Search Results

The S/5™ Critical Care Monitor with L-ICU02 and L-ICU02A is intended for multiparameter patient monitoring.

The S/5TM Critical Care Monitor with L-ICU02 and L-ICU02A software is indicated for monitoring of hemodynamic (including arrhythmia and ST-segment analysis), respiratory, ventilatory, gastrointestinal/regional perfusion, Bispectral index (BIS), and neurophysiological status of all hospital patients. The S/5TM Critical Care Monitor with L-ICU02 and L-ICU02A software when using BIS is for monitoring the state of the brain by data acquisition and processing of electroencephalograph signals and may be used as an aid in monitoring the effects of certain anesthetic agents*. (*Gan TJ, Glass P, Windsor A, Payne F, Rosow C, Sebel P, Manberg P. Bispectral Index Monitoring Allows Faster Ernergence and Improved Recovery from Propofol, Alfertanil and Nitrous Oxide Anesthesia. Anesthesiology, October 1997; (4) 87:808-15.) The S/5TM Critical Care Monitor with L-ICU02 and L-ICU02A software is indicated for use by qualified medical personnel only.

The S/5™ Critical Care Monitor is a patient monitor, which displays the measurement of patient physiological parameters in the hospital setting. The measurement of patient physiological parameters is accomplished by specialized measurement modules which, when plugged into the frame, allow the modules to communicate with the monitor. The care giver can select from a variety of available measurements (parameters) and apply those parameters that are best suited to patient care. Modules perform the functions of parameter measurement and minor data processing. The S/5TM Critical Care Monitor displays parameters on screen, signals alarms and performs advanced data processing. There are two software options available for the S/5 Critical Care Monitor with L-ICU02 and L-ICU02A.

L-ICU02A is equipped with extended arrhythmia analysis capability. Other than arrhythmia analysis capabilities, this software option is identical to L-ICU02.

The modifications to the device are:

1. Improved Central Processing Unit Board, B-CPU5, with increased memory capability.
2. Improved Universal Peripheral Interface Board, B-UPI4NET, which is a combination of the previous B-UPI and B-NET boards.
3. Rotating of the "ComWheel" now scrolls through different trend pages.
4. Technical alarms such as "SpO2 probe off", "Leads off" (ECG), and "Px No transducer" (InvBP) transferred to the Central Station.
5. Changed to include support for alarm silencing and alarm limits adjustment from Central Station.
6. The alarm priority of "X module removed" message has been increased from note level to yellow level.
7. Software can additionally send request for recording to Central Station.
8. Standby information is additionally sent to Central Station.
9. Snapshot printing speed 25 mm/s has been added.
10. Mean Arterial Pressure value replaces O2 F1 value in vital parameters numerical trend.
11. The NMT cycle time selections have been changed to be: 20 s / 1 min / 5 min / 15 min / 30 min / 60 min / 120 min.
12. Lifetime of an old NIBP value has been changed from 60 min to 245 min.
13. Support for M-BIS (Bispectral Index) module has been added. M-BIS is the subject of a separate 510(k) premarket notification
14. Support for the M-miniC (CO2 module) module has been added. The Mini CO2 module M-miniC is the subject of a separate 510(k) premarket notification.
15. Support for the N-DIS external device interfacing modules for interfacing of the following device categories: ventilators/anesthesia machines, stand-alone monitors, blood gas analyzers and heart-lung machines has been added. The N-DIS modules is the subject of a separate 510(k) premarket notification.
16. Uses arrhythmia analysis version which has an improved vfib algorithm compared to arthythmia analysis version submitted in the predicate 510(k).

The S/5™ Critical Care Monitor with L-ICU02 and L-ICU02A uses several types of plugin measurement modules. Modules are the subject of separate 510(k)'s and are not part of this notification.

