAP feature in BlueStar Rx provides directions to the patients based on prescription by their HCP for titrating long-acting insulin doses only.
  BlueStar® Rx will also maintain the following features of the primary predicate (WellDoc BlueStar Rx cleared under K190013): (1) ability to connect to the One Touch Verio Flex Blood Glucose Meter via Bluetooth which allows users to send data from their BG meter to the BlueStar® Rx app. which will provide coaching messages (motivational, and educational) based on the real-time blood glucose values and trends. (2) The BlueStar Server will also have the ability to transmit data to the OneTouch Reveal Server. With this application, 3-hour delayed continuous glucose monitoring device data can be accessed via API and uploaded for data visualization purposes only.

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

1. 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 mentions "Performance testing" including "Software verification and validation," "Cybersecurity," and "Human Factors" testing. However, it does not specify sample sizes for any test sets, nor does it provide information about the data provenance (e.g., country of origin or whether it was retrospective or prospective).

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

The document mentions "intended user populations of patients and healthcare providers" for human factors testing, but does not specify the number or qualifications of experts used to establish ground truth for any of the performance tests.

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

The document does not specify any adjudication method for the test set.

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 specifically mentioned or described in the provided text. The document refers to the device assisting self-management and providing calculated insulin doses, but not in the context of human reader performance improvement with AI assistance.

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

The document describes the "Insulin Adjustment Program (IAP)" which calculates appropriate long-acting basal insulin doses based on configuration by a healthcare provider. While the calculation itself is algorithmic, the system requires a "human-in-the-loop" for activation, configuration, and management by the healthcare provider, and the patient follows directions. Therefore, a purely standalone algorithm-only performance study in isolation from human interaction is not explicitly described in the context of the device's function. The performance testing focuses on software, cybersecurity, and human factors interaction with the system, implying a human-in-the-loop context.

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

The document does not explicitly state the type of ground truth used for the performance testing. For software verification and validation, ground truth would typically be derived from functional specifications and expected outputs. For human factors, it would likely involve observations and feedback from users regarding usability and clarity.

8. The sample size for the training set

The document does not provide any information regarding the sample size for a training set. This is generally because the device is a rule-based system (an "Insulin Adjustment Program" that "calculates appropriate long-acting basal insulin doses based on configuration by a healthcare provider") rather than a machine learning model that requires explicit training data.

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

Since the document does not mention a training set, it does not describe how ground truth for a training set was established.

Ask a specific question about this device

The WellDoc BlueStar® System is indicated for use by healthcare providers (HCPs) and their adult patients - aged 21 years and older - who have type 2 diabetes. The BlueStar System is intended to provide secure capture, storage, and transmission of blood glucose data as well as information to aid in diabetes self-management. The BlueStar® System analyzes and reports blood glucose test results and supports medication adherence. In addition, the BlueStar System provides coaching messages (motivational, behavioral, 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.

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

The WellDoc BlueStar® Rx System is indicated for use by healthcare providers (HCPs) and their adult patients - aged 21 years and older - who have type 2 diabetes. The BlueStar Rx System is intended to provide secure capture, storage, and transmission of blood glucose data as well as information to aid in diabetes self-management. The BlueStar® Rx System analyzes and reports blood glucose test results and supports medication adherence. In addition, the BlueStar Rx System provides coaching messages (motivational, behavioral, 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. BlueStar® Rx includes an insulin dose calculator to allow patients to use their prescribed regimen to calculate a dose of insulin for a given amount of carbohydrates and/or blood glucose value.

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

WellDoc® BlueStar® is a stand-alone software system intended to be used by healthcare providers (HCPs) and their adult patients – aged 21 years and older - who have Type 2 Diabetes. The system is intended to assist Type 2 Diabetes patients to self-manage their disease, as cleared under K100066. Patients receive guidance on diabetes self-management and are encouraged to reach out to their healthcare team when needed. There are two versions of BlueStar® -BlueStar® and BlueStar® Rx - which differ in the availability of the insulin dose calculator, which is restricted to a prescription from a HCP.

BlueStar® and BlueStar® Rx are implemented through an enterprise such as a health plan or large physician group in tandem with a patient's healthcare team and are comprised of the following applications:

• Enterprise Director Portal
• HCP Service
• Patient Mobile Application
• Patient Web Portal

The Enterprise Director application is used for administrative purposes (unchanged since cleared under K100066). The HCP Service houses the Medication Reconciliation feature, which allows for the process of identifying the most accurate list of all medications that the patient is taking, including name, dosage and frequency, by comparing the medical record to an external list of medications obtained from a patient, hospital, or other provider (cleared under K141273).

