Search Results

The OxyMinder is intended for continuous monitoring of the concentration of oxygen being delivered to patients ranging from newborns to adults. This device can be used in the hospital and subacute settings. The monitor is not intended as a life supporting device or for diagnostics.

The OxyMinder is an air / oxygen blender mounted oxygen monitor capable of measuring the oxygen concentration from 18 to 100%. A Bio-Med specified oxygen sensor mounted to the blender outputs a voltage which is used by the OxyMinder to determine the concentration of oxygen. The OxyMinder calibrates at ambient air (21%) and 100% oxygen. The OxyMinder is software controlled. To measure the gas mixture of the blender the OxyMinder takes a sample of the gases to the sensor through a separate port and manifold which is separate from the gas pathway to the patient. This sample is then exhausted to the room. The OxyMinder sampling stream is not part of the gas pathway to the patient.

The OxyMinder is used for continuous monitoring of the concentration of oxygen delivered to patients via air oxygen blenders. The monitor provides the following features:

• Continuously displays the concentrated Oxygen level delivered to a patient.
• Accepts user inputs via touch screen or button (power button).
• Provides visual alarm messages, and audible alarms.
• Displays the current alarm setting levels (High and Low O2 alarms).
• Provides on-screen configuration tools such as O2 sensor calibration, touchscreen calibration, audio test, etc.
• Monitors and displays the battery level and power source.
• Ensures clean hospital airlines by automatically purging system periodically.

The OxyMinder is designed to be mounted to a Bio-Med Devices air / oxygen blender via a manifold that houses the oxygen sensor and a solenoid.

In addition to the primary function of monitoring oxygen concentration, the OxyMinder provides an automatic gas supply line purge function.

The provided text is related to a 510(k) premarket notification for the "OxyMinder" device, an oxygen gas analyzer. It describes the device, its intended use, and compares it to a predicate device (Maxtec MaxO2ME). The document states that "A series of non-clinical performance / bench testing was performed" and lists the types of tests, concluding that "The test results met the applicable standards and are similar to the reported performance of the predicate device." However, the document does not provide detailed acceptance criteria or the specific results of these tests. It only broadly states that the performance was similar to the predicate and met applicable standards.

Therefore, many of the requested details about the study cannot be extracted from this document.

Here's a summary of what can be inferred or explicitly stated:

Acceptance Criteria and Reported Device Performance

Study Details:

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

   • The document mentions "a series of non-clinical performance / bench testing" but does not specify the sample size for any of these tests nor the data provenance. It implies laboratory testing rather than patient data.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Not applicable/Not provided. The testing appears to be bench/performance testing against specifications and standards, not expert-adjudicated clinical data.

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

   • Not applicable/Not provided.

4. 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 or human-in-the-loop study was done or mentioned. This is a standalone oxygen analyzer, not an AI-assisted diagnostic tool.

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

   • Yes, performance testing was done on the device (OxyMinder) as a standalone unit. The "Oxygen Accuracy with Blender" test refers to its performance when integrated with a Bio-Med Devices air/oxygen blender, but it's still about the device's accuracy rather than human interpretation.

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

   • For the bench testing, the "ground truth" would be the known and controlled oxygen concentrations and environmental conditions used during calibration and testing against established performance standards and specifications.

7. The sample size for the training set:

   • Not applicable. This device is not described as using machine learning or AI that would require a 'training set' in the traditional sense. It's an oxygen gas analyzer, likely with embedded software and algorithms based on known physics and engineering principles for sensor readings.

8. How the ground truth for the training set was established:

   • Not applicable, as there's no mention of a training set for machine learning.

Ask a specific question about this device

The TV-100 is intended for use by qualified medical personnel to provide intermittent to continuous ventilatory support to neonatal, pediatric, and adult patients. The TV-100 is intended for use in both invasive and non-invasive ventilation modes. The TV-100 is intended for use in hospital including intrahospital transport, pre-hospital, and air transport settings.

The TV-100 is designed to be a compact, lightweight, microprocessor controlled ventilator which allows for precise ventilatory control. The TV-100 features an internal compressor which allows the TV-100 to operate without the need for external pressurized gas supplies; however an external oxygen supply may be connected to blend with the air from the internal compressor. To further simplify use there are minimal ventilation controls. The TV-100 user interface (UI) is a touchscreen color LCD with full VGA resolution.

The TV-100 ventilator is a DC powered device operating on internal lithium ion batteries and powered by an external IEC 60601-1 compliant power supply. The external supply also charges the batteries.

Ventilation Modes include: A/C Mode (Assist/Control) CPAP Mode (Continuous Positive Airway Pressure) NIV Bilevel Mode (Non-invasive Ventilation) SIMV Mode (Synchronized Intermittent Mandatory Ventilation) PRVC Mode (Pressure Regulated Volume Control) Constant Flow Apnea Detection Standby Mode

The provided text describes the Bio-Med Devices TV-100, a continuous ventilator, and its substantial equivalence to predicate devices, but does not contain information about acceptance criteria or a study that specifically proves the device meets those acceptance criteria in the context of an AI/ML algorithm or its performance characteristics typically assessed in such a study.

The document details non-clinical performance testing for various ventilator functions, comparisons to predicate devices, and a usability study, but these are not presented as "acceptance criteria" and "device performance" in the way one would define them for an AI/ML component. The document focuses on hardware functionality, safety standards compliance, and general performance, not an AI model's accuracy, precision, recall, or other statistical measures.

Therefore, I cannot fulfill your request to provide a table of acceptance criteria and reported device performance for an AI/ML algorithm, nor can I provide information about sample sizes for test sets, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, standalone performance, type of ground truth used, or training set details as these are not discussed in the provided text.

The text explicitly states:
"#### Clinical Testing Summary: No clinical testing was performed" (page 9), which further indicates that the type of study you are asking about, especially one involving ground truth and expert consensus for an AI/ML device, was not conducted or reported here.

The device itself is a continuous ventilator, and the document is a 510(k) summary for its premarket notification, indicating it is a traditional medical device, not specifically an AI/ML-powered device for which such metrics would be typically reported.

Ask a specific question about this device