(21 days)
The Plum A+® and Plum A+®3 Infusion System with Hospira MedNet™ Software is indicated for use in parenteral, enteral and epidural therapies and the administration of whole blood and blood products.
The Plum A+® and A+®3 Infusion Systems with MedNet™ Software are electromechanical infusion pumps that use a stepper motor in conjunction with an inline cassette to meter IV fluids through dedicated intravenous administration sets. The infusion pumps and administration sets are manufactured and distributed by Hospira, Inc. The Plum A+® Infusion System is a single channel pump and Plum A+®3 Infusion System is a triple channel pump.
The subject devices are modifications of the predicate infusion pumps. The modifications provide networked (Ethernet wired and wireless) communication capability through new input/output (I/O) modules as well as enhancement of the optional drug library software (on CD-ROMs) to include an asset management function and have resident server software capability. In addition, enhancements are being made to the user interface of the infusion pumps. These enhancements include adding additional dose units, eliminating trailing zeros after a decimal point, dynamic font sizing to allow longer drug and clinical care area (CCA) names and allowing the clinician to change the CCA as required.
The provided text is a 510(k) summary for the Plum A+® and Plum A+®3 Infusion Systems with Hospira MedNet™ Software. This document focuses on demonstrating substantial equivalence to predicate devices, rather than presenting a detailed study proving the device meets specific acceptance criteria in the fashion typical for AI/ML medical devices.
Therefore, much of the requested information (acceptance criteria table, sample sizes, ground truth establishment, expert qualifications, adjudication methods, MRMC studies, standalone performance, training set details) is not applicable or not present in this type of submission.
This 510(k) summary primarily addresses:
- Device Description: The Plum A+® and A+®3 Infusion Systems with MedNet™ Software are electromechanical infusion pumps that use a stepper motor and inline cassette to meter IV fluids. The MedNet™ software adds networked communication capability (Ethernet wired and wireless), enhances the optional drug library software to include an asset management function, and enables resident server software capability. User interface enhancements are also described.
- Intended Use: Indicated for use in parenteral, enteral, and epidural therapies, and the administration of whole blood and blood products. This is the same as the predicate devices.
- Technological Characteristics Comparison: The proposed and predicate devices are similar in design, materials, components, intended use, labeling, and manufacturing processes. The modifications (networked communication, drug library enhancements, UI changes) do not raise new safety or effectiveness concerns.
- Substantial Equivalence: The claim is that the device is substantially equivalent to the Abbott Plum A+® Infusion Pump with HPL/RS Plug-and-Play Module (K031185) and the Abbott Plum A+3™ Multichannel Infusion Pump (K021350).
Detailed breakdown of the requested information based on the provided text:
1. A table of acceptance criteria and the reported device performance
| Acceptance Criteria (Explicitly stated) | Reported Device Performance (Implied by Substantial Equivalence) |
|---|---|
| Preamble: This document (a 510(k) summary) does not explicitly state acceptance criteria in a quantitative format typical for an AI/ML device study. Instead, the "acceptance criteria" for a 510(k) center around demonstrating that the new device is as safe and effective as a legally marketed predicate device. | |
| Functionality of networked communication (Ethernet wired and wireless) | Claimed to not raise new issues of safety and/or effectiveness; implies successful implementation and operation. |
| Functionality of enhanced drug library software (asset management, resident server) | Claimed to not raise new issues of safety and/or effectiveness; implies successful implementation and operation. |
| Functionality of user interface enhancements (dose units, no trailing zeros, dynamic font, CCA changes) | Claimed to not raise new issues of safety and/or effectiveness; implies successful implementation and operation. |
| Safety and effectiveness given new modifications | Substantially equivalent to predicate devices; modifications do not raise new issues of safety and/or effectiveness; compliance with IEC 60601-1-2 2nd Edition. |
| Compatibility with existing Plum A+® and Plum A+3™ pumps and administration sets | Plug 'n Play (I/O) Module is backwards compatible; I/O Modules and peripheral modules are backwards compatible; no changes to administration sets required. |
| Adherence to IEC 60601-1-2 2nd Edition | "All new factory released infusion systems will be in compliance with IEC 60601-1-2 2nd Edition." |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Not applicable / Not present. This document does not describe a clinical study with a test set of data. The submission relies on a comparison of technical specifications and intended use to predicate devices, and likely in-house testing to verify new functionalities, but no clinical data with a "test set" in the context of an AI/ML evaluation.
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)
- Not applicable / Not present. This type of ground truth establishment is not relevant for an infusion pump 510(k) submission focused on technical modifications.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not applicable / Not present. Adjudication methods are not described as there is no clinical "test set" in the AI/ML sense.
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, not done. MRMC studies are not applicable to the evaluation of an infusion pump's modifications. The device described does not involve "human readers" interpreting data with or without AI assistance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Not applicable. This device is an infusion pump with software enhancements, not a standalone AI algorithm being evaluated for diagnostic or predictive performance. The software acts as a control and communication system for the pump.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- Not applicable / Not present. The "ground truth" for this device would be its ability to safely and accurately deliver fluids according to its programming and intended use, verified through engineering bench testing and adherence to standards, rather than clinical ground truth from patient data or expert consensus.
8. The sample size for the training set
- Not applicable / Not present. This device does not use machine learning in a way that would require a "training set" of data for an algorithm.
9. How the ground truth for the training set was established
- Not applicable / Not present. As there is no training set mentioned or implied, this question is not relevant.
§ 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).