Search Results

The T1D1 mobile application is indicated for the management of diabetes by people with Type 1 diabetes age 2 and older by calculating insulin doses based on user-entered data.

Prior to use, a healthcare professional must provide the patient target blood glucose values, insulin-to-carbohydrate ratios, and the correction factor (also known as the insulin sensitivity factor) to be programmed into the App software.

The T1D1 application is a user-friendly mobile application designed for Android and Apple devices, specifically catering to individuals aged 2 and above who have Type 1 Diabetes Mellitus (T1DM) and undergo multiple daily injection (MDI) therapy. Its primary objective is to simplify insulin dosing management by providing essential features such as a bolus calculator, a convenient logbook, and various configurable user-specific settings. The T1D1 application is intended to be distributed free of charge and without advertisements while operating independently of any other diabetes care devices. The overarching aim of the app is to streamline the daily calculations required by individuals with T1DM, alleviating the time-consuming and error-prone task of manually calculating and keeping track of insulin dosing.

The key feature of the T1D1 application is the bolus calculator. This calculator implements the standard insulin bolus calculation, taking into account factors such as the user's current blood glucose levels, carbohydrate intake, and target blood glucose levels. By considering these variables, the app provides users with an insulin dose recommendation, which assists in maintaining stable blood sugar levels.

The logbook feature allows users to record, track, and share their diabetes-related information. This information includes blood glucose levels, insulin doses, carbohydrate intake, and other relevant information. The ability to log and share this information with healthcare professionals or family members allows for improved communication and collaboration between individuals with T1DM and their support network.

The T1D1 application offers several presets to simplify the insulin dosing process. These presets can be customized based on individual preferences and needs. By providing preset options, the app eliminates the need for manual input of commonly used settings, saving time and reducing the likelihood of errors. In summary, the T1D1 application is a user-friendly mobile application that assists individuals with T1DM in managing their everyday insulin dosing from day one of their diagnosis.

The provided FDA 510(k) clearance letter for the T1D1 device, while detailing the general process and regulatory compliance, does not contain the specific performance data for the device that would allow for the construction of the requested table of acceptance criteria and reported device performance. The "Performance Data" section on page 10 only lists the standards and guidances followed for risk analysis, software V&V, cybersecurity, and human factors, but does not present any quantitative results from these studies.

Therefore, I cannot fulfill your request for:

• A table of acceptance criteria and the reported device performance
• Sample size used for the test set and data provenance
• Number of experts and their qualifications
• Adjudication method
• MRMC comparative effectiveness study details
• Standalone (algorithm-only) performance details
• Type of ground truth used
• Sample size for the training set
• How ground truth for training set was established

To answer these questions, you would need access to the full 510(k) submission, which includes the detailed performance data, verification and validation reports, and clinical study summaries. The clearance letter only confirms that such data was reviewed and deemed acceptable by the FDA for the purpose of granting clearance.

Ask a specific question about this device

The MiniMed 780G insulin pump is intended for the subcutaneous delivery of insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin.

The MiniMed 780G insulin pump is able to reliably and securely communicate with compatible, digitally connected devices, including automated insulin dosing software, to receive, execute, and confirm commands from these devices.

The MiniMed 780G insulin pump contains a bolus calculator that calculates an insulin dose based on user-entered data.

The MiniMed 780G insulin pump is indicated for use in individuals 7 years of age and older.

The MiniMed 780G insulin pump is intended for single patient use and requires a prescription.

The MiniMed 780G insulin pump is an alternate controller enabled (ACE) pump intended for the subcutaneous delivery of insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin. It can reliably and securely communicate with compatible digitally connected devices, including an integrated continuous glucose monitor (iCGM), interoperable Medtronic continuous glucose monitor (CGM), and interoperable automated glycemic controller (iAGC). The pump is intended to be used both alone and in conjunction with compatible, digitally connected medical devices for the purpose of drug delivery.

The MiniMed 780G insulin pump is an ambulatory, battery-operated, rate-programmable micro-infusion pump that contains pump software and houses electronics, a pumping mechanism, a user interface, and a medication reservoir within the same physical device. The pump also contains a bolus calculator that calculates an insulin dose based on user-entered data. It is comprised of several discrete external and internal components including a pump case made of a polycarbonate blend, an electronic printed circuit board assembly stacks and a drive motor system.

The MiniMed 780G insulin pump is an interoperable device that can communicate via a Bluetooth Low Energy (BLE) wireless electronic interface with digitally connected devices. The MiniMed 780G insulin pump is a host device for the iAGC and integrates iAGC algorithm into the pump firmware. The pump is then able to receive, execute, and confirm commands from an iAGC to adjust delivery of insulin. The pump receives sensor glucose (SG) data via BLE interface from a compatible iCGM or a compatible interoperable Medtronic CGM and transmits these CGM data to the embedded iAGCs.

