Search Results

The GlucoCare IGC System is a software program indicated for the management of patient blood glucose levels in the hospital setting. The GlucoCare IGC System software, using an algorithm that is based on an established clinical protocol, calculates the dosage of intravenously administered insulin required to maintain the blood glucose level within a target range set by the protocol. No medical decisions are made by the GlucoCare IGC System software. The information provided by the software is intended to be used as a tool by qualified and trained medical personnel. The GlucoCare IGC System software is intended for use in patients over the age of 18 with no known insulin allergies. The device is not intended for use in patients with diabetic ketoacidosis.

The GlucoCare IGC System is a software program that implements an insulin infusion protocol intended for the treatment of hyperglycemic adult patients in a healthcare facility. The software directs insulin infusion rates based on the patient's blood glucose level history and target blood glucose level. Audible and visual alerts remind the medical staff when it is time to take blood glucose readings or change insulin drip rates. The system provides a complete time/date/username-stamped history of all patient activity in text and graphical formats, both on-screen and in a printable form. The GlucoCare IGC System software resides on the GlucoCare application server. Local client computers interact with the GlucoCare IGC System software using HTTPS.

The provided text does not contain specific acceptance criteria or a detailed study proving the device meets those criteria. The information focuses on establishing substantial equivalence to predicate devices rather than presenting performance metrics against predefined acceptance thresholds.

However, based on the limited information available, here's a breakdown of what can be inferred or explicitly stated about performance testing, and the missing elements:

1. Table of Acceptance Criteria and Reported Device Performance:

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

• Sample Size for Test Set: Not specified. The document only mentions "Software verification and validation testing activities." There is no mention of a clinical test set with patient data.
• Data Provenance: Not applicable, as there's no mention of using real patient data for "testing" in the sense of a clinical or retrospective patient study. The testing described appears to be software testing (unit, integration, system, functional).

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

• Not applicable. The document describes software verification and validation, not a clinical study where expert-established ground truth would be relevant for a test set. The algorithm is based on "an established clinical protocol," implying that domain experts (likely endocrinologists or critical care physicians) defined the protocol that the software implements, but this is distinct from establishing ground truth for a test set of the software's performance.

4. Adjudication Method for the Test Set:

• Not applicable. There is no mention of a test set requiring adjudication.

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

• No, a MRMC comparative effectiveness study was not done. The text does not describe any study comparing human readers (medical personnel) with and without AI (the GlucoCare IGC System) assistance. The device is described as a "tool" to assist medical personnel, implying it's always used with human-in-the-loop, rather than in comparison to unassisted human performance.

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

• Yes, in the context of software performance, a standalone evaluation was implicitly done. The "Software verification and validation testing activities" including unit, integration, system, and functional testing are evaluations of the algorithm's correctness and functionality on its own, independent of live human interaction. However, this is not a standalone clinical performance study regarding patient outcomes. The document explicitly states: "No medical decisions are made by the GlucoCare IGC System software. The information provided by the software is intended to be used as a tool by qualified, trained medical personnel." This indicates the device is not intended for standalone clinical decision-making.

7. Type of Ground Truth Used:

• For the software testing described, the "ground truth" would be the expected output or behavior of the software based on its design specifications and the underlying established clinical protocol. This is internal software validation, not a clinical ground truth like pathology or outcomes data.

8. Sample Size for the Training Set:

• Not applicable. This device is described as implementing "an established clinical protocol" using an algorithm. It is not an AI/ML model that would typically require a "training set" in the machine learning sense to learn patterns. The algorithm's rules are pre-defined based on clinical knowledge.

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

• Not applicable, as there is no training set in the typical AI/ML sense. The "ground truth" for the algorithm's logic would be rooted in established medical consensus and clinical guidelines that informed the "established clinical protocol" it implements.

Ask a specific question about this device