Search Results

The Respond OC Conserving Regulator (130-0800) is intended for prescription use only, to be used as part of a portable oxygen delivery system for patients that require supplemental oxygen in their home and for ambulatory use. It may also be used to deliver a constant flow of oxygen to the patient.

The Respond OC Conserving Regulator (130-0800) is a dual mode high pressure oxygen regulator and conserving device that allows for either a continuous or conserve flow of medical grade oxygen to the patient. The device is designed with a CGA 870 style yoke for use with ambulatory oxygen cylinders. The integrated regulator reduces cylinder pressure to 22psig (+/-3psi) to the sensing diaphragm which allows the Respond OC to sense the start of inhalation by the patient and release a controlled amount of oxygen by pneumatic timing in short bursts into the lungs via an oxygen cannula. The Respond OC supports a delivered oxygen equivalency of 1 to 5 LPM in the conserve mode, which extends the ambulatory time of cylinders up to 6:1 based on the cylinder pressure and selected setting. The continuous flow mode offers settings of 2, 3 and 4 LPM if the patient requires a constant flow of oxygen.

The provided FDA 510(k) clearance letter and summary for the Respond OC Conserving Regulator (K250322) outlines the device, its intended use, and its substantial equivalence to a predicate device. However, this documentation does not contain the detailed information typically found in a clinical study report or a comprehensive test report regarding acceptance criteria and the study that proves the device meets them, especially in the context of AI/ML-based medical devices or diagnostic tools.

The device described (an oxygen conserving regulator) is a mechanical device, not an AI/ML-driven diagnostic or treatment device. Therefore, many of the typical requirements for AI/ML device studies (such as MRMC, expert consensus for ground truth, training set details, and specific performance metrics like sensitivity/specificity/AUC) are not applicable here.

The document primarily focuses on bench testing and biocompatibility to demonstrate substantial equivalence to a predicate mechanical device.

Here's an analysis based on the provided document, highlighting what is and is not present concerning "acceptance criteria" and "study proof":

Analysis of Acceptance Criteria and Study Proof for Respond OC Conserving Regulator (K250322)

Based on the provided FDA 510(k) Summary, the device is a mechanical oxygen conserving regulator. The "acceptance criteria" and "study proof" are framed in the context of demonstrating substantial equivalence to a predicate mechanical device through non-clinical (bench) testing and biocompatibility assessments, rather than clinical efficacy studies or AI/ML performance evaluations.

1. Table of Acceptance Criteria and Reported Device Performance

The document summarizes the types of tests conducted and states that the device "met its acceptance criteria" and "performs similarly to the predicate device." However, it does not explicitly list the specific quantitative acceptance criteria for each test (e.g., a specific tolerance for oxygen flow, a defined pass/fail for impact resistance) nor does it present the raw, quantitative reported performance results against these criteria. Instead, it provides qualitative statements of compliance.

2. Sample Size for the Test Set and Data Provenance

Given this is a physical device, the "test set" refers to the manufactured units subjected to bench testing. The document does not specify the sample size (number of devices) used for each of the non-clinical tests (e.g., how many units were subjected to accelerated aging, or impact testing).

Data Provenance: The data provenance is from non-clinical bench testing conducted by the manufacturer, Responsive Respiratory, Inc. It's not clinical data or retrospective/prospective human data. The country of origin for the testing itself is not explicitly stated but would typically be where the manufacturer's testing facilities are located.

3. Number of Experts Used to Establish Ground Truth and Qualifications

This question is not applicable as the device is a mechanical oxygen regulator, not an AI/ML-driven diagnostic or classification device requiring expert-established ground truth from medical images or patient data. Ground truth for its performance would be established through calibrated laboratory equipment measuring physical parameters (flow, pressure, timing, etc.) against engineering specifications.

