Search Results

EndoTool SubQ is a software management system for use by trained healthcare professionals to calculate and recommend an individual patient's next dose of insulin to be administered subcutaneously to manage elevated blood glucose levels in both adult and pediatric patients (age 2 and above and 12 kg or more). The software is designed to recommend the insulin dose(s) (and on occasion a carbohydrate dose for the treatment of hypoglycemia) based on the prescribing healthcare provider's insulin regimen, target glucose level range, and nutritional regimen. The software provides an optional insulinon-board (IOB) calculation that estimates the sum of the remaining insulin activity from previously administered subcutaneous insulin(s). This IOB adjustment reduces the prescribed Bolus dose and, if appropriate, recommends a supplemental carbohydrate dose to the trained healthcare professional.

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

Monarch Medical Technologies' EndoTool SubQ Glucose Management System is a software application for use by trained healthcare professionals to calculate a hospitalized patient's next dose of insulin (administered subcutaneously) or carbohydrates to manage blood glucose levels in both adult and pediatric patients (age 2 and above and 12kg and above) based on their individual glucose response to previously administered insulin. The subject device, EndoTool SubO with optional Insulin-on-Board (IOB) calculation, and the predicate device, EndoTool SubQ (K142918), both provide an insulin dose recommendation based on the patient's clinical data and the physician's current prescribed dosing regimen.

EndoTool SubQ Glucose Management System is packaged in a user friendly, browser-based program using Microsoft .Net technologies. The application requires Windows. The application was developed for use on Personal Computers (PCs), network servers, and terminal server environments.

EndoTool SubQ Glucose Management System can utilize barcode scanning for patient identification/verification.

Other platform requirements of the system include installation of the following software: SQL Server 2005 or greater, Crystal Reports Basic for Visual Studio 2008, and Adobe Reader.

The medical device is the EndoTool SubQ, a software management system designed to calculate and recommend insulin doses for managing elevated blood glucose levels.

Here's an analysis of the acceptance criteria and study information provided:

1. Table of Acceptance Criteria and Reported Device Performance:

The document doesn't explicitly present a table of acceptance criteria with corresponding performance metrics. However, it states that "In all testing, the pre-determined acceptance criteria were met."

The non-clinical testing summary lists the following activities, which inherently define the acceptance criteria:

2. Sample Size Used for the Test Set and Data Provenance:

The document does not explicitly state the sample size used for the test set in terms of patient data. The non-clinical testing appears to involve software verification and validation using "Automated Algorithm Test Cases" and "Manual verification test cases," rather than a clinical dataset of patients.

The data provenance is not specified as patient data was not used for testing. The testing described focuses on software performance, not clinical outcomes with real patient data.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications:

This information is not provided. The ground truth for the software testing would likely be based on expected outputs of the algorithms, rather than expert clinical consensus.

4. Adjudication Method for the Test Set:

This information is not provided. Given that the testing focuses on software verification and automated algorithm tests, an adjudication method for clinical disagreement would not be applicable.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

A multi-reader multi-case (MRMC) comparative effectiveness study was not done. The document describes non-clinical testing focused on software functionality and algorithm verification, not a study comparing human readers with and without AI assistance.

6. Standalone (Algorithm Only Without Human-in-the-Loop) Performance Study:

A standalone performance study of the algorithm was done, in the sense that the device's algorithms were tested independently of human interaction. The "Automated Algorithm Test Cases for Insulin on Board" and "Automated algorithm test cases for the complete SubQ application" indicate testing of the algorithm's output against expected results. However, this is in the context of software verification, not a clinical trial to assess standalone clinical performance.

7. Type of Ground Truth Used:

The ground truth used for the testing appears to be expected algorithmic outputs and predefined software requirements. For example, "Verification Testing of Insulin on Board SRS Requirements" indicates comparison against system requirements, and "Automated Algorithm Test Cases" suggests comparing output with mathematically or logically expected results. There is no mention of pathology, expert consensus on patient outcomes, or other clinical ground truth types for the testing described.

8. Sample Size for the Training Set:

The document does not specify a sample size for a training set. This suggests that the device, being a "Predictive Pulmonary-Function Value Calculator" (though the device description refers to insulin dosing, which is a discrepancy in the regulation name) and an insulin dosing recommendation system, likely relies on predefined algorithms and logic rather than a machine learning model that requires a training set.

9. How the Ground Truth for the Training Set Was Established:

As no training set is mentioned or implied for a machine learning model, the method for establishing its ground truth is not applicable/not provided. The device's "Predictive Pulmonary-Function Value Calculator" (regulation name) or "insulin dose recommendation" (device description) functions would be based on established physiological models and drug pharmacokinetics, implemented as algorithms.

Ask a specific question about this device