Search Results

The DEKA Infusion System is indicated for continuous delivery of general maintenance fluids and supported antibiotics to adult patients through a peripheral intravenous (IV) site under the supervision of a qualified clinician.

The DEKA Administration Set is indicated for gravity administration of general maintenance fluids and supported antibiotics approved for peripheral intravenous (IV) infusion to adult patients under the supervision of a qualified clinician. The DEKA Administration Set is indicated for single patient use only. The DEKA Administration Set is not indicated for administration of high-alert medications, blood, and blood products.

The DEKA Administration Set is compatible with the DEKA Infusion Controller or can be used as a stand-alone administration set for performing manual gravity infusions.

The subject device is a modified version of the predicate DEKA Infusion System. Updates have been made to the predicate device software to increase the maximum programmable flow rate (from 300 to 600 mL/h), update the labeling to reflect the increased maximum programmable flow rate and update the performance of tilt angle detection. The administration set is unchanged.

The DEKA Infusion System, comprised of the DEKA Infusion Controller and DEKA Administration Set, is a gravity-based infusion controller. The Infusion Controller uses a camera to view drop formation in an Administration Set Drip Chamber in order to measure flow rate. During an infusion, the Infusion Controller can adjust the Flow Control Valve (FCV) as necessary against the DEKA Administration Set to maintain the desired flow rate without user intervention.

The DEKA Administration Set is a single-use, non-DEHP intravascular administration set provided sterile. It is compatible with the DEKA Infusion Controller or can be used as a standalone administration set for performing manual gravity infusions.

The provided text is a 510(k) summary for the DEKA Infusion System and DEKA Administration Set. It primarily focuses on demonstrating substantial equivalence to a predicate device after a modification, specifically an increased maximum programmable flow rate and an update to tilt angle detection.

However, the document does not contain the detailed information required to answer your specific questions about acceptance criteria, the study proving the device meets the criteria, sample sizes, expert involvement, ground truth, or MRMC studies for an AI/ML-based device.

This document is for a mechanical/electrical infusion system that uses a camera for drop formation detection and flow rate measurement, not an AI/ML diagnostic or prognostic device that would involve a training set, test set, expert adjudication, or MRMC studies in the way your questions imply. The "Vision System Performance" mentioned is likely related to the camera's ability to accurately detect drops, not a complex AI model requiring extensive human-in-the-loop validation or ground truth established by multiple medical experts interpreting images.

Therefore, I cannot extract the requested information from this document. The questions you've asked are typical for the validation of Artificial Intelligence/Machine Learning (AI/ML) medical devices, particularly those involving image interpretation or complex diagnostic algorithms. This 510(k) summary does not describe such a device or its corresponding validation studies.

The closest aspects discussed are:

• Acceptance Criteria for Flow Rate Accuracy: Mentioned as "± 10% nominally" and "± 25% under environmental limits of normal use." The document states "All tests met acceptance criteria."
• Study Proving Device Meets Criteria: "Formal performance testing was conducted on all areas of the subject device that are impacted by its changes with respect to the predicate device."
• Performance Data: "Flow Rate Accuracy," "Vision System Performance," "Stopping Flow," and "Device Handling Alarms" were tested.

But none of these provide the level of detail (sample size, expert ground truth, adjudication, MRMC) specific to AI/ML device validation that your questions are designed to elicit.

Ask a specific question about this device

The DEKA Infusion System is indicated for continuous delivery of general maintenance fluids and supported antibiotics to adult patients through a peripheral intravenous (IV) site under the supervision of a qualified clinician.

The DEKA Administration Set is indicated for gravity administration of general maintenance fluids and supported antibiotics approved for peripheral intravenous (IV) infusion to adult patients under the supervision of a qualified clinician. The DEKA Administration Set is indicated for single patient use only. The DEKA Administration Set is not indicated for administration of high-alert medications, blood, and blood products.

The DEKA Administration Set is compatible with the DEKA Infusion Controller or can be used as a stand-alone administration set for performing manual gravity infusions.

