(113 days)
The Philips Hemodynamic Application is intended for use by professional healthcare providers for physiologic/ hemodynamic monitoring, medical data processing and analytical assessment.
The software may be used to display analyze surface Electrocardiogram (ECG), Respiration. Invasive Blood Pressure (IBP), Pulse Oximetry (SpO2), End Tidal CO2 (ETCO2), Fractional Flow Reserve (FFR), Instant Wave-Free Ratio (iFR), Non-Invasive Blood Pressure (NIBP), surface body Temperature and thermal Cardiac Output.
The software is intended for use with other devices, such as physiological monitoring systems, information management systems, image acquisition and other medical devices.
Use of the software in combination with physiological monitoring system is not intended to be used where unattended patient monitoring is desired, or in situations where arrhythmia detection is required.
The software in combination with an information management system provides the ability to transmit patient data files for storage, viewing and analysis at distributed locations via the intranet or internet.
The software is indicated for use in the following areas; (interventional) cardiology, electrophysiology,
The Philips Hemodynamic Application is indicated for use for all human patients of all ages.
Philips Hemodynamic Application is a new software medical device that enables invasive investigation of cardiac and vascular disease. It will be offered as an optional accessory to the Xper Flex Cardio Physiomonitoring System, (K101571). Currently, the functionality offered by the Philips Hemodynamic Application is provided by "Hemodynamic Control Software" of the currently marketed and predicate Xper Flex Cardio Physiomonitoring System.
The software connects to the patient monitor (i.e. the Xper Flex Cardio Physiomonitoring System) and during the intervention continuously acquires realtime physiological data and alarms. In addition, Philips Hemodynamic Application provides the following functionality:
- Visualize and analyze: surface ECG, Respiration rate (RR), Invasive . Blood Pressure (IBP), Pulse Oximetry (SpO2), End Tidal CO2 (etCO2), Noninvasive monitoring and recording of Non-Invasive Blood Pressure (NIBP), Body surface temperature (Tskin);
- Provide Hemodynamic calculations: Fractional Flow Reserve (FFR), Instant Wave-Free Ratio (iFR), thermal cardiac output parameters, valve area and valve gradient.
Furthermore, Philips Hemodynamic Application also interfaces with Xper Information Management (XperIM) System (K101571) which it can transfer data to for the purpose of data collection/display, processing and patient reporting.
The provided text does not contain detailed acceptance criteria or a specific study proving the device meets those criteria with numerical performance metrics. Instead, it describes non-clinical performance and validation testing that supports the device's substantial equivalence to a predicate device.
Here's an analysis based on the available information:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly present a table of acceptance criteria with corresponding performance metrics. It states: "All these tests were used to support substantial equivalence of the subject device and demonstrate that Philips Hemodynamic Application: • complies with the aforementioned international and FDA-recognized consensus standards and FDA guidance documents, and • meets the acceptance criteria and is adequate for its intended use."
It also mentions "Algorithm verification was performed using calibrated simulator tools that confirmed the algorithm was correctly implemented in the product. Results demonstrated that all executed verification tests were passed." and "In-house simulated use design validation was performed with experienced Clinical Marketing specialists that fulfill the intended user profile... As part of the validation, the implemented algorithms were evaluated as part of the workflow. Results demonstrated that all executed validation protocols were passed."
This indicates that acceptance criteria were met, but the specific numerical targets and measured performance are not detailed in this summary. The acceptance criteria seem to be binary (pass/fail) based on compliance with standards and successful algorithm implementation and workflow validation.
2. Sample size used for the test set and the data provenance:
- Test Set Sample Size: Not explicitly stated. The verification and validation activities are described qualitatively.
- Data Provenance: Not specified. The verification was done using "calibrated simulator tools," and validation involved "simulated use environment" and "in-house simulated use design validation." This suggests internal testing without specific patient data provenance mentioned.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Not explicitly stated.
- Qualifications of Experts: For usability validation, it involved "cardiologists and monitoring nurse/technicians." For in-house simulated use design validation, it involved "experienced Clinical Marketing specialists that fulfill the intended user profile." Specific years of experience or board certifications are not provided.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
Not mentioned in the document.
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:
No MRMC comparative effectiveness study involving human readers or AI assistance is mentioned. The device, "Philips Hemodynamic Application R1.0," is described as a software medical device for physiological/hemodynamic monitoring, data processing, and analytical assessment, not specifically an AI-based interpretation tool that assists human readers in diagnostic tasks in the way typically associated with MRMC studies.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
Algorithm verification was performed using "calibrated simulator tools that confirmed the algorithm was correctly implemented in the product." This could be considered a form of standalone performance assessment for the algorithms' mathematical correctness. However, it's not a standalone clinical performance study. The device is intended for use by "professional healthcare providers," implying human-in-the-loop operation.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
The document implies that the ground truth for algorithm verification was derived from the expected outputs of the "calibrated simulator tools." For validation, the "implemented algorithms were evaluated as part of the workflow" by experienced specialists, suggesting a functional ground truth based on expected performance in a simulated clinical workflow. No mention of pathology or outcomes data is made.
8. The sample size for the training set:
The document does not describe the use of a training set for machine learning. The device is presented as applying "comparable technology as implemented in the Hemodynamic Control Software module" and implementing algorithms for hemodynamic calculations, including an iFR algorithm, without indicating machine learning or AI models requiring discrete training data.
9. How the ground truth for the training set was established:
Not applicable, as no training set for machine learning is mentioned.
§ 870.2300 Cardiac monitor (including cardiotachometer and rate alarm).
(a)
Identification. A cardiac monitor (including cardiotachometer and rate alarm) is a device used to measure the heart rate from an analog signal produced by an electrocardiograph, vectorcardiograph, or blood pressure monitor. This device may sound an alarm when the heart rate falls outside preset upper and lower limits.(b)
Classification. Class II (performance standards).