FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

The ViOptix Intra.Ox™ Handheld Tissue Oximeter is a sterile, cordless, batterypowered device that non-invasively estimates the percent oxygen saturation (StO2) in a volume of tissue. The device uses spatially-resolved optical measurements at four wavelengths. The device performs measurements on the patient by direct physical contact to the patient's tissue and displays the StO2 estimate on the built-in screen. The ViOptix Intra.Ox™ Handheld Tissue Oximeter is a single-use disposable constructed from biocompatible materials that can tolerate bodily fluids and other liquids such as disinfectants and marking materials.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study details for the Intra.Ox™ Handheld Tissue Oximeter, based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

Device: Intra.Ox™ Handheld Tissue Oximeter (Subject Device)
Predicate Device: T.Ox (formerly ODISsey) Tissue Oximeter

Acceptance Criterion (Bench Test)	Reported Device Performance (Bench Test)
Correlation coefficient > 0.9 for absorption coefficients measured in liquid phantoms for each of the four wavelengths.	The Intra.Ox™ devices were found to measure absorption coefficients with a high degree of correlation to actual absorption coefficients in liquid phantoms prepared with Intralipid and swine whole blood. The correlation coefficient was greater than 0.9 for each of the four wavelengths used in the devices.
Limits of agreement between Intra.Ox™ and predicate device (T.Ox) StO2% measurements to be less than ±10 percentage points over three full-scale blood desaturations.	Over three full-scale (complete oxygenation to complete deoxygenation) blood desaturations, three different Intra.Ox™ devices as compared to two T.Ox devices showed combined limits of agreement of +8.49 and -7.50 percentage points. (This meets the criterion as both are within ±10 percentage points).
Acceptance Criterion (Clinical Study)	Reported Device Performance (Clinical Study)
Not explicitly stated as a numeric criterion in the document. The aim was to demonstrate "excellent agreement in shape of the ischemic events" and "good agreement considering the physiological variances inherent between measurement sites," and that "Intra.Ox™ and T.Ox measure similar ranges of StO2 values for both healthy and compromised tissue."	There was excellent agreement in shape of the ischemic events between the Intra.Ox™ and T.Ox devices. A direct comparison with paired data showed good agreement considering the physiological variances inherent between measurement sites. The mean baseline value of 68% and mean desaturation dynamic range of 30 percentage points agrees well with literature-reported values of skin and muscle transient ischemia. Importantly, the Intra.Ox™ and T.Ox measure similar ranges of StO2 values for both healthy and compromised tissue, thus validating substantial equivalence.

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

Bench Tests: The sample size for the test set is not explicitly stated in terms of number of data points or phantom measurements. However, it mentions "three different Intra.Ox™ devices as compared to two T.Ox devices" for the agreement test, and "liquid phantoms prepared with Intralipid and swine whole blood" for the correlation test.
Clinical Study: Data from 11 subjects were analyzed.
Data Provenance (Clinical Study): The data was collected from healthy human volunteers. The country of origin is not explicitly stated, but the submission is to the US FDA, implying data collected under US regulatory standards or from a region that complies with such standards for submission. The study appears to be prospective as it involved measuring patients during "transient ischemic events."

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

The document does not mention the use of experts to establish ground truth for the test set in either the bench or clinical studies. The ground truth for the bench tests was derived from known absorption coefficients in liquid phantoms and the performance of the predicate device. For the clinical study, the ground truth was the physiological changes observed in human volunteers and the measurements from the predicate device.

4. Adjudication Method for the Test Set

The document does not describe any adjudication method used for the test set.

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, an MRMC comparative effectiveness study was not done. This device is a direct measurement device (tissue oximeter), not an AI-powered diagnostic tool requiring human interpretation. Therefore, the concept of human readers improving with AI assistance is not applicable here.

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

Yes, a standalone performance assessment was done. The entire performance testing described (both bench and clinical) evaluates the device's ability to measure StO2 independently. The clinical study compares the subject device's readings with those of the predicate device, but it doesn't involve human-in-the-loop interpretation of the device's output. The device itself provides the StO2 estimate.

7. The Type of Ground Truth Used

Bench Tests: The ground truth for absorption coefficients was established using known values from prepared liquid phantoms. For the comparative performance with the predicate, the predicate device (T.Ox) served as a reference point for "truth" in its StO2 measurements.
Clinical Study: The ground truth was essentially the physiological states of the human volunteers during induced transient ischemia, as measured by both the subject and predicate devices, and compared against "literature-reported values of skin and muscle transient ischemia." The predicate device (T.Ox) also served as a comparative ground truth.

8. The Sample Size for the Training Set

The document does not explicitly mention a separate "training set" or its sample size. This type of device (a biophysical measurement instrument) typically relies on validated physical principles and calibration, rather than machine learning models that require distinct training and test sets in the same way an AI diagnostic algorithm would. The development and internal calibration would implicitly use various data, but it's not defined as a "training set" in the context of this submission.

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

As a dedicated "training set" is not explicitly defined, the method for establishing its ground truth is also not specified. The underlying principles and calibration would be based on established physics and chemistry (e.g., spectroscopy of light absorption by oxygenated and deoxygenated hemoglobin), likely validated through laboratory experiments with known concentrations and conditions.

Summary

Regulation Number and Section

§ 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).