The DEKA Infusion System, comprised of the DEKA Infusion Controller and DEKA Administration Set, is a gravity-based infusion controller. The Infusion Controller uses a Camera to view drop formation in an Administration Set Drip Chamber in order to measure flow rate. During an infusion, the Infusion Controller can adjust the Flow Control Valve (FCV) as necessary against the DEKA Administration Set to maintain the desired flow rate without user intervention.

The DEKA Administration Set is a single-use, non-DEHP intravascular administration set provided sterile. It is compatible with the DEKA Infusion Controller or can be used as a standalone administration set for performing manual gravity infusions.

This document describes the regulatory submission for the DEKA Infusion System and DEKA Administration Set, emphasizing their substantial equivalence to previously cleared devices. It outlines performance data related to device testing but does not contain information on studies proving the device meets acceptance criteria related to AI/human reader performance or ground truth established by experts for such studies.

Therefore, I will extract relevant information that is present and note the absence of information specifically requested for AI/human reader performance studies.

Here's the analysis based on the provided text:

Acceptance Criteria and Device Performance (as far as described for the hardware components):

Study Details (based on provided text):

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

• See table above. The acceptance criteria are implicitly defined by the substantial equivalence comparison to the predicate devices and relevant industry standards. Performance is reported as "identical," "similar," or "equivalent." Specific quantitative performance values are provided for flow rate accuracy, range, VTBI, and time to detect occlusion.

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

• The document states "Performance testing was conducted in order to verify and validate each subject device for its respective intended use." However, it does not provide specific sample sizes (e.g., number of devices, number of test runs) for these tests, nor does it explicitly mention data provenance (e.g., country of origin, retrospective/prospective for any study in the typical sense of a human-in-the-loop or AI performance study). The tests are described as nonclinical in nature, implying laboratory testing of the devices themselves.

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

• This information is not applicable as the document describes performance testing of a physical medical device (infusion system and administration set), not an AI-enabled diagnostic device requiring expert interpretation for ground truth. There is no mention of "experts" beyond the general statement "under the supervision of a qualified clinician" for device use.

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

• This is not applicable for the type of device and testing described. Adjudication methods are typically used in clinical studies involving human readers and interpretations of medical images or data.

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 is not applicable as the DEKA Infusion System and Administration Set are hardware devices, not AI-enabled diagnostic software that assists human readers.

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

• This is not applicable as the device is not an algorithm for diagnostic interpretation. Its "control mechanism" uses a "Video camera and vision processing system with a flow control valve" to measure and control flow rates, which is an integrated system function, not a standalone AI algorithm for interpretation.

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

• For the hardware performance tests mentioned (e.g., flow rate accuracy, alarm conditions, electrical safety), the "ground truth" would be established by physical measurements, adherence to engineering specifications, and compliance with recognized industry standards (e.g., AAMI TIR101, IEC 60601 series, ISO 8536-4). It's not a medical "ground truth" like disease presence or absence.

8. The sample size for the training set:
* This is not applicable. There is no mention of an AI model or a "training set" in the context of this device's regulatory submission. The device uses "vision processing" for its function, but the approval is for the physical device, not an AI model that undergoes a typical training and validation regimen as seen in AI/ML submissions.

9. How the ground truth for the training set was established:
* This is not applicable. As there is no explicitly mentioned "training set" for an AI model for clinical interpretation, there is no ground truth establishment method described.

Summary of what is present and what is not:

• Present: Detailed comparison of the subject devices (DEKA Infusion System and DEKA Administration Set) to their respective predicate devices across various characteristics, including technical specifications, performance parameters (like flow rate, alarms), and adherence to relevant medical device standards. The document confirms that extensive nonclinical performance testing was conducted to support substantial equivalence.
• Not Present: Any information related to AI-specific study designs, human reader performance, expert consensus for ground truth in diagnostic interpretation, or sample sizes for clinical trials/test sets/training sets for AI models. This is consistent with the device being a hardware infusion system, not an AI-enabled diagnostic tool in the typical sense.

Ask a specific question about this device