Search Results

Intended use:
The Avoset Infusion Pump is a single-channel, volumetric infusion is delivered at continuous rate, and/or with an intermittent bolus, and/or with a patient bolus and/or with taper.

Indication of use:
Routes: Parenteral (intra-arterial, intra-venous, subcutaneous, perineural, epidural) and enteral infusions
Fluids: IV medication (including fluids), Total Parenteral Nutrition (TPN), enteral medication and nutrition, lipids, epidural medication.
Program Types (specific uses): The pump delivers in one of four program types: a continuous rate of infusion, and/or an intermittent bolus, and/or with patient-controlled intermittent doses, and/or with tapering.
Patient Population: Pediatric: infants, children, and adolescents and adult patients.
Intended Environments. Intended to be used in clinical environment including, home, plane and ground transportation.
Users: licensed health care professional and lay users
The dedicated Administration Sets for the Avoset Infusion Pump are intended for single-patient use and single-use only. Set configurations are: (i) Enteral; (ii) Epidural and (iii) General purpose for the routes: intra-arterial, intravenous, subcutaneous, perineural.
The Avoset Programming Tool is intended to be used with a computer to create a treatment-based protocol that is boaded onto the pump. The programming tool is intended for use by professional users.

The Avoset Infusion system (pump and accessories) covered by this submission is the Avoset infusion pump, an ambulatory pump intended for controlled infusion at rates between 0.1-300 mL/h at a continuous rate, and/or with an intermittent bolus, and/or with a patient bolus and/or with taper, in the hospital and home environments for pediatric and adult patients.
The Avoset infusion pump weighs 365 grams, has 89 parts, and allows infusion from (i) bags; (ii) syringes; and (iii) non collapsible medication reservoirs.
The device also contains an optional module (referred to as "Insight Tool"). The module receives data from the pump and uses it for (i) fleet management and (ii) treatment monitoring applications to ensure patient has completed the treatment. This module does not impact or pass data into the pump.
The dedicated Avoset Administration Sets are sterile (apart of the Enteral sets) and intended for singlepatient use and single-use only.

This document is a 510(k) Summary for the Avoset Infusion Pump system, which is a premarket notification to the FDA to demonstrate that the device is at least as safe and effective as a legally marketed device (predicate device). It is not a study report per se, but it summarizes the performance testing conducted to support substantial equivalence.

Here's an breakdown of the information requested, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample size used for the test set and the data provenance

The document does not specify general "test set" sample sizes or data provenance (e.g., country of origin, retrospective/prospective) for the overall device performance. It only lists various performance tests conducted. For example, for Human Factors studies, it mentions "conducted with the intended user population, use environment, and use scenarios," but no specific numbers are given.

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. The performance tests mentioned (e.g., accuracy, electrical safety, EMC, biocompatibility) typically rely on engineering specifications, standardized testing, and validated methods rather than expert consensus on a "ground truth" in the way that, for example, a diagnostic AI might.

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

This information is not applicable/not provided as the regulatory filing details engineering and performance testing rather than human-expert derived ground truth adjudication.

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

An MRMC comparative effectiveness study is not mentioned and is not relevant for an infusion pump's substantial equivalence demonstration. The device is an infusion pump, which is a physical medical device, not an AI-assisted diagnostic tool for human readers.

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

The "Insight Tool" is mentioned as an "optional module" that "receives data from the pump and uses it for (i) fleet management and (ii) treatment monitoring applications to ensure patient has completed the treatment. This module does not impact or pass data into the pump." This suggests it operates in a standalone manner for data analysis after the pump's operation, but its performance is not detailed in the context of specific acceptance criteria. The primary device performance testing focuses on the infusion pump itself, not this module's data analysis capabilities. The document does not describe "algorithm only" performance in the context of AI without human intervention.

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

The "ground truth" for the performance testing of an infusion pump would be defined by engineering specifications, international standards (e.g., IEC, ISO), and regulatory guidance. For example:

• Accuracy: Measured flow rate compared to programmed flow rate, against a defined tolerance range (e.g., ± 5%).
• Occlusion detection: Pressure measurements against specified thresholds.
• Air detection: Detection of air volumes against specified thresholds.
• Electrical Safety, EMC, Alarms, Biocompatibility: Compliance with the requirements of relevant IEC and ISO standards.

These are not "expert consensus" or "pathology" in the typical sense for AI/diagnostic devices but rather objective, measurable parameters against established norms.

8. The sample size for the training set

This information is not provided and is not applicable in the context of the regulatory submission for this type of device. The Avoset Infusion Pump is a hardware device with embedded software, not an AI/ML system that undergoes explicit "training" on a dataset for a specific task like image classification. The software verification and validation (V&V) mentioned refers to standard software development lifecycle testing, not machine learning model training.

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

As there is no mention of a "training set" in the context of machine learning for this device, this question is not applicable. Software validation typically involves testing against requirements derived from device specifications and established standards, rather than a machine learning "ground truth."

Ask a specific question about this device