Search Results

The BlueStar® CGM insulin dose calculator is software intended for the management of type 1 or type 2 diabetes in persons aged 18 years and older requiring fast-acting insulin. The BlueStar CGM insulin dose calculator allows patients to calculate a dose of bolus insulin for a given amount of carbohydrates, the most recent CGM glucose reading and rate of change, activity, and, optionally, insulin on board (IOB). The BlueStar CGM insulin dose calculator requires a prescription.

The BlueStar® CGM insulin dose calculator is a software device module existing in the same mobile medical application as BlueStar® Rx (K203434), which is intended for the management of diabetes. When connected to a compatible integrated continuous glucose monitor (iCGM) and under authorization from a qualified healthcare provider, the BlueStar CGM insulin dose calculator allows patients to calculate a dose of bolus insulin for a given amount of carbohydrates, the most recent iCGM glucose reading and its rate of change, activity, and, optionally, insulin on board (IOB). Other patient-specific inputs from BlueStar Rx are used in the calculation of the recommended dose- specifically, duration of insulin to carb ratio, correction factor, and target glucose. In addition to calculating specific dosing recommendations, the BlueStar CGM insulin dose calculator also provides coaching messages to assist the user in maintaining glucose within the target range.

The use of CGM inputs differentiates the BlueStar CGM insulin dose calculator from the insulin dose calculator included in the previously cleared BlueStar Rx, which uses blood glucose (BG) values from a BG meter using a "fingerstick" method. The CGM insulin dose calculator is intended to coexist with the BG insulin calculator function in the BlueStar Rx software application as the BG calculation may be necessary when CGM is unavailable or the CGM estimated blood glucose does not match how the user feels.

Here's the information about the acceptance criteria and the study that proves the device meets them, 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 specific numerical targets. However, the primary clinical endpoint serves as the de facto acceptance criterion for efficacy, while safety measures address other key concerns.

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

• Sample Size for Test Set: 27 adult subjects.
• Data Provenance: The document does not specify the country of origin of the data. The study was prospective as data was "collected for each subject for 30 days while using the BlueStar mobile app with the CGM insulin dose calculator."

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 mention the use of experts to establish ground truth for the test set. The ground truth was established by the CGM data itself, as it measured glucose time in range.

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

The document does not describe 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

No, an MRMC comparative effectiveness study was not done. The study focused on the effectiveness of the device (BlueStar® CGM insulin dose calculator) in improving or maintaining Time in Range compared to baseline, rather than comparing human reader performance with and without AI assistance.

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

Yes, the clinical study assessed the performance of the "BlueStar mobile app with the CGM insulin dose calculator" as used by the subjects. While patients are "human-in-the-loop" by entering carbohydrates, accepting recommendations, and performing activities, the primary performance metric (TIR) evaluates the algorithm's impact on glucose management, implying a standalone assessment of its functional impact when integrated into patient self-management. The device itself is software that calculates a dose, so the clinical study assesses the impact of these calculations on patient outcomes.

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

The ground truth used was outcomes data, specifically CGM glucose time in range (TIR) and time spent in hypoglycemia, measured directly from Continuous Glucose Monitoring (CGM) devices.

8. The sample size for the training set

The document does not provide information about a separate training set or its sample size. The clinical study described appears to be a validation study.

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

Since information about a training set is not provided, how its ground truth was established is also not available in this document.

Ask a specific question about this device

The InPen dose calculator, a component of the InPen app, is indicated for the management of diabetes by people with diabetes age 12 and older by calculating an insulin dose or carbohydrate intake based on user entered data. The device is indicated for use with NovoLog® or Humalog® U-100 insulin.

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 professional must provide patient-specific fixed doses/ meal sizes to be programmed into the software prior to use.

The InPen app is designed to manage the wireless transfer of insulin dose data from the InPen, log insulin dose data, and provide a dose calculator to aid mealtime insulin dose calculations. The insulin dose calculations provided by the app are meant for patients undergoing multiple daily injection (MDI) therapy. The InPen app is not intended to serve as an accessory to an insulin pump.

The provided text describes the InPen Dose Calculator, outlining its indications for use and
comparing it to a predicate device. However, it does not contain specific acceptance criteria, a
detailed study that proves the device meets those criteria, or the requested specific performance
metrics like sensitivity, specificity, or accuracy.