4. Adjudication Method for the Test Set

This question is not applicable for a mechanical device undergoing bench testing. Adjudication typically refers to resolving discrepancies between human readers or between AI and human readings. Test results for mechanical parameters are either within specification or not, based on objective measurements.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

No, an MRMC comparative effectiveness study was not done. This type of study is relevant for diagnostic devices (especially those using AI/ML) where human readers (e.g., radiologists) interpret cases, and the effectiveness of AI assistance on their performance is evaluated. The Respond OC Conserving Regulator is a therapeutic/delivery device, not a diagnostic one.

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

This question is not applicable in the typical sense for this device. There is no "algorithm" in the way an AI/ML device would have one. The device's "performance" is its mechanical function. The "bench testing" described in the summary is the standalone performance assessment of the device's mechanical and pneumatic operation (e.g., flow rates, bolus timing, pressure regulation) without human intervention beyond setting the controls for the test.

7. The Type of Ground Truth Used

For the bench tests, the "ground truth" would be physical measurements against engineering specifications and industry standards. For example:

• Flow rates: Measured by calibrated flow meters against specified LPM settings.
• Pressure: Measured by calibrated pressure gauges against specified PSI output.
• Timing of bolus delivery: Measured by sensors and timers to confirm delivery within the specified inspiratory cycle.
• Biocompatibility: Confirmed by laboratory analysis against ISO standards.
• Ignition Sensitivity: Confirmed by testing against ASTM standards.

It is not expert consensus, pathology, or outcomes data, as these are related to clinical diagnosis or patient outcomes, not the performance of a mechanical oxygen delivery device.

8. The Sample Size for the Training Set

This question is not applicable. There is no "training set" as this is not an AI/ML device that requires data for model training.

9. How the Ground Truth for the Training Set was Established

This question is not applicable for the same reason as point 8.

Ask a specific question about this device

The Proxima is intended for prescription use only, to be used for adult patients that require supplemental oxygen in a hospital setting.

The Proxima Model-100 is an electronic oxygen conserving device designed for use in a hospital environment. It incorporates a sensitive pressure sensor to detect inhalation, an electronic valve to deliver precise volume of oxygen and a graphical touch screen interface. In pulsed mode the Proxima delivers flows equivalent to 1 to 15 liters per minute of continuous oxygen flow. The volume of each bolus is calculated such that the patient receives the equivalent of the set volume regardless of how slow their breath rate is. To make sure the patient receives oxygen, even if inhalation is not detected, the Proxima automatically changes from pulsed to continuous oxygen flow at the set flow rate if inhalation is not detected for 15 seconds. Proxima displays a warning message to indicate low battery, low oxygen supply pressure, dislodged cannula, lack of inhalation and low nasal airflow. The Proxima is powered using an external 9-volt DC power supply and includes an internal back-up battery. The Proxima is for use with a customer supplied, dual lumen demand nasal cannula, for example the Salter Labs 4807 or similar, to ensure proper patient usage.

The provided text is a U.S. FDA 510(k) summary for a medical device called "Proxima". It describes the device, its intended use, and compares it to a predicate device to establish substantial equivalence for regulatory clearance.

However, the document does not contain information about acceptance criteria or a study proving the device meets specific performance criteria through a clinical or algorithmic performance study, as typically seen for AI/ML-enabled devices.

The "acceptance criteria" section you're asking for typically refers to the pre-defined performance thresholds (e.g., minimum accuracy, sensitivity, specificity, or clinically relevant metrics) that an AI/ML algorithm must meet on a test set to be considered acceptable. The "study that proves the device meets the acceptance criteria" would detail the methodology of that study, including test set characteristics, ground truth establishment, expert involvement, and the actual performance metrics achieved by the device.

The provided document focuses on bench testing for the Proxima device, which is an oxygen conserving device, not an AI/ML diagnostic or prognostic tool. The performance testing mentioned (ISO 80601-2-67) evaluates physical parameters like pulse volume, breath rate, oxygen delivery, continuous flow, leak compensation, and breath trigger pressure. These are engineering and functional performance tests for a hardware device, not a performance study for an AI/ML algorithm.

