K Number
K193350
Date Cleared
2020-04-27

(146 days)

Product Code
Regulation Number
870.2700
Panel
AN
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The Leadtek Fingertip Pulse Oximeter are intended for measuring functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate for both adults and adolescent as non-invasive spot checking in home and professional caring environment. It is designed for fingers between 0.8cm and 2.3cm (0.3 inches to 0.9 inches) and for patients during no-motion condition.

Device Description

The main function of the Leadtek Fingertip Pulse Oximeter is to measure the functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate as non-invasive spot checking. The Fingertip Pulse Oximeter determines the functional oxygen saturation of arterial hemoglobin (SpO2) by measuring the absorption of red and infrared light passing through perfused tissue. Changes in absorption caused by the pulsation of blood in the vascular bed are used to determine SpO2 reading and pulse rate. The characteristic of the device is a stand-alone device with 1 AAA Alkaline battery. It includes an OLED display screen and a warning or indicator function for abnormal readings.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text for the Leadtek Fingertip Pulse Oximeter (K193350).

Key Takeaways from the Document:

  • This device is a Fingertip Pulse Oximeter intended for non-invasive spot checking of SpO2 and pulse rate in adults and adolescents.
  • It's seeking Substantial Equivalence (SE) to a predicate device (Onyx Vantage 9590, K112843).
  • The primary performance evaluation is for SpO2 accuracy and Heart Rate (HR) accuracy.
  • The device's performance is gauged against recognized a standard: ISO 80601-2-61:2011 (Medical electrical equipment – Part 2-61: Particular requirements for basic safety and essential performance of pulse oximeter equipment).

1. Table of Acceptance Criteria and Reported Device Performance

Acceptance Criteria (Set by Standard/Regulatory Expectation for Pulse Oximeters)Reported Device Performance (Leadtek Fingertip Pulse Oximeter)
SpO2 Accuracy Range: 70% to 100%70% to 100%
SpO2 Accuracy (Arms - Root-Mean-Square): ≤ 2% (within 70%-100% range)1.72% (within 70%-100% range)
SpO2 Resolution: 1%1%
SpO2 Range: 0% to 100%0% to 100%
Heart Rate Range: 30 to 250 bpm30 to 250 bpm
Heart Rate Resolution: 1 bpm1 bpm
Heart Rate Accuracy: ±1 bpm or ±1% (whichever is greater)±1 bpm or ±1% (whichever is greater)

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

  • Sample Size: A total of 10 subjects were enrolled for the clinical evaluation.
  • Data Provenance:
    • Country of Origin: Not explicitly stated in the provided text.
    • Retrospective or Prospective: The clinical evaluation was "conducted," implying a prospective study where data was collected for this submission. The text doesn't mention the use of pre-existing data.

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

  • The document describes a clinical evaluation where SpO2 accuracy was measured against a reference method (likely arterial blood gas analysis, though not explicitly stated, this is standard for pulse oximeter accuracy studies).
  • It does not mention the use of "experts" in the sense of human readers interpreting data, as would be common for an AI/imaging device. The ground truth for pulse oximetry is derived from instrumental measurements, not human interpretation. Therefore, the concept of "number of experts" and their "qualifications" for establishing ground truth is not applicable in this context.

4. Adjudication Method for the Test Set

  • Not applicable. As noted above, the ground truth for SpO2 accuracy is typically established by invasively measured arterial oxygen saturation (SaO2) via co-oximetry, not by human adjudication of readings from the device itself.

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

  • No, an MRMC study was not done. This type of study is relevant for diagnostic imaging devices where human readers interpret images, sometimes with AI assistance. For a pulse oximeter, the core performance is algorithmic (device output) and doesn't involve human interpretation to the same degree. The study here focuses on the device's accuracy against a clinical reference standard.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

  • Yes, a standalone performance evaluation was indeed done. The clinical evaluation specifically assessed the "Leadtek Fingertip Pulse Oximeter" and its "SpO2 accuracy" and "performance results" against a reference standard. This is the direct, unassisted performance of the device's algorithm.

7. The Type of Ground Truth Used

  • The ground truth for SpO2 accuracy was established through clinical evaluation conducted in accordance with ISO 80601-2-61. This standard typically requires comparing the device's SpO2 readings with values obtained from a reference co-oximeter measuring arterial oxygen saturation (SaO2) in desaturation studies. The document states "The functional oxygen saturation (SpO2) measurements were validated in accordance with ISO 80601-2-61." and that the accuracy was "calculated using the root-mean-square (Arms)." This strongly implies direct physiological measurements from subjects desaturated to various SpO2 levels.

8. The Sample Size for the Training Set

  • The document does not mention a "training set" or "training data." This device is a traditional medical device (hardware with embedded software for signal processing and calculation), not an AI/Machine Learning model in the modern sense that typically requires a large training dataset distinct from a test set. The performance validation relies on the device itself as a complete system, built according to specified engineering principles, and then tested for accuracy and safety.

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

  • Not applicable, as no separate "training set" is described or implied for this type of device and its validation.

§ 870.2700 Oximeter.

(a)
Identification. An oximeter is a device used to transmit radiation at a known wavelength(s) through blood and to measure the blood oxygen saturation based on the amount of reflected or scattered radiation. It may be used alone or in conjunction with a fiberoptic oximeter catheter.(b)
Classification. Class II (performance standards).