The MiniMed 780G insulin pump can operate in one of two modes: Manual Mode or Auto Mode (also referred to as "SmartGuard Mode"). The pump provides the user with keypad pump controls, as well as a data screen for configuring therapy settings and viewing continuous real-time glucose values, glucose trends, alerts, alarms, and other information. The user interface and alerts provide the user with the ability to interact with the pump delivery system and digitally connected devices.

The provided text is a 510(k) clearance letter and summary for a medical device, specifically an insulin pump. It details the device's characteristics, intended use, comparison to predicate devices, and a summary of non-clinical performance data.

However, it does not contain the information requested regarding acceptance criteria and a study proving a device meets these criteria in the context of an AI/Machine Learning device for image analysis or diagnostics.

The request asks for details like:

• A table of acceptance criteria and reported device performance (which is present in a limited form for the pump's mechanical performance, but not for AI performance).
• Sample size for the test set and data provenance.
• Number of experts and their qualifications for ground truth.
• Adjudication method for the test set.
• MRMC study details and effect size.
• Standalone performance.
• Type of ground truth used.
• Sample size for the training set.
• How ground truth for the training set was established.

These specific points are highly relevant to the validation of AI/ML-enabled medical devices, particularly those that interpret or analyze data (like images) to aid in diagnosis or treatment decisions. The MiniMed 780G insulin pump, while having advanced software and interoperability, is primarily an infusion pump with a bolus calculator, not an AI/ML diagnostic or image analysis tool. Its software functions relate to pump control, communication, and basic dose calculation, not complex pattern recognition or inference typically associated with AI in medical devices that would require the detailed validation described in the prompt.

Therefore, I cannot extract the requested information from the provided text because the text describes a different type of medical device and its associated validation. The validation methods mentioned (Delivery Volume Accuracy, Occlusion Detection, Drug Stability, Cybersecurity, Human Factors) are appropriate for an insulin pump but do not align with the AI/ML-specific validation criteria outlined in your prompt.

Ask a specific question about this device

EndoTool IV 3.1 is a glucose management software system used by healthcare professionals in all inpatient care settings for adult and pediatric patients aged two years and above who weigh 12 kgs. or more. EndoTool adjusts and maintains a patient's glucose level within a configurable clinician-determined target range by recommending patient-specific intravenous insulin dosing, carbohydrate dosing for recovery or supplementation, and subcutaneous dosing for the transition from IV dosing.

EndoTool IV 3.1 logic is not a substitute for but rather an adjunct to clinical reasoning. No medical decision should be based solely on the recommended guidance provided by this software system.

EndoTool IV 3.1 is a software system for glucose management which uses the current and cumulative qlucose values provided by the user to calculate and recommend intravenous insulin or carbohydrate doses, to adjust and maintain the patient's glucose level within a provider-ordered target range. In addition, the application can recommend a subcutaneous Basal transition insulin dose when IV insulin therapy is no longer required.

The provided text is a 510(k) summary from the FDA, detailing the premarket notification for the "EndoTool IV 3.1" device. While it outlines the device's purpose, comparison to a predicate device, and general statements about software verification and validation, it does not contain the specific information required to answer your questions regarding acceptance criteria and a study proving the device meets those criteria.

The document states:

• "Software verification and validation testing was conducted per IEC 62304."
• "Clinical testing was not required to demonstrate the safety and effectiveness of the EndoTool IV 3.1. Instead, substantial equivalence is based upon benchtop performance testing."

This indicates that the validation was primarily software-focused and benchtop (likely simulated data or internal testing against predefined rules) rather than clinical. It does not provide:

• A table of acceptance criteria and reported device performance.
• Sample sizes for a test set, its provenance, or whether it was retrospective/prospective.
• Information on experts used for ground truth, their qualifications, or adjudication methods.
• Details of a Multi-Reader Multi-Case (MRMC) study or its effect size.
• Results from a standalone algorithm performance study.
• The type of ground truth used (e.g., expert consensus, pathology, outcomes data).
• Sample size for the training set or how its ground truth was established.

Therefore, based solely on the provided document, I cannot fulfill your request as the essential information about specific performance data, test methodologies, and ground truth establishment is not present. The document focuses on demonstrating substantial equivalence to a predicate device based on similar indications for use, technological characteristics, and conformance to a general software standard (IEC 62304).

Ask a specific question about this device

The InPen System is a home-use reusable pen for single-patient use by people with diabetes under the supervision of an adult caregiver, or by a patient aged 7 and older for the self-injection of a desired dose of insulin. The pen injector is compatible with Lilly Humalog® U-100 3.0 mL cartridges, Novo Nordisk Novolog® U-100 3.0 mL cartridges, and Novo Nordisk Fiasp® U-100 3.0 mL cartridges and single-use detachable and disposable pen needles (not included). The pen Smart Insulin pen allows the user to dial the desired dose from 0.5 to 30 units in one-half (1/2) unit increments.

The InPen dose calculator, a component of the InPen app, is indicated for the management of diabetes by people with diabetes under the supervision of an adult caregiver, or by a patient aged 7 and older for calculating an insulin dose or carbohydrate intake based on user entered data.