Therefore, based solely on the provided text, I cannot extract the information required to populate your requested table and answer questions 1-9 about AI/ML device performance studies. The document describes a traditional medical device clearance, not an AI/ML device.

If the "Proxima" device were an AI/ML product, the information would typically be found in sections detailing clinical performance studies, often in the "Performance Data" or "Clinical Data" sections of a 510(k) summary, which are absent or not relevant in this document for the type of device described.

Ask a specific question about this device

The Effortless Oxygen Conserver Systems are intended to deliver medical-grade oxygen for patients that require supplemental oxygen from oxygen gas sources. Pulsing oxygen allows patients to ambulate longer than they would with a continuous flow regulator on the same cylinder. The Effortless MOBILE may be used in hospital, healthcare facilities, or home care environments. The Effortless PRO is only intended for hospital and healthcare facilities under professional use.

The Effortless Oxygen Conserver Systems (EOCS) is a microprocessor-controlled device, which contains an oxygen pressure regulator and oxygen conserver. Depending upon the model they have been designed for use in ambulatory, home and medical facility settings to supply medical-grade oxygen therapy to patients. The built in oxygen regulator reduces oxygen pressures from an oxygen cylinder or from hospital wall supplies. There are two configurations: The Effortless Pro which connects to hospital wall oxygen and the Effortless Mobile which connects to tanks.

The provided document is a 510(k) Premarket Notification from the FDA for a medical device (Effortless Oxygen Conserver System). This type of submission focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than proving clinical effectiveness through extensive studies with defined acceptance criteria for individual performance metrics like those typically outlined for AI/ML devices.

Therefore, the document does not contain the detailed information required to answer many of the questions, especially those pertaining to:

• Acceptance criteria table with reported device performance: The document only provides a comparison table of features and specifications between the proposed device and a predicate, not performance metrics against specific acceptance criteria.
• Sample size and data provenance for a test set: No test set (in the context of AI/ML or clinical efficacy) is mentioned. The "bench testing" refers to engineering verification.
• Number of experts and qualifications for ground truth: Not applicable, as there's no mention of expert-established ground truth for a test set.
• Adjudication method: Not applicable.
• Multi-reader multi-case (MRMC) comparative effectiveness study: No such study is mentioned.
• Effect size of human readers improvement with AI assistance: Not applicable, as this is not an AI-assisted device in the diagnostic sense.
• Standalone performance (algorithm only): Not applicable for this type of device.
• Type of ground truth used: Not applicable.
• Sample size for training set and how ground truth was established for training set: Not applicable, as this is not an AI/ML device that requires training.

What the document does describe are several non-clinical tests to demonstrate device performance and safety, primarily for substantial equivalence to a predicate device, not clinical efficacy or AI/ML performance.

Here's an attempt to extract relevant information, acknowledging the limitations based on the document's content:

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

The document does not provide a formal table of "acceptance criteria" and "reported device performance" in the way one might expect for a diagnostic or AI/ML device (e.g., sensitivity, specificity thresholds). Instead, it lists the device's specifications and features, and states that various engineering and safety tests were performed to ensure it met applicable standards and performance requirements.

The "Table of Comparison and Differences" (Page 5-6) serves to show equivalence to the predicate device, not performance against specific criteria. However, for certain parameters, it implicitly suggests an acceptable range by stating what the device accomplishes.

Ask a specific question about this device

The Apogee is a gas conserver intended as a delivery device for medical grade oxygen from a high-pressure oxygen cylinders. Apogee is an ambulatory device which allows patients to ambulate longer than they would with continuous flow regulator on the same cylinder. The Apogee is intended to be used in the hospital, healthcare facilities, or home care environments.

