Search Results

The HVT 2.0 system provides high velocity nasal insufflation (HVNI) with simultaneous warmed and humidified respiratory gas delivery to augment breathing of spontaneously breathing adult and pediatric patients (5 kg and up) suffering from respiratory distress and/or hypoxemia in the hospital setting, via a small bore nasal cannula. HVT 2.0 is not intended to provide total ventilatory requirements of the patient and not for use during field transport. The flow rates may be from 5 to 45 liters per minute (BTPS).

The HVT 2.0 System is comprised of hardware containing software, and single use disposables that are designed to deliver the same High Velocity Nasal Insufflation (HVNI) as the Vapotherm Precision Flow HVNI.

The HVT 2.0 system consists of the HVT 2.0 hardware containing software, a Disposable Patient Circuit (DPC), and a patient interface (nasal cannula). The HVT 2.0 system utilizes an integrated internal blower to deliver warmed and humidified breathing gas at flows 5 to 45 L/min (BTPS) to spontaneously breathing patients, without the need of wall air or any pressurized air source. The addition of an external oxygen source (wall or tank for QAV indication) enables FiO2 delivery from 21% to 100%. The device incorporates a blender and flow sensors that allow the oxygen percentage and total gas flow to be set independently.

The HVT 2.0 main hardware device contains all the electrical and electronic components including the electronic blender and flow controllers, and sensors to monitor the disposable patient circuit. The main hardware device has no water pathways and the gas pathway only contains dry gas at room temperature, and therefore does not require internal cleaning or disinfection.

The available text does not describe an acceptance criteria and a study proving the device meets said criteria in the format requested. The document is a 510(k) summary for the HVT 2.0 device, which focuses on demonstrating substantial equivalence to a predicate device rather than presenting a performance study against predefined acceptance criteria for AI or automated system performance.

Here's why the requested information cannot be extracted and what is provided instead:

• 1. A table of acceptance criteria and the reported device performance: This is not present. The document includes a comparison table between the predicate and subject device (HVT 2.0) for various characteristics like Indications for Use, Patient Population, Flow Range, etc. While it lists "Temperature Accuracy" as "±2°C" and "Oxygen Accuracy" as "±2%", these are device specifications and not explicitly presented as "acceptance criteria" for a study in the context of an AI/algorithm performance. It then states "SAME" for the subject device, implying it meets these for equivalence.
• 2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective): Not applicable. The document discusses "bench / performance testing" and "comparative performance testing" but does not detail sample sizes for these tests in a way that would be relevant to a "test set" for an algorithm. There is no mention of data provenance (e.g., country of origin, 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. This document does not describe the use of experts to establish a "ground truth" for a test set, as it does not involve the evaluation of an algorithm's diagnostic or predictive performance.
• 4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable for the same reasons as point 3.
• 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 summary does not describe any MRMC studies or AI assistance for human readers. The device (HVT 2.0) is a high-flow humidified oxygen delivery device, a physical medical device, not an AI or software-as-a-medical-device (SaMD) that typically undergoes such evaluations.
• 6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. The device is not an algorithm. Its software is mentioned for verification and validation but not as a standalone performance entity.
• 7. The type of ground truth used (expert concensus, pathology, outcomes data, etc.): Not applicable.
• 8. The sample size for the training set: Not applicable, as there is no mention of a training set for an algorithm.
• 9. How the ground truth for the training set was established: Not applicable.

Summary of what is provided:

The document describes the HVT 2.0, a High Flow Humidified Oxygen Delivery Device, and its comparison to a predicate device (Precision Flow HVNI). The main point is to demonstrate "substantial equivalence" of the HVT 2.0 to the predicate device, not to prove algorithm performance against specific criteria.

