Search Results

The T1D1 mobile application is indicated for the management of diabetes by people with Type 1 diabetes age 2 and older by calculating insulin doses based on user-entered data.

Prior to use, a healthcare professional must provide the patient target blood glucose values, insulin-to-carbohydrate ratios, and the correction factor (also known as the insulin sensitivity factor) to be programmed into the App software.

The T1D1 application is a user-friendly mobile application designed for Android and Apple devices, specifically catering to individuals aged 2 and above who have Type 1 Diabetes Mellitus (T1DM) and undergo multiple daily injection (MDI) therapy. Its primary objective is to simplify insulin dosing management by providing essential features such as a bolus calculator, a convenient logbook, and various configurable user-specific settings. The T1D1 application is intended to be distributed free of charge and without advertisements while operating independently of any other diabetes care devices. The overarching aim of the app is to streamline the daily calculations required by individuals with T1DM, alleviating the time-consuming and error-prone task of manually calculating and keeping track of insulin dosing.

The key feature of the T1D1 application is the bolus calculator. This calculator implements the standard insulin bolus calculation, taking into account factors such as the user's current blood glucose levels, carbohydrate intake, and target blood glucose levels. By considering these variables, the app provides users with an insulin dose recommendation, which assists in maintaining stable blood sugar levels.

The logbook feature allows users to record, track, and share their diabetes-related information. This information includes blood glucose levels, insulin doses, carbohydrate intake, and other relevant information. The ability to log and share this information with healthcare professionals or family members allows for improved communication and collaboration between individuals with T1DM and their support network.

The T1D1 application offers several presets to simplify the insulin dosing process. These presets can be customized based on individual preferences and needs. By providing preset options, the app eliminates the need for manual input of commonly used settings, saving time and reducing the likelihood of errors. In summary, the T1D1 application is a user-friendly mobile application that assists individuals with T1DM in managing their everyday insulin dosing from day one of their diagnosis.

The provided FDA 510(k) clearance letter for the T1D1 device, while detailing the general process and regulatory compliance, does not contain the specific performance data for the device that would allow for the construction of the requested table of acceptance criteria and reported device performance. The "Performance Data" section on page 10 only lists the standards and guidances followed for risk analysis, software V&V, cybersecurity, and human factors, but does not present any quantitative results from these studies.

Therefore, I cannot fulfill your request for:

• A table of acceptance criteria and the reported device performance
• Sample size used for the test set and data provenance
• Number of experts and their qualifications
• Adjudication method
• MRMC comparative effectiveness study details
• Standalone (algorithm-only) performance details
• Type of ground truth used
• Sample size for the training set
• How ground truth for training set was established

To answer these questions, you would need access to the full 510(k) submission, which includes the detailed performance data, verification and validation reports, and clinical study summaries. The clearance letter only confirms that such data was reviewed and deemed acceptable by the FDA for the purpose of granting clearance.

Ask a specific question about this device

EndoTool IV 3.1 is a glucose management software system used by healthcare professionals in all inpatient care settings for adult and pediatric patients aged two years and above who weigh 12 kgs. or more. EndoTool adjusts and maintains a patient's glucose level within a configurable clinician-determined target range by recommending patient-specific intravenous insulin dosing, carbohydrate dosing for recovery or supplementation, and subcutaneous dosing for the transition from IV dosing.

EndoTool IV 3.1 logic is not a substitute for but rather an adjunct to clinical reasoning. No medical decision should be based solely on the recommended guidance provided by this software system.

EndoTool IV 3.1 is a software system for glucose management which uses the current and cumulative qlucose values provided by the user to calculate and recommend intravenous insulin or carbohydrate doses, to adjust and maintain the patient's glucose level within a provider-ordered target range. In addition, the application can recommend a subcutaneous Basal transition insulin dose when IV insulin therapy is no longer required.

The provided text is a 510(k) summary from the FDA, detailing the premarket notification for the "EndoTool IV 3.1" device. While it outlines the device's purpose, comparison to a predicate device, and general statements about software verification and validation, it does not contain the specific information required to answer your questions regarding acceptance criteria and a study proving the device meets those criteria.

The document states:

• "Software verification and validation testing was conducted per IEC 62304."
• "Clinical testing was not required to demonstrate the safety and effectiveness of the EndoTool IV 3.1. Instead, substantial equivalence is based upon benchtop performance testing."

This indicates that the validation was primarily software-focused and benchtop (likely simulated data or internal testing against predefined rules) rather than clinical. It does not provide:

• A table of acceptance criteria and reported device performance.
• Sample sizes for a test set, its provenance, or whether it was retrospective/prospective.
• Information on experts used for ground truth, their qualifications, or adjudication methods.
• Details of a Multi-Reader Multi-Case (MRMC) study or its effect size.
• Results from a standalone algorithm performance study.
• The type of ground truth used (e.g., expert consensus, pathology, outcomes data).
• Sample size for the training set or how its ground truth was established.

