(27 days)
Mac-Lab:
The Mac-Lab system is indicated for use on patients of all ages when a physician determines that a patient would benefit from a hemodynamic procedure. Mac-Lab may be used in a variety of hospital and clinical settings to record hemodynamic data and measurements which may then be displayed and/or transmitted.
CardioLab:
The CardioLab system is indicated for use on patients of all ages when a physician determines that a patient would benefit from an electrophysiology procedure. CardioLab may be used in a variety of hospital and clinical settings to record electrophysiology data and measurements which may then be displayed and/or transmitted.
ComboLab:
The ComboLab system is indicated for use on patients of all ages when a physician determined that a patient would benefit from either a hemodynamic or electrophysiology procedure. Combol ab may be used in a variety of hospital and clinical settings to record hemodynamic and electrophysiology data and measurements which may then be displayed and/or transmitted.
MLCL Client Software:
The MLCL Client Software is intended for recording, documenting and/or reviewing clinical data for hemodynamic and electrophysiology procedures and may then be displayed, filtered, digitized, amplified, measured, calculated and/or transmitted for storage, analysis and viewing at distributed locations.
Mac-Lab and CardioLab are hemodynamic and electrophysiology (EP) recording systems, respectively. A third configuration, ComboLab, allows the user to access both CardioLab and Mac-Lab functions, though only one application may be accessed at a time.
These devices are used during interventional and related procedures to process, display and record hemodynamic and electrophysiology (EP) data depending on the type of procedure performed. The data is acquired and displayed real-time for multiple physiological parameters to allow the user to view the data. The data may be entered manually through the use of a dedicated keyboard/mouse/barcode scanner or acquired via procedural information devices, imaging devices and interfaced data devices, and may then be displayed, filtered, digitized, amplified, measured, and calculated.
A fourth configuration, called the MLCL Client Software, is the core Mac-Lab and CardioLab application software which is available for installation on a stand-alone workstation (i.e. outside of the Mac-Lab/CardioLab/ComboLab acquisition systems described above). The MLCL Review Software may be used to record, document, analyze, store and transmit data, including data from supported patient monitors.
Mac-Lab, CardioLab, ComboLab and the MLCL Client Software provide the ability to transmit patient data for storage, analysis and viewing at distributed locations within a clinical facility via network connectivity but may also be used stand-alone (not connected to a network).
Mac-Lab, CardioLab, ComboLab and the MLCL Client Software are not intended to be used as a patient monitor and are not intended to alert the licensed health care practitioner of a change in patient status.
The provided text is a 510(k) summary for the GE Healthcare Mac-Lab, CardioLab, ComboLab, and MLCL Client Software AltiX AI.i. This document primarily focuses on demonstrating substantial equivalence to a predicate device rather than presenting a study proving that the device meets specific acceptance criteria in the context of, for example, diagnostic performance metrics (sensitivity, specificity, AUROC).
The changes described in this 510(k) are related to:
- Introduction of a new version of the EP amplifier.
- Updates to signal filtering and gain.
- Inclusion of opSens/HAEMONETICS Diastolic Pressure Ratio (dPR™).
- Introduction of PruckaStream.
- Utilization of Barco Nexxis OR™ for video distribution.
These are technical modifications to existing systems that process and display physiological data, not an AI/ML algorithm that provides a diagnostic output requiring specific performance metrics like sensitivity or specificity. Therefore, the information requested in points 1-9 regarding acceptance criteria and a study proving the device meets them (typically relevant for AI/ML diagnostic devices) is largely not applicable in the traditional sense for this submission.
However, based on the non-clinical tests and statements, we can infer the "acceptance criteria" were met through compliance with recognized standards and internal quality processes.