The "studies" mentioned are non-clinical performance and bench testing, including:

• Biocompatibility testing (leveraged from prior testing, compliant with ISO 10993-1)
• Electrical safety and electromagnetic compatibility (compliant with IEC 60601-1 and IEC 60601-1-2)
• Alarms testing (compliant with IEC 60601-1-8)
• RFID testing (compliant with AIM 7351731)
• Software verification, validation, and hazard analysis (compliant with FDA guidance for software and ISO 14971:2019)
• Bench/Performance Testing, including:
  • Precision Flow and HVT 2.0 Comparison Testing (to demonstrate same HVNI technological characteristics and performance)
  • Oxygen accuracy/Blender Performance
  • Temperature accuracy/Thermal Stability
  • Flow rate accuracy
  • Humidification output (ISO 80601-2-74)
  • Patient contacting surface temperature/Thermal Safety
  • Volume of liquid exiting the humidification chamber outlet
  • Continuous use (Use Lifespan)
  • Operating environment
  • Nurse call compatibility
  • Usability/Human Factors
  • Cleaning Validation (for hardware)

The conclusion is that "Any differences in technological characteristics of the devices do not raise different questions of safety and effectiveness based on the performance testing, further supported by the prior clearance of the Reference Device HVT 2.0, cleared under K203357. The devices are substantially equivalent."

Ask a specific question about this device

The Vapotherm Aerosol Adapter AAA-2 is intended to facilitate the connection between Vapotherm High Velocity Therapy HVT 2.0 and the Aerogen Solo Nebulizer.

The Vapotherm Aerosol Adapter AAA-2 is an accessory that is intended to facilitate the connection between Vapotherm High Velocity Therapy HVT® 2.0, cleared under K203357, and the Aerogen Aeroneb® Solo Nebulizer System, cleared under K133360, and more recently with K143719. which is intended to aerosolize solutions for inhalation. The AAA-2 facilitates the connection between the noted devices, and therefore aerosolization use is dictated by the Aerogen Aeroneb Solo Nebulizer System labeling.

The provided text describes the Vapotherm Aerosol Adapter AAA-2 (subject device) and its equivalence to a predicate device. However, it does not contain the detailed acceptance criteria or the specific numerical results of a study that directly proves the device meets those criteria in a tabular format as requested.

Instead, the document outlines the types of non-clinical performance testing conducted and generally states that the device passed these tests or demonstrated similar performance to the predicate device.

Here's an attempt to extract and infer the information based solely on the provided text, while noting where information is missing:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: Not specified for any of the individual tests. The text describes "testing" and "running" the device but doesn't quantify the number of units or repetitions.
• Data Provenance: Not explicitly stated. The tests were performed by Vapotherm Inc. or a contracted lab. It's bench testing, not clinical data, so country of origin of data (patients) is not applicable. This is retrospective bench testing on the device itself.

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

This section is not applicable. This document describes physical and performance bench testing of a medical device accessory, not an AI or diagnostic system that requires expert consensus for ground truth. Biocompatibility and performance standards (like ISO 10993-1, ISO 18562-1, ISO 5356-1) serve as the "ground truth" or accepted standards that the device performance is measured against.

4. Adjudication method for the test set

This section is not applicable. Adjudication methods like 2+1 or 3+1 typically refer to expert review processes for clinical data, especially in AI studies, to establish ground truth. As this is bench testing against established engineering and material standards, such methods are not used. The device's performance is either within the specified limits or it is not.

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 section is not applicable. This document describes an accessory product (an adapter for a nebulizer) and its bench testing, not an AI system, diagnostic tool, or a product that interacts with human readers/interpretations. Therefore, an MRMC study and AI-assisted human reader improvement are not relevant.

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

This section is not applicable. The device is a hardware accessory; it does not involve any algorithm or AI component.

7. The type of ground truth used

The ground truth for the various tests described is based on:

• Established engineering specifications and performance limits for flow rates, rain-out, connection integrity.
• International standards for medical device safety and performance (e.g., ISO 10993-1 for biocompatibility, ISO 18562-1 for breathing gas pathways, ISO 5356-1 for connections).
• The performance of the predicate device (Aeroneb Solo Adapter) for aerosolization comparison.

8. The sample size for the training set

This section is not applicable. The device is a hardware accessory and does not involve AI/machine learning, so there is no training set.

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

This section is not applicable. As there is no training set for an AI/ML algorithm, the establishment of ground truth for such a set is not relevant.

Ask a specific question about this device

The HVT 2.0 system is intended to deliver warmed and humidified high-flow respiratory gases to spontaneously breathing adult patients and pediatric patients (5 kg and up). The device is intended to be used in hospital, sub-acute facility, and home-use settings.

The HVT 2.0 system is intended to deliver warmed and humidified high-flow respiratory gases to spontaneously breathing adult patients and pediatric patients (5 kg and up). The device is intended to be used in hospital, sub-acute facility and home-use settings.

