(37 days)
iSage Rx is indicated for use by adult patients with type 2 diabetes, and by their healthcare providers to provide ongoing support for understanding and following a titration plan for the following medications, with the goal of reaching optimal medication dose and/or target fasting blood sugar control:
-Basal insulins
-Combinations of basal insulin and GLP-1 receptor agonists
iSage Rx System includes a web-based, HIPAA-compliant, password protected Health Care Provider (HCP), Account Administrated websites, and a patient mobile app. The system was designed to enable HCPs to digitize and deploy their basal insulin titration plan such that adult patients with type 2 diabetes may better understand and follow their basal insulin treatment plan through the iSage Rx app. The iSage Rx patient app is a stand-alone, prescription-use only (Rx-only) software device for use under the direction of a healthcare provider, that has the capability to titrate basal insulin and medications that combine basal insulin and GLP-1 receptor agonists, via rule-based protocols as part of a Titration Plan ordered by a Health Care Provider (HCP). It is intended for use in type 2 diabetes in a nonacute care setting.
The primary purpose of the iSage Rx device is to help the patient safely reach their fasting blood glucose targets and reach a maintenance dose of insulin through regular monitoring of blood glucose levels and titration of insulin doses.
This document is a 510(k) summary for the iSage Rx Platform. It details the device's intended use, comparison to a predicate device, and performance data to demonstrate substantial equivalence.
Here's a breakdown of the requested information based on the provided text:
1. A table of acceptance criteria and the reported device performance
The document does not explicitly present a table of acceptance criteria with corresponding performance metrics in a pass/fail format. Instead, it relies on the concept of "substantial equivalence" to a predicate device (iSage Rx, K161865). The performance data section describes "Software Verification and Validation Testing" that was conducted to demonstrate the device performs as intended and meets identified requirements.
However, based on the document's content, we can infer some implicit acceptance criteria:
| Acceptance Criteria (Inferred) | Reported Device Performance |
|---|---|
| Functional Equivalence to Predicate Device | The iSage Rx Platform's "purpose, design, function, and intended use... is identical to the predicate device." The "iSage Rx Platform contains all functionality of iSage Rx and Dose Check products." "iSage Rx includes all available feature configurations, whereas Dose Check contains only those features configured for a specific geography." Software verification and validation testing were conducted, and documentation was provided, to demonstrate the effectiveness of design control mitigations for identified risks. The "Traceability Matrix for iSage Rx Platform displays a matrix of all requirements by type and ID along with the related individual verification and validation test cases demonstrating that the requirement has been satisfied." The device "will perform as intended under specified use conditions." |
| Safety and Effectiveness Equivalence to Predicate Device | "Having no significant differences from the predicate device, it is therefore concluded that the iSage Platform has a similar safety and effectiveness profile and is substantially equivalent." "The non-clinical data affirms the device's safety." |
| Accuracy of Dose Calculation | The device is a "Predictive Pulmonary-Function Value Calculator" (Regulation Name) and "Calculator, Drug Dose" (Device Classification Name). The "Device Description" states its primary purpose is "to help the patient safely reach their fasting blood glucose targets and reach a maintenance dose of insulin through regular monitoring of blood glucose levels and titration of insulin doses." The system "calculates a fasting blood glucose average and generates an insulin dose according to the prescribed titration plan." The performance data section mentions "nonclinical datasets in the form of testing protocols and reports" that summarize "verification and validation of the key design requirements associated with safety and performance." This implicitly covers the accuracy of dose calculations as a critical safety and performance aspect, although specific metrics (e.g., calculation deviation) are not provided. |
| Interoperability with Supported Glucose Meters | "The iSage Rx Platform is interoperable with supported glucose meters noted in table 3 below. This interoperability is substantially equivalent to that of the predicate device in terms of the functionality enabling Bluetooth connections between the glucose meter and the device (K161865)." The document lists specific supported models (e.g., CONTOUR® NEXT ONE, Accu-Chek® Guide). "Integration with the following devices is supported by the iSage Rx device." |
| Compliance with Regulatory Standards | "All product development activities for the iSage Rx Platform were conducted in compliance with EN ISO 13458:2016 under the quality management system that has been certified by Intertek Medical Notified Body AB (Certificate Number:0139273)." "Software verification and validation testing were conducted, and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, 'Content of Premarket Submissions for Device Software Functions.'" |