Here's a breakdown of the requested information based on the provided text, indicating what is applicable and what is not:
1. A table of acceptance criteria and the reported device performance
This document does not present quantitative acceptance criteria (e.g., sensitivity, specificity, accuracy) for a diagnostic AI model, nor does it report device performance against such metrics. The "performance" described is in terms of meeting electromagnetic compatibility, safety, and functionality standards.
| Acceptance Criteria (Inferred from non-clinical tests) | Reported Device Performance (Summary of results) |
|---|---|
| Compliance with IEC 60601-1-2 Ed 4.1 (EMC) | Compliance demonstrated |
| Compliance with IEC 60601-1 Ed 3.2 (General Safety) | Compliance demonstrated |
| Compliance with IEC 60601-2-27 Ed 3.0 (ECG Safety) | Compliance demonstrated |
| Compliance with IEC 60601-2-34 Ed 3.0 (BP Monitoring Safety) | Compliance demonstrated |
| Software Quality Assurance (Risk Analysis, Requirements Reviews, Design Reviews, Unit/Integration/Performance/System Testing) | Testing and results did not raise new or different questions of safety and effectiveness than the predicate device. |
| Functionality of new features (dPR, PruckaStream, Barco Nexxis OR integration, EP amplifier updates, filtering/gain) | Functionality verified to be safe and effective, comparable to predicate. |
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
Not applicable. This device is not an AI diagnostic algorithm, so there is no "test set" of patient data in the context of evaluating diagnostic performance. The testing involved non-clinical performance and safety testing against engineering and regulatory standards.
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)
Not applicable. As this is not an AI diagnostic algorithm, there are no medical experts establishing ground truth for a test set of patient data.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable.
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
Not applicable. This is not an AI assistance device for human readers.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This device does not have a "standalone algorithm" performance as it is an integrated system for recording, displaying, and transmitting physiological data. Its function is to provide accurate data to clinicians, not to make independent diagnoses.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
Not applicable. For this type of device, "ground truth" would relate to the accuracy of signal acquisition, processing, and display against known physical inputs or validated measurement standards, rather than medical diagnostic ground truth.
8. The sample size for the training set
Not applicable. This document describes hardware and software updates to a data acquisition and display system, not a machine learning model requiring a training set.
9. How the ground truth for the training set was established
Not applicable.
Summary of the Study that Proves the Device Meets Acceptance Criteria:
The "study" described in the 510(k) submission to demonstrate device safety and effectiveness, and thus "meet acceptance criteria" for its intended purpose, is a comprehensive set of non-clinical tests and adherence to quality assurance measures.
-
Non-Clinical Tests: The device and its applications were independently tested for conformity with several voluntary standards:
- IEC 60101-1 Ed 3.2 2020-08 CONSOLIDATED VERSION (General requirements for basic safety and essential performance)
- IEC 60601-1-2 Ed 4.1 2020-09 CONSOLIDATED VERSION (Electromagnetic disturbances - Requirements and tests)
- IEC 60601-2-27 Ed 3.0 2011-03 (Requirements for the safety of electrocardiographic monitoring equipment)
- IEC 60601-2-34 Ed 3.0 2011-05 (Requirements for the safety of invasive blood pressure monitoring equipment)
- Additionally, partial applicability of IEC 80601-2-30 Ed 2.0 (Automated sphygmomanometers), IEC 80601-2-55 Second Edition (Respiratory gas monitors), IEC 80601-2-56 Second Edition (Clinical thermometers), and IEC 80601-2-61 Second Edition (Pulse oximeter equipment) was considered for specific features and functionality.
-
Quality Assurance Measures: The development process followed robust quality assurance, including:
- Risk Analysis
- Requirements Reviews
- Technical Design Reviews
- Formal Design Reviews
- Unit-level Testing (Module verification)
- Integration Testing (System verification)
- Performance Testing (Verification)
- System Testing (including Safety testing and System performance testing)
Conclusion from the Submission:
The manufacturer concluded that "The testing and results did not raise new or different questions of safety and effectiveness than those associated with the predicate device." They further determined that the proposed device is "as safe, as effective and performs as well as the legally marketed predicate device" due to these non-clinical tests, software documentation for a "Basic" level of concern, and quality system processes. No clinical studies were required to support substantial equivalence.
§ 870.1425 Programmable diagnostic computer.
(a)
Identification. A programmable diagnostic computer is a device that can be programmed to compute various physiologic or blood flow parameters based on the output from one or more electrodes, transducers, or measuring devices; this device includes any associated commercially supplied programs.(b)
Classification. Class II (performance standards).