The HVT 2.0 system is intended to be used by qualified medical professionals, such as physicians, nurses, respiratory therapists and by patients in a home-use setting under the supervision of qualified medical professionals.

The HVT 2.0 system consists of the HVT 2.0 main device, a Disposable Patient Circuit (DPC), and a patient interface (nasal cannula). The HVT 2.0 system utilizes an integrated internal blower to deliver warmed and humidified breathing gas at flows up to 45 L/min to spontaneously breathing patients, without the need of wall air or any pressurized air source. The device incorporates a blender and flow sensors that allow the oxygen percentage and total gas flow to be set independently. The addition of an external oxygen source (wall, tank, or oxygen concentrator) enables FiO2 delivery from 21% to 100%, dependent on the oxygen source.

The HVT 2.0 main device contains all the electrical and electronic components including the electronic blender and flow controllers, and remote sensors to monitor the disposable patient circuit. The main device has no water pathways, and the gas pathway only contains dry gas at room temperature, and consequently does not need internal cleaning or disinfection.

The provided text describes the HVT 2.0 respiratory gas humidifier and its review by the FDA for substantial equivalence to a predicate device. However, the document primarily focuses on regulatory approval, device description, and non-clinical performance testing. It does not contain information about acceptance criteria and a study proving the device meets those criteria, particularly within the context of artificial intelligence (AI) or machine learning (ML) performance.

Therefore, I cannot provide the requested table and details because the input text does not contain that information. The document focuses on the HVT 2.0 being "substantially equivalent" to a predicate device based on non-clinical performance testing, not on meeting specific, reported performance metrics with acceptance criteria, especially not in the context of an AI/ML study.

Specifically, the document does not include:

1. A table of acceptance criteria and reported device performance related to a diagnostic or analytical function. The testing described is for physical characteristics and safety of the humidifier.
2. Sample size for a test set, data provenance, ground truth establishment, or expert involvement. These are typically relevant for AI/ML performance studies.
3. Adjudication method.
4. Multi-Reader Multi-Case (MRMC) comparative effectiveness study information.
5. Information about standalone (algorithm-only) performance.
6. Type of ground truth used (pathology, outcomes data, etc.) relevant to AI/ML or comparative diagnostic performance.
7. Sample size for a training set or how ground truth for a training set was established.

Ask a specific question about this device

The Palladium High Flow Therapy System is intended to deliver warmed and humidified high-flow respiratory gases to spontaneously breathing adult and pediatric patients weighing at least 3.5 kg within hospital, sub-acute and homecare settings.

The Palladium High Flow Therapy System is designed to heat and humidify respiratory gases and deliver high flow respiratory therapy via a small-bore nasal cannula to spontaneously breathing pediatric and adult patients within hospital, sub-acute and homecare settings.

Palladium is portable, self-contained, AC driven or battery powered with high flow therapy driven by an internal blower room air source and supplied with external oxygen or other gas sources, which is the same as the predicate Vapotherm Flowrest® device.

Palladium utilizes similar semi-permeable small-bore tubing technology for humidification and integrity of a closed, single-use water path disposable as the reference Vapotherm Precision Flow® device.

The provided document is a 510(k) premarket notification for the "Palladium High Flow Therapy System". It details the device's indications for use, its comparison to predicate devices, and non-clinical performance testing. The document focuses on demonstrating substantial equivalence to a predicate device rather than presenting a standalone study with specific acceptance criteria and detailed quantitative results for the Palladium system's performance.

Based on the provided text, a table of acceptance criteria and reported device performance, and details about a specific study proving the device meets these criteria, is not fully available in the requested format. The document describes several non-clinical tests (biocompatibility, electrical safety, software, and bench/performance testing) and states that the "results demonstrated that the device performance was met after conditioning and was substantially equivalent to the predicate device." However, it does not provide the specific numeric acceptance criteria or the measured performance values for the Palladium device in a clear, quantifiable manner for each test.

Here's a breakdown of what can be extracted based on your requested information:

1. Table of Acceptance Criteria and Reported Device Performance:

The document describes general categories of performance testing and states that the outcomes met expectations or demonstrated substantial equivalence. Specific measurable acceptance criteria values and the actual results of the Palladium device (e.g., "Oxygen accuracy: ±X%" and "Measured: Y%") are not provided.

