Search Results

The Dolphin Medical Stand-Alone Pulse Oximeter, Model No. 2100 and Accessories are indicated for the continuous noninvasive monitoring of functional oxygen saturation of arterial hemoglobin (SpO₂) 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 monitor consists of a screen that displays the pulse plethysmographic waveform, the pulse rate, SpOz value, the high and low SpO2 and pulse rate alarms, trends and status messages. It contains the electronic hardware and software that receives and calculates the signals from the LEDs within the sensor to determine the functional oxygen saturation of arterial hemoglobin (SpO-) and pulse rate, and provide for the connection to the connecting cable. The Dolphin Medical Pulse Oximeter Model 2100 is available in one configuration as a portable standalone oximeter that is 10 cm / 3.94 inches high, 27.5 cm / 10.83 inches wide, 25 cm / 9.84 inches deep and weighs about 4 kg / 8,8 lbs. The unit is powered either with a voltage input of 100-240 Vac. 50-60 Hz or with a sealed lead-acid battery with an operating time of approximately 4 hours based upon 2 Ampere hour battery (200mA OEM Module) and a charge time of about 4,5 hours to 80% capacity. The extension cable connects between the monitor and oximetry sensor(s) and transfers LED drive power and the calibration drive to the oximetry sensor from the monitor receives the detector signal from the oximetry sensor. The extension cable is available in one configuration and is approximately 8 feet / 2.44m in length, and the sensor(s) are approximately 18 inches / 45.72 cm in lenath. The sensor(s) measure light absorption of blood from two light emitting diodes (LED's). Oxygen saturated blood absorbs light differently as compared to unsaturated blood. The amount of light absorbed by the blood is used to calculate the ratio of oxygenated hemoglobin to total hemoglobin in arterial blood, The oximetry sensor is available in either a disposable configuration, and with one configuration for the extension cable (8 feet).

The Dolphin Medical 2100 Pulse Oximeter and Accessories were evaluated for continuous noninvasive monitoring of functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate. The information provided heavily emphasizes regulatory compliance and substantial equivalence to previously marketed devices, rather than a detailed standalone performance study.

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

Based on the provided text, specific numerical acceptance criteria and direct reported performance metrics (e.g., accuracy +/- X%) are not explicitly stated. However, the document refers to compliance with several standards, including FDA Guidance Document for Pulse Oximeters: 9/7/1992 and EN 865:1997. These standards typically define accuracy requirements for pulse oximeters. Without access to the specific content of these standards and the detailed testing reports, precise numerical acceptance criteria cannot be extracted.

Implicit Acceptance Criteria (based on standards listed):

• Accuracy for SpO2: Based on the FDA Guidance Document for Pulse Oximeters, this would typically involve a root mean square (Arms) difference between the pulse oximeter reading and a co-oximeter reference within a specified range (e.g., ±2% or ±3% for 70-100% SpO2 in adults, and potentially different for neonates).
• Accuracy for Pulse Rate: Typically defined as a range of difference (e.g., ±3 bpm or ±2% of reading) compared to an ECG reference.
• Performance in Motion and Low Perfusion: Testing would ensure the device maintains accuracy under these challenging conditions, again with specified accuracy limits.
• Safety and EMC Standards Compliance: As indicated by compliance with a long list of IEC, CSA, UL, and other standards.

Reported Device Performance:
The document states: "Additional performance validation testing has been performed for the 560 neonatal disposable sensor and has been included in this submission." However, the results of this testing, including specific accuracy figures or performance data, are not provided in this summary. The document primarily asserts "substantial equivalence" to predicate devices, implying that its performance meets the level demonstrated by those devices, which would have adhered to the same general performance standards.

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

The document does not specify the sample size for any test set or the data provenance (e.g., country of origin, retrospective/prospective nature) for the performance validation testing mentioned for the neonatal sensor.

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)

Given that this is a pulse oximeter, ground truth for performance testing is typically established using a co-oximeter for SpO2 and an ECG device for pulse rate, rather than human experts interpreting data. The document does not mention human experts being used to establish ground truth for performance testing. If studies involved human subjects, medical professionals would be involved in monitoring, but not typically in "establishing ground truth" in the way an expert panel would for image interpretation.

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

Not applicable, as ground truth is established by objective measurement devices (co-oximeter, ECG) rather than human interpretation requiring adjudication.

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 medical device (pulse oximeter) for direct measurement, not an AI-assisted diagnostic tool that would involve human readers or image interpretation.

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

Yes, the device is intrinsically standalone. A pulse oximeter provides direct measurements (SpO2 and pulse rate) without requiring human interpretation of complex outputs in the way an AI-driven image analysis system would. The performance validation testing would be on the algorithm's ability to accurately calculate these parameters based on the sensor's optical signals. The document implicitly supports this by stating it "receives and calculates the signals from the LEDs within the sensor to determine the functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate".

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

For pulse oximeters, the accepted gold standard (ground truth) for SpO2 accuracy is typically:

• Co-oximetry: Direct measurement of arterial oxygen saturation (SaO2) from arterial blood samples using a laboratory co-oximeter. This is usually performed during a "hypoxia study" where subjects' oxygen levels are carefully lowered.
• Electrocardiogram (ECG): For pulse rate, an ECG device is the gold standard.

The document refers to "performance validation testing" and compliance with standards like the "FDA Guidance Document for Pulse Oximeters: 9/7/1992" and "EN 865: 1997", both of which mandate the use of co-oximetry and ECG for establishing ground truth during such studies.

8. The sample size for the training set

The document does not provide any information regarding a training set sample size. Given this is a 510(k) submission for a traditional medical device (pulse oximeter), the concept of a "training set" in the context of machine learning algorithms is likely not directly applicable in the way it would be for AI/ML-driven devices. While the device contains electronic hardware and software, the development process might involve calibration and optimization using engineering data rather than a distinct "training set" as defined for AI models.

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

As there is no mention of a distinct "training set" in the context of AI/ML, this information is not provided. For traditional medical device development, internal validation and calibration would occur using established measurement methods, but the document does not elaborate on these details.

Ask a specific question about this device