Search Results

The Genesis Health Record System is an accessory to the Genesis Health Technologies Blood Glucose Meter, Model TD-4123 to assist in the review and evaluation of blood glucose test results and related information to aid in diabetes management. It is indicated for use by adult diabetic patients for use in the home and by healthcare professionals in the professional setting. The System is not intended to provide automated treatment guidance or decisions. The System is not indicated for the diagnosis or screening of diabetes.

1. The Genesis Health Record System (GHRS) is an internet browser based data management system for use with the Genesis Health Technologies Blood Glucose Meter Cleared under K121224.
2. The GHRS data management system allows patients to wirelessly transmit the results of glucose testing including the test result, date and time from the blood glucose meter via a CDMA module in the blood glucose meter over the Verizon wireless network, to a secure central database. The results are then stored on a secure central database and can be accessed through the internet by patients and/ or authorized healthcare professionals, on a personal computer running any operating system with access to the internet. The user can review and evaluate results of blood glucose tests and related information to aid in the management of diabetic patients. Results can be displayed on the computer in the form of a Log Book report showing test results from a specified date range, a graphical display of the patient's results and a trending report showing within target and out of target percentages.
3. A current internet browser and internet access are required to reach the MyGHR website. No other programs or applications need to be installed on a computer terminal. No cables are required. The User goes to the MyGHR website and sets up their account.

The Genesis Health Record System (GHRS) is a data management system intended to be an accessory to the Genesis Health Technologies Blood Glucose Meter, Model TD-4123. It assists in the review and evaluation of blood glucose test results and related information to aid in diabetes management. It is indicated for use by adult diabetic patients in the home and by healthcare professionals in a professional setting. The system is not intended to provide automated treatment guidance or decisions, nor is it indicated for the diagnosis or screening of diabetes.

Here's the breakdown of the acceptance criteria and the study that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for the GHRS device are inferred from the non-clinical testing performed, focusing on software verification and validation, as well as human factors testing to ensure usability and data integrity.

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

The document primarily describes validation and verification activities rather than a traditional "test set" for performance evaluation in the way one might evaluate an AI/ML model for diagnostic accuracy.

• For Software Functionality/Data Transfer: No specific "test set" sample size of patient data is mentioned. The validation involves testing algorithms and software functions described in specific V&V plans (e.g., GHRS V & V Test Plan 2.21.4, 2.21.5, 2.21.6, GHT BGM V & V Test Plan 1.13.1). These tests would likely involve simulated or artificially generated data to cover all defined scenarios and parameters. The provenance of this data is not specified, but it would be internal to the company's development and testing process.
• For Human Factors:
  • Sample Size: 25 Home Use participants and 4 Healthcare Professionals.
  • Data Provenance: The study was conducted using the actual device and intended users, likely in a controlled environment. The country of origin is not explicitly stated but can be assumed to be within the US given the submission to the FDA. The data generated was prospective, as it involved participants performing tasks with the device.

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

Given the nature of the device (a data management system for blood glucose meters), the "ground truth" for the software functionality tests would be the correct operation and calculation according to predefined specifications and mathematical rules.

• Software Functionality: The ground truth would be established by the software designers and engineers who define the expected behavior and calculations. The number and qualifications of these individuals are not specified in the document.
• Human Factors: The ground truth for the human factors study's data accuracy aspect was 100% accuracy of transmitted data, which would be determined by comparing the readings taken from the physical meter to the data stored in the database. This doesn't necessarily involve "experts" establishing a subjective ground truth, but rather technical verification.

4. Adjudication Method for the Test Set

• Software Functionality: Not applicable in the sense of expert adjudication. Software verification and validation typically involve comparing system output against predefined behavioral requirements and calculated results for known inputs. Deviations would be considered defects.
• Human Factors: The human factors study involved "an analysis of user completed tasks" and a "user evaluation analysis incorporating a 5 point Likert Scale." This suggests direct observation and user feedback rather than an adjudication method for disagreements among multiple evaluators. The 100% data accuracy claim would be a direct comparison, not 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

No, an MRMC comparative effectiveness study was not done. This device is a data management system, not a diagnostic AI/ML algorithm that assists human readers in interpreting medical cases. Therefore, the concept of "human readers improve with AI vs without AI assistance" is not applicable.

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

Yes, standalone testing, in the form of software verification and validation, was primarily done for the core functionality of the device. The "algorithm" in this context refers to the data processing, display, and calculation functions of the software. These were tested independent of a human user's diagnostic interpretation. The human factors study separately validated the human-in-the-loop (i.e., user interaction) aspects, but the core data handling and processing would have been verified as a standalone system function.

7. The Type of Ground Truth Used

• Software Functionality: The ground truth was based on predefined design specifications and mathematical correctness. This refers to the accuracy of displayed data, calculations, filtering, and reporting matching the expected behavior and standards for blood glucose data management.
• Data Transfer: The ground truth was direct comparison of meter readings to stored database values to confirm 100% accuracy of transmission and integrity.
• Human Factors: The ground truth for the data accuracy component was the actual meter reading compared to the transmitted and displayed data. For usability, the ground truth was the successful completion of tasks by users and their subjective feedback via the Likert scale.

8. The Sample Size for the Training Set

Not applicable. This device is a data management system and not an AI/ML algorithm that requires a training set in the conventional sense (i.e., for learning patterns from data to make predictions or classifications). Its functionality is based on programmed logic and calculations, not trained models.

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

Not applicable, as there was no training set for an AI/ML algorithm.

Ask a specific question about this device