(109 days)
Sapphire Primary Sets are indicated for the delivery of fluids from a container to a patient's vascular system.
Sapphire Blood Sets are indicated for the delivery of fluids including but not limited to blood and blood products to a patient's vascular system.
Sapphire Epidural Sets are indicated for the delivery of fluids from a container to a patient's epidural space.
Sapphire Sets are intended for use with the Sapphire Infusion System. Sapphire sets are comprised of various components including the following: male luer adapter with cap, female luer with cap, piercing pin connector, sapphire cassette, tubing, flow control device, filter, in-line adapter, injection site assembly, check valve, pressure activated valve and blood chamber. Sapphire sets are configured to ensure the intended use of the device is met. The sets are disposable devices for single patient use.
The provided text describes the 510(k) summary for "Sapphire Sets," which are administration sets intended for use with the Sapphire Infusion System. This document focuses on demonstrating substantial equivalence to predicate devices for regulatory approval, rather than detailing the performance of an AI/ML-driven medical device. Therefore, a direct answer to the request regarding acceptance criteria and study proving performance for an AI/ML device, as outlined in the prompt, cannot be fully provided from this document.
The document discusses non-clinical tests for the infusion set components, assuring their material and functional integrity, and their compatibility with the Sapphire Infusion System. It does not refer to AI/ML device performance or associated studies like MRMC or standalone algorithm performance.
However, I can extract information related to the closest aspects from the document:
1. Table of acceptance criteria and reported device performance:
The document doesn't provide a typical "acceptance criteria vs. reported performance" table like one would expect for an AI/ML algorithm with metrics like sensitivity, specificity, or AUC. Instead, it lists the types of non-clinical tests performed to demonstrate that the new Sapphire Sets perform as intended and meet applicable standards, confirming they are "acceptable."
| Acceptance Criteria (Applicable Test Requirements) | Reported Device Performance |
|---|---|
| Material Testing (Biocompatibility) | |
| ISO 10993-4 Hemocompatibility | Met (All testing is acceptable) |
| ISO 10993-5 Cytotoxicity | Met (All testing is acceptable) |
| ISO 10993-10 Sensitization/Intracutaneous Irritation | Met (All testing is acceptable) |
| ISO 10993-11 Systemic Toxicity/Subacute Toxicity | Met (All testing is acceptable) |
| Pyrogenicity | Met (All testing is acceptable) |
| Functional Performance Testing | |
| ISO 8536-4.6.1 Particulate Contamination | Met (All testing is acceptable) |
| ISO 8536-4.6.2 Leakage | Met (All testing is acceptable) |
| ISO 8536-8.6.3 (Leakage) | Met (All testing is acceptable) |
| ISO 8536-4.6.3 Tensile Strength | Met (All testing is acceptable) |
| ISO 8536-4.6.4 Coring | Met (All testing is acceptable) |
| ISO 8536-4.6.9 Flow Regulator | Met (All testing is acceptable) |
| ISO 1135-4.5.8 Flow Regulator | Met (All testing is acceptable) |
| Flow rate accuracy testing with Sapphire Infusion System | Met (All testing is acceptable) |
| Sterility Assurance | |
| Sterility Assurance Level (SAL) | 10^-6 |
2. Sample size used for the test set and the data provenance:
This document does not specify a "test set" in the context of an AI/ML algorithm validating against a dataset. The testing described is for physical properties and functionality of medical device components. The document implies laboratory testing of device samples. Data provenance (country of origin, retrospective/prospective) is not relevant to this type of device submission.
3. Number of experts used to establish the ground truth for the test set and qualifications of those experts:
Not applicable. Ground truth for an AI/ML algorithm involving expert review is not relevant to the physical and functional testing of an infusion set.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
Not applicable. This is not an image-based or diagnostic AI/ML device where adjudication methods for ground truth would be used.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done:
No. This type of study is for evaluating human performance (e.g., radiologists) with and without AI assistance, which is not applicable to an infusion set.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
No. This document is not about an AI/ML algorithm.
7. The type of ground truth used:
The 'ground truth' for the Sapphire Sets relates to established engineering standards (e.g., ISO standards for material properties, leakage, tensile strength, flow rate accuracy) and biological safety tests. It's based on objective, quantitative measurements and adherence to recognized industry standards, rather than expert consensus on diagnostic interpretations or clinical outcomes in the way an AI/ML model's performance would be assessed.
8. The sample size for the training set:
Not applicable. This document is not about an AI/ML algorithm.
9. How the ground truth for the training set was established:
Not applicable. This document is not about an AI/ML algorithm.
In summary: The provided document is a 510(k) premarket notification for a medical device (infusion sets) demonstrating substantial equivalence to predicate devices, primarily through engineering and material testing, and compliance with established standards. It does not describe the evaluation of an AI/ML medical device as outlined in the prompt's detailed questions.
§ 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).