(243 days)
The ACCU-CHEK Connect Diabetes Management App is indicated as an aid in the treatment of diabetes. The software provides for electronic download of blood glucose meters, manual data entry, storage, display, transfer, and self-managing of blood glucose and other related health indicators which can be shown in report and graphical format.
The ACCU-CHEK Bolus Advisor, as a component of the ACCU-CHEK Connect Diabetes Management App, is indicated for the management of diabetes by calculating an insulin dose or carbohydrate intake based on user-entered data. Before its use, a physician or healthcare professional must activate the bolus calculator and provide the patient-specific target blood glucose. insulin-to-carbohydrate ratio, and insulin sensitivity parameters to be programmed into the software.
The ACCU-CHEK Connect Diabetes Management App is designed to facilitate efficient collecting, transmitting, and analyzing of blood glucose results and other diabetes management data. The App helps:
• Wireless transfer of data from ACCU-CHEK Aviva Connect Blood Glucose Meter.
• Assist in general diabetes management through logging of contextual data.
• ACCU-CHEK Bolus Advisor support of mealtime insulin dosing calculations.
• Perform structured testing.
• Wireless transfer of data from mobile devices to ACCU-CHEK Connect Online Diabetes Management System and optionally share this data with healthcare provider (HCP) or caregiver.
The insulin bolus calculations provided by the app are meant for patients undergoing multiple daily injection therapy. Bolus calculators, such as the ACCU-CHEK Bolus Advisor, have been demonstrated to facilitate the optimization of glycemic control in patients who are trained in multiple daily insulin injection therapy and under the supervision of healthcare professional experienced in managing insulin-treated patients. Such calculators have also been shown to reduce patient fear of hypoglycemia and improve patient confidence in diabetes management.
The ACCU-CHEK Connect Diabetes Management App is not intended to serve as an accessory to an insulin pump.
Here's an analysis of the provided text regarding the acceptance criteria and study for the ACCU-CHEK Connect Diabetes Management App, structured as requested:
Acceptance Criteria and Device Performance for ACCU-CHEK Connect Diabetes Management App
The provided FDA 510(k) summary (K141929) for the ACCU-CHEK Connect Diabetes Management App primarily focuses on demonstrating substantial equivalence to a predicate device (ACCU-CHEK Aviva Combo meter). While it mentions "performance requirements" and "algorithm validation," it does not explicitly state specific quantitative acceptance criteria (e.g., in terms of accuracy, sensitivity, specificity, or precision) with corresponding reported device performance values in a table. Instead, it refers to a qualitative assessment that the device "meets the performance requirements for its intended use" and "demonstrated that the device functions as intended."
The document emphasizes that the Bolus Advisor algorithm within the app is "unchanged as compared to the predicate device." Therefore, the performance of the algorithm is implicitly tied to the cleared performance of the predicate.
Here's an attempt to structure the available information, noting the absence of explicit quantitative criteria in the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
| Feature/Metric | Acceptance Criterion (Implicit) | Reported Device Performance (Implicit) | Notes |
|---|---|---|---|
| Bolus Calculation Accuracy | Functionality and accuracy should be equivalent to the predicate device (ACCU-CHEK Aviva Combo meter's bolus calculator). | Algorithm is unchanged from predicate device, therefore deemed to perform equivalently. | The submission relies on the prior clearance of the predicate's algorithm. No new specifics are provided. |
| Usability | Device functions as intended for users (persons with diabetes and caregivers) and adheres to safety risk-mitigating controls. | "Human Factors clinical study demonstrated the diabetes management app fulfilled all predefined requirements for safety risk-mitigating controls when handled by persons with diabetes mellitus or their caregivers, according to its intended use." | Qualitative assessment from human factors study. No quantitative error rates or specific usability metrics are provided. |
| Software Functionality | Software components (data transfer, logging, display, reporting) operate correctly as designed. | "Software testing and performance testing of the device demonstrate the device functions as intended." | General statement of verification and validation. No specific bugs, errors, or performance metrics are detailed. |
| Data Transfer | Wireless data transfer from ACCU-CHEK Aviva Connect Blood Glucose Meter to app, and from app to ACCU-CHEK Connect Online Diabetes Management System works reliably. | Implicitly demonstrated as part of "software testing" and "performance testing." | No specific success rates or error rates are given for data transfer. |
2. Sample Size for the Test Set and Data Provenance
The document mentions "software testing and performance testing of the device" and a "Human Factors clinical study."