For an insulin dose based on amount of carbohydrates, a healthcare provide patient-specific target blood glucose, insulin-to-carbohydrate ratio, and insulin sensitivity parameters to be programmed into the software prior to use.

For an insulin dose based on fixed/variable meal sizes, a healthcare provide patient-specific fixed doses/ meal sizes to be programmed into the software prior to use.

The InPen App is a software application with versions that are compatible with mobile phones running the iOS or Android operating system. The App is a component of the InPen system and is used with the InPen Smart Insulin pen for the management of insulin-requiring diabetes. The InPen App communicates with the InPen Smart Insulin pen to communicate doses that are delivered by the user. The InPen App is also compatible for use with blood glucose (BG) meters, Medtronic Continuous Glucose Monitors (CGMs), and the Dexcom CGMs. The InPen App includes a dose calculator that can calculate and recommend a dose for the user to review and consider as part of following the treatment plan prescribed by the healthcare provider. The dose calculator features in the App require that a healthcare professional provide patient-specific values for various therapy settings for programming into the App prior to use by the patient. These therapy settings include glucose target(s), duration of insulin action time, insulin sensitivity factor(s), and insulin-to-carbohydrate ratio(s) or fixed insulin doses for meal types and sizes. The dose calculator feature is unavailable to the user until these patient-specific values, provided by the healthcare professional, are programmed and an InPen has been paired to the App. A healthcare provider may also provide long-acting insulin settings to be programmed into the InPen App. The App includes a logbook feature that displays the patient's recent activity related to BG values, meal types and sizes, dose calculations, doses by insulin type (rapid- or long-acting), cartridge replacement and priming. The App also provides reminders and alerts that can notify the user to check their glucose, dose insulin (for potential missed meals, correction doses, and longacting insulin doses) and log doses according to schedule, replace a cartridge, or if the insulin pen has been exposed to very low or very high temperatures. The App can generate a supplemental summary report of recent therapy information for review by the patient or healthcare professional (HCP).

The InPen Cloud includes a therapy report component that the user and the health care provider (HCP) can view and print to assess the overall diabetes control and treatment plan. The report displays data based upon user and HCP-defined inputs, such as glucose, insulin and carb trended information, during the defined period, as well as dose calculator usage and alerts and reminders. The Insulin Notification Service (INS) is a subcomponent of the InPen Cloud that can receive Medtronic CGM sensor glucose measurements from the CareLink Cloud. The INS includes two algorithms that assess "real time" sensor glucose measurements to identify whether a user has missed a dose or if their glucose is rising and a correction dose is needed. If either of these conditions exist, a silent notification is sent by the INS to the InPen App. The InPen App confirms the data and can provide and visual alert to the user. The user can act on the alert by assessing their glucose levels followed by calculating a dose utilizing the InPen App dose calculator.

The provided text is a 510(k) summary for the Medtronic MiniMed InPen System. It describes the device, its indications for use, and a comparison to a predicate device to establish substantial equivalence. However, the document does not contain the specific details about acceptance criteria, the study design (including sample size, data provenance, expert ground truth establishment, or adjudication methods), or performance data in the way requested in the prompt.

The "Performance Data" section (Page 10) broadly states that "Software verification and validation testing was performed in accordance with the FDA's Guidance..." and mentions "unit level testing, integration level testing, and systems testing." It also notes "Cybersecurity Testing" and "risk management activities." Finally, it mentions an "additional assessment of the changes to the InPen Cloud occurred through a summative usability evaluation" where "patients...used the InPen Cloud to perform a series of critical tasks involving the use of the InPen App and Cloud, including the additional alerts and reminder."

Therefore, it is not possible to fill in most of the requested information based on the provided text. The document focuses on regulatory arguments for substantial equivalence rather than detailed clinical or technical study results that would typically include such specifics.

Here's a breakdown of what can be extracted and what cannot:

Information that CANNOT be extracted from the provided text:

1. A table of acceptance criteria and the reported device performance: This detail is not present. The document focuses on showing the device is substantially equivalent to a predicate, not on specific performance metrics against pre-defined acceptance criteria.
2. Sample sizes used for the test set and the data provenance: No specific sample sizes for particular tests (e.g., test sets for algorithms) are mentioned, nor is the data provenance (country, retrospective/prospective). The "summative usability evaluation" is mentioned, but without sample size or details about the data used.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not mentioned.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not mentioned.
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 mentioned. This type of study is more common for diagnostic imaging AI, whereas this device is an insulin management system with a dose calculator.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: While the InPen App has an algorithm for dose calculation and the InPen Cloud has algorithms for notifications, the document doesn't provide performance data for these algorithms in isolation. The "summative usability evaluation" implies human-in-the-loop testing.
7. The type of ground truth used (expert concensus, pathology, outcomes data, etc): Not explicitly stated how the accuracy of the dose calculations or alert effectiveness was verified as "ground truth." The "summative usability evaluation" likely involved checking if users performed tasks correctly, but the underlying ground truth for algorithm accuracy isn't detailed.
8. The sample size for the training set: Not mentioned.
9. How the ground truth for the training set was established: Not mentioned.