Therefore, based solely on the provided document, I cannot fulfill your request as the essential information about specific performance data, test methodologies, and ground truth establishment is not present. The document focuses on demonstrating substantial equivalence to a predicate device based on similar indications for use, technological characteristics, and conformance to a general software standard (IEC 62304).

Ask a specific question about this device

The InPen System is a home-use reusable pen for single-patient use by people with diabetes under the supervision of an adult caregiver, or by a patient aged 7 and older for the self-injection of a desired dose of insulin. The pen injector is compatible with Lilly Humalog® U-100 3.0 mL cartridges, Novo Nordisk Novolog® U-100 3.0 mL cartridges, and Novo Nordisk Fiasp® U-100 3.0 mL cartridges and single-use detachable and disposable pen needles (not included). The pen Smart Insulin pen allows the user to dial the desired dose from 0.5 to 30 units in one-half (1/2) unit increments.

The InPen dose calculator, a component of the InPen app, is indicated for the management of diabetes by people with diabetes under the supervision of an adult caregiver, or by a patient aged 7 and older for calculating an insulin dose or carbohydrate intake based on user entered data.

For an insulin dose based on amount of carbohydrates, a healthcare provide patient-specific target blood glucose, insulin-to-carbohydrate ratio, and insulin sensitivity parameters to be programmed into the software prior to use.

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

The InPen App is a software application with versions that are compatible with mobile phones running the iOS or Android operating system. The App is a component of the InPen system and is used with the InPen Smart Insulin pen for the management of insulin-requiring diabetes. The InPen App communicates with the InPen Smart Insulin pen to communicate doses that are delivered by the user. The InPen App is also compatible for use with blood glucose (BG) meters, Medtronic Continuous Glucose Monitors (CGMs), and the Dexcom CGMs. The InPen App includes a dose calculator that can calculate and recommend a dose for the user to review and consider as part of following the treatment plan prescribed by the healthcare provider. The dose calculator features in the App require that a healthcare professional provide patient-specific values for various therapy settings for programming into the App prior to use by the patient. These therapy settings include glucose target(s), duration of insulin action time, insulin sensitivity factor(s), and insulin-to-carbohydrate ratio(s) or fixed insulin doses for meal types and sizes. The dose calculator feature is unavailable to the user until these patient-specific values, provided by the healthcare professional, are programmed and an InPen has been paired to the App. A healthcare provider may also provide long-acting insulin settings to be programmed into the InPen App. The App includes a logbook feature that displays the patient's recent activity related to BG values, meal types and sizes, dose calculations, doses by insulin type (rapid- or long-acting), cartridge replacement and priming. The App also provides reminders and alerts that can notify the user to check their glucose, dose insulin (for potential missed meals, correction doses, and longacting insulin doses) and log doses according to schedule, replace a cartridge, or if the insulin pen has been exposed to very low or very high temperatures. The App can generate a supplemental summary report of recent therapy information for review by the patient or healthcare professional (HCP).

The InPen Cloud includes a therapy report component that the user and the health care provider (HCP) can view and print to assess the overall diabetes control and treatment plan. The report displays data based upon user and HCP-defined inputs, such as glucose, insulin and carb trended information, during the defined period, as well as dose calculator usage and alerts and reminders. The Insulin Notification Service (INS) is a subcomponent of the InPen Cloud that can receive Medtronic CGM sensor glucose measurements from the CareLink Cloud. The INS includes two algorithms that assess "real time" sensor glucose measurements to identify whether a user has missed a dose or if their glucose is rising and a correction dose is needed. If either of these conditions exist, a silent notification is sent by the INS to the InPen App. The InPen App confirms the data and can provide and visual alert to the user. The user can act on the alert by assessing their glucose levels followed by calculating a dose utilizing the InPen App dose calculator.

The provided text is a 510(k) summary for the Medtronic MiniMed InPen System. It describes the device, its indications for use, and a comparison to a predicate device to establish substantial equivalence. However, the document does not contain the specific details about acceptance criteria, the study design (including sample size, data provenance, expert ground truth establishment, or adjudication methods), or performance data in the way requested in the prompt.

The "Performance Data" section (Page 10) broadly states that "Software verification and validation testing was performed in accordance with the FDA's Guidance..." and mentions "unit level testing, integration level testing, and systems testing." It also notes "Cybersecurity Testing" and "risk management activities." Finally, it mentions an "additional assessment of the changes to the InPen Cloud occurred through a summative usability evaluation" where "patients...used the InPen Cloud to perform a series of critical tasks involving the use of the InPen App and Cloud, including the additional alerts and reminder."

Therefore, it is not possible to fill in most of the requested information based on the provided text. The document focuses on regulatory arguments for substantial equivalence rather than detailed clinical or technical study results that would typically include such specifics.