The proposed device, Apogee, senses each nostril independently through a bifurcated cannula and responds to the dynamic changes in nasal air-flow making a breath-to-breath determination of where to deliver the next bolus of oxygen: to the left, the right, or both nostrils. The Apogee Device is composed of the main components as detailed below: Control Unit, Control Board (Regulated Voltage Supply), Embedded Processor, User supplied Demand Cannula, The Apogee Bypass Cannula and Restrictor and Cylinder Tubing.

This document is an FDA 510(k) summary for the Apogee oxygen conserver. It describes the device, its intended use, and compares it to a predicate device (Inspired Technologies Model 350G). The information provided focuses on the device's design, technology, and non-clinical performance testing rather than clinical study results involving human patients or complex AI algorithms with specific performance metrics like sensitivity, specificity, or AUC.

Therefore, many of the requested elements for acceptance criteria and study details (like sample size for test sets, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, standalone AI performance, and training set details) are not applicable or not present in this type of regulatory document concerning a mechanical-electronic medical device like an oxygen conserver. The "performance data" section primarily refers to engineering and safety bench testing, not clinical performance studies with diagnostic accuracy targets for AI.

Here's a breakdown based on the provided document:

Acceptance Criteria and Device Performance for Apogee Oxygen Conserver

This 510(k) summary focuses on demonstrating substantial equivalence to a predicate device through engineering and safety testing. It does not contain specific "acceptance criteria" in the context of diagnostic performance (e.g., sensitivity, specificity, AUC) for an AI algorithm. Instead, the "acceptance criteria" are implied by compliance with recognized standards and comparable performance to the predicate device in bench tests.

1. Table of Acceptance Criteria and Reported Device Performance

Since this is a non-AI, mechanical-electronic device, the acceptance criteria are not typically expressed as diagnostic accuracy metrics. Instead, they relate to engineering specifications and performance in bench testing to ensure safety and effectiveness comparable to the predicate. The document highlights the following:

• Gas emission VOC
• Particulate Matter (PM2.5)
• Inorganic gases CO, CO2 and Ozone
• Toxicological Risk Assessment | Materials are safe for patient contact. |
  | Oxygen Bolus Delivery Equivalence
  (compared to predicate, volume and time) | Bench testing demonstrated that both devices (Apogee and predicate) delivered an equivalent amount of oxygen bolus to the patient in the same time. | Key functional performance matched the predicate. |
  | Trigger Sensitivity
  (compared to predicate) | Bench testing performed, details not quantified but implied comparable to predicate (-0.3 cmH2O for Apogee vs. +0.03 to -0.2 cmH2O for predicate). | Demonstrated a similar ability to sense patient inhalation. |
  | Volume Flow Performance | Bench testing performed. | Functional flow characteristics validated. |
  | Performance Pre- and Post-Cleaning | Bench testing performed. | Device maintains performance after cleaning. |
  | Breath Range Capability
  (e.g., up to 35 BPM for predicate) | Apogee: Up to 40 BPM | Apogee performs across a relevant physiological breath rate range, slightly better than predicate. |
  | Patient Oxygen Outlet Pressure
  (e.g., 19-25 psig for predicate) | Apogee: 19-30 psig | Comparable and within safe operating range. |
  | Water Ingress Protection
  (e.g., IPX1 for predicate) | Apogee: IP22 | Improved liquid ingress capability (IP22 for Apogee vs. IPX1 for predicate). No differences in safety or effectiveness found due to this improvement. |

Study Proving Device Meets Acceptance Criteria:

The study described is a series of non-clinical bench tests and compliance assessments against recognized industry standards, rather than a diagnostic accuracy or comparative effectiveness study involving human subjects or AI-assisted diagnostic tasks.

2. Sample Size Used for the Test Set and Data Provenance:

• Sample Size: Not specified in terms of patient data. The "test set" refers to physical units of the device tested in a lab setting. The number of units tested is not provided, but it would typically be a small number of engineering samples.
• Data Provenance: Not applicable in the context of patient data. This involves laboratory bench testing of physical device units, not patient data sets. The testing was presumably conducted by the manufacturer or contracted labs.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:

• Number of Experts: Not applicable. Ground truth for an oxygen conserver's performance in bench testing is based on engineering specifications, calibrated measurement equipment, and industry standards, not expert interpretation of medical images or clinical data.
• Qualifications of Experts: Not applicable. The "ground truth" for this device's performance is objective measurement against engineering specifications.