Regarding temperature accuracy, the comparison table states "Temperature Accuracy: SAME - K103316 ± 2 °C" for the subject device, indicating this was the acceptance criteria and presumably met. For other performance metrics, only a general statement of meeting performance and substantial equivalence is given. |

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

• Sample Size: Not specified for any of the non-clinical tests.
• Data Provenance: The tests are non-clinical (bench testing, lab-based safety, and performance evaluations), therefore no patient data or geographical provenance is applicable in the context of the supplied text. The company (Vapotherm, Inc.) is based in Exeter, NH, USA. The testing would have been conducted in a controlled lab environment.

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

• This information is not applicable. The documentation refers to non-clinical (bench) testing, software verification, and compliance with established standards. There is no mention of "ground truth" established by experts in the context of clinical expert review.

4. Adjudication method for the test set:

• This information is not applicable. Adjudication methods are typically used in clinical studies involving interpretation of medical data by multiple human readers, which is not described here.

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 MRMC study was conducted or mentioned in this document. This is a 510(k) submission for a respiratory gas humidifier, not an AI-assisted diagnostic device.

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

• This is not applicable as the device is a physical medical device (humidifier), not an algorithm or AI system. Its performance is evaluated through engineering and physiological testing, not AI-centric standalone performance studies.

7. The type of ground truth used:

• For the non-clinical performance and safety tests, the "ground truth" would be the objective measurements against pre-defined engineering specifications and internationally recognized standards (e.g., ISO, IEC). For example, temperature measurements against a calibrated reference, flow rate measurements, or chemical analysis for biocompatibility tests. It's based on technical standards and specifications, not expert consensus, pathology, or outcomes data in the usual clinical sense.

8. The sample size for the training set:

• Not applicable. This is not an AI/Machine Learning device that requires a training set.

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

• Not applicable for the same reason as above.

Ask a specific question about this device

Precision Flow® HVNI is intended for use to add warm moisture to breathing gases from an external source for administration to a neonate/infant, pediatric and adult patients in the hospital and subacute institutions settings. It adds heat and moisture to a blended medical air/ oxygen mixture and assures the integrity of the precise air/oxygen mixture via an integral oxygen analyzer. The flow rates may be from 1 to 40 liters per minute via nasal cannula.

Precision Flow® HVNI provides high velocity nasal insufflation (HVNI) with simultaneous oxygen delivery to augment breathing of spontaneously breathing patients suffering from respiratory distress and/or hypoxemia in the hospital setting. Precision Flow® HVNI is not intended to provide total ventilatory requirements of the patient and not for use during field transport.

The Precision Flow® HVNI system delivers high flow rates of heated and humidified blended breathing gas through high flow nasal cannulas. The Precision Flow® HVNI system can connect to air and oxygen source. The Precision Flow® HVNI may be operated with limited performance at gas inlet pressures as low as 4 psi (28 kPa). For the full specified range of gas flows and oxygen percentages, both gas inlet pressures must be at minimum 40 psi (276 kPa).The main unit contains an integrated blender that delivers the targeted gas mixture to the disposable patient circuit (DPC). The Disposable Patient Circuit contains:

• Water path: tubing from sterile water supply to vapor transfer cartridge
• . Vapor transfer (humidification) cartridge: 2 types; low flow (1-8 lpm) and high flow (5-40 lpm)
• Delivery Tube: triple lumen tubing
• . Nasal Cannula

The device automatically senses cartridge type. The available set temperature range is 33 °C to 39 °C. The device also contains a backup battery to provide power only for 15 minutes.

Here's a breakdown of the acceptance criteria and the study information for the Precision Flow® HVNI, based on the provided text:

Acceptance Criteria and Device Performance

The acceptance criteria for the Precision Flow® HVNI are primarily non-clinical, focusing on safety, performance standards, software validation, and labeling requirements. The clinical studies establish safety and effectiveness by demonstrating non-inferiority or comparable outcomes to existing treatments.

*   **Data Provenance for all neonate studies:** Published literature, likely international based on author names and journal types, but not explicitly stated for each study.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
* Similar to the adult study, ground truth involved clinical outcomes assessed by treating medical professionals (neonatologists, nurses, etc.) within the context of their respective clinical trials or retrospective data collection. Specific expert qualifications beyond clinical roles are not detailed within the provided text.