Here's a breakdown of what can be extracted and what cannot:

Information that CANNOT be extracted from the provided text:

1. A table of acceptance criteria and the reported device performance: This detail is not present. The document focuses on showing the device is substantially equivalent to a predicate, not on specific performance metrics against pre-defined acceptance criteria.
2. Sample sizes used for the test set and the data provenance: No specific sample sizes for particular tests (e.g., test sets for algorithms) are mentioned, nor is the data provenance (country, retrospective/prospective). The "summative usability evaluation" is mentioned, but without sample size or details about the data used.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not mentioned.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not mentioned.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance: Not mentioned. This type of study is more common for diagnostic imaging AI, whereas this device is an insulin management system with a dose calculator.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: While the InPen App has an algorithm for dose calculation and the InPen Cloud has algorithms for notifications, the document doesn't provide performance data for these algorithms in isolation. The "summative usability evaluation" implies human-in-the-loop testing.
7. The type of ground truth used (expert concensus, pathology, outcomes data, etc): Not explicitly stated how the accuracy of the dose calculations or alert effectiveness was verified as "ground truth." The "summative usability evaluation" likely involved checking if users performed tasks correctly, but the underlying ground truth for algorithm accuracy isn't detailed.
8. The sample size for the training set: Not mentioned.
9. How the ground truth for the training set was established: Not mentioned.

Information that CAN be extracted or inferred from the provided text:

• Device Type: Insulin management system (reusable pen, app with dose calculator).
• Regulatory Class: Class II (Product Code: NDC).
• Software Level of Concern: Major.
• Key Software Features: Dose calculator (insulin dose based on carbohydrates or fixed/variable meal sizes), logging, reminders, alerts (missed dose, high glucose).
• New Features (compared to predicate):
  • Two new algorithms in the InPen Cloud (Insulin Notification Service) to identify and send "silent notifications" to the InPen App for missed insulin doses or rising glucose.
  • Two new visual and audible alerts in the InPen App for missed insulin doses or high glucose, for users with a Medtronic CGM.
  • Improved existing Long-Acting Reminder to include both audible and visual alerts.
• Performance Data (General Statement): "Software verification and validation testing was performed in accordance with the FDA's Guidance for Industry and FDA Staff, "Content of Premarket Submissions for Device Software Functions'', and FDA's guidance "General Principles of Software Validation". Verification and validation activities included software testing consisting of unit level testing, integration level testing, and systems testing of the InPen App and InPen Cloud. Cybersecurity Testing was performed... Risk management activities... were undertaken... Additional assessment of the changes to the InPen Cloud occurred through a summative usability evaluation."

In summary, the provided document is a regulatory submission focused on substantial equivalence, not a detailed technical report of study results with specific performance metrics and study methodologies.

Ask a specific question about this device

iSage Rx is indicated for use by adult patients with type 2 diabetes, and by their healthcare providers to provide ongoing support for understanding and following a titration plan for the following medications, with the goal of reaching optimal medication dose and/or target fasting blood sugar control:

-Basal insulins

-Combinations of basal insulin and GLP-1 receptor agonists

iSage Rx System includes a web-based, HIPAA-compliant, password protected Health Care Provider (HCP), Account Administrated websites, and a patient mobile app. The system was designed to enable HCPs to digitize and deploy their basal insulin titration plan such that adult patients with type 2 diabetes may better understand and follow their basal insulin treatment plan through the iSage Rx app. The iSage Rx patient app is a stand-alone, prescription-use only (Rx-only) software device for use under the direction of a healthcare provider, that has the capability to titrate basal insulin and medications that combine basal insulin and GLP-1 receptor agonists, via rule-based protocols as part of a Titration Plan ordered by a Health Care Provider (HCP). It is intended for use in type 2 diabetes in a nonacute care setting.

The primary purpose of the iSage Rx device is to help the patient safely reach their fasting blood glucose targets and reach a maintenance dose of insulin through regular monitoring of blood glucose levels and titration of insulin doses.

This document is a 510(k) summary for the iSage Rx Platform. It details the device's intended use, comparison to a predicate device, and performance data to demonstrate substantial equivalence.

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

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

The document does not explicitly present a table of acceptance criteria with corresponding performance metrics in a pass/fail format. Instead, it relies on the concept of "substantial equivalence" to a predicate device (iSage Rx, K161865). The performance data section describes "Software Verification and Validation Testing" that was conducted to demonstrate the device performs as intended and meets identified requirements.

However, based on the document's content, we can infer some implicit acceptance criteria:

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 refers to "Software Verification and Validation Testing" and "nonclinical datasets in the form of testing protocols and reports." However, it does not specify the sample size of the test set, nor does it specify the data provenance (country of origin, retrospective or prospective). It mentions that "All product development activities for the iSage Rx Platform were conducted in compliance with EN ISO 13458:2016," but this refers to the quality management system, not the specifics of the data used for testing. The product is localized to the USA for specific configurations.

