(30 days)
The CARESCAPE ONE is both a multi-parameter physiological patient monitor and an accessory to a multi-parameter patient monitor intended for use in multiple areas and intra-hospital transport within a professional healthcare facility.
The CARESCAPE ONE is indicated for the monitoring of hemodynamic (including ECG, ST segment, arrhythmia detection, invasive pressure, non-invasive blood pressure, SpO2, pulse rate, and temperature), and respiratory (impedance respiration and CO2 airway gas) physiological parameters.
The CARESCAPE ONE can be used as a standalone monitor. In this mode of operation, the CARESCAPE ONE provides ECG, ST segment, arrhythmia detection, invasive pressure, non-invasive blood pressure, SpO2, pulse rate, temperature, impedance respiration, and CO2 airway gas parameter acquisition and monitoring.
The CARESCAPE ONE can be connected as an accessory to a compatible CARESCAPE monitor. In this mode of operation, the CARESCAPE ONE provides ECG, ST segment, arrhythmia detection, invasive pressure, non-invasive blood pressure, SpO2, pulse rate, temperature, impedance respiration, and CO2 airway gas parameter acquisition. Visual and audible alarms, user controls, and user interface on the CARESCAPE ONE are not active in this mode.
The CARESCAPE ONE is indicated for use on adult, pediatric, and neonatal patients and on one patient at a time.
The CARESCAPE ONE is indicated for use under the direct supervision of a licensed healthcare practitioner, or by personnel trained in the proper use of the equipment in a professional healthcare facility.
Contraindications for using CARESCAPE ONE: The CARESCAPE ONE is not intended for use within a controlled MR environment.
CARESCAPE ONE, with CARESCAPE Software version 3 belongs to the CARESCAPE V3 patient monitor family. The concept of the CARESCAPE ONE is to provide a flexible bedside monitor that can also be used during intra-hospital transport. The flexibility of the CARESCAPE ONE allows the user to configure the monitor's vital sign acquisition for only the parameters they require. This is achieved using plug and play Active Cable Modules (ACM) that connect via medical grade USB ports on the CARESCAPE ONE monitor. Note that the USB ports are not compatible with commercial USB items on the market due to a custom connector design. Each ACM is dedicated to measuring a particular vital sign, currently we have ECG/Respiration, Invasive Blood Pressure, Temperature, SpO2, or CO2. The only exception is the Non-Invasive Blood Pressure (NIBP) measurement which does not require a separate ACM since the capability to measure NIBP is built-in to the CARESCAPE ONE monitor itself. CARESCAPE ONE provides the users the acquired display values, waveforms, alarms and status messages in compact footprint monitor that runs on an internal battery as well as AC power when connected to the docking station.
When connected to a compatible host monitor, CARESCAPE ONE operates as an acquisition device. In this mode, the CARESCAPE ONE screen and user interface is effectively disabled and it transmits data received from the Active Cable Modules to the host monitor, which is responsible for managing clinical configuration settings, and displaying values, waveforms, alarms, and status messages.
The provided text is a 510(k) Pre-Market Notification for the GE Healthcare CARESCAPE ONE device. It describes the device, its intended use, and argues for its substantial equivalence to a predicate device (K190008, also CARESCAPE ONE).
However, the document does not describe a study that proves the device meets specific acceptance criteria in the way typically expected for an AI/ML medical device (e.g., performance metrics like sensitivity, specificity, or AUC for an algorithm). Instead, this document focuses on demonstrating substantial equivalence to a previously cleared device. The "study" mentioned is primarily focused on compliance with updated medical standards and the ability of the device to function as an acquisition module when connected to a host monitor, rather than a clinical performance study of a novel algorithm against pre-defined acceptance criteria.
Specifically, the document states:
- "Clinical studies of the CARESCAPE ONE device performance were not required to establish substantial equivalence." (Page 14)
- The only "clinical study" mentioned ("U-TruSignal SpO2, Testing in Neonates") is related to a component (GE TruSignal sensors) and is described as an update to older data to ensure compliance with a specific FDA guidance for pulse oximeters, not a general performance study of the CARESCAPE ONE itself or its new features. It explicitly states there is "no change to the GE TruSignal Parameter active cable module in hardware, software or pulse oximetry algorithm, or in the sensors used compared to the predicate CARESCAPE ONE (K190008)."
Therefore, based on the provided text, I cannot extract information regarding a study that proves the device meets acceptance criteria in terms of algorithmic performance against a defined ground truth using a test set, expert consensus, etc. The submission's focus is on demonstrating safety and effectiveness through substantial equivalence and compliance with relevant standards.
Therefore, many parts of your request cannot be answered directly from the provided text.
Here's what can be extracted and inferred, with limitations noted:
1. A table of acceptance criteria and the reported device performance
The document does not provide a table of acceptance criteria for algorithmic performance, nor does it present "reported device performance" in terms of specific diagnostic or predictive metrics (e.g., sensitivity, specificity, accuracy). The acceptance criteria for this submission are focused on demonstrating substantial equivalence to a predicate device and compliance with updated industry standards.
The table on pages 8-9 compares the new CARESCAPE ONE to the predicate CARESCAPE ONE (K190008) across various specifications. The "Discussion of Differences" column implicitly reflects the "performance" relative to the predicate, often stating "Identical" or "Equivalent". For example, for "Medical Standards," the acceptance criterion would be compliance with the listed standards, and the reported performance is that it complies with newer editions. For "Monitored Parameters" and "EK-Pro arrhythmia detection algorithm," the performance is that they are "Identical" to the predicate.
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Test Set Sample Size: Not applicable in the context of an algorithmic performance test. The clinical study mentioned "U-TruSignal SpO2, Testing in Neonates" used "convenience samples collected in neonatal patients." The exact sample size is not stated in this document.
- Data Provenance: Not specified for the "U-TruSignal SpO2, Testing in Neonates" study. It's noted as a clinical study, implying prospective data collection, but no further details are given.
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. The document does not describe a study involving expert readers or establishing ground truth for an AI algorithm. The mentioned "clinical study" pertains to pulse oximetry sensor performance, which typically relies on arterial blood gas measurements for ground truth, not expert adjudication in the traditional sense of image interpretation.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable. No expert adjudication method is described.
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. The document explicitly states: "Clinical studies of the CARESCAPE ONE device performance were not required to establish substantial equivalence." This type of MRMC study is not mentioned or implied.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Not applicable in the context of a new AI algorithm. The device incorporates existing algorithms (like EK-Pro arrhythmia detection V14) which were part of the predicate device and are stated to be "identical." The type of "performance" testing done was bench testing and verification of compliance with updated standards.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
For the "U-TruSignal SpO2, Testing in Neonates" study, the ground truth for pulse oximetry studies typically involves direct arterial blood gas measurements (SaO2), considered the "gold standard" for oxygen saturation. The document mentions compliance with "Pulse Oximeters - Premarket Notification Submissions [510(k)s], Guidance," which outlines the ground truth methodology for such devices.
8. The sample size for the training set
Not applicable. This submission is not about a new AI/ML algorithm that requires a training set. The device utilizes existing algorithms.
9. How the ground truth for the training set was established
Not applicable. As above, this document does not describe a new AI/ML algorithm requiring a training set with established ground truth.
§ 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.