(282 days)
The Pulse Oximeter is a handheld non-invasive device intended for spot-checking of oxygen saturation of arterial hemoglobin (SpO2) and Pulse Rate of adult, adolescent, child and infant patients.
Respiratory rate (RR) is intended for adults only.
The Pulse Oximeter is intended for use in hospitals, hospital-type facilities and homecare environment.
The Pulse Oximeter is not intended for patients with:
- cardiopulmonary disease
- cardiac dysrhythmias, unstable patients, or patients in the ICU
- respiratory insufficiency or recovering from surgery or trauma
- morbid obesity
- severe arrhythmia
The Pulse Oximeter is not intended for patients who are:
- injured, disabled or physically deformed
- pregnant or lactating
- taking drugs that stain the blood.
The Pulse Oximeter is not designed to detect apneas.
The proposed device Fingertip Pulse Oximeter MD300CI218R is a battery powered device. It can detect and display the measured %SpO2 ,pulse rate,respiratory rate and perfusion index and will automatically power off when there is no signal for longer than 8 seconds. The proposed device is adopted colorful color OLED screen to display SpO2, PR , respiratory rate, perfusion index, and waveform which can be displayed in 2 directions. And it is designed with the battery indicator function to warn the user that the battery power mav be low.
The proposed device is a handheld non-invasive device intended for spot-checking of oxygen saturation of arterial hemoglobin (SpO2) and Pulse Rate of adult, adolescent, child and infant patients, respiratory rate (RR) for adult in hospital-type facilities and homecare environment. And it can transmit the measurements to Smart Device installed the mobile APP via Bluetooth 4.0 to help the users to organize and track their health information.
The proposed device consists of power supply module, detector and emitter LED, signal collection and processor module, display module, Bluetooth module, user interface and button control.
The fingertip pulse oximeter works by applying a sensor to a pulsating arteriolar vascular bed. The sensor contains a dual light source and photo detector. The one wavelength of light source is 660nm, which is red light; the other is 905nm, which is infrared-red light. Skin, bone, tissue and venous vessels normally absorb a constant amount of light over time. The photo detector in finger sensor collects and converts the light into electronic signal which is proportional to the light intensity. The arteriolar bed normally pulsates and absorbs variable amounts of light during systole and diastole, as blood volume increases and decreases. The ratio of light absorbed at systole and diastole is translated into an oxygen saturation measurement. This measurement is referred to as SpO2.
The proposed device is not for life-supporting or life-sustaining, not for implant.
The device is not sterile and the transducers are reusable and do not need sterilization and re-sterilization.
The device is for prescription.
The device does not contain drug or biological products.
The device is software-driven and the software validation is provided in software.
Here's an analysis of the acceptance criteria and study information for the Pulse Oximeter (K211400), based on the provided FDA 510(k) summary:
Acceptance Criteria and Reported Device Performance
The document describes the device performance in terms of accuracy for SpO2 and Pulse Rate (PR), and Mean Error and Root Mean Square (RMS) error for Respiratory Rate (RR).
| Performance Metric | Acceptance Criteria (from predicate) / Standards | Reported Device Performance (Proposed Device) |
|---|---|---|
| SpO2 Accuracy | 70%-100%, ±2%; 0-69% no definition | 70%-100%, ±2%; 0-69% no definition |
| PR Accuracy | 30bpm-99bpm, ±2bpm; 100bpm-250bpm, ±2% | 30bpm-99bpm, ±2bpm; 100bpm-250bpm, ±2% |
| RR Accuracy (Mean Error) | Not explicitly stated as acceptance criteria but implied by predicate: 1 RPM Mean Error (primary predicate) | ±1 rpm |
| RR Accuracy (RMS Error) | Not explicitly stated as acceptance criteria but implied by predicate: 3 RPM ARMS (primary predicate) | ≤ 2 |
| RR Measurement Range | 4-70 rpm (primary predicate) | 4-45 rpm |
Note: The reported device performance for SpO2 and PR is stated as "same as" or "similar to" the predicate devices in the comparison table, which indicates it meets the predicate's performance. For RR, a specific clinical study was performed.
Study Information
Here's an breakdown of the study information based on your requested criteria:
-
Sample size used for the test set and the data provenance:
- SpO2 Measurement: The summary states that clinical testing for SpO2 measurement was conducted as part of K181503 (secondary predicate device) and was not repeated for this submission, as there was no change in the SpO2 measurement function. The sample size and data provenance for the original SpO2 clinical test are not provided in this document.
- Respiratory Rate (RR) Measurement: A specific clinical test was performed for RR.
- Sample Size: 11 healthy adult volunteer subjects and 22 patients. (Total of 33 subjects)
- Data Provenance: Not explicitly stated (e.g., country of origin, retrospective/prospective), but it was a clinical test performed by "Choice" (Beijing Choice Electronic Technology Co., Ltd.), implying it was likely prospective for the purpose of this submission. No specific region or country is disclosed for the subjects.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- For SpO2: Not applicable in this submission as the clinical test data was carried over from the predicate. Information on ground truth experts for the original predicate study is not available in this document.
- For RR: The document does not specify the number of experts used or their qualifications for establishing the ground truth for the respiratory rate during the clinical test. It only states that a "clinical test" was performed and a "clinical study report was presented in Performance Testing-Clinical Study Report."
-
Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- The document does not provide information about any adjudication method used for either the SpO2 (from predicate) or the RR clinical test.
-
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 MRMC comparative effectiveness study was mentioned. This device (Pulse Oximeter) is a standalone measurement device and not described as incorporating AI for human reader assistance.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, the device itself is a standalone measurement device (algorithm only, without human-in-the-loop assistance in the sense of AI-aided diagnosis). The clinical test for Respiratory Rate directly assessed the device's performance against a reference standard in patients.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- SpO2: The type of ground truth for SpO2 from the predicate study is not specified in this document, but typically, pulse oximeter accuracy studies use fractional arterial oxygen saturation (SaO2) measured by a co-oximeter from arterial blood samples as the gold standard.
- RR: The document does not explicitly state the specific method used to establish the ground truth for respiratory rate in the clinical study. Common ground truth methods for RR measurement include manual counting by trained personnel or capnography.
-
The sample size for the training set:
- The document does not provide any information about a "training set" or "training data" for this device. This implies that the device's algorithms were likely developed and validated internally against engineering standards and potentially historical data, rather than through a separate, explicitly described machine learning training pipeline in this regulatory submission. For traditional medical devices like this, the 'training' phase might be part of the R&D and engineering design process rather than a distinct 'training set' as understood in AI/ML contexts.
-
How the ground truth for the training set was established:
- Not applicable, as no training set information is provided.
§ 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).