3. Adjudication method for the test set:

   • Not explicitly stated as a formal adjudication panel. Outcomes were generally defined by protocol-driven clinical events (e.g., extubation failure, need for intubation, physiological parameters).

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. These are clinical studies comparing therapies, not AI assistance for human readers.

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

   • No.

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

   • Outcomes Data: Primary ground truths included extubation failure rates, rates of intubation/mechanical ventilation, occurrences of pneumothorax, nosocomial infection, ROP surgery, bronchopulmonary dysplasia (BPD), air leaks, IVH, NEC, sepsis, duration of respiratory support, need for surfactant, time to full feeds, length of stay, mortality, and nasal trauma scores.

7. The sample size for the training set:

   • Not applicable.

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

   • Not applicable.

Ask a specific question about this device

The Precision Flow® - Heliox is intended to warm and add moisture to breathing gases from an external source for administration to neonate/infant, pediatric and adult patients in the hospital and sub-acute institutions. It adds heat and moisture to a blended medical heliox (79% helium. 21% oxygen)/oxygen mixture and assures the integrity of the precise heliox (79% helium, 21% oxygen)/oxygen mixture via an integral oxygen analyzer. The flow rates may be from 1 to 40 liters per minute via nasal cannula.

The Precision Flow® - Heliox consists of two parts: The main unit which contains all the electrical and electronic components including the electronic blender and flow controllers. All the sensors are located in the main unit. The main unit has no water pathways and the gas pathway contains only dry gas at room temperature, and consequently does not need internal cleaning or disinfection. The disposable components comprising the disposable water module, vapor transfer cartridge and heated delivery tube. Conditions in the circulating water and gas streams are sensed remotely via the interface between the main unit and the disposable module.

The Vapotherm Precision Flow® - Heliox is a medical device intended to warm and humidify breathing gases, specifically a heliox/oxygen mixture, for neonate/infant, pediatric, and adult patients in hospital and sub-acute settings.

Here's a breakdown of the acceptance criteria and study information:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document lists various standards that the Precision Flow® - Heliox met, with some exceptions. It also includes functional and design verification tests. The "Reported Device Performance" for these tests is generally stated as: "In all instances, the Precision Flow® - Heliox functioned as intended and the results observed were as expected." Specific quantitative performance data is limited within this summary but is generally implied by compliance with the referenced standards.

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

The 510(k) summary does not provide specific sample sizes for particular performance tests or explicitly mention a "test set" in the context of clinical or image-based studies. The performance data section broadly states: "In all instances, the Precision Flow® - Heliox functioned as intended and the results observed were as expected." This implies that the design verification tests listed were conducted on the device.

• Sample Size for Test Set: Not explicitly stated for each test, but implied to be sufficient for demonstrating compliance with cited standards and internal design verification plans.
• Data Provenance (Country of Origin, Retrospective/Prospective): Not specified. The tests are likely laboratory or bench testing, not clinical studies involving patient data.

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

• This information is not applicable to this type of device and study. The testing for the Precision Flow® - Heliox involves engineering and performance validation against objective technical standards (e.g., flow rates, temperature, alarm function, electrical safety), not subjective interpretation requiring expert consensus.

4. Adjudication Method for the Test Set

• This information is not applicable as the evaluation relies on objective measurements against engineering specifications and regulatory standards, not subjective interpretations requiring adjudication.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size of AI vs. Without AI Assistance

• No, an MRMC comparative effectiveness study was not done. This device is a medical gas humidifier/blender, not an AI-powered diagnostic or decision-support tool. It does not involve human readers interpreting cases with or without AI assistance.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

• No, this is not applicable. The device is hardware with integrated software for control, not a standalone algorithm. Its performance is inherent to its physical operation and control systems.

7. The Type of Ground Truth Used

• The "ground truth" for this device's performance is established by objective engineering specifications, technical standards (e.g., ISO, ANSI/AAMI, IEC), and manufacturer-defined design requirements. This includes accuracy of gas blending, flow rates, temperature control, alarm thresholds, electrical safety, and biocompatibility.