Here's an attempt to answer the questions based only on the provided text, highlighting
where information is missing:

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

The document does not explicitly state numerical acceptance criteria or present a table of device
performance against such criteria. It generally states that the device "satisfies
all functional performance and safety requirements, meets its intended use, and is safe for the
intended user population."

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

The text mentions a "summative evaluation" where "patients with sufficient diabetes knowledge
completed self-training and then completed a series of critical tasks." However, it does not
specify the sample size of this test set, the country of origin of the data, 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 (e.g. radiologist with 10 years of experience)

This information is not provided in the document. The "ground truth" for the dose calculations
would theoretically be the correct insulin dose based on provided parameters, but the process of
establishing this for the test set is not detailed.

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

The document does not describe 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

The document does not mention a Multi-Reader Multi-Case (MRMC) comparative effectiveness study.
The InPen Dose Calculator is an algorithm to calculate insulin doses, not designed for human
"readers" to interpret medical images or data. Therefore, the concept of human readers improving
with AI assistance in this context does not apply in the manner typically associated with MRMC
studies.

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

The "summative evaluation" involved patients using the device, but the core function is an algorithm
calculating doses based on user input. The document states that the "dose calculator uses the
standard approach using healthcare provider specified insulin-to-carbohydrate ratio and insulin
sensitivity factors for making calculations." This implies a standalone algorithmic function based
on pre-programmed parameters. The "Clinical Evidence" section focuses on usability and safety with
human users, rather than solely on the algorithm's performance in isolation.

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

For the dose calculations, the "ground truth" is implied to be the standard approach using
healthcare provider specified insulin-to-carbohydrate ratio and insulin sensitivity factors for
making calculations. The text also mentions: "the calculator includes a consideration for insulin
on-board based on the published study by Mudaliar et al (1999) for the duration of insulin action."
This suggests calculations are validated against established medical formulas and literature.

8. The sample size for the training set

The document does not provide any information about a training set or its sample size. The device
appears to be a rule-based calculator rather than a machine learning model that would typically
require a training set.

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

As no training set is mentioned or implied for this rule-based dose calculator, this question is not
applicable based on the provided text.

Ask a specific question about this device

The InPen dose calculator, a component of the InPen app, is indicated for the management of diabetes by people with diabetes age 12 and older by calculating an insulin dose or carbohydrate intake based on user entered data. Prior to use, a healthcare professional must provide the patient-specific target blood glucose, insulin-to-carbohydrate ratio, and insulin sensitivity parameters to be programmed into the software.

The InPen app is designed to manage the wireless transfer of insulin dose data from the InPen, log insulin dose data, and provide a dose calculator to aid mealtime insulin dose calculations. The insulin dose calculations provided by the app are meant for patients undergoing multiple daily injection (MDI) therapy. The InPen app is not intended to serve as an accessory to an insulin pump.

Here's a breakdown of the acceptance criteria and study information for the InPen Dose Calculator, based on the provided FDA 510(k) summary:

This document primarily focuses on demonstrating substantial equivalence to a predicate device (K160629) rather than presenting a novel clinical study with quantitative performance metrics against specific acceptance criteria. Therefore, the "acceptance criteria" discussed below are inferred from the demonstrated equivalence and risk management, not explicit numerical thresholds.

Acceptance Criteria and Reported Device Performance

Given that this 510(k) is for demonstrating substantial equivalence to a previously cleared device (K160629) and not presenting new clinical performance data with explicit numerical acceptance criteria, the "acceptance criteria" are primarily established by the equivalence of the product's attributes and the successful completion of verification and validation activities. The reported "device performance" is therefore that it functions identically to the predicate device in its calculations and features, and that risks are mitigated.

Study Information

The submission details primarily focus on demonstrating substantial equivalence to a predicate device (InPen System K160629) and robust software verification and validation (V&V), rather than a traditional clinical study with a test set of patient cases.

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

   • No explicit "test set" of patient cases with clinical outcomes is mentioned in this summary for demonstrating diagnostic or predictive accuracy. The performance data section refers to "Software Verification and Validation Testing" and "Risk Analysis."
   • It is likely that comprehensive software testing (unit testing, integration testing, system testing) was performed on a variety of input scenarios, but the specific "sample size" of test cases for these software tests is not quantified in this summary.
   • Data provenance is not applicable in the context of a clinical test set from patient data, as no such study is described. The V&V activities would involve internally generated test data.

