(80 days)
DIDGET® World Reports Diabetes Management Software is an over-the-counter software program for use by healthcare professionals and patients with diabetes for viewing and printing reports that display blood sugar readings from Bayer's DIDGET® blood glucose meter.
This software application allows the transfer of blood glucose results, along with time, date, and certain data markers, from Bayer's DIDGET® blood glucose meter to the DIDGET®World Reports web server through the use of a USB cable. Data analysis includes allowing the home-user or healthcare professional to view the data in five different ways:
Electronic logbook where all of the data can be seen
Glucose trend of the results by date
Daily blood glucose trend (standard day)
Weekly blood glucose trend (standard week)
Summary chart (histogram or pie chart)
The DIDGET® World Reports Diabetes Management Software is a diabetes data management software program. The performance assessment focused on its ease of use and understandability of results.
1. Table of Acceptance Criteria and Reported Device Performance:
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Program is easy to use | The study showed that the program is easy to use |
| Results are understandable by users | The study showed that the results are understandable by the users |
2. Sample size used for the test set and the data provenance:
- Test Set Sample Size: Fifty (50) subjects.
- 3 healthcare professionals (HCPs)
- 47 lay users (35 young adults with diabetes and 12 parents or legal guardians of children with diabetes).
- Data Provenance: The document does not specify the country of origin. The study was a "Performance Assessment," implying it was a prospective study designed specifically to evaluate this software.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
This device is software for viewing and printing blood sugar readings. The performance assessment was about usability and understandability rather than diagnostic accuracy against a "ground truth" established by experts in the typical clinical sense (e.g., radiologists interpreting images). The "ground truth" in this context was subjective user feedback on ease of use and understandability of the presented data. The study included 3 healthcare professionals, but their role was as participants providing feedback, not as independent adjudicators establishing a gold standard for the data.
4. Adjudication method for the test set:
Not applicable. The study assessed subjective user experience (ease of use and understandability) rather than objective clinical outcomes requiring adjudication.
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 applicable. This is a data management software, not an AI-powered diagnostic tool, and the study did not involve human readers interpreting cases or AI assistance for diagnosis.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
The performance assessment focused on the human-in-the-loop experience (users interacting with the software). A standalone performance of the algorithm itself (e.g., data transfer accuracy, report generation accuracy) is implied by the "verification and validation studies" mentioned, but specific details of such standalone tests are not provided in this summary. The stated performance assessment is user-centric.
7. The type of ground truth used:
The "ground truth" for this performance study was subjective user feedback and experience regarding the software's ease of use and the understandability of its presented data.
8. The sample size for the training set:
Not applicable. This regulatory submission concerns a diabetes data management software. There is no mention of a machine learning or AI model being trained, thus no "training set" in that context. The software's functionality is based on displaying and organizing existing data, not on learning from data to make predictions or classifications.
9. How the ground truth for the training set was established:
Not applicable, as there is no training set for a machine learning model.
§ 862.1345 Glucose test system.
(a)
Identification. A glucose test system is a device intended to measure glucose quantitatively in blood and other body fluids. Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus, neonatal hypoglycemia, and idiopathic hypoglycemia, and of pancreatic islet cell carcinoma.(b)
Classification. Class II (special controls). The device, when it is solely intended for use as a drink to test glucose tolerance, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 862.9.