Search Results

The Dolphin Medical 2100 Pulse Oximeter is intended for continuous nonitoring of functional oxygen saturation of arterial hemoglobin (SpO-) and pulse rate (measured by an SpO2 sensor).

The Dolphin Medical Pulse Oximeter Model 2100 and Accessories is a portable stand-alone device, connecting cable, and oximetry sensor(s) to noninvasively calculate the functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate for adult, pediatric and neonatal patients.

The document provided is a 510(k) summary for the Dolphin Medical 2100 Pulse Oximeter, which is a medical device regulation submission to the FDA. It outlines the product's intended use, predicate devices, and compliance with various standards. However, it does not contain the detailed study information required to answer many of your specific questions regarding acceptance criteria, device performance, sample sizes, expert involvement, and ground truth establishment.

A 510(k) summary typically focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than providing a detailed clinical study report with specific performance metrics and study design details as might be found in a clinical trial publication.

Based on the provided text, here’s what can be extracted and what cannot:

1. A table of acceptance criteria and the reported device performance

• Cannot be created. The document mentions compliance with standards like ISO 9919:1992 and EN 865:1997, and the FDA Guidance Document for Pulse Oximeters: 9/7/1992. These standards and guidance documents define the acceptance criteria for pulse oximeters (e.g., accuracy against a co-oximeter in induced hypoxia studies). However, the actual acceptance criteria values (e.g., A_rms value) and the reported device performance values against these criteria are not present in this 510(k) summary. The summary only states that the device has been "designed to comply" and implies that "additional performance validation testing has been performed," but it does not present the results of that testing or the specific acceptance thresholds.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Cannot be determined. The document mentions "additional performance validation testing" for certain sensor models but provides no details about the sample size, the nature of the test set (e.g., number of subjects, type of patients), or data provenance (e.g., country, retrospective/prospective).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Not applicable/Cannot be determined. For pulse oximeters, the "ground truth" for SpO2 accuracy is typically established by arterial blood gas analysis using a co-oximeter during controlled desaturation studies, not by human experts interpreting data. The document does not mention any role for human experts in establishing ground truth for performance testing.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• Not applicable. Adjudication methods like 2+1 or 3+1 are typically used in studies where human readers interpret medical images or data and their interpretations need to be reconciled to establish a consensus ground truth. This is not how pulse oximeter performance accuracy is determined.

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

• Not applicable. This device is a standalone pulse oximeter, not an AI-powered diagnostic tool that assists human readers. Therefore, an MRMC study comparing human reader performance with and without AI assistance is not relevant to this device.

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

• Yes, implicitly. A pulse oximeter by nature is a standalone device that provides a measurement (SpO2 and pulse rate) without human interpretation in the loop to determine the primary output. The document states its intended use is for "continuous noninvasive monitoring." The performance validation mentioned would evaluate the accuracy of this standalone measurement against a reference standard.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

• Implicitly, a reference standard for physiological measurement. For pulse oximeters, the ground truth for SpO2 accuracy is established by a reference method, typically an invasive co-oximetry measurement of arterial blood samples, often performed during controlled desaturation studies in human volunteers. The document does not explicitly state this, but it is the standard method for SpO2 accuracy testing as per relevant standards (e.g., ISO 9919, EN 865, FDA Guidance 1992 mentioned).

8. The sample size for the training set

• Not applicable/Cannot be determined. Traditional pulse oximeters use established optical principles and signal processing algorithms, not machine learning or AI that requires a "training set" in the common sense of the term. While algorithms are part of the device, they are typically developed using engineering principles and validated, not "trained" on a dataset in the way a neural network would be. The document does not mention any training set.

9. How the ground truth for the training set was established

• Not applicable. As above, the concept of a "training set" and its associated ground truth establishment is not relevant to this type of traditional medical device, particularly as described in this 510(k) summary.

Ask a specific question about this device