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

   • Not applicable as there is no mention of a clinical test set requiring expert ground truth establishment for diagnostic or predictive accuracy. The "ground truth" for the software's calculations would be the mathematically correct output based on the predefined algorithm, parameters, and input data.

3. Adjudication method for the test set:

   • Not applicable, as no clinical test set with expert adjudication is described.

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 MRMC comparative effectiveness study is mentioned. The device is a "dose calculator" with specific instructions for healthcare professionals to program patient-specific parameters. It assists the patient in calculating doses based on these established parameters and user input, rather than augmenting human interpretation of complex medical images or data that would typically feature in an MRMC study.

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

   • The "Software Verification and Validation Testing" would essentially be a standalone evaluation of the algorithm's performance against its specifications, assuming various inputs. The summary states: "Companion Medical has demonstrated the InPen dose calculator is appropriate for its intended use through the use of hazard analysis according ISO 14971. The dose calculator uses the standard approach using healthcare provider specified insulin-to-carbohydrate ratio and insulin sensitivity factors for making calculations. In addition, the calculator includes a consideration for insulin on-board based on the published study by Mudaliar, et.al. (1999) for the duration of insulin action." This indicates the algorithm's core functionality was evaluated.

6. The type of ground truth used:

   • For the software's calculation accuracy: The ground truth would be the mathematically correct insulin dose or carbohydrate intake as determined by the predefined algorithms and formulas using the input parameters (target blood glucose, insulin-to-carbohydrate ratio, insulin sensitivity, insulin on-board, and user-entered data). This would be established by independent calculation or a trusted reference implementation of the algorithm.
   • For risk management and safety: Ground truth is implicitly established by adherence to standards like ISO 14971 and relevant FDA guidance documents.

7. The sample size for the training set:

   • Not applicable. This device is a rule-based dose calculator, not a machine learning model that typically requires a "training set" of data to learn from. Its "knowledge" is encoded within the algorithms and patient-specific parameters provided by a healthcare professional.

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

   • Not applicable, as there is no training set for this type of device. The algorithm's logic is based on established medical formulas and and a published study for insulin on-board (Mudaliar, et al., 1999).

Ask a specific question about this device

The Sun Nuclear Dose Calculator is a software product intended to compute a radiotherapy dose volume.

Model 1218028 Dose Calculator computes a dose volume for a user-specified treatment delivery device based on user-provided three dimensional volumetric imaging information (e.g., computed tomography) and beam intensity values. Both the imaging data and beam intensity values are specified in DICOM-RT format. The beam model for the specified treatment delivery device is provided with the software. The output of the SDC is a DICOM RT dose volume.

The Dose Calculator is for use with external beam photon radiation therapy calculations. Charged particle radiotherapy calculations (including electron, proton, and heavy ion therapy) are not indicated for use with this product.

The Dose Calculator software application is considered to be a software module that may be used by several Sun Nuclear Corporation products and/or 300 party applications.

The provided document is a 510(k) premarket notification for a medical device called the "Model 1218028 Dose Calculator." It does not contain the detailed study information typically found in a clinical trial report or a comprehensive validation study. The document primarily focuses on establishing substantial equivalence to a predicate device.

Therefore, many of the requested categories cannot be fully answered with the information available.

Here's an attempt to extract what is present and indicate what is missing:

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

The document states: "Test results of the modified device have demonstrated that the device performs within its design specifications and equivalently to the predicate device." However, specific acceptance criteria or quantitative performance metrics are not provided in this summary.

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

The document mentions "appropriate bench testing methods" but does not specify the sample size of the test set, the provenance of the data, 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 (e.g. radiologist with 10 years of experience)

This information is not provided and is unlikely to be relevant for this type of device (a dose calculator) where "ground truth" would likely be established through physical measurements or established theoretical models, not expert consensus on images.

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

Adjudication methods are typically used for subjective assessments by experts. Since the device calculates dose volumes, and the "ground truth" establishment is not explicitly described, this information is not provided and likely not applicable in the traditional sense.