The S/5™ Critical Care Monitor with L-ICU02 and L-ICU02A is typically furnished with a module that measures BCG, invasive and non-invasive blood pressures, pulse oximerry and temperature. Modules are placed in the S/5™ monitor frame and are automatically recognized by the monitor. The patient cables are connected to the module plug in jacks and then monitoring can begin. The S/5TM Critical Care Monitor with L-ICU02 and L-ICU02A can display measurements in the form of numeric values, traces and trends. Audible and visual alarms are used to indicate patient status. The priority profile of an alarm depends on the parameter. The S/5TM Critical Care Monitor with L-ICU02 and L-ICU02A is overated by a kevboard. Typically pressing a key results in a pop up menu appearing on the screen. Selections can then be made easily from the menu using a unique ergonomically designed pointing device on the keyboard called a ComWheel™. The software L-ICU02 and L-ICU02A perform some module related tasks like arrhythmia analysis, ST-values calculation, heart rate calculation, impedance and respiration rate calculation, energy expenditure calculation, drug calculation, EEG spectrum analysis and evoked potential response averaging. All the module communication is also handled in the main software. There are various optional types of keyboards, some are like standard keyboards and another is a hand-held Remote controller (K-REMCO) which is still directly connected to the S/5TM Critical Care Monitor via a long cord but provides more flexibility in controlling the monitor while the doctor or nurse is handling other patient care needs. The S/5™ Critical Care Monitor can be in a stand-alone or networked configuration. If networked, measurements are sent to the network for central station or monitor-to-monitor viewing. Trends can also be sent via a network to a central computer for archiving.

The provided text does not contain specific acceptance criteria or a detailed study proving device performance against such criteria. Instead, it describes a Premarket Notification 510(k) Summary for a modified patient monitor, the Datex-Ohmeda S/5™ Critical Care Monitor with L-ICU02 and L-ICU02A software.

This document focuses on demonstrating substantial equivalence to a predicate device (Datex-Ohmeda CS/3™ Critical Care Monitor with S-ICU99(A) software, K000168), rather than presenting a standalone performance study with defined acceptance criteria for the new device.

The "Summary of Nonclinical Testing" section (Page 4) lists compliance with various safety standards (e.g., IEC 60601-1, ANSI/AAMI EC57). This implies that the device meets the requirements set forth in these standards, but it doesn't provide specific performance metrics or thresholds for clinical accuracy or efficacy.

Therefore, many of the requested details about acceptance criteria, specific performance numbers, sample sizes, expert involvement, and ground truth for a performance study are not available in the provided text.

Here's an analysis based on the available information:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample size used for the test set and the data provenance

• The document describes "nonclinical testing" including "software validation and verifications," and compliance with standards. It does not specify a "test set" in the context of a clinical performance study with human subjects or a dataset for evaluating an AI algorithm.
• Data provenance: Not applicable as a clinical or AI-specific dataset is not described. The testing described is primarily in vitro/bench testing for compliance with engineering and safety standards.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

• Not applicable. The document doesn't describe a study involving expert-established ground truth for performance evaluation of an AI algorithm or clinical device.
• The "compliance with standards" implies that the device's technical specifications and functional performance were verified against established norms, likely by engineers and testers, rather than clinical experts providing ground truth for diagnostic accuracy.

4. Adjudication method for the test set

• Not applicable as there is no specific "test set" and ground truth establishment process described that would require adjudication.

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 is described. This device is a patient monitor, not an AI diagnostic standalone or assistive tool in the modern sense. The "AI" mentioned in the prompt's question for this section (human readers improve with AI) is not relevant to this type of device and its submission. The closest mention of "AI" in the document is the "improved vfib algorithm," which is an internal processing algorithm, not an AI system for human reader assistance.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

• The document implies that the device, including its software and algorithms (like the "arrhythmia analysis version which has an improved vfib algorithm"), underwent "software validation and verifications." This could be interpreted as standalone testing of the algorithm's performance against specifications derived from standards or predicate device performance. However, no specific standalone performance results (e.g., sensitivity, specificity for vfib detection) are provided. The focus is on compliance and substantial equivalence rather than detailed performance reporting.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

• Not explicitly stated for performance evaluation. For compliance with standards, the ground truth would be the requirements defined by those standards (e.g., an alarm must trigger within X seconds of a simulated event, a measurement must be accurate within Y tolerance).
• For the "improved vfib algorithm," the ground truth would likely be established through a combination of simulated cardiac signals, annotated ECG databases, or comparison to established, validated arrhythmia detection methods. However, no specifics are given.

8. The sample size for the training set

• Not applicable. The document does not describe the development of a machine learning or AI model that would typically involve a "training set." The "improved vfib algorithm" is mentioned, suggesting algorithmic development and verification, but details of datasets used for its development or validation are not provided.

9. How the ground truth for the training set was established

• Not applicable, as no training set for an AI model is described.

Ask a specific question about this device