8. The Sample Size for the Training Set

• This is not applicable in the context of a traditional "training set" for machine learning or AI models. The device's software is likely developed using standard software engineering practices and verified accordingly, rather than trained on a dataset.

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

• This is not applicable for the reasons stated above. The "ground truth" for the device's operational parameters is derived from engineering design, relevant medical standards, and intended physiological effects of humidified gas delivery.

Ask a specific question about this device

The Flowrest® delivers warmed humidified high-flow breathing gases. The Flowrest® is intended for treating spontaneously breathing patients who require warmed and humidified high-flow respiratory gases within the homecare, subacute and hospital settings.

The Flowrest® is an integrated non-invasive high flow device incorporating a blower, an air flow heater, a heated humidifier, and a dual lumen breathing circuit and cannula. Filtered room air is drawn in through a blower, where it passes a heater. The heated air is split between the inner lumen and outer lumen of the dual lumen breathing circuit. The heated air in the inner lumen passes through a heated humidifier and is delivered to the patient through a cannula. The heated air in the outer lumen passes through the entire length of the breathing circuit and serves to insulate the humidified patient air, thus minimizing condensation and rainout.

The Flowrest® is comprised of two functional, yet integrated components. One is a motorized fan assembly that provides the physician prescribed high flows of heated breathing and insulating gases between 15 and 35 liters per minute. The fan speed is directly related to flow rate and is controlled by software. The blower assembly output connects directly to a humidification chamber at the front of the device.

The second component of the Flowrest® is a heated humidifier. The water is contained in the humidification chamber positioned on a heater plate at the front of the unit. The chamber connects directly to the blower assembly. Air flow from the device passes through the heated humidification chamber, is warmed and humidified and after passing through the breathing circuit, is delivered to the patient through a cannula. The second flow of warm air through the outside lumen of the delivery tube bypasses the humidification chamber through the top of the humidifier chamber. Ambient temperature is monitored in order to reduce humidified patient air condensation. Temperature controls are controlled by software.

The provided document is a 510(k) summary for the Vapotherm Flowrest®, a respiratory gas humidifier. It details the device's intended use, technological characteristics, and a comparison to a predicate device to establish substantial equivalence.

However, the document does not contain the kind of information typically found in studies proving an AI/Machine Learning device's performance against acceptance criteria. Specifically, it lacks:

• A table of acceptance criteria for AI performance metrics (e.g., sensitivity, specificity, AUC).
• Details about a test set (sample size, provenance).
• Information on expert ground truth establishment (number of experts, qualifications, adjudication).
• MRMC studies, standalone AI performance, or training set details.
• The type of ground truth used (pathology, outcomes data, etc.)

The document focuses on the engineering and safety performance of a medical device (a humidifier) against established medical device standards (e.g., ISO, IEC), and its substantial equivalence to a predicate device.

Therefore, I cannot fulfill your request for AI-specific performance criteria and study details based on the provided text. The "Performance Data" section in the document refers to compliance with safety and design standards for a gas humidifier, not the performance of an AI algorithm.

If this was an AI/ML device, the information would typically look like this (hypothetically, what you are asking for):

1. A table of acceptance criteria and the reported device performance (Hypothetical for an AI device):

Ask a specific question about this device

Precision Flow™ is intended for use to add warm moisture to breathing gases from an external source for administration to a neonate/infant, pediatric and adult patients in the hospital, sub-acute institutions, and home settings. It adds heat and moisture to a blended medical air/oxygen mixture and assures the integrity of the precise air/oxygen mixture via an integral oxygen analyzer. The flow rates may be from 1 to 40 liters per minute via nasal cannula.

The Precision Flow™ consists of two parts: The main unit which contains all the electrical and electronic components including the electronic blender and flow controllers. All the sensors are located in the main unit. The main unit has no water pathways and the gas pathway contains only dry gas at room temperature, and consequently does not need internal cleaning or disinfection. The disposable components comprising the disposable water module, vapor transfer cartridge and heated delivery tube. Conditions in the circulating water and gas streams are sensed remotely via the interface between the main unit and the disposable module.

This 510(k) summary describes a medical device, the Vapotherm Precision Flow™, which is a respiratory gas humidifier. It is not an AI/ML powered device, therefore, many of the requested categories related to AI performance, ground truth, and expert evaluation are not applicable.

