(21 days)
The ambIT™ Infusion Pump is intended for continuous volumetric delivery of intravenous medicines and/or fluids into patients at a consistent volume for prescriptive treatment by a physician.
Sorenson Medical's amblT™ Continuous Ambulatory Infusion Pump is compact, lightweight, microcomputer-controlled pumps that use rotary peristaltic pumping technology. The modified device differs only slightly from the Palm Pumps (K002434) already marketed. Changes have been made to that pump to incorporate three roller gears instead of two, a modified PCB, a change to color and name, and a software revision to provide for continuous fluid delivery to specified output requirements
This document is a 510(k) premarket notification for the ambIT™ Continuous Infusion Pump. It focuses on demonstrating substantial equivalence to a predicate device (Palm Pump, K002434) rather than a comprehensive de novo validation study. Therefore, much of the information typically present in a study proving a device meets acceptance criteria (like specific acceptance criteria values, detailed study designs, expert involvement, and ground truth methodologies) is not explicitly provided in the provided text.
However, based on the information available, here's a breakdown of what can be inferred and what is not present:
1. Table of Acceptance Criteria and Reported Device Performance
The acceptance criteria are not explicitly detailed with specific numerical targets in the provided text. Instead, the general requirement is that the device "met documented performance and safety requirements specified for the new device" and that "the design modifications made to the subject device met documented performance and safety requirements."
The reported device performance is that the modifications were "fully validated" and "do not raise issues of safety and effectiveness." The core performance claim is "continuous volumetric delivery... at a consistent volume for prescriptive treatment by a physician," which is the intended use shared with the predicate.
| Acceptance Criteria (Inferred from text) | Reported Device Performance |
|---|---|
| Adherence to documented performance and safety requirements for the new device. | "All tests were conducted according to written test protocol, with defined test expectations and documented conclusions. All test data has been attached to the verification and validation testing performed and is a permanent record of Sorenson Medical's Design History Record." |
| Continuous volumetric delivery of intravenous medicines and/or fluids. | Confirmed implicitly by the device's intended use and the statement that it "provide[s] for continuous fluid delivery to specified output requirements." |
| Consistency of fluid delivery. | Confirmed implicitly by the device's intended use and the statement that it "provide[s] for continuous fluid delivery to specified output requirements." |
| No new issues of safety and effectiveness compared to the predicate device. | "The technological differences between the subject and predicate devices are minor, have been fully validated and they do not raise issues of safety and effectiveness." |
2. Sample Size Used for the Test Set and Data Provenance
The document states, "All tests were conducted according to written test protocol, with defined test expectations and documented conclusions." However, no specific sample sizes for the test sets are provided.
Given that it's a 510(k) for an infusion pump, the "tests" would likely involve laboratory-based performance testing (e.g., flow rate accuracy, occlusion detection, battery life) rather than clinical data from human patients. Therefore, the concept of "country of origin of the data" and "retrospective or prospective" as typically applied to clinical studies involving patient data is not directly applicable here. The data would be generated in a controlled laboratory environment by Sorenson Medical.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
This information is not provided in the document. For a product like an infusion pump, "ground truth" for performance testing is typically established by engineering specifications and objective measurements using calibrated equipment, not by human expert assessment in the way it would be for diagnostic imaging.
4. Adjudication Method for the Test Set
This information is not provided and is generally not relevant for device performance testing of this nature. Adjudication methods (like 2+1, 3+1) are typically used in clinical studies, especially those involving subjective interpretations (e.g., image reading), to resolve discrepancies between multiple human reviewers.
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 comparative effectiveness study was done. This device is an infusion pump, not a diagnostic AI system that would involve human readers interpreting output. Therefore, the concept of human readers improving with or without AI assistance is not applicable.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
This question is not applicable in the context of an infusion pump. While the device has a "microcomputer-controlled" system and "software revision," it is a standalone medical device that operates autonomously to infuse fluids, not an "algorithm" in the sense of a diagnostic or assistive AI that would be evaluated for human-in-the-loop vs. standalone performance. The device itself is the "standalone" entity.
7. The Type of Ground Truth Used
The ground truth for the verification and validation tests would have been engineering specifications and measurable performance parameters (e.g., flow rate accuracy, pressure limits, alarm triggers, battery life). These are objective, quantifiable criteria established during the device's design and development, rather than subjective expert consensus, pathology, or outcomes data.
8. The Sample Size for the Training Set
This information is not provided and is not directly applicable in the traditional sense of a "training set" for machine learning with large datasets. While the software was revised, it's not described as an AI/ML model being "trained" on data. Any "training" would refer to the internal development and testing cycles of the software and hardware, where parameters are tuned and verified against expected outputs, using internal test data or simulations, rather than a distinct "training set" used for an algorithm.
9. How the Ground Truth for the Training Set Was Established
As above, the concept of a "training set" and associated ground truth is not applicable in the context of this device in the same way it would be for an AI/ML product. The ground truth for the device's design, software development, and functional verification would have been established through engineering specifications, design requirements, and standard testing methodologies to ensure the device performs according to its intended function (e.g., precise fluid delivery).
§ 880.5725 Infusion pump.
(a)
Identification. An infusion pump is a device used in a health care facility to pump fluids into a patient in a controlled manner. The device may use a piston pump, a roller pump, or a peristaltic pump and may be powered electrically or mechanically. The device may also operate using a constant force to propel the fluid through a narrow tube which determines the flow rate. The device may include means to detect a fault condition, such as air in, or blockage of, the infusion line and to activate an alarm.(b)
Classification. Class II (performance standards).