(33 days)
The XTRA Autotransfusion System is indicated for intraoperative recovery of blood, washing of blood collected in the postoperative period, and preoperative sequestration (with indirect patient connection). Typical clinical applications include the following surgical specialties: Cardiovascular, Orthopedics, Thoracic, Transplant Surgery, Emergency (Trauma), Neurosurgery, Obstetrics and gynecology, Urology
XTRA is an Autotransfusion System designed to recover shed blood during intraoperative and postoperative procedures and for collection of platelet poor plasma (PPP) and platelet rich plasma (PRP) in preoperative procedures. It is a software-controlled device provided with disposable and hardware elements that include the following major components: centrifuge, blood pump, automatic clamps, control and monitoring sensors, and an user interface (display panel and kevboard). The modified device is a software upgraded version (SW 1.0.2.0) of the unmodified device. Besides fixing the software bugs, the main differences introduced with the new SW upgrade consist of: change of the parameters of the Pstd intraoperative factory protocol (when a 225 mL bowl size is used for blood processing); change of the table related to hematocrit measurement. when Heparin is used as anticoagulant; addition of Sorin Group Deutschland GmbH as supplementary manufacturing site for the device. Labeling has been also generally updated.
Here's an analysis of the provided text regarding the XTRA Autotransfusion System, addressing your specific questions:
1. Table of Acceptance Criteria and Reported Device Performance
The provided text does not explicitly state specific numerical acceptance criteria for the device's performance. Instead, it focuses on demonstrating substantial equivalence to the unmodified device and compliance with "safety and effectiveness requirements" through "established performance specifications."
The performance reported is generally qualitative:
- The results of in vitro tests "met established performance specifications."
- The device is "substantially equivalent to the unmodified device in terms of safety and effectiveness."
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: Not specified. The document only mentions "in vitro testing" without detailing the number of samples or runs.
- Data Provenance: The tests were "in vitro," implying laboratory-based testing. While the submitter is Sorin Group Italia S.r.l., the location of the actual testing is not explicitly stated, although it can be inferred to be internal to the manufacturer. The data is retrospective in the sense that it was conducted on the modified device after its creation to demonstrate its performance.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
- Number of Experts: Not applicable. The "ground truth" for this device, an autotransfusion system, would typically relate to its mechanical performance, blood processing efficiency, and safety parameters (e.g., cell viability, contaminant removal). These are objective measurements determined through laboratory testing and engineering specifications rather than expert consensus on diagnostic images or clinical assessments.
- Qualifications of Experts: Not applicable.
4. Adjudication Method for the Test Set
- Adjudication Method: Not applicable. As mentioned above, the "ground truth" is based on objective in vitro measurements and engineering specifications, not on subjective interpretations requiring adjudication.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance
- MRMC Study: No. This device is an autotransfusion system, a medical device for blood processing, not an AI-assisted diagnostic tool for human readers. Therefore, an MRMC study comparing human reader performance with and without AI assistance is irrelevant and was not performed.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
- Standalone Performance: Yes, in the sense that the device's performance was evaluated based on its own operational parameters and outputs (e.g., processed blood quality) through "in vitro testing." Since it's an autotransfusion system, its primary function is automated blood processing, not providing diagnostic information that would then be interpreted by a human. The "algorithm" here refers to the software controlling the machine. The "in vitro studies" directly assess the algorithmic and mechanical performance of the device without a human in the diagnostic loop.
7. The Type of Ground Truth Used
- Type of Ground Truth: The ground truth for this device is based on objective laboratory measurements and established performance specifications for autotransfusion systems. These specifications would relate to parameters like:
- Blood processing efficiency (e.g., red blood cell recovery).
- Removal of contaminants (e.g., plasma, anticoagulant, cellular debris).
- Hemolysis levels.
- System accuracy and consistency.
- Biocompatibility, as evidenced by cross-referencing to the unmodified device and ISO standards.
8. The Sample Size for the Training Set
- Sample Size: Not applicable/Not specified. This document describes a software upgrade (SW 1.0.2.0) to an existing autotransfusion system. Such systems are traditionally developed and validated through engineering design, rigorous testing, and verification/validation activities against specifications. They are not typically "trained" in the machine learning sense with a "training set" of data to learn patterns. The software upgrade focused on fixing bugs and changing parameters, which would be part of a traditional software development lifecycle, not an AI/machine learning training process.
9. How the Ground Truth for the Training Set Was Established
- How Ground Truth Was Established: Not applicable. As explained above, there isn't a "training set" in the context of an AI-driven learning algorithm for this device. The software's "ground truth" or correct behavior is defined by its engineering specifications and the functional requirements of the autotransfusion process. Any "training" would have been in the traditional engineering sense of testing and refining the software against known correct outputs based on physical principles and established medical standards for blood processing.
§ 868.5830 Autotransfusion apparatus.
(a)
Identification. An autotransfusion apparatus is a device used to collect and reinfuse the blood lost by a patient due to surgery or trauma.(b)
Classification. Class II (performance standards).