Information that CAN be extracted or inferred from the provided text:

• Device Type: Insulin management system (reusable pen, app with dose calculator).
• Regulatory Class: Class II (Product Code: NDC).
• Software Level of Concern: Major.
• Key Software Features: Dose calculator (insulin dose based on carbohydrates or fixed/variable meal sizes), logging, reminders, alerts (missed dose, high glucose).
• New Features (compared to predicate):
  • Two new algorithms in the InPen Cloud (Insulin Notification Service) to identify and send "silent notifications" to the InPen App for missed insulin doses or rising glucose.
  • Two new visual and audible alerts in the InPen App for missed insulin doses or high glucose, for users with a Medtronic CGM.
  • Improved existing Long-Acting Reminder to include both audible and visual alerts.
• Performance Data (General Statement): "Software verification and validation testing was performed in accordance with the FDA's Guidance for Industry and FDA Staff, "Content of Premarket Submissions for Device Software Functions'', and FDA's guidance "General Principles of Software Validation". Verification and validation activities included software testing consisting of unit level testing, integration level testing, and systems testing of the InPen App and InPen Cloud. Cybersecurity Testing was performed... Risk management activities... were undertaken... Additional assessment of the changes to the InPen Cloud occurred through a summative usability evaluation."

In summary, the provided document is a regulatory submission focused on substantial equivalence, not a detailed technical report of study results with specific performance metrics and study methodologies.

Ask a specific question about this device

Ascent Cardiorespiratory Diagnostic Software is intended to be used for measurements, data collection and analysis of lung function (PFT) parameters, and cardiopulmonary testing (CPET) parameters, aiding in the diagnosis of related conditions.

All the measurements are performed via a mouthpiece or a mask.

The results of the test can be viewed on-line with the help of a computer screen and can be printed after the test. The test results can be saved for further referral or report generation purposes.

For use of the Bronchial Challenge option, the medical director of the laboratory, physician, or person appropriately trained to treat acute bronchoconstriction, including appropriate use of resuscitation equipment, must be close enough to respond quickly to an emergency.

The product can be utilized for patients from 4 years old and older as long as they can cooperate in the performance -- no special limit to patient's sex or height.

Measurements will be performed under the direction of a physician in a hospital environment, physician's office or similar settings.

Ascent™ Cardiorespiratory Diagnostic Software ("Ascent") is a stand-alone software application which can be used with several hardware devices in the Medical Graphics Corporation product line.

The core purpose of the software for measurement, data collection and analysis of testing in patients who may be suffering from pulmonary illnesses like chronic obstructive pulmonary disease (COPD), asthma, exercise intolerance, heart failure and/or cardiorespiratory concerns where diagnosis and prognosis needs to be determined.

In conjunction with diagnostic hardware, Ascent is used to collect data pertaining to the patient's degree of obstruction, lung volumes, and diffusing capacity. It is also used to present the collected lung diagnostic information so that it can be checked for quality and interpreted by a qualified physician, often a pulmonologist or cardiologist.

All the measurements are performed via a mouthpiece or a face mask.

The provided text is a 510(k) summary from the FDA, which outlines the substantial equivalence determination for a medical device. This type of document focuses on comparing a new device to existing legally marketed predicate devices rather than providing detailed acceptance criteria and the results of a specific clinical study with granular performance metrics. As such, the document does not contain the specific information needed to fulfill all aspects of your request, particularly regarding detailed performance metrics, sample sizes for test sets (beyond general validation statements), expert qualifications, ground truth establishment methods for test sets, MRMC studies, or training set details.

However, I can extract the information that is present and highlight what is missing based on your request.

Missing Information:

• Detailed Acceptance Criteria Table with Specific Performance Metrics: The document states that the software was "extensively validated per medical device software standards and guidance" and that "Testing results support that Ascent fulfills its intended use/indications for use." It also mentions "Performance tests included FEV1, MVV, FRC, SVC, DLCO, VA, TGV, VO2, VCO2, and VE." However, it does not provide specific quantitative acceptance criteria (e.g., "FEV1 must be within X% of ground truth") or the reported performance for these metrics.
• Sample Size for Test Set and Data Provenance: The document does not specify the sample size for the test data used for performance validation, nor does it detail the provenance (country, retrospective/prospective) of this data.
• Number of Experts and Qualifications for Ground Truth: The document does not describe how ground truth for the test set was established, including the number or specific qualifications of experts involved.
• Adjudication Method for Test Set: No information is provided regarding adjudication methods (e.g., 2+1, 3+1).
• Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study: The document does not indicate that an MRMC study was performed or provide any effect size for human reader improvement with AI assistance.
• Standalone Performance (Algorithm Only): While the document states "Ascent Cardiorespiratory Diagnostic Software is a stand-alone software application," it describes validation as "Performance validation testing was done with the subject software device and recommended hardware devices working together." It does not provide specific performance metrics for the algorithm only without human interaction in a diagnostic capacity beyond its intended function of measuring, collecting, and analyzing parameters. The software aids diagnosis, implying human interpretation.
• Type of Ground Truth Used (for Test Set): The document implicitly refers to "performance tests" for various physiological parameters (FEV1, DLCO, etc.), suggesting comparison to a reference standard for these measurements. However, it does not explicitly state the nature of this "ground truth" (e.g., expert consensus, pathology, outcome data) beyond reference to ATS/ERS guidelines for standardization.
• Sample Size for Training Set: No information on training data or its size is provided. This is typical for a 510(k) for software that calculates and analyzes data from hardware, rather than an AI/ML model that learns from large datasets.
• How Ground Truth for Training Set was Established: Not applicable as training data details are not provided.