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)

The document does not provide information on the number or qualifications of experts used to establish ground truth for the test set. It mentions the "Healthcare Provider (HCP) portal" and HCPs configuring titration plans, implying medical expertise is involved in the overall system, but not specifically for the ground truth of the validation testing.

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

This document describes a software device that provides a titration plan for patients with type 2 diabetes. It is a standalone software device intended for patient and HCP use to manage medication dosage, not an AI-assisted diagnostic tool for human readers interpreting medical images. Therefore, an MRMC comparative effectiveness study involving human readers improving with AI assistance would not be applicable in this context. The document focuses on the software's functional accuracy and safety in calculating and presenting drug doses.

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

Yes, a form of standalone performance evaluation was implicitly done for the algorithm. The "Software Verification and Validation Testing" and "nonclinical datasets" would involve testing the algorithm's output against expected results based on predefined rules for titration plans. The device's function is to "calculate a fasting blood glucose average and generates an insulin dose according to the prescribed titration plan." This is an algorithmic function that would be tested independently of patient or HCP interaction to confirm its computational accuracy.

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

The document strongly implies that the "ground truth" for the device's dose calculation and titration logic is established based on "evidence-based preset clinical titration plans" and "evidence-based protocols from treat-to-target studies or other patient-led titration studies." HCPs can also create their own plans or customize these, further indicating that the ground truth is derived from established medical guidelines and clinical evidence for diabetes treatment. While not explicitly stated as "expert consensus" for the test set itself, the underlying principle is rooted in validated clinical practice.

8. The sample size for the training set

The document describes software that applies rule-based protocols for dose titration. It does not mention a training set or machine learning components that would require a "training set sample size" in the context of predictive algorithms that learn from data. The device operates on "rule-based protocols."

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

As the device operates on "rule-based protocols" and does not appear to use machine learning from a training set, the concept of establishing ground truth for a training set is not applicable here. The "ground truth" for the rules themselves would be derived from clinical guidelines and evidence as mentioned in point 7.

Ask a specific question about this device

The Insulia Bolus Companion is indicated for the management of diabetes by adults with diabetes, by calculating an insulin dose or suggesting carbohydrate intake based on user entered data.

Prior to use, a healthcare professional must provide a patient-specific target blood glucose, insulin doses based on fixed or variable meal sizes, and insulin sensitivity parameters to be programmed into the software. This can be done through a dedicated, secured web portal.

Insulia Bolus Companion is a prescription device indicated for the management of diabetes, for adults with diabetes, by calculating an insulin dose or suggesting carbohydrate intake based on user entered data; and for healthcare professionals (HCP) having experience in the management of people with diabetes treated with bolus insulin.

Insulia Bolus Companion is for prescription use and is not for over-the-counter sale.

Insulia Bolus Companion includes a Bolus Calculator intended to provide direction to the patient in response to blood glucose (BG) and health events, within the scope of a preplanned treatment program prescribed by their HCP for insulin suggestions. The guidance is similar to the directions provided to patients as a part of routine clinical practice: prior to use, a healthcare professional must provide a patient-specific target blood glucose, insulin doses based on fixed or variable meal sizes, and insulin sensitivity parameters to be programmed into the software.

An HCP can only start using Insulia Bolus Companion after having been registered by the Manufacturer or the delegate field-support team.

Insulia Bolus Companion includes three components:

• · A mobile application for use by people with diabetes on commercially available smartphones (iPhone or Android) and tablets, enabling patients to document BG measurements, meals, and generate dose suggestions for bolus insulin
• · A web-based application for use by HCPs in professional healthcare settings through a compatible web browser on a computer, allowing patient inclusion and patient monitoring in-person and by distance
• · A secure database hosted in a private cloud environment and used to securely store patient data

The provided text does not contain detailed information about the acceptance criteria and the study that proves the device meets those criteria, specifically regarding numerical performance metrics, sample sizes for test and training sets, expert qualifications, or adjudication methods.

The document states that "Design verification and validation testing on Insulia Bolus Companion demonstrated that the device meets the performance requirements for its intended use" and "performance testing has demonstrated that Insulia Bolus Companion performs as intended and is substantially equivalent to the predicate device." However, it does not provide the specifics of this performance testing.

Therefore, I cannot provide a detailed answer to your request that includes:

1. A table of acceptance criteria and reported device performance.
2. Sample size and data provenance for the test set.
3. Number of experts and their qualifications used for ground truth.
4. Adjudication method.
5. Effect size for MRMC study (as no mention of such a study is made).
6. Standalone performance details.
7. Type of ground truth used.
8. Sample size for the training set.
9. How ground truth for the training set was established.

