Search Results

The Propeller System includes the Propeller Sensor Model 2018-S. The sensor is an accessory device intended for singlepatient use to assist physicians and patients in recording and monitoring the actuations of prescribed pMDI usage for the Symbicort device.

The Propeller Mobile Application records, stores, and transmits usage events from Propeller Sensors, or via manual user entry, to a remote storage system. With the Propeller Mobile Application the user can review information collected from the pMDI sensor, and report and review symptoms and other information about their disease management and its impact. The user may also share their information with their caregivers, physician, and healthcare providers.

The Propeller Web Application is software that, like the Propeller Mobile Application, is intended to allow users to review the collected information and characteristics of their pMDI and its use, to capture other patient-reported information and outcomes, and to allow that information to be shared with their caregivers, physicians, and health care providers.

When used with a prescribed pMDI, the system can report on information captured during the normal course of use, such as the time between actuations that can be helpful in assessing pMDI technique.

The Propeller System is intended to be used in populations from Child (>2 years) to Adult.

The Propeller System can be used both indoors; home, work, and clinical settings, as well as on aircraft.

The Propeller System may also be used in clinical trials where researchers need to know information about the use of pMDI medication(s) by a participant.

The output of the Propeller System is not intended to diagnosis provided by a licensed physician. The Propeller System is not intended for use as an pMDI dose counter, nor is it intended to indicate the quantity of medication remaining in an pMDI.

Pressurized Metered Dose Inhaler (pMDI) / Symbicort Accessory that monitors inhaler usage. The portable sensor mounts to the back of the pMDI and records inhalation events when the inhaler is used.

This document is a 510(k) Premarket Notification from the FDA regarding the "Propeller Sensor for Symbicort" (Model 2018-S). It asserts that the device is substantially equivalent to a previously cleared predicate device (Propeller Sensor Model 2017-B).

Based on the provided text, the device in question is a sensor that attaches to a Pressurized Metered Dose Inhaler (pMDI) to record and monitor its usage. The main purpose of the testing described here is to demonstrate that the new model (2018-S) is substantially equivalent to the previous model (2017-B), especially regarding its ability to detect and record inhaler actuations, and its safety.

Here's an analysis based on your request:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria or a direct performance table for features like accuracy of actuation detection. Instead, it relies on demonstrating substantial equivalence to a predicate device. The "Test Summary" statement, "Test results indicate that the Propeller Sensor Model 2018-S and its predicate Propeller Sensor Model 2017-B complies with predetermined specifications. Software verification and validation testing confirms this result," acts as the overall conclusion of meeting the implicit criteria of functioning similarly and safely to the predicate.

The primary comparison is regarding technological characteristics and their sameness between the new device and the predicate. The table on page 6-7 serves as the direct "comparison" showing where the devices are similar or identical.

Here's how we can infer the "acceptance criteria" and "performance" from this document:

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

• Sample Size: The document does not specify a sample size for any specific "test set" or the number of devices or uses tested. It generally refers to "bench testing."
• Data Provenance: Not explicitly stated, but given it's a submission to the FDA for a medical device company in Madison, WI, the testing would typically be conducted by the manufacturer, which is usually in the U.S. or through their contract labs. The document does not indicate if data was retrospective or prospective in the sense of clinical study data, as no clinical testing was required or performed.

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

• Not applicable. This submission focuses on engineering and performance testing to demonstrate substantial equivalence, not on establishing a "medical ground truth" from experts interpreting diagnostic data (like radiology images). The device's function is to record actuation events, not to interpret complex medical data.

4. Adjudication Method for the Test Set

• Not applicable. As there's no interpretation of complex data by multiple readers necessitating adjudication, this method is not relevant to the type of testing described (bench testing, software verification/validation, electrical safety).

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 study was not conducted. The document explicitly states: "Clinical Testing: No clinical testing was required." The device is intended as an accessory to record pMDI usage, not to provide diagnostic interpretations that would assist human readers in an MRMC setting.