Information that can be extracted from the document:

The provided document is a 510(k) summary for the "Ascent Cardiorespiratory Diagnostic Software" (K242809). It details the device's substantial equivalence to predicate devices, focusing on its intended use, technological characteristics, and conformity to relevant standards and guidelines.

1. A table of acceptance criteria and the reported device performance:

As noted above, specific quantitative acceptance criteria and reported performance metrics are NOT provided in this document. The document generally states that "Ascent Cardiorespiratory Diagnostic Software was extensively validated per medical device software standards and guidance. Testing results support that Ascent fulfills its intended use/indications for use..."

It mentions that "Performance tests included FEV1, MVV, FRC, SVC, DLCO, VA, TGV, VO2, VCO2, and VE." However, no numerical results or thresholds are given. The validation was done referencing the following guidelines/standards for "acceptability and repeatability":

• ATS/ ERS Standardisation of Spirometry (2019)
• ERS/ ATS Standardisation of the Measurements of Lung Volumes (2023)
• 2017 ERS/ ATS Standards for Single-Breath Carbon Monoxide Uptake in the Lung
• ERS Technical Standard on Bronchial Challenge Testing (2017)
• 2017 ATS Guidelines for a Standardized PF Report
• ATS/ ACCP Statement on Cardiopulmonary Exercise Testing (2003)

Summary of available information for a table format (conceptual, as specific numerical data is missing):

2. Sample sized used for the test set and the data provenance:

• Sample Size: Not specified. The document only states "Software validation testing involved system level tests, performance tests and safety testing based on hazard analysis. Performance validation testing was done with the subject software device and recommended hardware devices working together."
• Data Provenance: Not specified (e.g., country of origin, retrospective or prospective).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• This information is not provided in the document.

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

• This information is not provided in the document.

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 MRMC study is mentioned or implied. The software is described as
  "aiding in the diagnosis of related conditions" and presenting "diagnostic information so that it can be checked for quality and interpreted by a qualified physician." This device is a "Predictive Pulmonary-Function Value Calculator" and performs measurements and analysis, but it is not described as an AI system assisting human readers in image interpretation or diagnosis in a comparative effectiveness study context.

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

• The device is indeed described as a "stand-alone software application." However, the performance validation was done "with the subject software device and recommended hardware devices working together." Its output (measurements and analysis) is intended to be "displayed to the user" and "interpreted by a qualified physician."
• The document does not provide performance metrics for the algorithm only in a way that suggests a diagnostic output without human interpretation or hardware interaction. It's a software that processes data from hardware to provide measurements and analysis, not, for example, a diagnostic image analysis AI.

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

• The document implies that the ground truth for the performance tests (FEV1, DLCO, etc.) would be established by the standardized measurement techniques defined by governing bodies like ATS/ERS/ACCP. These typically involve comparing the device's calculated values against accepted reference methods for deriving those physiological parameters, often involving highly calibrated equipment and expert technicians following strict protocols. However, the exact nature of this "ground truth" (e.g., what gold standard was used for comparison) is not explicitly detailed beyond referencing the standards themselves.

8. The sample size for the training set:

• This information is not provided in the document. This type of device (a calculator/analyzer) is typically engineered based on established physiological formulas and algorithms, rather than being "trained" on large datasets in the way a deep learning AI model would be.

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

• Not applicable, as training set details are not provided and the device functions as a calculator based on established science, not a machine learning model that learns from a labeled training set.

Ask a specific question about this device

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:

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.

Ask a specific question about this device

The SpiroSphere is a compact device inspiratory and expiratory lung function parameters in adults and children aged 4 years and older. It can be used by physicians in the office or hospital.

With the option ECG, electrocardio measurements can be made under resting conditions. For this purpose a 12channel surface electrocardiogram can be measured and recorded. The acquired ECG can be displayed on the screen or printed on paper. The interpretation software is intended to support the physician in evaluation of the resting ECG in terms of morphology and rhythm. Automatic interpretation of the ECG is not possible for pediatric subjects with an age below 16 years and for pacemaker subjects. It is not intended for intra-cardial use.

A qualified physician has to reassess all ECG measurements. An interpretation by SpiroSphere ECG is only significant if it is considered in connection with other clinical findings. ECG interpretation statements made by the SpiroSphere ECG represent partial qualitative and quantitative information on the patient's cardiovascular condition and no therapy or drugs can be administered based solely on the interpretation statements. The SpiroSphere ECG is not intended for use in an EMS environment (Emergency Medical Services Environment).

