(44 days)
The Delphi Infusion Pump is intended for use in the controlled delivery of epidural and IV solutions.
The Delphi Infusion Pump is a large volume infusion pump customizable to meet the specific needs of multiple care areas and deliver a wide range of therapies in a safe and effective manner. For each area of care, clinically appropriate alarms, alerts, and performance specifications can be established. With the available Safety Suite, the pharmacy can define default and safe operating ranges for all drugs being infused. There are four basic infusion modes available plus epidural delivery. The Delphi Infusion Pump uses a rotary peristaltic pumping mechanism with dedicated disposable administration sets. Each administration set includes a precision-molded cassette designed for fast, safe, and secure single-handed pump loading. A safety slider switch on the cassette, along with a roller clamp, provides redundant free-flow protection when the tubing is unloaded. The user interface was designed using extensive input from clinical and human factors experts to offer a unique combination of a large touch screen display and a keypad for alpha-numeric data entries. The pump is designed for use on AC power with battery backup during power failure and is available during patient ambulation and transport. The portable light weight single-channel design allows for a dedicated display ("one screen, one drug") and improved utilization and increased flexibility in device placement.
The provided text details a 510(k) submission for the Delphi Infusion Pump, focusing on its substantial equivalence to a predicate device. However, it does not contain information about acceptance criteria for a study, reported device performance metrics in a study, sample sizes for test or training sets, data provenance, expert qualifications, ground truth establishment, or multi-reader multi-case studies.
The document discusses the device's intended use, description, and technological characteristics, and concludes with a statement of substantial equivalence based on bench performance testing and comparison against predicate devices.
Here's a breakdown of what is and is not present:
1. A table of acceptance criteria and the reported device performance
- Information Not Found: The document states that "Bench performance testing has also demonstrated that the Delphi Infusion Pump is substantially equivalent in performance as the predicate device in flow accuracy and in construction when compared using performance standards for infusion pumps." However, it does not provide specific acceptance criteria, quantitative reported device performance metrics (e.g., specific flow accuracy percentages or error rates), or a table comparing them.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Information Not Found: No information is provided regarding sample sizes for any test sets, the nature of the data (retrospective or prospective), or its country of origin. The testing mentioned is "bench performance testing," implying laboratory-based evaluation rather than clinical data from human subjects.
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)
- Information Not Found: Since the testing described is bench performance testing for a physical device (infusion pump), the concept of "ground truth established by experts" in the context of diagnostic imaging or clinical interpretation does not apply. The document mentions "extensive input from clinical and human factors experts" for the user interface design, but this is distinct from establishing ground truth for a test set's performance evaluation.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Information Not Found: Not applicable given the type of device and testing described.
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
- Information Not Found: This is an infusion pump, which does not involve "readers" or "AI assistance" in the sense of interpreting medical images or data. Therefore, an MRMC study is not relevant to this device.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Information Not Found: Not applicable. The device is a physical pump, not an algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- Information Not Found: For "flow accuracy and construction," the ground truth would typically be established by precise measurement instruments and engineering specifications according to recognized performance standards for infusion pumps (e.g., ISO standards), rather than clinical "ground truth" derived from patient outcomes or expert consensus on a diagnosis. The document states "performance standards for infusion pumps" were used for comparison.
8. The sample size for the training set
- Information Not Found: The device is a physical infusion pump, not a machine learning model, so there is no "training set" in the context of AI/ML.
9. How the ground truth for the training set was established
- Information Not Found: Not applicable for an infusion pump.
In summary, the provided submission focuses on physical and functional characteristics of an infusion pump and its substantial equivalence to a predicate device, rather than the type of performance study data typically associated with AI/ML diagnostic or prognostic devices as implied by many of the requested categories.
§ 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).