4. Adjudication Method for the Test Set:

• Adjudication Method: Not applicable. This is not a study where human interpretations are being adjudicated.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:

• MRMC Study: No. This type of study is typically performed for diagnostic devices (e.g., imaging AI) where human readers' performance is evaluated with and without an AI assist. This document concerns a therapeutic mechanical device.

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

• Standalone Performance: The "software" in this device controls the mechanical function (sensing breath and delivering oxygen bolus). Its "standalone performance" is implicitly assessed through the bench testing described (e.g., bolus delivery accuracy, trigger sensitivity). It's not a diagnostic algorithm with standalone performance metrics like sensitivity/specificity.

7. The Type of Ground Truth Used:

• Type of Ground Truth: The ground truth for this device's performance is based on engineering specifications, physical measurements from calibrated instruments, and compliance with recognized national and international standards for medical device safety and performance (e.g., AAMI ANSI ES 60601-1, IEC 60601-1-11, ISO 80601-2-67).

8. The Sample Size for the Training Set:

• Sample Size for Training Set: Not applicable. This is a non-AI mechanical device. The "software" mentioned is embedded control software, not a machine learning model that requires a training set in the conventional sense of AI development.

9. How the Ground Truth for the Training Set Was Established:

• Ground Truth for Training Set: Not applicable. As there's no machine learning training set, no such ground truth establishment occurred. The control logic for the device's functions (e.g., breath sensing, oxygen delivery) is derived from engineering design principles, physiological understanding, and validated algorithms for precise control, not from a data-driven training process.

Ask a specific question about this device

The intended use is to deliver oxygen to the patient nasally, controlled by a demand system.

The demand cannula is a special cannula designed to give adult and pediatric users of dual port oxygen conservation delivery system all the comfort and conveniences of a Salter-Style® cannula. Unique dual tubing delivers oxygen on demand through one tube while inspiratory / expiratory effort is also sensed through the other tube. Meets dual port device manufacturers' specifications.

The provided document describes the acceptance criteria and a study to demonstrate substantial equivalence for the NOP Demand Nasal Oxygen Cannula and NOP Modified Demand Nasal Oxygen Cannula.

Here's the breakdown of the requested information:

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

2. Sample size used for the test set and the data provenance

• Sample Size: A minimum required sample size of 29 was used for the performance testing.
• Data Provenance: The document does not specify the country of origin of the data. It is a retrospective study conducted by the manufacturer (Salter Labs) to demonstrate substantial equivalence for a material change.

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

This information is not provided in the document. The study focuses on direct physical and performance testing of the device, not on expert evaluation or consensus for a "ground truth" as might be relevant for diagnostic or AI-based devices.

4. Adjudication method for the test set

This information is not applicable/provided as the study did not involve expert adjudication for establishing ground truth. The testing involved objective measurements against predefined criteria.

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

This information is not applicable. The device is a nasal oxygen cannula, not an AI-based diagnostic tool, so an MRMC study is not relevant.

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

This information is not applicable. The device is a physical medical device, not an algorithm, so standalone algorithm performance is not relevant.

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

The concept of "ground truth" as typically defined for diagnostic or AI studies is not directly applicable here. Instead, the study establishes "truth" through direct physical performance measurements (e.g., back pressure, bond strength, temperature resistance) against specified engineering and product design criteria.

8. The sample size for the training set

This information is not applicable. There is no training set mentioned or implied as this is not an AI/machine learning device.

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

This information is not applicable. As there is no training set, there is no ground truth for it. The study established performance data through direct physical testing.