The document primarily focuses on the regulatory submission process, demonstrating substantial equivalence to a predicate device, and outlining the device's indications for use and general technological characteristics.

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 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

Digital Routines is indicated for use by healthcare providers (HCPs) and their patients - aged 21 years and older - who have type 2 diabetes. Digital Routines is intended to provide secure capture, storage, and transmission of blood glucose data as well as information to aid in diabetes self-management. The Digital Routines system analyzes and reports blood glucose test results and supports medication adherence. In addition, Digital Routines provides coaching messages (motivational, behavioral, and educational) based on blood glucose values and trends. It includes software intended for use on mobile phones (for patients) or personal computers (for HCPs) 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 following Digital Routines insulin management features are for prescription use only:

· For bolus insulin users with type 2 diabetes, Digital Routines 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. The healthcare provider must activate the insulin dose calculator for patient.

· For basal insulin users with type 2 diabetes, Digital Routines includes an Insulin Adjustment Program (1AP) 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 IAP and configure it with patient-specific parameters.

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

The Digital Routines is a stand-alone medical software system intended to be used by patients aged 21 and older who have type 2 diabetes. Digital Routines is a new kind of approach to support in helping patients manage their type 2 diabetes. Digital Routines real-time feedback and guidance fit into daily life to help patients stay on track with their diabetes care plan.

Digital Routines is accessible directly from the patient's mobile phone, but also includes the patient's HCP throughout the process. It supports the healthcare provider`s treatment plan while helping with building the patient's knowledge about diabetes and stay motivated. The device also incorporates an insulin calculator for bolus insulin users and an insulin adjustment program for basal insulin users. These features require the approval of a physician before the patient can access them.

The system comprises three core software components:

• the Patient Mobile Application (i)
• the HCP Web Portal (ii)
• the Enterprise Director Web Portal (iii)

HCPs can authorize the Insulin Calculator or initiate an Insulin Adjustment Program (Rx only). The Insulin Adjustment Program is designed to help physicians and their patients with type 2 diabetes to adjust their long-acting (basal) insulin to improve diabetes management. The program works by collecting and analyzing blood glucose readings to adjust basal insulin doses according to the physician's instructions. Physicians can view and adjust their patient's treatment plan at any time, and they receive safety notifications such as if a patient experiences hypoglycemia or takes insulin doses that substantially differ from the recommended amount.

The Insulin Calculator uses the physician authorized regimen to calculate the corresponding dose of bolus insulin to take based on a patient's carbs and blood glucose value. Patients eligible to use the Insulin Calculator have the option within Digital Routines to request access to it. The patient's physician must authorize the Insulin Calculator for it to be activated. Prior to using the Insulin Calculator, the patient will be required to complete in-app training on the use of the calculator. The Insulin Calculator may also include an optional Insulin on Board feature that must be authorized by the physician.

Here's an analysis of the provided text regarding the acceptance criteria and study information for "Digital Routines":

The provided document (a 510(k) summary) does not contain specific acceptance criteria, nor does it detail a study that directly proves the device meets such criteria in a quantitative sense (e.g., performance metrics, statistical results from a clinical trial). Instead, it focuses on demonstrating substantial equivalence to a predicate device, which is the primary mechanism for FDA clearance in this pathway.

The type of studies mentioned are Software Validation & Verification (V&V), cybersecurity evaluation, and human factors testing. These are general categories of testing required for software-based medical devices, not specific performance studies with quantitative acceptance criteria for the core functionality as one might expect for an AI/ML diagnostic or predictive algorithm.

Therefore, many of the requested sections will be answered as "Not provided" or "Not applicable" based on the content.

Acceptance Criteria and Reported Device Performance

Additional Study Information:

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

   • Not provided. The document states "Software V&V testing was performed" and "Human factors testing was conducted," but does not detail the sample sizes for these tests, the type of data used (beyond "blood glucose data"), or its provenance.

2. 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):

   • Not provided. Ground truth establishment, in the context of expert review for performance evaluation, is not mentioned in this summary. The device's primary function involves calculations based on patient-entered data and HCP-configured parameters, and coaching messages derived from trends, rather than interpreting complex medical images or signals requiring a panel of expert human reviewers for ground truth.

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

   • Not applicable / Not provided. The summary does not describe any test sets or adjudication processes that would involve expert review for ground truth consensus.

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

   • No. An MRMC study is not mentioned. The device, "Digital Routines," is a diabetes self-management system with insulin dose calculation/adjustment features. Its purpose is to assist patients and HCPs with managing diabetes, not to improve human reading of diagnostic images/cases. The summary does not provide any information about human reader performance improvement.

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

   • Partially applicable. The device includes an "Insulin Calculator" and an "Insulin Adjustment Program (IAP)." While these are "Rx only" features requiring HCP activation and configuration, the calculations themselves are performed by the algorithm. The software V&V would, in principle, test the accuracy and correctness of these algorithmic calculations. However, the summary does not provide specific performance metrics for these algorithms (e.g., accuracy of insulin dose calculations against a gold standard). It merely states that "Software V&V testing has demonstrated that the device meets the applicable software requirements."