The minimum age for ECG application is 4 years.

It can be used by physicians in the office or hospital.

With the CardioSphere, electrocardio measurements can be made under resting conditions. For this purpose a 12channel surface electrocardiogram can be measured and recorded. The acquired ECG can be displayed on the screen or printed on paper. The interpretation software is intended to support the physician in evaluation of the resting ECG in terms of morphology and rhythm. Automatic interpretation of the ECG is not possible for pediatric subjects with an age below 16 years and for pacemaker subjects. It is not intended for intra-cardial use.

A qualified physician has to reasurements. An interpretation by CardioSphere is only significant if it is considered in connection with other clinical findings. ECG interpretation statements made by the CardioSphere represent partial qualitative and quantitative information on the patient's cardition and no therapy or drugs can be administered based solely on the interpretation statements. The CardioSphere is not intended for use in an EMS environment (Emergency Medical Services Environment).

The minimum age for ECG application is 4 years.

It can be used by physicians in the office or hospital.

SpiroSphere is a compact spirometry device. Its Sensor Unit is batterypowered. The Main Unit can be powered by battery or power supply. The SpiroSphere / SpiroSphere ECG is used to measure inspiratory and expiratory lung function parameters in adults and children 4 years and older. The measured data is saved to the device and can be read out at any time.

SpiroSphere ECG is a compact spirometry device. Its Sensor Unit is battery-powered. The Main Unit can be powered by battery or power supply. The SpiroSphere / SpiroSphere ECG is used to measure inspiratory and expiratory lung function parameters in adults and children 4 years and older. The measured data is saved to the device and can be read out at any time.

With the ECG option (subject of this 510(k)), 12-channel surface electrocardiogram can be measured and recorded.

The Main Unit can be powered by battery or power supply. The Main Unit is wirelessly connected to an ECG amplifier via Bluetooth.

With the ECG option (subject of this 510(k)), 12-channel surface electrocardiogram can be measured and recorded.

A printer can be connected and data (e.g. reports, screenshots) can be printed. Moreover, it is possible to transfer data by USB. Wifi. 3G. and Ethernet connections.

Pulmonary function assessments

• Slow Spirometry .
• Forced Spirometry .
• Flow-Volume loop and Volume-Time tracing, pre/post tests ●
• Trending capabilities ●

Cardiovascular assessments

• 12 Lead Electrocardiogram ●

The provided text does not contain information about acceptance criteria and the study that proves the device meets the acceptance criteria. The document is a 510(k) premarket notification letter from the FDA, along with a device description and comparison tables to predicate devices. It discusses general information about the device, its intended use, technological characteristics, and a summary of device testing (e.g., software verification, risk analysis, electrical safety, EMC, human factors, cybersecurity, reprocessing validation). However, it does not specify quantitative acceptance criteria for performance metrics (such as sensitivity, specificity, accuracy) for its interpretation software, nor does it detail a specific study proving these criteria were met.

Therefore, I cannot provide the requested information based on the given text.

Ask a specific question about this device

The Pulmonary Function Tester (Model: A9) is intended to be used for measurement and data collection of lung function parameters. The system performs cooperation-dependent flow-volume measurements shall be performed under the direction of a physician in the clinic, doctors' office or hospital. The Pulmonary Function Tester (Model: A9) is intended for use in patients from 4 years of age and older who can understand and perform instructions of the physician.

The Pulmonary Function Tester (Model: A9) is a hand-held pulmonary function testing device which can be used by patients older than 4 years old under the direction of a physician in the clinic, doctors' office or hospital. The Pulmonary Function Tester (Model: A9) is comprised of the main unit (display screen, sensor and communication module), USB cable, application software (computer software, mobile software), and a power supply. The device use is very simple, it adopts mouth blowing method. The device uses a flow sensor to measure the air flow and volume of the patient's exhaled or inhaled air. According to the volume-time curve and the flow-volume curve, the pulmonary ventilation indicators of human respiratory physiology, such as slow vital capacity, maximum minute ventilation and forced vital capacity, are estimated and reported on the LCD screen and computer/mobile software. The pulmonary Function Tester is powered by lithium battery (DC 3.7V, 1500mAh) or tablet/computer USB port, or the equipped power supply.

The provided text is a 510(k) Summary for a Pulmonary Function Tester. It describes the device, its intended use, and its substantial equivalence to a predicate device. However, it does not contain the detailed acceptance criteria for specific performance metrics nor the results of a specific clinical study used to prove the device meets those criteria.

Instead, the document states that "Non-clinical tests were conducted to verify that the Pulmonary Function Tester (Model: A9) meets all design specifications which supports the conclusion that it's Substantially Equivalent (SE) to the predicate device." It then lists the standards the device complies with. While these standards define acceptable performance ranges and test methods, the actual acceptance criteria and the device's reported performance against these criteria for each specific lung function parameter are not explicitly detailed in a table or narrative form in the provided text.