Ask a specific question about this device

The TheraFlow Oxygen Conserving Device Regulator is intended for prescription use only, to be used in conjunction with a portable oxygen tank for adult patients prescribed supplemental oxygen therapy for use inside the home or outside in ambulatory applications on patients with mobility. It is not intended for life support applications.

Not Found

I am sorry, but the provided text does not contain any information about acceptance criteria or a study proving that a device meets such criteria. The document is an FDA 510(k) clearance letter for a device called "TheraFlow Single and Dual Lumen Regulation" (K131023).

This letter acknowledges that the device is substantially equivalent to legally marketed predicate devices and outlines general regulatory compliance requirements. It does not include performance data, study designs, sample sizes, expert qualifications, or ground truth establishment methods.

Therefore, I cannot fulfill your request for information regarding acceptance criteria and device performance based on the input text.

Ask a specific question about this device

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

The Chad Therapeutics Evolution Model OM-900 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 7 liters per minute, in their home and for ambulatory use

The Inovo Evolution 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 convert 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 7 liters per minute depending on the flow rate setting

Here's an analysis of the provided text regarding the acceptance criteria and study information for the Inovo Evolution OM-900 Series:

Disclaimer: The provided text is a 510(k) summary from 2010. It focuses on demonstrating substantial equivalence to a predicate device, which means it might not contain the detailed, quantitative acceptance criteria and study results typically found in full clinical study reports or newer FDA submissions. Much of the information requested (e.g., sample sizes for training/test sets, expert qualifications, specific metrics for acceptance criteria) is not present in the provided document.

Acceptance Criteria and Reported Device Performance

The 510(k) summary for the Inovo Evolution OM-900 Series is primarily a submission for substantial equivalence. It does not explicitly state quantitative acceptance criteria in a table format with corresponding performance results in the way a performance study might. Instead, it relies on demonstrating that its design, function, and features are comparable to the predicate device (Chad Therapeutic Lotus Models OM-700 & OM-700S) and that testing confirms it performs as intended and meets the same "performance criteria" as the predicate.

The key acceptance criteria, as implied by the document, revolve around:

• Same Intended Use: The device must serve the same purpose for the same patient population.
• Basic Modes and Settings: It must offer comparable operational modes and settings.
• Similar Materials: The materials used should be equivalent.
• Equivalent Oxygen Delivery Method: The fundamental way it delivers oxygen should be the same.
• Performance (General): Testing must demonstrate it meets performance criteria and functions as intended, implying that its oxygen delivery characteristics (bolus size, equivalence to L/min, breath detection) are comparable to the predicate.

Since no specific quantitative metrics or a comparative table are provided in the document, I cannot populate a table with "acceptance criteria" vs. "reported performance" with specific numbers. The document states a general conclusion:

"together with the results of testing demonstrates the device to be substantially equivalent to the predicate device in terms of meeting performances criteria and functioning as intended."

This indicates that internal testing was conducted to ensure the device performs similarly to the predicate, particularly regarding breath detection (even though the circuitry is new) and bolus sizes. The bolus sizes are explicitly mentioned as "the same with the exception of one additional setting No. 7."

Detailed Study Information (Based on Available Text)

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

   • Not provided. The document states "results of testing," but does not specify the type of testing (e.g., in vitro, animal, human clinical), sample size, or data provenance. Given the nature of a 510(k) for an oxygen conserver, it's likely initial testing focused on engineering and performance verification in a lab setting, possibly with some human-factors or usability testing, rather than a large clinical trial with patient data.

2. 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/Not provided. This type of information is usually relevant for studies involving image interpretation or diagnostic accuracy where expert consensus is needed to establish ground truth. For an oxygen conserver, ground truth would likely be established through objective measurements of oxygen delivery, breath detection accuracy, and functionality, rather than expert interpretation.

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

   • Not applicable/Not provided. Adjudication methods are typically used in studies where multiple human readers interpret data (e.g., medical images) and their discrepancies need to be resolved to establish ground truth. This is not the type of study described or implied for this device.

