(54 days)
The Spacelabs Medical Multiparameter Module 91496 is intended for use with the PCMS to acquire, monitor and process various clinical parameters from adult or neonatal/infant populations in any type of clinical environment other than home use. Physiologic parameters that may be monitored include cardiac activity, respiration, invasive and noninvasive blood pressure, temperature, oxygen saturation (SpO2), and cardiac output. Acquired data may then be communicated to an information network for display, recording, editing and analysis.
Patient conditions indicated by abnormalities in various physiologic parameters, including ECG waveform, respiratory effort, invasive and noninvasive blood pressure measurements, temperature, cardiac output, and pulse oximeter (SpO2) readings. Prescription use only.
The Spacelabs Medical Multiparameter Module 91496 with Option M is a slim, lightweight singular modular unit that, when used in conjunction with a Spacelabs Medical Patient Care Management System (PCMS), provides the capability to acquire various common physiologic data in a clinical setting.
The Module 91496 is the primary interface to the patient being monitored. The Module 91496 is capable of acquiring and processing ECG, respiration, invasive and noninvasive blood pressure, temperature, cardiac output and SpO2 parameters for a single patient. The Module 91496 accumulates the patient physiological data of interest and provides both waveform and digital data to a Spacelabs Medical PCMS monitor via SDLC communications. The PCMS monitor will provide the display capabilities for the care provider.
Option M utilizes Masimo SET oximetry and sensors and SET-compatible adapter cables.
This 510(k) summary does not contain the level of detail necessary to answer all sections of your request comprehensively. The document focuses on demonstrating substantial equivalence to predicate devices rather than providing a detailed report of a new clinical study with specific acceptance criteria, sample sizes, and expert adjudications.
However, based on the information provided, here's what can be extracted and inferred:
1. A table of acceptance criteria and the reported device performance
The document does not explicitly state quantitative acceptance criteria or detailed device performance metrics in a tabular format. The "Test Discussion" states that the device was "validated through rigorous testing that, in part, supports the compliance of the Module 91496 to applicable standards." However, it does not specify what those standards are or what performance thresholds were met.
For the SpO2 component, it claims "The Spacelabs Medical Multiparameter Module 91496 with Option M is...substantially equivalent...to the Masimo SET Rad-5 Oximeter with regard to SpO2 analysis." This implies that the performance of the SpO2 Option M is considered acceptable if it matches that of the predicate Masimo SET Rad-5 Oximeter.
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
This information is not provided in the document. The general statement "validated through rigorous testing" does not include details on sample sizes or data provenance.
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)
This information is not provided in the document. Given that this is a hardware device for monitoring physiological parameters, the "ground truth" would likely come from established medical testing methods or reference devices, not necessarily expert consensus on interpretations of images/signals.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
This information is not provided 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
This is not applicable to this submission. The device is a "Multiparameter Module 91496 with SpO₂ Option M" which is a physiological monitoring device, not an AI-powered diagnostic tool for human readers. Therefore, an MRMC study related to AI assistance for human readers would not be performed for this type of medical device.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
A "standalone" performance study in the context of an algorithm's classification or diagnostic ability is not directly applicable here. The device itself is a standalone monitoring unit that acquires and processes physiological data. Its performance would be evaluated based on the accuracy and reliability of its measurements compared to reference standards. The document states it was "validated through rigorous testing" and that "the software for the Module 91496 was developed following a robust software development process and was fully specified and validated," suggesting that the device's inherent performance was tested. However, specific details of this "standalone" performance (in terms of metrics like sensitivity, specificity, accuracy for a classification task) are not provided, as its function is primarily measurement rather than a diagnostic classification by an algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
The document does not explicitly state the specific type of ground truth used. For physiological monitoring devices like this, ground truth would typically be established by:
- Reference standard devices: Comparing the device's measurements (ECG, NIBP, SpO2, etc.) to highly accurate, calibrated reference instruments.
- Physical simulators/phantoms: For some tests, artificial signals or physical models simulating human physiology might be used.
- Clinical observation/measurements: For some parameters, direct clinical measurements might serve as a reference.
8. The sample size for the training set
This information is not provided. As this is a hardware device with embedded software for signal processing and measurement, it's unlikely to have a "training set" in the sense of modern machine learning algorithms that learn from vast datasets. The software development process likely involved traditional engineering validation and verification using test data, not a "training set" for an AI model.
9. How the ground truth for the training set was established
This information is not provided and is likely not applicable given the nature of the device (see point 8).
§ 870.1025 Arrhythmia detector and alarm (including ST-segment measurement and alarm).
(a)
Identification. The arrhythmia detector and alarm device monitors an electrocardiogram and is designed to produce a visible or audible signal or alarm when atrial or ventricular arrhythmia, such as premature contraction or ventricular fibrillation, occurs.(b)
Classification. Class II (special controls). The guidance document entitled “Class II Special Controls Guidance Document: Arrhythmia Detector and Alarm” will serve as the special control. See § 870.1 for the availability of this guidance document.