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

• Yes, in essence. The testing described (bench testing, software verification/validation) is a form of standalone performance evaluation of the device's ability to detect and record inhaler actuations, and its software's ability to process and display that data accurately. The core function of the device (detecting actuation) is an algorithmic function performed by the sensor. The reported "Test Summary" and "Conclusion" indicate this standalone performance meets "predetermined specifications" and is "substantially equivalent" to the predicate.

7. The Type of Ground Truth Used

• For the core function of detecting pMDI actuations: The "ground truth" would be the actual physical actuation events of the pMDI during bench testing. This would be established by direct observation or synchronized, validated measurement techniques during the testing process. The device's recorded actuation event would be compared against the actual event occurring.
• For compliance with standards (IEC, ISO): The ground truth is the specified requirements within those engineering and safety standards. The device's performance is measured against these established quantitative and qualitative criteria.

8. The Sample Size for the Training Set

• Not applicable. This device is a sensor that records physical events and transmits data. It's not described as an AI/ML algorithm that requires a "training set" in the conventional sense of machine learning for classification or prediction tasks based on complex data (e.g., image analysis). The "algorithms" would be embedded logic for event detection and data processing, which are validated through standard software V&V and bench testing.

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

• Not applicable. (See point 8).

In summary, this 510(k) submission establishes substantial equivalence primarily through comparing the new device's engineering specifications and performance (demonstrated through bench testing and compliance with recognized standards) to a previously cleared predicate device. It avoids significant clinical studies or complex AI/ML "training/ground truth" methodologies because its function is a relatively straightforward data acquisition task rather than a diagnostic interpretation or predictive AI model.

Ask a specific question about this device

The Propeller System includes the Propeller Sensor Model 2017-B. The sensor is an accessory device intended for singlepatient use to assist physicians and patients in recording and monitoring the actuations of prescribed DPI usage for the Neohaler and Breezhaler devices.

The Propeller Mobile Application records, stores, and transmits usage events from Propeller Sensors, or via manual user entry, to a remote storage system. With the Propeller Mobile Application the user can review information collected from the DPI sensor, and review symptoms and other information about their disease management and its impact. The user may also share their information with their caregivers, physician, and healthcare providers.

The Propeller Web Application is software that, like the Propeller Mobile Application, is intended to allow users to review the collected information and characteristics of their DPI and its use, to capture other patient-reported information and outcomes, and to allow that information to be shared with their caregivers, physicians, and health care providers.

When used with a prescribed DPI, the system can report on information captured during the normal course of use, such as the time between actuations that can be helpful in assessing DPI technique.

The Propeller System is intended to be used in populations from Child (>2 years) to Adult.

The Propeller System can be used both indoors home, work, and clinical settings, as well as on aircraft.

The Propeller System may also be used in clinical trials where researchers need to know information about the use of DPI medication(s) by a participant.

The output of the Propeller System is not intended to diagnosis provided by a licensed physician. The Propeller System is not intended for use as an DPI dose counter, nor is it intended to indicate the quantity of medication remaining in an DPI.

Dry Powder Inhaler (DPI) / Neohaler Accessory that monitors inhaler usage. The portable sensor mounts on top of a DPI and records inhalation events when the inhaler is used.

The provided text describes the Propeller Sensor Model 2017-B, an accessory device for Dry Powder Inhalers (DPIs), and its substantial equivalence to a predicate device (Propeller Sensor Model 2015-E). However, the document does NOT contain information regarding acceptance criteria and a study that proves the device meets those criteria in the context of diagnostic performance metrics (e.g., sensitivity, specificity, accuracy).

Instead, the document focuses on:

• Regulatory clearance (510(k) summary): Demonstrating "substantial equivalence" to a previously cleared device.
• Technological comparison: Highlighting the similarities between the new device and the predicate.
• Bench testing: Confirming compliance with various standards and specifications (e.g., electrical safety, biocompatibility, battery performance).