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

   • Not explicitly stated for performance evaluation. For the Insulin Calculator and IAP, the "ground truth" would implicitly be the mathematically correct calculation based on the prescribed regimen and patient parameters set by the HCP. For coaching messages, the ground truth would be adherence to predefined rules for generating messages based on blood glucose values and trends. The summary does not elaborate on how this ground truth was formally established or used in testing.

7. The sample size for the training set:

   • Not applicable / Not provided. The description of "Digital Routines" suggests a rules-based system or an application directly implementing medical guidelines (for insulin calculations and adjustments) rather than a machine learning model that requires a training set in the typical sense. It analyzes blood glucose data and provides coaching "based on blood glucose values and trends," which could be rule-based. No mention of machine learning model training is made, nor are training sets discussed.

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

   • Not applicable / Not provided. As no training set is described, the method for establishing its ground truth is also not provided.

In summary: The provided 510(k) summary focuses on establishing substantial equivalence by comparing the device's features, intended use, and technological characteristics to a predicate device, and by confirming general software, cybersecurity, and human factors compliance. It lacks specific quantitative acceptance criteria and detailed performance study results that would typically be associated with direct clinical performance claims or advanced AI/ML algorithms requiring extensive training and test sets with defined ground truth.

Ask a specific question about this device

EndoTool SubQ 2.1 is a software application for use by trained healthcare professionals to calculate and recommend an individual patient's next dose of insulin to be administered subcutaneously to manage blood glucose levels in patients with hyperglycemia including adult and pediatric patients (age 2 years and above and 12 kg or more). The software is designed to recommend the insulin dose(s) and when indicated a carbohydrate dosed on the prescribing healthcare Provider's nutritional regimen, insulin regimen, target glucose range, and patient specific characteristics.

EndoTool SubQ 2.1 logic is not a substitute for clinical reasoning but an aid for trained healthcare professionals based on obtained glucose readings and entered clinical data. Final dose recommendations for a patient must be made only after consideration of the full clinical status of the patient. No medical decision should be made based solely upon the results provided by this software program.

EndoTool SubQ 2.1 is a software application for use by trained healthcare professionals to calculate and recommend an individual patient's next dose of insulin to be administered subcutaneously to manage blood glucose levels in patients with hyperglycemia including adult and pediatric patients (age 2 years and above and 12 kg or more). The software is designed to recommend the insulin dose(s) and when indicated a carbohydrate dose based on the prescribing healthcare Provider's nutritional regimen, insulin regimen, target glucose range, and patient specific characteristics.

The EndoTool® SubQ 2.1 Glucose Management system includes security, software, and technical support features. Each user has an individual User Identification (ID) and Password to access portions of the application. EndoTool SubQ 2.1 is designed to safeguard the confidentiality, integrity, and availability of electronic protected health information of patients according to the Health Insurance Portability and Accountability Act (HIPAA) privacy rules.

EndoTool SubQ 2.1 is packaged in a user friendly, stand-alone program. The application is installed on Windows Server 2008 R2 or newer. The end-user should access the application using a compatible web browser, such as Internet Explorer 9 and higher, or Google Chrome 58 and higher. The application was developed for use on Personal Computers (PCs), network servers, and terminal server environments. As EndoTool SubQ 2.1 data is time sensitive, it is also imperative that all PCs and servers be set with the correct date and time using UTC.

EndoTool SubQ can utilize barcode scanning in Code 39 format (also known as Alpha39, Code 3 of 9, Code 3/9, Type 39, USS Code 39, or USD-3) for patient identification/verification.

The provided text does not contain detailed information about specific acceptance criteria for the output of the EndoTool SubQ 2.1 software or a study demonstrating that the device meets such criteria. Instead, it focuses on demonstrating substantial equivalence to a predicate device through comparison of technological characteristics and general software verification and validation activities.

Here's an analysis of the information that is available and what is missing:

1. Table of Acceptance Criteria and Reported Device Performance

Not available in the provided text. The document states that "Software verification and validation testing was conducted per IEC 62304 and FDA's software validation guidance to demonstrate the performance of the device is substantially equivalent to the predicate." It then lists types of testing performed (requirements-based, module and integration, data integration, algorithm test cases, static analysis, regression testing), but it does not provide specific quantitative acceptance criteria (e.g., target accuracy, precision, or other performance metrics for insulin dose recommendations) or the reported performance values against these criteria.

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

Not explicitly available. The document mentions "Algorithm test cases (automated and manual)" as part of performance testing, which implies a test set was used. However, the size of this test set, the nature of the data (e.g., patient records, simulated data), and its provenance (country of origin, retrospective or prospective collection) are not specified.

