Search Results

The Chad Therapeutics Evolution Model OM-900M is intended for prescription use only, to be used as part of a portable oxygen delivery system for patients that require supplemental oxygen up to 6 liters per minute, in their home and for ambulatory use.

The Inovo Evolution OM-900M is a microprocessor-controlled device, which is a combination of a oxygen pressure regulator and a oxygen conserver, designed for use with ambulatory oxygen systems. The built in oxygen regulator reduces the oxygen pressure from the oxygen cylinder to ensure proper operation of the oxygen conserving device. The low pressure oxygen enters the conserver portion of the device where the breath detection circuitry and inhalation sensors control the low pressure oxygen to deliver a precise amount of supplemental oxygen at a specific point in the breathing cycle. It delivers boluses of oxygen that is equivalent to 1 to 6 liters per minute depending on the user setting. The OM-900M is also able to detect motion via a 3 axis accelerometer. If motion is detected the software will automatically increase the oxygen delivery(active mode) to the patient. After motion has ceased, the software will then revert to the original rest setting(rest mode). The motion technology is taken from a previously cleared device Chad Sage Model TD-100 - K033364.

The Inovo Evolution OM-900M is an oxygen conserver. The provided text describes the device, its intended use, and a comparison to predicate devices, focusing on the addition of a motion detection feature.

Here's an analysis to extract the requested information regarding acceptance criteria and the study proving the device meets them:

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

The provided 510(k) summary (K113111) for the Inovo Evolution OM-900M does not explicitly state a table of quantifiable acceptance criteria with corresponding device performance metrics for the overall device or its new motion detection feature. Instead, it relies on demonstrating substantial equivalence to predicate devices through verification and validation activities.

However, based on the text, the implicit acceptance criteria are that the modifications (motion detection software and hardware) do not introduce new safety and effectiveness issues and that the device functions as intended, similar to the predicate devices.

The "reported device performance" is broadly stated as passing all tests outlined in the validation protocols. Specific quantitative performance targets for the motion detection feature itself (e.g., accuracy of motion detection, response time to motion, or how much oxygen delivery increases) are not detailed in this summary.

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 a separate "test set" in the context of and AI/algorithm-focused study with a defined sample size of patients or images. The verification and validation activities (PV-192 and PV-193) are described as testing the software and hardware of the device. This implies engineering or laboratory testing rather than a clinical trial with human subjects.

Therefore, information on sample size for a "test set" and data provenance (country of origin, retrospective/prospective) related to AI/algorithm performance is not applicable or provided in this 510(k) summary. These types of details are typically found in clinical study reports, which are not included here.

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)

This information is not applicable as the document does not describe a study involving expert-established ground truth for a test set (e.g., for image interpretation or disease diagnosis). The verification and validation activities are for the device's functional performance, not for an AI algorithm making diagnostic interpretations.

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

This information is also not applicable as there is no mention of a test set requiring adjudication of findings, which is typical for clinical studies involving multiple reviewers or diagnostic outputs.

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

No, an MRMC comparative effectiveness study was not done or described in this 510(k) summary. This type of study is relevant for AI systems that assist human readers in tasks like medical image interpretation. The Inovo Evolution OM-900M is an oxygen conserver with a motion detection feature, not an AI-powered diagnostic tool in that sense.

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

The device's motion detection feature can be considered a standalone algorithmic component that senses motion and automatically adjusts oxygen delivery without direct human intervention once activated. The "Non Clinical Verification" section describes that the software for the motion detection algorithm underwent full Software Verification and Validation (PV-192), and the hardware was tested via Product Validation (PV-193).

However, the nature of these tests is focused on the correct functioning of the motion detection system (e.g., does it detect motion, does it switch to active mode, does it revert to rest mode correctly) rather than a comparative performance against a "ground truth" of human activity, or direct clinical outcomes. The document does not provide specifics on the metrics used to assess this "standalone" performance beyond stating that it "passed all tests."

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

For the verification and validation of the motion detection feature, the "ground truth" would likely be based on engineering specifications and predefined performance thresholds for the accelerometer and associated software.

• For software verification (PV-192), the ground truth for tests would be the expected software behavior based on the Software Requirements Specification (SP-210) and Software Design Description (SP-209). For example, if a specific motion is simulated, the device should switch to active mode.
• For hardware validation (PV-193), the ground truth would involve confirming that the accelerometer correctly senses motion within specified parameters and that the additional button functions as intended.

It is not based on expert consensus, pathology, or clinical outcomes in the traditional sense of a diagnostic AI system study.

8. The sample size for the training set

This information is not applicable. The motion detection functionality appears to be based on an algorithm that processes accelerometer data rather than a machine learning model that requires a "training set" of data to learn from. The description suggests a rule-based or threshold-based system rather than a deep learning approach.

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

This information is not applicable as there is no mention of a training set for a machine learning algorithm.

Ask a specific question about this device