(30 days)
The Philips CompuRecord Peri-Operative Anesthesia Information System Software is a computer-based system which collects, processes, and records data directly from medical monitors which themselves are attached to the patients in the operating room environment.
CompuRecord is generally indicated in the peri-operative environment when the anesthetist decides to generate a paper and electronic version of the administration of anesthesia to a patient, perform a pre-operative assessment, and document (chart) nursing care in the PACU.
The name of this device is the CompuRecord® Peri-Operative Anesthesia Information System Software Release F.O
The new device is substantially equivalent to the previously cleared Philips 1. CompuRecord Software, Release D.0 marketed pursuant to K030939.
2. The modifications made to CompuRecord include the following enhancements plus non-safety related bug fixes:
Improved PAE Search Configurable Paired Events Improved Case Browser Search Document Export from Case Browser Enhanced Vitals Warning Advanced Reporting Service Dynamic Anesthesia Worklist Surgical Outcome Score
The provided text describes a 510(k) premarket notification for the Philips CompuRecord® Peri-Operative Anesthesia Information System Software Release F.0. This document focuses on demonstrating substantial equivalence to a legally marketed predicate device (Philips CompuRecord Software, Release D.0, K030939) rather than presenting a standalone study with acceptance criteria and device performance metrics in the typical sense of a clinical trial for a novel AI/ML device.
Therefore, many of the requested detailed points regarding acceptance criteria, sample sizes, ground truth establishment, expert qualifications, and specific AI/ML performance metrics are not explicitly available or applicable in this document.
Here's an analysis based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
This document does not provide a table of acceptance criteria with numerical performance targets and reported device performance metrics (e.g., sensitivity, specificity, accuracy) as would be expected for a novel AI/ML device study.
Instead, the acceptance criteria are implicit: the new device must meet "defined reliability requirements and performance claims" and demonstrate "substantial equivalence" to the predicate device. The performance is assessed through "system level tests, performance tests, and safety testing from hazard analysis."
| Acceptance Criteria (Implicit) | Reported Device Performance |
|---|---|
| Meets defined reliability requirements. | "The results demonstrate that Philips CompuRecord, Release F.0 meets all defined reliability requirements." |
| Meets defined performance claims. | "The results demonstrate that Philips CompuRecord, Release F.0 meets all... performance claims." |
| Substantial equivalence to predicate device (Philips CompuRecord Software, Release D.0, K030939). | "Test results showed substantial equivalence." |
| Functionality and reliability characteristics established with respect to the predicate device. | "Verification, validation, and testing activities establish the performance, functionality, and reliability characteristics of the new device with respect to the predicate." |
| Pass/Fail criteria for testing based on specifications cleared for the predicate device. | "Pass/Fail criteria were based on the specifications cleared for the predicate device." |
| All enhancements (Improved PAE Search, Configurable Paired Events, etc.) function as intended. | Implicitly covered by "performance and functionality characteristics." |
| Non-safety related bug fixes are successfully implemented. | Implicitly covered by "performance and functionality characteristics." |
2. Sample Size Used for the Test Set and Data Provenance
The document does not specify a "test set" in the context of clinical data for algorithmic performance. The testing described refers to system-level verification and validation. Therefore, there is no information on:
- Sample size for the test set: Not applicable in this context.
- Data provenance: Not applicable. The document refers to "system level tests, performance tests, and safety testing," which would typically involve internal testing and validation of software functionality rather than external clinical data.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications
This is not applicable to the information provided. The testing described is functional and performance testing of software, not an assessment of an AI/ML algorithm's output against expert-established ground truth from clinical data.
4. Adjudication Method for the Test Set
This is not applicable. There's no "test set" in the context of clinical cases requiring expert adjudication.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
No. The document explicitly states that the device is a "Peri-Operative Anesthesia Information System Software" with enhancements and bug fixes. It is not an AI/ML diagnostic or assistive device that would typically undergo an MRMC study to measure improvement in human reader performance.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
While "system level tests" and "performance tests" were done, these are likely functional software tests rather than a standalone performance evaluation of a predictive algorithm against clinical outcomes. The device's primary function is data collection, processing, and recording, not making autonomous decisions or diagnoses.
7. The Type of Ground Truth Used
Given the nature of the device as an information system software, the "ground truth" for its testing would be the expected functional behavior and accuracy of data collection/display as defined by its technical specifications and requirements. This would not be clinical ground truth like pathology, expert consensus, or outcomes data, but rather:
- System specifications: The software functions as designed.
- Predicate device behavior: The new software performs comparably to the previously cleared predicate.
- Hazard analysis: Safety functions are correctly implemented.
8. The Sample Size for the Training Set
This is not applicable. The device described does not appear to be an AI/ML model that requires a training set. It is a software system with programming logic.
9. How the Ground Truth for the Training Set Was Established
This is not applicable, as there is no "training set" for this type of device described.
§ 868.5160 Gas machine for anesthesia or analgesia.
(a)
Gas machine for anesthesia —(1)Identification. A gas machine for anesthesia is a device used to administer to a patient, continuously or intermittently, a general inhalation anesthetic and to maintain a patient's ventilation. The device may include a gas flowmeter, vaporizer, ventilator, breathing circuit with bag, and emergency air supply.(2)
Classification. Class II (performance standards).(b)
Gas machine for analgesia —(1)Identification. A gas machine for analgesia is a device used to administer to a patient an analgesic agent, such as a nitrous oxide-oxygen mixture (maximum concentration of 70 percent nitrous oxide).(2)
Classification. Class II (performance standards).