Search Results

Digital Routines is indicated for use by healthcare providers (HCPs) and their patients - aged 21 years and older - who have type 2 diabetes. Digital Routines is intended to provide secure capture, storage, and transmission of blood glucose data as well as information to aid in diabetes self-management. The Digital Routines system analyzes and reports blood glucose test results and supports medication adherence. In addition, Digital Routines provides coaching messages (motivational, behavioral, and educational) based on blood glucose values and trends. It includes software intended for use on mobile phones (for patients) or personal computers (for HCPs) in the home or in professional healthcare settings. The software also allows for entry of other diabetes-related healthcare information and provides educational information. The following Digital Routines insulin management features are for prescription use only:

· For bolus insulin users with type 2 diabetes, Digital Routines includes an insulin dose calculator to allow patients to use their prescribed regimen to calculate a dose of bolus insulin for a given amount of carbohydrates and/or blood glucose value. The healthcare provider must activate the insulin dose calculator for patient.

· For basal insulin users with type 2 diabetes, Digital Routines includes an Insulin Adjustment Program (1AP) which calculates appropriate long-acting basal insulin doses for titrating insulin levels based on configuration by a healthcare provider knowledgeable in the care and management of diabetes. The healthcare provider must activate the IAP and configure it with patient-specific parameters.

Digital Routines is not intended to replace the care provided by a licensed healthcare professional, including prescriptions. diagnosis, or treatment.

The Digital Routines is a stand-alone medical software system intended to be used by patients aged 21 and older who have type 2 diabetes. Digital Routines is a new kind of approach to support in helping patients manage their type 2 diabetes. Digital Routines real-time feedback and guidance fit into daily life to help patients stay on track with their diabetes care plan.

Digital Routines is accessible directly from the patient's mobile phone, but also includes the patient's HCP throughout the process. It supports the healthcare provider`s treatment plan while helping with building the patient's knowledge about diabetes and stay motivated. The device also incorporates an insulin calculator for bolus insulin users and an insulin adjustment program for basal insulin users. These features require the approval of a physician before the patient can access them.

The system comprises three core software components:

• the Patient Mobile Application (i)
• the HCP Web Portal (ii)
• the Enterprise Director Web Portal (iii)

HCPs can authorize the Insulin Calculator or initiate an Insulin Adjustment Program (Rx only). The Insulin Adjustment Program is designed to help physicians and their patients with type 2 diabetes to adjust their long-acting (basal) insulin to improve diabetes management. The program works by collecting and analyzing blood glucose readings to adjust basal insulin doses according to the physician's instructions. Physicians can view and adjust their patient's treatment plan at any time, and they receive safety notifications such as if a patient experiences hypoglycemia or takes insulin doses that substantially differ from the recommended amount.

The Insulin Calculator uses the physician authorized regimen to calculate the corresponding dose of bolus insulin to take based on a patient's carbs and blood glucose value. Patients eligible to use the Insulin Calculator have the option within Digital Routines to request access to it. The patient's physician must authorize the Insulin Calculator for it to be activated. Prior to using the Insulin Calculator, the patient will be required to complete in-app training on the use of the calculator. The Insulin Calculator may also include an optional Insulin on Board feature that must be authorized by the physician.

Here's an analysis of the provided text regarding the acceptance criteria and study information for "Digital Routines":

The provided document (a 510(k) summary) does not contain specific acceptance criteria, nor does it detail a study that directly proves the device meets such criteria in a quantitative sense (e.g., performance metrics, statistical results from a clinical trial). Instead, it focuses on demonstrating substantial equivalence to a predicate device, which is the primary mechanism for FDA clearance in this pathway.

The type of studies mentioned are Software Validation & Verification (V&V), cybersecurity evaluation, and human factors testing. These are general categories of testing required for software-based medical devices, not specific performance studies with quantitative acceptance criteria for the core functionality as one might expect for an AI/ML diagnostic or predictive algorithm.

Therefore, many of the requested sections will be answered as "Not provided" or "Not applicable" based on the content.

Acceptance Criteria and Reported Device Performance

Additional Study Information:

1. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):

   • Not provided. The document states "Software V&V testing was performed" and "Human factors testing was conducted," but does not detail the sample sizes for these tests, the type of data used (beyond "blood glucose data"), or its provenance.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience):

   • Not provided. Ground truth establishment, in the context of expert review for performance evaluation, is not mentioned in this summary. The device's primary function involves calculations based on patient-entered data and HCP-configured parameters, and coaching messages derived from trends, rather than interpreting complex medical images or signals requiring a panel of expert human reviewers for ground truth.

3. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

   • Not applicable / Not provided. The summary does not describe any test sets or adjudication processes that would involve expert review for ground truth consensus.

4. 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 study is not mentioned. The device, "Digital Routines," is a diabetes self-management system with insulin dose calculation/adjustment features. Its purpose is to assist patients and HCPs with managing diabetes, not to improve human reading of diagnostic images/cases. The summary does not provide any information about human reader performance improvement.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

   • Partially applicable. The device includes an "Insulin Calculator" and an "Insulin Adjustment Program (IAP)." While these are "Rx only" features requiring HCP activation and configuration, the calculations themselves are performed by the algorithm. The software V&V would, in principle, test the accuracy and correctness of these algorithmic calculations. However, the summary does not provide specific performance metrics for these algorithms (e.g., accuracy of insulin dose calculations against a gold standard). It merely states that "Software V&V testing has demonstrated that the device meets the applicable software requirements."

6. The type of ground truth used (expert concensus, pathology, outcomes data, etc.):

   • Not explicitly stated for performance evaluation. For the Insulin Calculator and IAP, the "ground truth" would implicitly be the mathematically correct calculation based on the prescribed regimen and patient parameters set by the HCP. For coaching messages, the ground truth would be adherence to predefined rules for generating messages based on blood glucose values and trends. The summary does not elaborate on how this ground truth was formally established or used in testing.

7. The sample size for the training set:

   • Not applicable / Not provided. The description of "Digital Routines" suggests a rules-based system or an application directly implementing medical guidelines (for insulin calculations and adjustments) rather than a machine learning model that requires a training set in the typical sense. It analyzes blood glucose data and provides coaching "based on blood glucose values and trends," which could be rule-based. No mention of machine learning model training is made, nor are training sets discussed.

8. How the ground truth for the training set was established:

   • Not applicable / Not provided. As no training set is described, the method for establishing its ground truth is also not provided.

In summary: The provided 510(k) summary focuses on establishing substantial equivalence by comparing the device's features, intended use, and technological characteristics to a predicate device, and by confirming general software, cybersecurity, and human factors compliance. It lacks specific quantitative acceptance criteria and detailed performance study results that would typically be associated with direct clinical performance claims or advanced AI/ML algorithms requiring extensive training and test sets with defined ground truth.

Ask a specific question about this device