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

Not available. Since the details of the "Algorithm test cases" are not provided, there is no information on how ground truth was established for these cases, nor the number or qualifications of any experts involved.

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

Not available. This information is dependent on the details of how the ground truth was established, which is not provided.

5. If a multi-reader, multi-case (MRMC) comparative effectiveness study was done, and its effect size

No, a MRMC comparative effectiveness study was not explicitly mentioned and does not appear to have been performed. The document focuses on the software's performance and its substantial equivalence to a predicate device, not on comparing human reader performance with and without AI assistance. The device is described as "an aid for trained healthcare professionals," not a tool to enhance human reading of medical images or data in a comparative effectiveness study context.

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

Yes, implicitly. The "Algorithm test cases (automated and manual)" would involve evaluating the algorithm's output independently. The device's description as a "software application for use by trained healthcare professionals to calculate and recommend an individual patient's next dose of insulin" implies standalone algorithmic calculations. However, the performance metrics from this standalone evaluation are not provided.

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

Not explicitly available. For "Algorithm test cases," the ground truth would likely be a clinically validated optimal insulin dose or a set of expected outcomes based on established medical protocols for various patient scenarios. However, the specific method of establishing this ground truth is not detailed.

8. The sample size for the training set

Not available. The document describes a software application that calculates insulin doses. While such applications often involve algorithms that might be "trained" or developed based on data, there is no mention of a distinct "training set" or its size in the context of machine learning or AI. The software is described as having an "algorithm" and being "designed to recommend the insulin dose(s)", suggesting it operates based on predefined logic and parameters rather than a continuously learning model with a training phase.

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

Not applicable/Not available. As above, the concept of a "training set" and establishing ground truth for it is not explicitly discussed for this type of software, which appears to be rule-based or algorithmic rather than a machine learning model requiring labeled training data.

In summary: The provided document is a 510(k) summary focused on demonstrating substantial equivalence of EndoTool SubQ 2.1 to a predicate device, EndoTool SubQ (K180366). It outlines general software validation practices and a comparison of features but lacks the specific performance data, acceptance criteria, and details of clinical studies that would typically be described for a diagnostic AI device requiring quantitative performance metrics against a defined ground truth. The device is a "Predictive Pulmonary-Function Value Calculator" (Regulation Name) but its "Indications for Use" clearly state its function is for "calculat[ing] and recommend[ing] an individual patient's next dose of insulin... to manage blood glucose levels." This discrepancy might be a clerical error in the regulatory classification.

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

Insulia Diabetes Management Companion is indicated for use by healthcare professionals (HCPs) and their type 2 adult diabetes patients treated with long-acting insulin analog.

Insulia Diabetes Management Companion is intended to provide secure capture, storage and transmission of diabetesrelated healthcare information, to enhance data management, to display reports and graphs, and to aid the HCP and the patient in the review, and evaluation of patient data in order to support effective diabetes management.

Insulia Diabetes Management Companion includes a basal calculator intended to provide direction to the patient in response to blood glucose and health events, within the scope of a pre-planned treatment program from a healthcare professional for insulin adjustments, similar to the directions provided to patients as a part of routine clinical practice.

Insulia Diabetes Management Companion intended for use on commercially available mobile platforms, personal computers, in the home or in professional healthcare settings, and uses generally available networks and communication protocols.

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

Insulia Diabetes Management Companion is a mobile and web-based diabetes management system for adult type 2 diabetes patients and their healthcare team. Insulia Diabetes Management Companion includes three components:

• A mobile medical application for use by patients on commercially available smartphones (iPhones and Android phones) and tablets.
• A web-based application for use by patients in their home on their personal computer and on their mobile device, or by HCPs in professional healthcare settings through a compatible web browser on a personal computer.
• A secure database hosted in a private cloud environment and used to securely store patient data.

Insulia Diabetes Management Companion provides secure capture, storage and transmission of blood glucose data and other diabetes-related healthcare information to enhance data management, to display reports and graphs, and to aid the HCP and the patient in the review, analysis, and evaluation of patient data in order to support effective diabetes management.

Insulia Diabetes Management Companion includes a Basal Calculator intended to provide directions to the patient in response to blood glucose measurements and other diabetesrelated events, within the scope of a pre-planned treatment program from a healthcare professional for insulin adjustments. The guidance is similar to the directions provided to patients as a part of routine clinical practice.

Insulia Diabetes Management Companion provides educational coaching messages based on blood glucose values.

Insulia Diabetes Management Companion is only indicated for use with insulin detemir (Levemir® U-100) once or twice daily, insulin degludec (Tresiba® U-100) once daily, and insulin glargine (Basaglar® U-100, Lantus® U-100, Semglee® U-100, Toujeo® U-300) once daily.

