(134 days)
The ENVOY Monitor is a physiological patient monitor intended to be used for monitoring vital signs of critically ill adult and pediatric patients in the hospital environment, such as: ECG/Heart Rate, Invasive Blood Pressure, Respiration, Temperature, Noninvasive Blood Pressure, and Pulse Oximetry. The ENVOY may be used to monitor a wide range of patient conditions in many different clinical specialties within the hospital. The device is intended for use by qualified health care providers, who will determine when use of the device is indicated, based upon their professional assessment of the patient's medical condition.
ENVOY is hospital based, multiparameter patient monitor for monitoring physiological patient vital signs. The ENVOY patient monitor system consists of the following components: Main Processing Unit, Display Unit, Module Rack, Vital Signs Plug-in Modules. ENVOY vital signs modules acquire vital signs data from the patient, and display their waveforms and alarms indications on the ENVOY display unit. Vital signs and waveform information are displayed simultaneously on the ENVOY Display Unit. Up to 8 traces can be displayed at any one time. The vital signs modules interface with readily available physiologic transducers through electrically isolated patient input connections. After amplification, the signals are digitized, analyzed and displayed. All processing and alarm determination for ECG, Respiration and Invasive Blood Pressure is made using proprietary algorithms and software based on previously marketed Mennen Medical monitoring devices tested against well known and accepted data bases that present representative examples of waveform artifact to be encountered in real case conditions. SpO2 and Non-Invasive Blood Pressure Modules use sofware/hardware from vendors whose products already appearing on the USA market. Information from each vital sign is presented in a separate portion of the display. Each vital sign is labeled for identification and numeric value. Displayed Vital sign information can include: Primary Vital Sign Name, Waveform, Vital Sign Numeric Value, Alarm Status Message. Operation of the ENVOY is accomplished by interaction with front panel controls on the main processor unit. A quick-knob control allows direct interaction with displayed menus for direct parameter selection and setup. Where manual entry of alphanumeric information is required, a menu keyboard menu is display. ENVOY is a reusable, software driven, patient monitor, intended for use as part of a physiological monitoring system in a hospital environment. As such it is not a life supporting, or life sustaining device; nor is it implantable and therefore sterility is not a consideration.
This submission K974510 for the ENVOY Patient Monitor describes various validations against industry standards and the manufacturer's design specifications for different physiological parameters. However, it does not provide a table of acceptance criteria with corresponding reported device performance values in a structured format that can be easily extracted for all parameters. It also lacks detailed information on studies concerning AI assistance, multi-reader multi-case studies, or specific AI algorithms.
Here's an analysis based on the provided text, highlighting what is present and what is missing:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly provide a single, comprehensive table outlining acceptance criteria and reported device performance for all vital signs. Instead, it describes general compliance with standards and internal design specifications.
| Parameter/Aspect | Acceptance Criteria (from recognized standards or design specs) | Reported Device Performance (as stated in the document) |
|---|---|---|
| ECG/Heart Rate Response | AAMI/ANSI Cardiac Monitors, Heart Rate Meters, and Alarms Standards. | "ECG/Heart Rate response was evaluated against the AAMI/ANSI Cardiac Monitors, Heart Rate Meters, and Alarms Standards." Implicitly met, as the clinical trial for NIBP is separate. |
| Other Vital Signs | Mennen Medical's Design Specifications. | "Testing of other Vital signs was performed against Mennen Medical's Design specifications. Measurements were within published specifications." (Specific values not provided). |
| Non-Invasive Blood Pressure (NIBP) | IEC601-2-30 Requirements for automatic cycling indirect blood pressure monitoring. AAMI SP-10 Electronic or Automated Sphygmomanometers Standard. | "The performance of the ENVOY was compared against another automated non-invasive blood pressure device (Mennen Medical HORIZON XL)." "The study followed the AAMI Electronic or Automate Sphygmomanometers Standard SP-10 (Refer to Part 8 for NIBP clinical trials and results)." (Specific results are referenced to "Part 8" but not provided in the summary). |
| Pulse Oximetry | (Not explicitly stated in this summary regarding specific standard limits) | "Clinical validation studies of the Pulse Oximetry Module are present in Part 8 of the submittal." (Specific results are referenced to "Part 8" but not provided in the summary). |
| Patient Safety (Electrical) | EN60601-1 and AAMI/ANSI Safe Current Limits for Electromedical Apparatus standard. | "Patient safety was confirmed by testing EN60601-1 and AAMI/ANSI Safe Current Limits for Electromedical Apparatus standard." (Implicitly met). |
| Environmental (Flammability, Mechanical, Temp, Humidity) | IEC 601-1 requirements, IEC-68 series (2-1, 2-2, 2-3, 2-56, 2-13, 2-6, 2-36, 2-27), MIL-STD-810E. | "ENVOY complies with IEC 601-1 requirements for flammability, mechanical abuse, temperature and humidity. Environmental testing was conducted pursuant to IEC-68-2-1 (Cold), IEC-68-2-2 (Dry Heat), IEC-68-2-3 and IEC-68-2-56 (Damp heat steady state), IEC-68-2-13 (Low air pressure), IEC-68-2-6 (Vibration - sinusoidal), IEC-68-2-36 (Random vibration wide band), IEC 68-2-27 (Shock) and MIL-STD-810E." (Implicitly met). |
| EMC | IEC 601-1-2. IEC 801-1/2/3/4 and 5. EN 55011 and CISPR 16. | "EMC testing, pursuant to IEC 601-1-2. IEC 801-1/2/3/4 and 5. EN 55011 and CISPR 16 was conducted and compliance verified." (Implicitly met). |
| Software Validation | Mennen Medical's test plan protocol (verified functionality, user input/output, error recovery, hidden functionality). | "Software validation verified the functionality of the Mennen Medical ENVOY from a 'black box' approach." "The results met expectations and the software was approved for release..." (Specific quantitative metrics not provided). |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: Not explicitly stated in this summary. The text mentions "Simulated inputs were used to test the vital signs monitored by the ENVOY" and "Simulated patient waveforms were generated using a DNI Navada Inc. 217A Patient simulator and Mennen Medical simulators." For NIBP and Pulse Oximetry, it refers to "clinical trials" in "Part 8" but doesn't detail the sample size or provenance in this summary.