The Patient Web Portal and the Patient Mobile application have a similar feature set (unchanged since cleared under K100066). Data (including blood glucose values, medications, carbohydrates, and activity) entered into these applications is stored in the database and can be retrieved for display in either applications require the initial web- or mobilebased registration before the patient can access them. On the patient applications (Mobile and Web), BlueStar® and BlueStar® Rx function as an (1) information repository (logbook and Personal Health Record) and (2) diabetes education resource (learning library and health tips) and provide (3) motivational, behavioral, and educational coaching based on real-time blood glucose values and trends, (4) a secure communication system (Message Center), (5) medication information (dose and schedule), and (6) workflow and decision support for healthcare providers.

In BlueStar® Rx, the patient web portal and mobile application also provide an insulin dosing calculator to allow patients to use their prescribed regimen to calculate a dose of insulin for a given amount of carbohydrates and/or blood glucose value. The insulin dose calculator is restricted to prescription-use only.

Furthermore, as cleared under K16225 (reference device), BlueStar® and BlueStar® Rx have the ability to connect to the One Touch Verio Flex Blood Glucose Meter (K150214) via Bluetooth. This will allow users to send data from their meter to the BlueStar® Rx app, which will provide coaching messages (motivational, behavioral, and educational) based on the real-time blood glucose values and trends. The BlueStar Server will also have the ability to transmit data to the OneTouch Reveal Server. These modifications do not change the fundamental scientific technology of the device.

The provided documentation is a 510(k) summary for the WellDoc BlueStar® and BlueStar® Rx systems. It describes the device, its indications for use, and a comparison to predicate devices, but does not appear to contain detailed information about specific acceptance criteria or a dedicated study proving the device meets those criteria.

Instead, the document primarily focuses on demonstrating substantial equivalence to pre-existing predicate devices (K100066 and K162225) based on intended use, design, materials, and overall performance characteristics. The "Non-Clinical Performance Data" section mentions "Software Verification, Software Validation, Human Factors Testing" as data provided to support substantial equivalence, suggesting these activities were performed. However, it does not provide the specific acceptance criteria for these tests or the detailed results that would allow for a table of acceptance criteria versus reported device performance.

Therefore, many of the requested fields cannot be filled directly from this document.

Here's a breakdown based on the information available:

1. Table of acceptance criteria and the reported device performance

Information Not Available in Document: The document does not provide a specific table of acceptance criteria or quantifiable performance metrics beyond stating that "Verification, validation and human factors testing showed that the system can be used by a layperson without HCP oversight, meets its requirements and functions as intended." It does not list target accuracy, specificity, sensitivity, or other predefined benchmarks with corresponding measured values.

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

Information Not Available in Document: The document does not specify the sample size used for the mentioned "Software Verification, Software Validation, Human Factors Testing" or the provenance of any data used in these tests.

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)

Information Not Available in Document: The document does not mention the use of experts to establish ground truth for any test set. The focus is on software functionality and human factors for a self-management diabetes system, not diagnostic accuracy requiring expert interpretation.

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

Information Not Available in Document: The document does not describe any adjudication methods, as no expert-based ground truth establishment is mentioned.

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

Information Not Available in Document: An MRMC comparative effectiveness study is not mentioned. The device, an AI-powered diabetes self-management system, isn't described in a way that suggests "human readers" or "AI assistance" in the context of image interpretation or similar diagnostic tasks. Its function is to provide coaching messages and an insulin dose calculator.

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

Information Available:
The device ("WellDoc BlueStar®" and "WellDoc BlueStar® Rx") is a "stand-alone software system" intended for use by both patients and healthcare providers. The document states that "software intended for use on mobile phones or personal computers" and that the system "provides coaching messages (motivational, behavioral, and educational) based on real-time blood glucose values and trends." BlueStar® Rx also "includes an insulin dose calculator." These descriptions imply standalone algorithm performance in generating coaching messages and calculating insulin doses based on input data. The "human factors testing" mentioned confirms that the system is designed to be used by a layperson, indicating that the core functionality operates somewhat independently, though the system is meant to support self-management with HCP oversight (for Rx version).

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

Information Not Available in Document: The document does not specify the type of ground truth used for any testing. Given the nature of the device (diabetes management, coaching, insulin calculation), "ground truth" would likely relate to the correctness of calculations or the appropriateness of coaching messages, which might be assessed against clinical guidelines or pre-defined rules rather than expert consensus on medical images or pathology.

8. The sample size for the training set

Information Not Available in Document: The document does not provide any information about a training set size or methodology. It's unclear if machine learning/AI techniques that require explicit training sets were used in a manner that necessitated reporting such a detail in this K162532 summary, as the "AI" aspect is described more generally as providing "coaching messages... based on real-time blood glucose values and trends."

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

Information Not Available in Document: As no training set is mentioned, the method for establishing its ground truth is also not provided.

Ask a specific question about this device