Insulia should not be used for:

• basal dose recommendations for intermediate-acting insulin (NPH - Neutral Protamine Hagedorn);
• premixed insulin

Insulia should not be used in the following populations:

• pregnant women;
• non-adult patients;
• patients that are treated with a basal-plus or a basal-bolus regimen (i.e multiple mealtime insulin injections per day or insulin pump therapy)

The provided text is a 510(k) summary for the Insulia Diabetes Management Companion, specifically addressing a modification to the device (K202596), which is the addition of compatibility with Semglee® (Glargine U-100) insulin. The document focuses on demonstrating substantial equivalence to a previously cleared predicate device (K172177).

Crucially, the provided text does not contain detailed information about specific acceptance criteria or the study that proves the device meets those criteria in the typical sense of a performance study with quantitative results (e.g., sensitivity, specificity, accuracy). Instead, it references general design control processes, risk management, and verification/validation testing without providing the numerical results or the specific methodology of such tests.

The information primarily describes the device, its intended use, and argues for its substantial equivalence to a predicate device based on similar intended use and technological characteristics, with the minor modification (Semglee compatibility) not raising new safety or effectiveness concerns.

Therefore, many of the requested points in your prompt cannot be directly answered from the provided text. However, I will extract and infer what information is available:

Device: Insulia Diabetes Management Companion (K202596)

Purpose of the study (as described here): To demonstrate substantial equivalence of the modified device (adding Semglee® compatibility) to the predicate device (K172177). The document implies that the "performance data" refers to verification and validation testing to ensure the modification does not negatively impact the device's functionality.

1. Table of acceptance criteria and the reported device performance:

The document does not provide a quantitative table of acceptance criteria (e.g., target accuracy, sensitivity, specificity for the basal calculator/insulin dose recommendations) or corresponding reported performance metrics. It generally states that "Design verification and validation testing on the modification of Insulia Diabetes Management Companion demonstrated that the device meets the performance requirements for its intended use" and "the data demonstrate that the new device is substantially equivalent to the predicate device."

Without specific numerical criteria or results, a table as requested cannot be constructed from this document. The "performance requirements" are not explicitly defined in terms of metrics.

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

• Sample size for test set: Not explicitly stated. The document refers to "Design verification and validation testing" but does not give details on cohort size, number of cases, or data points used in these tests.
• Data provenance: Not explicitly stated (e.g., country of origin, retrospective/prospective). It refers to "risk assessment," "risk analysis," and "Failure Mode Effect and Analysis" (FMEA) as part of design control, but these are processes, not data sets.

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

• Number of experts: Not specified.
• Qualifications of experts: Not specified. The document mentions "a multidisciplinary team" conducting the risk assessment, which implies experts, but their number and specific qualifications (e.g., cardiologists, neurologists, imaging specialists, years of experience) are not detailed.

4. Adjudication method for the test set:

• Adjudication method: Not specified. Given the lack of detail on the test set itself, no adjudication method (e.g., 2+1, 3+1) 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:

• MRMC study: Not mentioned or implied. The device is a "basal calculator intended to provide direction to the patient" and a "diabetes management system." It's not an imaging AI device that assists human readers in diagnosis. Therefore, an MRMC study is not relevant to this type of device.

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

• The document implies that the "basal calculator" algorithm itself was subject to "verification and validation testing." It states that "The basal insulin calculator is unchanged as compared to the predicate device, i.e. the calculation rules are the same." The modification was only about compatibility with a new insulin type (Semglee®). Therefore, the calculation logic itself would have been tested previously for the predicate device, and the current submission likely focused on verifying its continued correct operation with the new compatible insulin type and ensuring the system as a whole functions as intended. However, specific details of such standalone testing (metrics, results) are not provided in this summary.

7. The type of ground truth used:

• For a basal insulin calculator, ground truth would typically refer to physiologically correct insulin dose recommendations or patient outcomes based on those recommendations. The document states the device provides "directions...similar to the directions provided to patients as a part of routine clinical practice" based on a "pre-planned treatment program from a healthcare professional." This suggests the ground truth for evaluating the calculator's outputs would be adherence to established medical guidelines or physician-prescribed treatment plans, potentially validated by clinical experts or simulation models. However, the specific method for establishing this "ground truth" for testing is not detailed.

8. The sample size for the training set:

• Given that the device uses a "basal calculator" with "calculation rules," it's more likely based on deterministic algorithms derived from medical guidelines and pharmacokinetics rather than a machine learning model that requires a training set in the typical sense. The document does not mention any "training set." If any part of the device involved machine learning (unlikely for a basal calculator of this description), no information on a training set size is provided.

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

• As no training set is mentioned (see point 8), this question is not applicable based on the provided text. The "ground truth" for the basal calculator's logic would be established by clinical consensus, medical literature, and expert input that defined the "pre-planned treatment program" and "calculation rules."

Ask a specific question about this device