(257 days)
The Plum Solo™ Precision IV Pump is intended for administration of parenteral fluids, medications, and whole blood and blood products through the following routes of administration: intravenous, intra-arterial, and subcutaneous.
The Plum Solo™ Precision IV Pump is intended for use in clinical environments in the hospital and other outpatient healthcare facilities by licensed healthcare professionals. These healthcare professionals are trained in the use of the infusion pump and the administration of therapies consistent with the intended use.
The Plum Solo™ Precision IV Pump is intended for adults, pediatric (including infants and children), and neonatal patient populations.
The Plum Solo™ Precision IV Pump is a large volume pump (LVP) with one pump channel that can deliver fluid to a patient from 1 to 2 lines independently. The Plum Solo™ Precision IV Pump can only be used with dedicated PlumSet™ administration sets (not subject of this filing). The pump channel accepts a cassette that is part of a PlumSet™ administration set and can connect to a primary and/or secondary container. The fluid is delivered from the upstream lines either serially (piggyback) or concurrently through the cassette to the downstream line. The flow rate accuracy precision has been improved (lower allowed variance) by implementing the new motor mechanism, as well as increased precision for programming concentration, flow rate and VTBI entries. The overall delivery accuracy of the system has improved to +/- 3% per TIR 101 standard condition testing and +/-5% for non-standard conditions.
The provided FDA 510(k) clearance letter pertains to the Plum Solo™ Precision IV Pump, which is a large volume infusion pump. The document focuses on demonstrating substantial equivalence to a predicate device, the Plum Duo™ Infusion System (K223607).
It's important to note that the detailed information typically associated with acceptance criteria and study results for AI/ML-enabled medical devices (like the number of experts, adjudication methods, MRMC studies, or specific ground truth methodologies for training data) is not present in this clearance letter. This is because an IV pump, while an advanced medical device, is not an AI/ML diagnostic or prognostic system that relies on interpreting complex data like medical images, waveforms, or patient parameters to derive a diagnosis or predict an outcome.
Instead, the acceptance criteria and study results described for the Plum Solo™ Precision IV Pump focus on engineering performance specifications, reliability, and human factors validation, which are standard for such devices.
Therefore, the following information is extracted and presented based on the provided text, and where information is not available (as it is not typically part of the clearance for this class/type of device), it will be explicitly stated.
Overview of Device and Study Focus
The Plum Solo™ Precision IV Pump is a large volume pump (LVP) designed for administering parenteral fluids, medications, and blood products. The primary goal of the 510(k) submission was to demonstrate substantial equivalence to its predecessor, the Plum Duo™ Infusion System. The key improvements highlighted are enhanced flow rate accuracy and increased precision for programming.
1. Acceptance Criteria and Reported Device Performance
The acceptance criteria are primarily defined by the performance targets for flow rate accuracy and bolus delivery accuracy, compared to the predicate device.
| Characteristic | Acceptance Criteria (Implied by Predicate Performance or New Target) | Reported Device Performance (Plum Solo™) |
|---|---|---|
| Flow Rate Delivery Accuracy | +/- 5% for 0.1 - 999 mL/hr (Predicate performance) | +/- 3% for 0.1 - 999 mL/hr |
| Cassette Service Duration for Flow Accuracy | 0 to 96 hours | 0 to 96 hours |
| Bolus Delivery Accuracy | +/- 5% for delivery volumes as low as 0.1 ml at 999 ml/hr | +/- 5% for delivery volumes as low as 0.1 ml at 999 ml/hr |
Note on Acceptance Criteria: For a device like an infusion pump, "acceptance criteria" are implicitly met when the device demonstrates performance that is either equivalent to or improved upon a legally marketed predicate, in addition to meeting relevant safety standards (e.g., IEC standards, risk management requirements, human factors). In this case, the improved flow rate accuracy (from +/-5% to +/-3%) is a key performance metric that exceeds the predicate, serving as a strong point of "acceptance" in terms of performance.
2. Sample Size Used for the Test Set and Data Provenance
The document does not specify a sample size for the test set in terms of "patient data" as this is not an AI/ML diagnostic device analyzing patient-derived data. Instead, testing involves engineering verification and validation runs on the physical device and its software. The provenance of such data would be controlled laboratory settings.
- Sample Size: Not applicable in the context of "patient data" or "images." Testing involved verification and validation of product requirements, reliability goals, and human factors. The exact number of test units or test repetitions for each performance metric (e.g., flow rate accuracy tests per AAMI TIR101) is not specified in the summary but would be detailed in internal test reports.
- Data Provenance: Not applicable in the sense of country of origin for "data" like patient scans. This is laboratory-generated performance data from device testing. The testing was conducted as part of the device's design verification and validation processes. It is implicitly retrospective in the sense that the testing was performed before the 510(k) submission.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
This concept is not applicable to the type of device discussed. Ground truth for an infusion pump's performance (e.g., flow rate, bolus accuracy) is established through precise physical measurements using calibrated equipment and reference standards (e.g., gravimetric methods for flow rate), not through expert interpretation of medical data.
- Number of Experts: Not applicable.
- Qualifications of Experts: Not applicable.
4. Adjudication Method for the Test Set
This concept is not applicable to the type of device discussed. Adjudication (e.g., 2+1, 3+1 for imaging consensus) is used for subjective evaluations where multiple human readers assess data. Performance metrics for an infusion pump are objective and measured.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done
No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. This type of study is specifically designed for assessing the impact of AI on human reader performance, typically in diagnostic imaging or similar fields. An infusion pump's primary function is fluid delivery, not diagnostic interpretation.
6. If a Standalone (Algorithm-Only Without Human-in-the-Loop) Performance Study was done
The term "standalone performance" in the context of an infusion pump refers to its ability to accurately deliver fluids based on its internal mechanics and software programming, independent of immediate human intervention during the delivery phase. The document details that:
- Flow rate and bolus accuracy testing were conducted by following AAMI TIR101. This is a standard for evaluating the performance of infusion pumps without a human directly influencing each delivery cycle. This essentially serves as the "standalone" performance assessment for this device.
- The reported performance of +/- 3% for flow rate accuracy directly reflects this standalone capability.
7. The Type of Ground Truth Used
The ground truth for an infusion pump's performance is established through physical measurements against established standards, not through expert consensus, pathology, or outcomes data in the medical sense.
- Ground Truth: Utilized reference standards and precise measurement techniques (e.g., gravimetric measurement for flow rate) as per AAMI TIR101. The "truth" is the actual volume delivered compared to the commanded volume, measured by calibrated instruments.
- Human Factors Validation: While not "ground truth" per se, human factors evaluations were conducted to validate the effectiveness of safety-critical use-related features/functionality and use error-related mitigations, in accordance with FDA guidance and IEC 62366-1. This ensures the user interface and interactions are safe and effective.
8. The Sample Size for the Training Set
This concept is not applicable to the type of device discussed. Infusion pumps are not "trained" on large datasets in the way AI/ML algorithms are. Their operational parameters are set by design and engineering specifications. While the device contains software, it's not a machine learning model that learns from a "training set."
9. How the Ground Truth for the Training Set Was Established
This concept is not applicable because there is no "training set" for an infusion pump in the AI/ML sense. The device's functionality is a result of engineering design, mathematical algorithms for pump control, and calibration, not machine learning from data.
§ 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).