Search Results

The DEKA ACE Pump System is intended for the subcutaneous delivery of insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin, ages six and above. The 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 pump is intended for single patient, home use and requires a prescription.

The bolus calculator is indicated for use for aiding the bolus insulin dosage for management of diabetes mellitus based on consumed carbohydrates, operator entered blood glucose, insulin to carbohydrate ratio, target glucose values, and current insulin on board.

The DEKA ACE Pump system is a modification of the previously cleared DEKA ACE Pump System (K213536). The modified device is a wearable alternate controller enabled (ACE) insulin infusion pump (DEKA ACE Pump System) with the addition of an embedded iAGC (DEKA Loop). The user interface is an iOS app that can be downloaded to a user's iPhone.

The updated system is still intended to subcutaneously deliver insulin, at set and variable rates, for the management of diabetes mellitus in persons requiring insulin. The pump is able to reliably and securely communicate with compatible, digitally connected devices to receive, confirm, and execute commands. The Pump is intended for single patient, ambulatory use and requires a prescription. The Pump is indicated for use with Humalog U-100 insulin.

The DEKA ACE Pump System is indicated for the management of mellitus in persons six years of age and greater.

The system as described in this submission is able to be integrated with an integrated Continuous Glucose Monitor (iCGM). This submission also details the integration process that was used to incorporate the DEKA Loop iAGC Algorithm onto the DEKA ACE Pump.

The DEKA ACE Pump System consists of the following durable and disposable components:

• Pump: A durable pump that incorporates fluid delivery algorithms and interfaces to a cassette, external wireless user interface, and iCGM. The pump is powered by a rechargeable lithium ion battery.
• Cassette: A single-use pumping cassette that combines microfluidic valves, a pump chamber, insulin reservoir, and Acoustic Volume Sensing (AVS) measurement chamber. The cassette interfaces to a pump and off-the-shelf infusion sets.
• DEKA Loop App: An iOS mobile application that serves as the primary user face for the system. The DEKA Loop app can be downloaded onto the user's personal iPhone.

The provided text is a 510(k) summary for the DEKA ACE Pump System, focusing on demonstrating substantial equivalence to a previously cleared predicate device. It addresses modifications, primarily the addition of an embedded iAGC (DEKA Loop) and a change in the user interface to an iOS app, as well as a broadened age indication (from 13+ to 6+).

However, the document does not contain the specific information required to answer your request about acceptance criteria and study proving the device meets those criteria for aspects like deep learning model performance (e.g., accuracy, sensitivity, specificity, or AUC). The request is structured as if the document describes an AI/ML-based diagnostic device where performance metrics against a ground truth dataset would be evaluated.

Instead, this document describes a medical device (insulin pump) where the "performance testing" refers to engineering and quality assurance testing against technical standards and safety requirements (e.g., electrical safety, electromagnetic compatibility, biocompatibility, delivery accuracy of insulin). The "Acceptance Criteria" implicitly refer to meeting these established engineering and regulatory standards rather than statistical performance metrics of a diagnostic algorithm against a labeled test set.

Specifically:

• There is no mention of a deep learning model's performance metrics (accuracy, sensitivity, specificity, AUC) or related test set details (sample size, data provenance, ground truth establishment, expert adjudication, MRMC studies).
• The "DEKA Loop iAGC Algorithm" is mentioned as being integrated, but there are no details on how its performance was evaluated, other than "Human Factors testing demonstrates equivalent safety and effectiveness for the indicated population" (page 7). This suggests focus on usability and safety in human interaction, not algorithmic diagnostic performance.
• The document explicitly states "No clinical data was obtained in support of this premarket submission" (page 13), reinforcing that the evaluation was primarily non-clinical and focused on substantial equivalence based on existing data and engineering tests.

Given the content of the provided document, I cannot fulfill your request for the specific details outlined for an AI/ML-based diagnostic device. The available information relates to the regulatory submission for an insulin pump, which is evaluated against different types of performance criteria.

Ask a specific question about this device