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

The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study. This device is a dose calculator, not an AI-assisted diagnostic tool that would typically involve human readers.

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

The document describes the device as "a software product intended to compute a radiotherapy dose volume." This inherently implies a standalone performance of the algorithm in its primary function, as it computes the dose volume based on inputs. The statement "Test results of the modified device have demonstrated that the device performs within its design specifications" suggests standalone testing, but explicit details of "standalone performance" metrics are not provided.

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 a dose calculator, the ground truth would likely be derived from:

• Physical measurements: Using phantoms and dosimeters to measure actual dose distribution.
• Established reference calculations/models: Comparing the device's output to results from validated and widely accepted dose calculation algorithms or commercial treatment planning systems.
• Theoretical physics principles: Ensuring calculations adhere to fundamental physics.

Given the context of "bench testing," it's highly probable that physical measurements or comparisons to established reference systems were used, but this is not explicitly stated.

8. The sample size for the training set

The document does not mention a training set sample size. This type of device, which computes dose volumes based on physical models and inputs, is generally not "trained" on a dataset in the way a machine learning algorithm for image recognition would be. Its "knowledge" is embedded in its beam model and calculation algorithms.

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

As there is no mention of a traditional "training set" for machine learning, this information is not applicable/provided. The "ground truth" for the device's underlying models (like beam models) would be established through extensive calibration and measurement using dosimetric equipment and physical phantoms, but this process is not detailed here.

Ask a specific question about this device

The REACH Access Telemedicine Dose Calculator is designed for used by trained clinicians to calculate any individual patient's dose for a given agent based on a weight determined by the clinician. Drug dosing for a patient must be made only after careful consideration of the full clinical status of the patient by the ordering clinician and the software provides no validation as to the appropriateness of the entered weight-based dose. The REACH Access Telemedicine Dose Calculator is a convenience feature for trained clinicians based upon accurately entered data. No medical decision should be based solely upon the results provided by this software program. The REACH Access Telemedicine Dose Calculator is intended to be used as an aid in the consultative process and does not overrule or replace physician judgment or diagnosis.

REACH Access is a highly integrated Telemedicine solution that combines workflow, video conferencing, electronic clinical documentation, and medical imaging into a comprehensive and secure internet-based service. It enables healthcare organizations to form virtual collaborative care teams which are created based on patient need rather than availability of specialists. With a flexible, template-based design tool, REACH Access can build template sets which support clinician workflow and documentation relevant to numerous protocols. REACH Access templates support a specific point-in-time consult. This means the workflow processes and clinical content is captured and coordinated with the integrated audio/video conference to allow a remote provider to collaborate with caregivers at a different location in the care of a patient.

The normal process is the patient is assessed and treated in the Emergency Department (ED) by ED staff and the video conference support of a specialist consultant. After reviewing key patient data and assessing the patient, the remote consultant renders an impression, recommends the treatment order as indicated, and helps determine the appropriate disposition. This usually concludes the consultant's part in the session. The ED continues to render care by completing the recommended treatment order and monitoring patient vital signs and other assessments. The disposition commonly consists of transferring the originating hospital to the Hub with which the consultant is associated. However, if there is adequate local support, the decision may be made to admit the patient to the local facility.

This process/workflow is similar to what may be required for other point-in-time consults needed to provide additional remote assistance to caregivers for other patient problems or conditions at the patient point of care. A protocol/template can be part of a coordinated collection of toolsets. The flexible template design process in REACH Access addresses the need for multiple protocols to support the various phases of care. The flexibility of the tool allows for the unique presentation of data for a specific condition; e.g., stroke, in the format most relevant to the patient's current need/condition. This flexibility can be replicated to address similar capability. This can be handled through a combination of both individual and a series of protocols arranged in clinically logical groups.

This document is a 510(k) premarket notification decision letter from the FDA for the "REACH Access Telemedicine Dose Calculator." It focuses on establishing substantial equivalence to a predicate device rather than presenting a performance study with acceptance criteria and results from an independent test set.

Therefore, most of the information requested in your prompt regarding acceptance criteria, study design, sample sizes, ground truth establishment, expert involvement, and MRMC studies is not present in this document. This typically wouldn't be included in a 510(k) summary for devices like a dose calculator where the primary demonstration of safety and effectiveness relies on software verification and validation, and comparison to a predicate device with similar operational principles.

