3304 PULSE OXIMETER by BCI INTL., INC.

The 3304 provides fast, reliable SpO2, pulse rate and pulse strength measurements. It may be used in the hospital or clinical environment, during emergency air or land transport and in the home. The oximeter will operate accurately over an ambient temperature range of 32 to 104° F (0 to 40° C). The oximeter works with all BCI oximetry probes providing SpO2 and pulse rate on all patients from neonate to adult. The oximeter permits continuous patient monitoring with adjustable alarm limits as well as visible and audible alarm signals

Device Description

The new BCI 3304 pulse oximeter is an updated version of existing pulse oximeters legally marketed by BCI International. This updated device is designed to provide full featured monitoring capabilities in a light weight, transportable design. The system consists of a small table top oximeter with a wall mount charger. The system features an SpO2 probe interface, display of patient data via an LED display (SpO2, Pulse Rate, Pulse Strength), system status LEDs (Probe, Lo Batt, Silence, Alarm, Artifact, Search), and the function keypad area consisting of eight keys (O/I, ID/Clear, Up and Down Arrows, Alarm Select, Alarm Silence, Alarm Volume, Pulse Volume). The oximeter has a printer / pc port that is used for data communication, an optional analog output and an optional digital alarm adapter for a remote location.

AI/ML Overview

This document describes the BCI 3304 Pulse Oximeter, an updated version of existing pulse oximeters.

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria for pulse oximeters typically relate to the accuracy of SpO2 measurements compared to a reference standard, often expressed as a standard deviation (SD) within specific saturation ranges. While specific predefined acceptance criteria (e.g., "SD must be <= 2.0%") are not explicitly stated in the provided text, the study presents the achieved accuracy.

Performance Metric	Acceptance Criteria (Implicit/Typical for Pulse Oximeters)	Reported Device Performance
SpO2 Accuracy (70-100%)	(Implicitly, a low standard deviation is desired, typically < 2% for this range)	Standard Deviation = 1.92%
SpO2 Accuracy (50-69%)	(Implicitly, a low standard deviation is desired, typically < 3% for this range)	Standard Deviation = 2.31%
R-squared value	(Implicitly, a high R-squared value is desired, approaching 1 for good correlation)	0.978 (over the entire range)

The study aims to demonstrate that the BCI 3304 "accurately displays the patient's blood oxygen level within its accuracy limits as compared to a co-oximeter." The reported standard deviations of 1.92% for 70-100% SpO2 and 2.31% for 50-69% SpO2, along with an R-squared of 0.978, support the accuracy claims and imply that these values meet the unstated acceptance criteria.

2. Sample Size and Data Provenance

Sample Size for Test Set: The document does not explicitly state the number of subjects or data points used in the clinically controlled desaturation studies.
Data Provenance: The studies were described as "clinically controlled desaturation studies," which implies a prospective study design. The country of origin of the data is not specified.

3. Number of Experts and Qualifications for Ground Truth

The document does not mention the use of experts to establish ground truth for the test set.

4. Adjudication Method

Not applicable. The ground truth was established by a co-oximeter, not through expert consensus requiring adjudication.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not performed. This study focuses on the standalone performance of the device against a reference standard.

6. Standalone Performance Study

Yes, a standalone performance study was conducted. The device's accuracy was directly compared to a co-oximeter. This is indicated by the statement: "clinically controlled desaturation studies were done to demonstrate that the 3304 accurately displays the patient's blood oxygen level within its accuracy limits as compared to a co-oximeter (OSM-3)."

7. Type of Ground Truth Used

The type of ground truth used was comparison to a reference device (co-oximeter). Specifically, an "OSM-3" co-oximeter served as the gold standard for blood oxygen level measurements during the desaturation studies.

8. Sample Size for the Training Set

Not applicable. The BCI 3304 Pulse Oximeter is a hardware device (oximeter) and not an AI/ML algorithm. Therefore, there is no "training set" in the context of machine learning.

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

Not applicable, as there is no training set for this hardware device.

Summary

{0}------------------------------------------------

K962156

Summary of Safety and Effectiveness

Submitter:	BCI International, Inc.
Address:	W238 N1650 Rockwood DriveWaukesha, WI 53188
Telephone:	(414) 542-3100
Contact:	VP Regulatory Affairs
Prepared:	May 31, 1996
Proprietary Name:	3304 Pulse Oximeter
Common/Classification Name:	Pulse Oximeter
Predicate Devices:	BCI 3301, 3302 & 3100 Oximeters

New Device Description:

Intended Use:

{1}------------------------------------------------

Performance Data:

The design of this device utilizes currently available technology found in many legally marketed devices. Testing was done to ensure that it would perform within the environment(s) for which it is to be marketed. The testing was performed in accordance with the guidelines and standards found in the reviewers guide for respiratory devices. This testing included EMC, electrical, mechanical durability, safety (operator and patient), and temperature/humidity. The results of the testing demonstrated that the device was in compliance with the guidelines and standards referenced in the reviewers guide and that it performed within its specifications and functional requirements.

Additionally, clinically controlled desaturation studies were done to demonstrate that the 3304 accurately displays the patient's blood oxygen level within its accuracy limits as compared to a co-oximeter (OSM-3). Statistical analysis on the data collected from the studies were compared to those from a co-oximeter during the controlled subject desaturation runs. The results from the clinical studies support the accuracy claims of the device, with a standard deviation of 1.92 for the measurement range of 70-100% and 2.31 for the range of 50-69%. The R squared value was 0.978 over the entire range. (R squared - measure of how true the regression line is. R squared = 1 is a perfect fit.) On the basis of these results and the above-referenced testing it is our determination that the device is safe, effective, and performs as well as or better than the legally marketed predicate device(s).

This summary of 510(k) safety and effectiveness information is being submitted in accordance with the requirements of SMDA 1990 and 21 CFR 807.92.

Respectfully,

Donald Alexand

Donald Alexander VP Regulatory Affairs

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).