- Data Provenance:
- Simulated Data: For general vital signs (ECG, Respiration, Invasive BP), "proprietary algorithms and software based on previously marketed Mennen Medical monitoring devices tested against well known and accepted data bases that present representative examples of waveform artifact to be encountered in real case conditions."
- Clinical Data: For NIBP and Pulse Oximetry, "clinical validation studies" are mentioned, with results in "Part 8." The country of origin and whether data was retrospective or prospective is not specified in this summary.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
- The document does not mention the use of experts to establish ground truth for the test set explicitly. The ground truth for simulated inputs would be the known parameters set on the simulators. For the clinical studies (NIBP, Pulse Oximetry), the "ground truth" would typically come from reference devices or expert-interpreted data, but details are not provided in this summary.
4. Adjudication Method for the Test Set
- The document does not describe any adjudication method for the test set.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
- No, a multi-reader multi-case (MRMC) comparative effectiveness study is not indicated or described in this document. The device is a patient monitor, not an AI-assisted diagnostic tool for human readers.
- Effect size of human readers improving with AI vs. without AI assistance: Not applicable, as this is not an AI-assisted diagnostic device for human interpretation improvements in the context of MRMC studies.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) Was Done
- Yes, the core of the validation described for ECG/Heart Rate and "other Vital signs" (excluding SpO2 and NIBP modules that use vendor software/hardware) implicitly involves standalone algorithm performance. The device's "proprietary algorithms and software" for ECG, Respiration, and Invasive Blood Pressure were tested using simulated inputs. The performance for these parameters against AAMI/ANSI standards (for ECG/HR) and Mennen Medical's Design specifications (for others) indicates a standalone evaluation.
- It's important to note that "standalone" here refers to the device's algorithms processing data and displaying results without human intervention in the processing itself, which is standard for patient monitors. However, the clinical use always involves a human-in-the-loop (healthcare provider) to interpret the displayed information.
7. The Type of Ground Truth Used
- For ECG/Heart Rate, Respiration, Invasive BP: The ground truth came from "Simulated patient waveforms generated using a DNI Navada Inc. 217A Patient simulator and Mennen Medical simulators," and "well known and accepted data bases." This is a form of simulated data/known input ground truth.
- For Non-Invasive Blood Pressure and Pulse Oximetry: These parameters underwent "clinical validation studies" and their results are in "Part 8," implying reference device comparisons (e.g., against an established, accurate NIBP device or pulse oximeter) or potentially directly measured physiological data. The summary doesn't specify if it was pathology, outcomes data, or expert consensus for these clinical trials. Given the nature of vital sign monitoring, it's most likely comparison against a gold-standard measurement.
8. The Sample Size for the Training Set
- The document does not specify a sample size for a "training set." The proprietary algorithms for ECG, Respiration, and Invasive Blood Pressure were "based on previously marketed Mennen Medical monitoring devices tested against well known and accepted data bases." This suggests the algorithms were likely developed and refined (trained/tuned) using these historical "data bases," but the size of these databases is not provided. Modern AI/ML terminology like "training set" might not have been standard practice in medical device submissions in 1997.
9. How the Ground Truth for the Training Set Was Established
- The document states that the proprietary algorithms were "based on previously marketed Mennen Medical monitoring devices tested against well known and accepted data bases that present representative examples of waveform artifact to be encountered in real case conditions."
- This implies the ground truth for these "data bases" was established through:
- Reference device comparison: Likely, the older Mennen Medical devices and the data they collected were compared against established, validated reference measurements for physiological parameters and artifact detection.
- Expert knowledge/manual annotation: For "waveform artifact," it's highly probable that experts (e.g., cardiologists, intensivists) annotated or identified these artifacts in the "well known and accepted data bases."
- The exact methodology for establishing ground truth for these historical "data bases" is not detailed in this summary.
§ 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.