Here's an analysis of the provided text based on your request, highlighting the non-applicability of AI/ML specific criteria:

Acceptance Criteria and Device Performance (Non-AI/ML Device)

The Vapotherm Precision Flow™ is cleared based on demonstrating substantial equivalence to predicate devices, primarily through non-clinical performance data (testing) and a comparison of its technological characteristics to existing devices. The "acceptance criteria" here are implicitly that the device performs its intended functions (humidifying and blending medical gases) safely and effectively, and that these performance characteristics are comparable to legally marketed predicate devices without raising new safety or effectiveness concerns.

Since this is not an AI/ML device, performance metrics like sensitivity, specificity, accuracy, or AUC are not applicable or reported in this 510(k) summary. Instead, the performance is demonstrated through various engineering, safety, and biocompatibility tests.

Non-Applicable (N/A) for AI/ML Specific Questions:

Given that K072845 describes a humidifier, not an AI/ML-powered device, the following categories are not applicable. The submission process for such a device focuses on engineering specifications, safety testing, and performance validation against established standards and predicate devices, rather than statistical performance against a ground truth dataset.

2. Sample size used for the test set and the data provenance: N/A (Not an AI/ML device, no "test set" in the context of an algorithm's classification/prediction performance). Testing involved physical hardware, software, and biological compatibility, not a data-driven test set.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: N/A (Not an AI/ML device, no ground truth established by experts for algorithmic performance).

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set: N/A (Not an AI/ML device, no adjudication of algorithm 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: N/A (Not an AI/ML device. No human-in-the-loop AI assistance involved).

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: N/A (Not an AI/ML device, no standalone algorithm performance to evaluate).

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): N/A (Not an AI/ML device). The "ground truth" for this device relates to physical measurements meeting specifications (e.g., oxygen percentage, temperature, bacterial counts being zero).

8. The sample size for the training set: N/A (Not an AI/ML device, no "training set"). Software verification and validation are described, but this refers to traditional software engineering processes, not machine learning model training.

9. How the ground truth for the training set was established: N/A (Not an AI/ML device, no "training set" or ground truth in the ML context).

Ask a specific question about this device

The Vapotherm 2000i and 2000h are designed to add moisture to and to warm breathing gases for administration to patients, including neonates/infants, and adults. The flow rates may be from 1 to 40 liters per minute via nasal cannula. Environments for use -- Home, Hospital, Sub-acute Institutions.

The Vapotherm 2000i device is a modification to cleared Vapotherm 2000i device. The base device of the modified Vapotherm 2000i device has the same technological characteristic as the predicate Vapotherm 2000i device. The software contained in the modified device has not been modified as a result of the corrections being effected and remains identical to the software resident in the predicate device.

The provided 510(k) summary for Vapotherm's 2000i Respiratory Gas Humidifier is for a Special 510(k) Corrective Action Being Effected. This means the submission is for a modification to an already cleared device, and the focus is on demonstrating that the modifications do not raise new issues of safety or effectiveness.

Therefore, the document does not contain specific acceptance criteria, study details, sample sizes, expert qualifications, or ground truth establishment methods in the way a traditional de novo or full 510(k) submission for a novel device or significant change might.

Here's an analysis based on the provided text, addressing your points where possible and noting where information is absent:

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

• Explanation: The document states that the software has not been modified and remains identical to the predicate device. The modifications are implied to be non-software related and do not raise new issues of safety or effectiveness. The "extensive testing" would likely have focused on verifying that the changes did not negatively impact the device's original performance specifications (e.g., humidification output, temperature control, safety alarms), rather than establishing new performance criteria.

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

• Sample Size for Test Set: Not mentioned.

• Data Provenance: Not mentioned.

• Explanation: Given this is a Special 510(k) for corrective action on an existing device, the testing would likely be internal verification and validation testing, not a clinical study on a patient population.

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)

• Number of Experts: Not applicable.

• Qualifications of Experts: Not applicable.

• Explanation: As this is a medical device humidifier, not an AI or diagnostic device, the concept of "ground truth" derived from expert consensus for a test set is not relevant in this context. Performance would be measured against engineering specifications and regulatory standards for humidification.

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

• Adjudication Method: Not applicable.

• Explanation: Again, this is for a hardware modification to a humidifier, not a diagnostic or AI device where adjudication of expert opinions would typically be required for ground truth.