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. An MRMC comparative effectiveness study is not mentioned and is not relevant for an oxygen conserver device, which is a therapeutic device, not an AI-assisted diagnostic tool for human readers.

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

   • Not applicable/Not provided in this context. While the device is microprocessor-controlled and has "breath detection circuitry," it's a medical device delivering oxygen, not an AI algorithm generating a diagnosis or prediction without human interaction. Performance testing would have evaluated the device's standalone operation and its ability to deliver oxygen accurately based on detected breaths. However, the term "standalone" in the context of AI performance metrics (algorithm only) is not relevant here.

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

   • Objective Measurements/Engineering Specifications. For an oxygen conserver, ground truth would be established through objective measurements based on engineering specifications and physiological principles. This would include accurately measuring:
     • Oxygen flow rates and bolus sizes
     • Accuracy of breath detection
     • Battery life
     • Pressure regulation
     • Safety parameters (e.g., leaks, pressure limits)
   • The document implies that these measurements were compared against the predicate device's known performance characteristics and relevant standards.

7. The sample size for the training set

   • Not applicable/Not provided. This device is hardware-based with microprocessor control, not a machine learning or AI algorithm that requires a "training set" in the conventional sense. The "training" for such a device involves design, engineering, and iterative testing/refinement of the hardware and embedded software.

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

   • Not applicable/Not provided. As above, the concept of a "training set" and its "ground truth" is not directly applicable to this type of device development process. Ground truth for the underlying principles (e.g., desired oxygen bolus sizes, breath detection sensitivity) would be established by medical standards, physiological requirements, and the performance characteristics of the predicate device.

Ask a specific question about this device

The Inspired Technologies 350G Gas Conserver is intended as a delivery device for medial-grade oxygen from high-pressure oxygen cylinders. This is an ambulatory device, which allows patients to ambulate longer than they would with a continuous flow regulator on the same cylinder. The 350G Gas Conserver is intended to be used in the hospital, healthcare facilities, or home care environments.

The Inspired Technologies Model 350G Gas Conserver is designed to extend the use time of oxygen cylinders. It contains an integral pressure regulator with CGA 870 style yoke. The pressure regulator reduces the cylinder pressure to 19 - 25 psig. While the device is normally operated in the conserving mode, there is a continuous flow over-ride switch that allows 2 LPM of oxygen to bypass all valves for delivery to the patient. This continuous flow mode is typically used in the event of low or no battery power. In the conserving mode, the 350G Gas Conserver delivers oxygen to the patient by sensing inhalation via a pressure switch and opening one, two or both control valves for a specified period of time as determined by the microprocessor control algorithm. In the conserving mode, the device uses SmartDose™ technology to accomplish the oxygen savings. SmartDose™ senses the start of inhalation and releases a short "pulsed" dose at the very beginning of the inhalation cycle. The 350G Gas Conserver intended to be used by trained clinicians in the hospital, clinical or home care environments.

This document describes the Inspired Technologies Model 350G Gas Conserver, a device designed to extend the use time of oxygen cylinders via a "SmartDose™" technology.

This device is not an AI/ML device, and therefore the majority of the information requested (AI/ML specific questions) cannot be answered. However, I can still provide the available information regarding its testing and acceptance within the provided text.

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

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

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

This information is not provided in the document. The document mentions "the following tests" were performed, but does not specify sample sizes for any of these tests.

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 device is a hardware medical device and the tests performed are primarily engineering and compliance tests, not diagnostic or interpretive tests requiring expert "ground truth" establishment in a clinical sense.

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

This information is not applicable as the tests described are technical performance and compliance tests, not clinical evaluations requiring adjudication of subjective interpretations.

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

This information is not applicable as the device is a hardware medical device, not an AI/ML diagnostic tool. There is no mention of an MRMC study or human reader assistance.

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

This information is not applicable in the context of typical AI/ML standalone performance. The device does contain a "microprocessor control algorithm" for the conserving mode, which operates in a standalone manner to deliver oxygen. However, this is a deterministic control algorithm, not an AI/ML algorithm.