- Software and Performance Testing: No specific sample size (e.g., number of test cases, specific data points) is provided for the device's main software and performance testing.
- Human Factors Clinical Study: No specific sample size (e.g., number of participants) is provided for the "Human Factors clinical study."
- Data Provenance: The document does not specify the country of origin of the data or whether the tests were retrospective or prospective. Given it's a 510(k) submission to the FDA, it's highly likely that the studies were conducted with data relevant to the US market or in a manner acceptable to the FDA.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
This information is not provided in the given document. The submission focuses on demonstrating substantial equivalence to a predicate device whose bolus calculation algorithm is adopted directly. The Human Factors study involved "persons with diabetes mellitus or their caregivers," but these are considered users, not experts establishing ground truth for algorithmic performance.
4. Adjudication Method for the Test Set
This information is not provided in the given document. Given the nature of a software application for diabetes management and bolus calculation, adjudication might not be relevant in the same way it would be for diagnostic imaging where expert consensus is often used. For software functionality, ground truth often comes from predefined requirements and expected outputs based on established medical formulas.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done
No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done as described in the provided text. The device is a "Drug Dosing Calculator" and a "diabetes management app," not an AI-assisted diagnostic tool that would typically involve human readers interpreting cases. The document states that the Bolus Advisor algorithm is unchanged from the predicate device, implying that its effectiveness has already been established and accepted with that predicate. No effect size of human improvement with AI assistance is mentioned because this type of study was not conducted or reported.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) Study was Done
Yes, implicitly, a standalone assessment of the algorithm was done. The document states: "The insulin bolus calculator algorithm is unchanged as compared to the predicate device." This means the algorithm's performance was previously validated in its standalone form within the predicate device (ACCU-CHEK Aviva Combo meter). The current submission leverages that prior validation. There's no new, separate standalone study explicitly described for the ACCU-CHEK Connect Diabetes Management App, beyond the confirmation that it uses the same algorithm.
7. The Type of Ground Truth Used
For the bolus calculation algorithm, the ground truth would be based on established medical formulas and diabetes management guidelines for insulin dosing and carbohydrate intake calculations. The accuracy of these calculations against the established formulas would have been the ground truth for the predicate device. For the ACCU-CHEK Connect App, the ground truth for its software functionality relies on validated software requirements and the expected output of its operations.
8. The Sample Size for the Training Set
This information is not applicable/not provided in the context of this device. The ACCU-CHEK Connect Diabetes Management App, particularly its Bolus Advisor, is a rule-based system employing an "unchanged" algorithm from a predicate device. It is not an AI/Machine Learning model that would typically have a "training set" in the conventional sense. The algorithm is based on well-defined clinical parameters (target blood glucose, insulin-to-carbohydrate ratio, insulin sensitivity, etc.) provided by a healthcare professional.
9. How the Ground Truth for the Training Set was Established
As noted above, this device does not appear to involve machine learning or AI that would require a "training set" with ground truth established through typical methods like expert annotation or pathology. The "ground truth" for the bolus calculation algorithm stems from established medical science and clinical practice guidelines for insulin dosing, which determine the correct output for given input parameters. The validation of such an algorithm would involve testing it against a wide range of clinically relevant scenarios, where the "correct" insulin dose is derived from these established medical principles.
§ 868.1890 Predictive pulmonary-function value calculator.
(a)
Identification. A predictive pulmonary-function value calculator is a device used to calculate normal pulmonary-function values based on empirical equations.(b)
Classification. Class II (performance standards).