Therefore, I cannot populate the requested table and answer questions 2-9 with specific information from the provided document, as that level of detail is not present. The document focuses on demonstrating compliance with recognized standards rather than presenting a detailed study report of the device's performance against specific, pre-defined acceptance criteria.

Key Missing Information for Your Request:

• Specific Acceptance Criteria: While compliance with standards like ISO 26782 and ISO 23747 implies certain performance expectations, the document does not list explicit numerical acceptance criteria for parameters like FVC accuracy, FEV1 accuracy, PEF accuracy, etc., for the subject device itself.
• Reported Device Performance: Relatedly, the document does not provide a table or narrative of the subject device's measured performance (e.g., "FVC accuracy achieved X%") against these (unspecified) acceptance criteria.
• Detailed Study Design: There is no description of a clinical or non-clinical study with details about sample size, ground truth establishment, expert involvement, or adjudication methods. The "non-clinical tests" are mentioned as being conducted to verify design specifications and compliance with standards, but the specifics of these tests are not provided beyond the standards themselves.

Based on the provided text, here is what can and cannot be stated:

1. A table of acceptance criteria and the reported device performance

Cannot be fully provided as the specific acceptance criteria and reported device performance (e.g., FVC accuracy = X%, PEF accuracy = Y%) are not explicitly stated in a table or narrative form in the provided text.

The document references standards that contain performance requirements. For example, under "Flow (PEF) Accuracy" it states for the subject device: "

Ask a specific question about this device

The Insulia Bolus Companion is indicated for the management of diabetes by adults with diabetes, by calculating an insulin dose or suggesting carbohydrate intake based on user entered data.

Prior to use, a healthcare professional must provide a patient-specific target blood glucose, insulin doses based on fixed or variable meal sizes, and insulin sensitivity parameters to be programmed into the software. This can be done through a dedicated, secured web portal.

Insulia Bolus Companion is a prescription device indicated for the management of diabetes, for adults with diabetes, by calculating an insulin dose or suggesting carbohydrate intake based on user entered data; and for healthcare professionals (HCP) having experience in the management of people with diabetes treated with bolus insulin.

Insulia Bolus Companion is for prescription use and is not for over-the-counter sale.

Insulia Bolus Companion includes a Bolus Calculator intended to provide direction to the patient in response to blood glucose (BG) and health events, within the scope of a preplanned treatment program prescribed by their HCP for insulin suggestions. The guidance is similar to the directions provided to patients as a part of routine clinical practice: prior to use, a healthcare professional must provide a patient-specific target blood glucose, insulin doses based on fixed or variable meal sizes, and insulin sensitivity parameters to be programmed into the software.

An HCP can only start using Insulia Bolus Companion after having been registered by the Manufacturer or the delegate field-support team.

Insulia Bolus Companion includes three components:

• · A mobile application for use by people with diabetes on commercially available smartphones (iPhone or Android) and tablets, enabling patients to document BG measurements, meals, and generate dose suggestions for bolus insulin
• · A web-based application for use by HCPs in professional healthcare settings through a compatible web browser on a computer, allowing patient inclusion and patient monitoring in-person and by distance
• · A secure database hosted in a private cloud environment and used to securely store patient data

The provided text does not contain detailed information about the acceptance criteria and the study that proves the device meets those criteria, specifically regarding numerical performance metrics, sample sizes for test and training sets, expert qualifications, or adjudication methods.

The document states that "Design verification and validation testing on Insulia Bolus Companion demonstrated that the device meets the performance requirements for its intended use" and "performance testing has demonstrated that Insulia Bolus Companion performs as intended and is substantially equivalent to the predicate device." However, it does not provide the specifics of this performance testing.

Therefore, I cannot provide a detailed answer to your request that includes:

1. A table of acceptance criteria and reported device performance.
2. Sample size and data provenance for the test set.
3. Number of experts and their qualifications used for ground truth.
4. Adjudication method.
5. Effect size for MRMC study (as no mention of such a study is made).
6. Standalone performance details.
7. Type of ground truth used.
8. Sample size for the training set.
9. How ground truth for the training set was established.

The document primarily focuses on the regulatory submission process, demonstrating substantial equivalence to a predicate device, and outlining the device's indications for use and general technological characteristics.

Ask a specific question about this device

endo.digital Platform is intended for the management of diabetes by people with diabetes and their healthcare providers in order to report, upload, log, track, share, monitor and review their data using web and mobile applications. endo.digital Platform also enables communication between people with diabetes and their healthcare providers as well as among healthcare providers.

endo.digital Platform enables the healthcare provider to use endo.digital Algorithm for treatment recommendations as described below and prescribe endo.digital Bolus Calculator for patient use.

endo.digital Algorithm is a decision-support software intended for assisting healthcare professionals in the management of their patients with diabetes who monitor their glucose levels using continuous glucose monitor (CGM) and/or Self-Monitoring Blood Glucose (SMBG) meter; and use any of the following insulin types as their therapy to manage glucose levels via subcutaneous injections or continuous sub-cutaneous insulin infusion (CSII; insulin pump) reported either manually or automatically:

• Long acting insulins (for injections only)
• Short acting insulins:
  • Rapid acting analogs (for injections and insulin pump according to manufacturer indications for use)
  • Regular human insulin (for injections only)

endo.digital Algorithm is intended to be used for patients with:

• Type 1 diabetes over the age of 6 using an insulin pump or subcutaneous insulin injections.
• Type 2 diabetes over the age of 10 who use subcutaneous insulin injections.

endo.digital Algorithm is indicated for use by healthcare professionals when analyzing CGM, SMBG and/or insulin delivery data to generate recommendations for optimizing a patient's insulin treatment plan for basal therapy and/or bolus therapy and/or glucose targets, without considering the full clinical status of a particular patient. endo.digital Algorithm does not replace clinical judgement.

endo.digital Bolus Calculator, a component of the DreaMed Diary App, is a diabetes management tool for people with type 1 diabetes above the age of 6 and type 2 diabetes above the age of 10, who use subcutaneous insulin injections therapy (not for pump use). This tool can help calculate their rapid acting analogs for insulin bolus doses based on user-entered blood glucose and/or meal information.

The initial setup of the user's treatment plans, and bolus calculator settings must be performed by a healthcare provider.

endo.digital Platform is a software device that is designed to be a diabetes management platform. It includes endo.digital Algorithm that provides insulin therapy adjustment recommendations to physicians to assist in the management of diabetes for patients with Type 1 diabetes using an insulin pump or multiple daily injections, a continuous glucose monitoring (CGM) system and/or self-management blood glucose meter (SMBG). endo.digital Algorithm also provides insulin therapy adjustment recommendations to physicians to assist in the management of diabetes for patients with Type 2 diabetes on basal-bolus therapy via multiple daily injections (MDI), a continuous glucose monitoring (CGM) system and/or self-management blood glucose meter (SMBG). endo.digital Algorithm gathers and analyzes information inputted through the Diabetes Management Systems (DMS), which collect biological input information from various diabetes devices and data sources including the DreaMed Diary App. Diabetes device information required and used by endo.digital Algorithm includes glucose readings (either CGM sensor readings and/or capillary blood glucose measurements), insulin dosing logs, and meal data during daily routine care. Following data collection and analysis, the endo.digital Algorithm generates results containing summary data and recommendations for adjustments to the patient's insulin therapy parameters, including basal insulin delivery rate(s), insulin to carbohydrate ratio and correction factor (insulin sensitivity) for pump patients, and for MDI patients a daily injection plan including a basal plan and either a sliding scale (which can include Fixed Meal and Meal Estimation plans) or insulin to carbohydrate ratio and correction factor (insulin sensitivity) for bolus injections. endo.digital Algorithm may also advise on personalized diabetes management tips. Results are sent to the Diabetes Management System, which displays results to physicians and a report provided by the algorithm. The physician can approve, reject or change the recommendations and issue the updated treatment plan to the patient. For MDI patients using rapid acting analogs for insulin bolus dose, the healthcare provider may prescribe endo.digital Bolus Calculator which is integrated in the DreaMed Diary App to aid in calculating their bolus injections.

The provided text details the 510(k) premarket notification for the "endo.digital Platform." While it discusses the device's intended use, description, and substantial equivalence to a predicate device, it does not contain specific information about the acceptance criteria or the study that proves the device meets those criteria. The document states that "software performance data demonstrates that endo.digital Platform is as safe and effective as the predicate device" and that "Design validation testing results confirmed that endo.digital Platform performs according to the stated intended use. Software evaluation consisted of functional testing performed pursuant to DreaMed's software test plan. All test results fell within the pre-determined specification parameters and acceptance criteria." However, it does not provide the acceptance criteria themselves, nor the details of the studies conducted to meet them.

Therefore, I cannot fulfill your request for:

1. A table of acceptance criteria and the reported device performance: This information is not present in the document.
2. Sample size used for the test set and the data provenance: This information is not provided.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not provided.
4. Adjudication method for the test set: Not provided.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and its effect size: Not mentioned. The device is a "decision-support software intended for assisting healthcare professionals," implying a human-in-the-loop, but no MRMC study details are shared.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not specified.
7. The type of ground truth used: Not specified.
8. The sample size for the training set: Not provided.
9. How the ground truth for the training set was established: Not provided.

The document focuses on the regulatory submission, equivalence to a predicate device ("Advisor Pro Platform, K210561"), and the general statement that "software performance data demonstrates that endo.digital Platform is as safe and effective as the predicate device." It also mentions "functional testing performed pursuant to DreaMed's software test plan" and that "All test results fell within the pre-determined specification parameters and acceptance criteria," but it does not disclose the specifics of these tests or criteria.

To obtain the requested information, one would typically need to review the full 510(k) submission, which often includes detailed validation reports, clinical studies, and software verification and validation documentation. These are usually not fully disclosed in the public 510(k) summary letter.

Ask a specific question about this device