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

This information is not applicable in the AI/ML sense. For the engineering tests, "ground truth" would be established by validated test equipment and calibration standards (e.g., pressure gauges for verifying pressure regulator, flow meters for dosing, timers for battery life), but these details are not provided.

8. The sample size for the training set

This information is not applicable. The device uses a deterministic control algorithm, not an AI/ML algorithm that requires a training set.

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

This information is not applicable as there is no training set for an AI/ML algorithm.

Summary of the Study that Proves the Device Meets Acceptance Criteria:

The document states that to demonstrate the safety and efficacy of the Model 350G Gas Conserver, "the following tests according to the following standards" were performed:

• Regulatory Compliance Standards:
  • FCC CFR 47 Parts 15B and 18
  • Industry Canada BS EN 55011:2007
  • IEC 60601-1
• Bench and Performance Testing:
  • Low battery voltage tests
  • Battery Life
  • Battery reverse polarity
  • Pressure regulator verification
  • Storage at high and low temperatures
  • Operation at high and low temperatures
  • Cleaning verification
  • IPX1 - Drip proof verification

The FDA's letter states that they have reviewed the premarket notification and "determined the device is substantially equivalent" to legally marketed predicate devices, implying that the submitted test results sufficiently demonstrate that the device meets safety and effectiveness requirements. The specific results of these tests (e.g., actual battery life in hours, exact pressure regulator output values, temperature ranges survived) are not detailed in this summary, but the completion of these tests according to the standards served as the proof of compliance.

Ask a specific question about this device

The Chad Therapeutics Bonsai (modified Chad Therapeutics OXYPNEUMATIC CYPRESS Model 511) is intended for use in the same manner as the unmodified device, i.e., for prescription use only, to be used as part of a portable oxygen delivery system for patients that require supplemental oxygen in their home and for ambulatory use.

The Chad Therapeutics Bonsai a pneumatic-controlled device, which is a combination of r the Onad Therapoulator and an oxygen conserver, designed for use with ambulatory a low probute regulativers boluses of oxygen that is equivalent to 1 to 7 liters per minute, depending on the flow rate setting.

The provided text describes a 510(k) submission for the Chad Therapeutics Bonsai Model 800, which is a modified oxygen conserver. However, the document does not contain an acceptance criteria table or a study report detailing specific performance metrics against acceptance criteria. Instead, it focuses on demonstrating substantial equivalence to a predicate device through general statements about design verification and validation activities.

Therefore, many of the requested sections below cannot be populated from the provided text.

Here's an attempt to answer the questions based on the available information:

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

The document states that "The Bonsai passed all of the test criteria established in the Bonsai design verification and validation tests." However, it does not provide a table with specific acceptance criteria or the reported performance data for each criterion. It only mentions one specific safety test the regulator passed.

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

This information is not provided in the document. The document only generally states "All risk assessment, design verification and validation activities were conducted in accordance with approved product requirements to demonstrate that the Chad Therapeutics Bonsai would perform as intended."

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 this device is an oxygen conserver and the document describes engineering verification and validation, not studies requiring expert visual assessment or ground truth establishment in a medical imaging or diagnostic context.

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

This information is not applicable for the type of device and testing described.

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

This information is not applicable as this device is an oxygen conserver and does not involve human readers interpreting images or data with or without AI assistance.

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

This information is not applicable as this is a mechanical medical device, not an algorithm or AI system.

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

For this type of device (oxygen conserver), "ground truth" would generally refer to established engineering standards, specifications, and physical measurements. The document implies that the "ground truth" for the tests involved verifying the device's performance against predefined "product requirements" and industry standards like ASTM G 175-03.

8. The sample size for the training set

This information is not applicable as this is a mechanical medical device, not an algorithm or AI system that requires a "training set."

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

This information is not applicable for the same reason as above.

Ask a specific question about this device