Here's what can be extracted and what cannot be from the provided text:

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

• Acceptance Criteria: Not explicitly stated as formal, quantitative acceptance criteria for a performance study. The core "acceptance" for this device is "substantial equivalence" to the predicate, based on its intended use, technological characteristics, and principles of operation, and that it raises "no issues of safety or effectiveness."
• Reported Device Performance: Instead of performance metrics from a clinical study, the document reports "Validation and Verification" was done. The conclusion states "The performance of the REACH Access Telemedicine Dose Calculator is substantially equivalent to that of the Picis Weight Based Dose Converter and raises no safety or effectiveness issues and performs as well or better than the predicate device."
  • Implication: For a dose calculator, "performance" would primarily relate to the accuracy of its mathematical calculations. The mention of "Validation and Verification" suggests that the software was tested to ensure it correctly computes doses based on the input weight and dose rate, as per its simple mathematical equation. However, no specific numerical performance results (e.g., error rates, precision) are provided.

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

• Sample Size (Test Set): Not mentioned. "Validation and Verification" for a software like a dose calculator typically involves testing a defined set of inputs and expected outputs, not a "sample size" in the sense of patient data in a clinical trial.
• Data Provenance: Not applicable in the context of this device type and the information provided. The "data" being processed is clinician-entered weight.

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

• Number of Experts: Not applicable. Ground truth for a mathematical calculation is the correct mathematical result, not expert interpretation.
• Qualifications of Experts: N/A

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

• Adjudication Method: Not applicable.

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

• MRMC Study: No. This is not an AI-assisted diagnostic imaging device. It's a simple dose calculator.

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

• Standalone Performance: For a dose calculator, the "standalone performance" refers to its mathematical accuracy. While "Validation and Verification" implies such testing was done, no specific results or methods are detailed in this summary. The device's function is purely algorithmic: "Uses simple mathematical equation to calculate dosing based on patient weight."

7. The type of ground truth used:

• Ground Truth: For a drug dose calculator, the ground truth would be the quantitatively correct mathematical dose calculation based on the entered weight and the specified drug dose per unit weight (which the clinician determines). This ground truth is derived from the fundamental mathematical operations the calculator performs.

8. The sample size for the training set:

• Training Set Sample Size: Not applicable. This device is not an AI/ML model that requires a training set. It is a rule-based software performing a direct calculation.

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

• Ground Truth for Training Set: Not applicable as there is no training set for this type of device.

Summary of what is present in the document relevant to your query:

• The device is a "REACH Access Telemedicine Dose Calculator."
• Its purpose is to "calculate any individual patient's dose for a given agent based on a weight determined by the clinician."
• The calculation "Uses simple mathematical equation to calculate dosing based on patient weight."
• The study done was "Validation and Verification" (which for such a device implies testing the accuracy of the calculation).
• The primary method of demonstrating legitimacy was to show "Substantial Equivalence" to a predicate device (Picis Weight Based Dose Converter, K121542), meaning it has the "same intended uses, technological characteristics and principles of operation."

This document does not describe the kind of performance study one would expect for an AI/ML diagnostic or prognostic device, but rather a software validation process for a simple calculation tool.

Ask a specific question about this device

The EndoTool™ Drug Dose Calculator is a software support system designed for use by trained healthcare professionals to calculate any individual patient's optimal next dose for insulin administered intravenously to control blood glucose level for critically ill patients without inducing hypoglycemia (low blood glucose levels). EndoTool™ is for use with patients who are receiving a relative constant nutritional intake via intravenous fluids with dextrose, total parental nutrition or continuous gastro-intestinal feedings by any route of delivery.

EndoTool™ Drug Dose Calculator is software that resides on a Microsoft/Intel platforms to calculate (see Section 9.2, page 20) the drug dose of insulin to control blood glucose levels for critically ill patients on continuous feeding (IV, TBN, or tube feeding).

I'm sorry, but relevant sections of this document are either missing or do not contain enough information to generate a comprehensive answer for the requested subsections. The provided text primarily focuses on regulatory information, device description, intended use, and substantial equivalence to a predicate device, rather than detailed study design or performance metrics. Therefore, I cannot provide details on acceptance criteria and study results.

Ask a specific question about this device