| Cybersecurity | "Cybersecurity Information" is listed as a labelling information item, implying that this was addressed as part of the overall evaluation. |
| User Interface and Experience | The "Device Description" mentions that the "iSage Rx patient app is a stand-alone, prescription-use only (Rx-only) software device for use under the direction of a healthcare provider, that has the capability to titrate basal insulin and medications that combine basal insulin and GLP-1 receptor agonists, via rule-based protocols..." "The iSage Rx Platform contains all functionality of iSage Rx and Dose Check products. iSage Rx/Dose Check is localized to the USA and contains a set of features, configured specifically for this particular geography based on market configurations." The patient app "prompts the patient every day to record their fasting blood glucose measurements and daily insulin doses." "If enough blood glucose information has not been recorded by the patient, the dose is not changed, and the patient is informed why the dose hasn't changed and is reminded to record their fasting blood glucose values." This indicates user flow and messaging were tested and met expectations. Dose Check is noted to have "identical in function, with the difference in the user interface only." |
2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)
The document refers to "Software Verification and Validation Testing" and "nonclinical datasets in the form of testing protocols and reports." However, it does not specify the sample size of the test set, nor does it specify the data provenance (country of origin, retrospective or prospective). It mentions that "All product development activities for the iSage Rx Platform were conducted in compliance with EN ISO 13458:2016," but this refers to the quality management system, not the specifics of the data used for testing. The product is localized to the USA for specific configurations.
3. 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)
The document does not provide information on the number or qualifications of experts used to establish ground truth for the test set. It mentions the "Healthcare Provider (HCP) portal" and HCPs configuring titration plans, implying medical expertise is involved in the overall system, but not specifically for the ground truth of the validation testing.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The document does not specify any adjudication method for the test set.
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
This document describes a software device that provides a titration plan for patients with type 2 diabetes. It is a standalone software device intended for patient and HCP use to manage medication dosage, not an AI-assisted diagnostic tool for human readers interpreting medical images. Therefore, an MRMC comparative effectiveness study involving human readers improving with AI assistance would not be applicable in this context. The document focuses on the software's functional accuracy and safety in calculating and presenting drug doses.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, a form of standalone performance evaluation was implicitly done for the algorithm. The "Software Verification and Validation Testing" and "nonclinical datasets" would involve testing the algorithm's output against expected results based on predefined rules for titration plans. The device's function is to "calculate a fasting blood glucose average and generates an insulin dose according to the prescribed titration plan." This is an algorithmic function that would be tested independently of patient or HCP interaction to confirm its computational accuracy.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
The document strongly implies that the "ground truth" for the device's dose calculation and titration logic is established based on "evidence-based preset clinical titration plans" and "evidence-based protocols from treat-to-target studies or other patient-led titration studies." HCPs can also create their own plans or customize these, further indicating that the ground truth is derived from established medical guidelines and clinical evidence for diabetes treatment. While not explicitly stated as "expert consensus" for the test set itself, the underlying principle is rooted in validated clinical practice.
8. The sample size for the training set
The document describes software that applies rule-based protocols for dose titration. It does not mention a training set or machine learning components that would require a "training set sample size" in the context of predictive algorithms that learn from data. The device operates on "rule-based protocols."
9. How the ground truth for the training set was established
As the device operates on "rule-based protocols" and does not appear to use machine learning from a training set, the concept of establishing ground truth for a training set is not applicable here. The "ground truth" for the rules themselves would be derived from clinical guidelines and evidence as mentioned in point 7.
§ 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).