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

• MRMC Study: No.

• Effect Size: Not applicable.

• Explanation: This type of study is relevant for AI-powered diagnostic tools. It is not applicable to a respiratory gas humidifier.

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

• Standalone Performance Test: Not applicable in the context of an algorithm.

• Explanation: The device is a physical humidifier. While it has embedded software, the performance assessment would be of the device's physical functions (e.g., humidification, temperature control, flow rates), not a standalone algorithm's diagnostic or predictive capabilities. The document explicitly states the software "has not been modified" and "remains identical to the software resident in the predicate device."

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

• Type of Ground Truth: Not explicitly stated, but for a humidifier, "ground truth" would be established through engineering specifications and quantifiable physical measurements (e.g., hygrometry, thermometry, flow meters) against established performance standards for respiratory gas humidifiers.

8. The sample size for the training set

• Sample Size for Training Set: Not applicable.

• Explanation: The term "training set" is typically used for machine learning models. This device is a traditional medical device, not an AI model, so there is no training set in that sense.

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

• Ground Truth Establishment for Training Set: Not applicable.

• Explanation: Similar to point 8, this pertains to AI/ML development and is not relevant for this device.

Summary of Device and Approval:

• Device Name: Vapotherm™ 2000i and 2000h Respiratory Gas Humidifier
• Submission Type: Special 510(k) Corrective Action Being Effected
• Purpose of Submission: Modification to a previously cleared Vapotherm 2000i device (K042245).
• Key Statement for Performance: "Vapotherm has conducted extensive testing to verify and validate the changes to the previously marketed Vapotherm 2000i device."
• Reason for Approval: The modified device has the same intended use and indications for use, similar principles of operation, and similar technological characteristics as the previously cleared predicate, and the modifications "do not raise any new issues of safety or effectiveness." The software was explicitly not modified.
• Regulatory Outcome: Found substantially equivalent to the predicate device (K042245).

Ask a specific question about this device

The Vapotherm™ 2000h and 2000i are designed to add moisture to and to warm breathing gases for administration to patients, including neonates/infant, pediatrics, and adults. The flow rates may be from 1 to 40 liters per minute via nasal cannula. Environments of use - Home, Hospital, Sub-acute Institutions

The Vapotherm 2000i and Vapotherm 2000h are identical and share the concept of humidification by transpiration of water vapor across a membrane by the use of a low or high flow cartridge with membrane bundles. The difference in the cartridges is only the number of membrane bundles included, fewer in the low flow. Both units and cartridges produce a highly humidified air (relative humidity >95%), virtually free of droplets, at body temperature or above at flow rates from 1 to 40 lpm via a nasal cannula. The water content at 41℃ is 40-50 mg/liter, about fourfold higher than can be achieved by humidification at room temperature. The unique combination of high flow and high vapor-phase humidity allow an unusually wide range of clinical applications. Applications previously considered impractical because of limited patient tolerance for high nasal flow can now be routine because of the comfort provided by warmth and high humidity.

The provided text primarily consists of regulatory summaries and approval letters for the Vapotherm 2000h and 2000i devices. It details the device's function, indications for use, and a comparison to predicate devices. However, it does not contain information about acceptance criteria, specific studies conducted to demonstrate performance against those criteria, sample sizes, expert involvement, or any statistical evaluation of device performance.

Therefore, I cannot directly answer your request based on the provided input. The document focuses on regulatory equivalence rather than an empirical study demonstrating performance against specific acceptance criteria.

To elaborate, the document states:

• Device Description: The Vapotherm 2000i and 2000h produce "a highly humidified air (relative humidity >95%), virtually free of droplets, at body temperature or above at flow rates from 1 to 40 lpm via a nasal cannula. The water content at 41℃ is 40-50 mg/liter..."
• Comparison to Predicate Devices: It highlights "Same" or "No changes" for several attributes when comparing to predicate devices (K000401, K013486, K040862).

These descriptions are technical specifications and comparisons, not acceptance criteria for a validation study. The FDA approval K042245 is based on substantial equivalence to predicate devices, meaning it largely relies on the predicate devices having already met safety and effectiveness standards, rather than requiring extensive new clinical trial data for this specific iteration.

Ask a specific question about this device