K Number
K982969
Date Cleared
1999-08-12

(352 days)

Product Code
Regulation Number
868.1400
Panel
AN
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The NONIN® Pulse Oximeter and Carbon Dioxide Detector (Model 9840-Series) is indicated for use in measuring and displaying functional oxygen saturation of arterial hemoglobin (SpO2), pulse rate, and approximate carbon dioxide (CO2) changes in the airway of intubated patients. These functions may be used separately or simultaneously.

Device Description

The NONIN® Pulse Oximeter and Carbon Dioxide Detector (Model 9840-Series), is a hand-held, battery-operated, noninvasive monitoring device that has visual and audible indicators for tracking patient status. Each Pulse Oximeter and Carbon Dioxide Detector model performs similar basic functions, but each model has been customized to meet the needs of different demands placed upon the health care professional. Each model of the NONIN® Models 9840-Series has informational tones, (along with visible indicators) to alert healthcare providers to patient conditions. However only Model 9845 and Model 9847 have an high priority "absence-of-breath" (apnea) audible alarm. The Model 9843 indicates that there is an "absence-of breath" by the cessation of the information tone, the breath-beep indicator. Model 9845 and Model 9847 have medium priority (equipment) alarm that either indicates that the batteries have reached a critically low power state or that a CO2 sensor alarm condition is occurring. The Model 9843 indicates a low battery condition by an illuminated low battery indicator. Model 9847 has a high priority (patient) alarm to alert the healthcare provider to "absence of breath" (apnea), a high or low oxygen saturation, a high or low pulse rate or inadequate pulse quality conditions. Audible alarms can be "permanently" or "temporarily" disabled using the audible alarm disable switch on Model 9845 and Model 9847.

AI/ML Overview

The provided 510(k) summary for the NONIN Pulse Oximeter and Carbon Dioxide Detector (Model 9840-Series) offers limited detail on specific acceptance criteria and the comprehensive study methodologies for performance validation. While it states that "Field evaluations have confirmed the accuracy of the Carbon Dioxide Detector in a controlled clinical environment," it does not provide the detailed information requested in the prompt.

Here's a breakdown of the available information and what is missing based on the prompt's requirements:


1. Table of Acceptance Criteria and Reported Device Performance:

The document broadly states that the device's performance was confirmed through "Field evaluations" and "extensive software/hardware verification and validation procedures." However, it does not provide a table with specific acceptance criteria (e.g., accuracy ranges for SpO2, pulse rate, or CO2 measurements) and the corresponding reported device performance against those criteria.

Acceptance CriteriaReported Device Performance
Not provided.Not provided.
(e.g., SpO2 accuracy: ±2% between 70-100%)(e.g., "The field evaluations confirmed SpO2 accuracy within ±1.5% for 95% of measurements.")
(e.g., CO2 accuracy: ±3 mmHg)(e.g., "CO2 measurements were within ±2.8 mmHg of reference standard in clinical settings.")

2. Sample Size for the Test Set and Data Provenance:

The document mentions "Field evaluations" in a "controlled clinical environment."

  • Sample Size for Test Set: Not specified.
  • Data Provenance (e.g., country of origin, retrospective/prospective): Not specified. We only know it was a "clinical environment" but not if it was prospective, retrospective, or where it took place.

3. Number of Experts Used to Establish Ground Truth and Their Qualifications:

This information is not provided in the summary. While a "controlled clinical environment" implies medical oversight, it doesn't detail the role or number of experts involved in establishing ground truth.


4. Adjudication Method for the Test Set:

This information is not provided.


5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done:

No, an MRMC comparative effectiveness study is not mentioned. Pulse oximeters and CO2 detectors are typically standalone measurement devices, and the concept of human readers "improving with AI vs. without AI assistance" does not directly apply to the primary function of these devices as described. The device provides direct physiological measurements, not interpretations that would typically be augmented by AI for human readers.


6. If a Standalone (Algorithm Only) Performance Study Was Done:

The "Field evaluations" implicitly relate to the standalone performance of the device in a clinical setting. The "extensive software/hardware verification and validation procedures" also confirm a standalone evaluation of the algorithm and hardware. However, specific details of a standalone study, such as the methodology or specific results, are not explicitly described beyond the general statement of validation.


7. The Type of Ground Truth Used:

The document states, "Field evaluations have confirmed the accuracy of the Carbon Dioxide Detector in a controlled clinical environment." This implies that the ground truth for the CO2 detector was established using a reference standard or another validated method in a clinical setting (e.g., a laboratory-grade capnograph, blood gas analysis for oxygen saturation). However, the specific type of ground truth (e.g., expert consensus vs. pathology vs. outcomes data) is not explicitly detailed. For SpO2, historically, pulse oximeter validation involves human desaturation studies with co-oximetry as the ground truth. This is not mentioned here.


8. The Sample Size for the Training Set:

This information is not applicable/provided as the device is a medical measurement instrument. It's not an AI/ML-based diagnostic system that typically requires a distinct "training set" in the conventional sense. The "training" for such devices refers to internal calibration and design optimization rather than learning from labeled data sets.


9. How the Ground Truth for the Training Set Was Established:

This information is not applicable/provided for the reasons stated above.

§ 868.1400 Carbon dioxide gas analyzer.

(a)
Identification. A carbon dioxide gas analyzer is a device intended to measure the concentration of carbon dioxide in a gas mixture to aid in determining the patient's ventilatory, circulatory, and metabolic status. The device may use techniques such as chemical titration, absorption of infrared radiation, gas chromatography, or mass spectrometry.(b)
Classification. Class II (performance standards).