Therefore, I cannot provide the requested information about acceptance criteria and performance metrics for diagnostic purposes. The device described here is a sensor for monitoring inhaler usage, not a diagnostic tool requiring such performance studies.

Here's what can be extracted from the document regarding the type of testing and its conclusion:

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

Since the device is an accessory for monitoring inhaler usage and not a diagnostic device, the acceptance criteria are not in terms of diagnostic performance metrics (e.g., sensitivity, specificity). Instead, they relate to compliance with regulatory standards and functional specifications.

2. Sample size used for the test set and the data provenance:
Not applicable as no diagnostic performance study involving test sets from patients was conducted. The testing focused on engineering, software verification, and biocompatibility.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
Not applicable. No ground truth establishment by experts for diagnostic performance was required as it's not a diagnostic device.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
Not applicable.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
Not applicable. This device is a sensor for inhaler usage, not an AI-assisted diagnostic tool for human readers.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
Not applicable. While the device does have an "algorithm" to detect inhaler actuations, the document does not describe it in terms of standalone "performance" in the way a diagnostic algorithm would be evaluated (e.g., sensitivity/specificity for a disease). The testing confirms its functional operation (e.g., compliance with specifications) rather than diagnostic accuracy.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):
Not applicable in the context of diagnostic performance. The "ground truth" for the device's functionality would likely be physical measurements and observations during bench testing to confirm accurate detection of inhaler actuations.

8. The sample size for the training set:
Not applicable. As a non-AI diagnostic device, there is no mention of a "training set" in the context of machine learning. The device's operation is based on physical principles (sensors detecting actuation) rather than learned patterns from a training dataset.

9. How the ground truth for the training set was established:
Not applicable.

Ask a specific question about this device

The Propeller System includes the Propeller Sensor is an accessory device intended for singlepatient use to assist physicians and patients in recording and monitoring the actuations of prescribed DPI usage for the Ellipta devices.

The Propeller Mobile Application records, stores, and transmits usage events from Propeller Sensors, or via manual user entry, to a remote storage system. With the Propeller Mobile Application the user can review information collected from the DPI sensor, and review symptoms and other information about their disease management and its impact. The user may also share their information with their caregivers, physician, and healthcare providers.

The Propeller Web Application is software that, like the Propeller Mobile Application, is intended to allow users to review the collected information and characteristics of their DPI and its use, to capture other patient-reported information and outcomes, and to allow that information to be shared with their caregivers, physicians, and health care providers.

When used with a prescribed DPI, the system can report on information captured during the normal course of use, such as the time between actuations that can be helpful in assessing DPI technique.

The Propeller System is intended to be used in populations from Child (>2 years) to Adult.

The Propeller System can be used both indoors home, work, and clinical settings, as well as on aircraft.

The Propeller System may also be used in clinical trials where researchers need to know information about the use of DPI medication(s) by a participant.

The output of the Propeller System is not intended to diagnosis provided by a licensed physician. The Propeller System is not intended for use as an DPI dose counter, nor is it intended to indicate the quantity of medication remaining in an DPI.

Dry Power Inhaler (DPI) / Ellipta Accessory that monitors a patient's inhaler usage. The portable, polycarbonate sensor clips on top of a DPI mouthpiece cover and passively records inhalation events when the inhaler is used using infra-red (IR) sensors. The sensor then sends the event information via Bluetooth to the mobile phone or wireless gateway.

The provided text does not contain detailed acceptance criteria or a study proving that the device meets those criteria with specific performance metrics. This document is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device rather than providing intricate details of performance studies against defined acceptance criteria.

However, based on the information available, I can infer some aspects and present the information as requested, using placeholders where specific data is absent.

Here's a breakdown of what can be extracted and what is missing:

1. Table of Acceptance Criteria and Reported Device Performance

The document mentions that "Test results indicate that the Propeller Sensor Model 2015-E... complies with predetermined specifications." However, the specific predetermined specifications (acceptance criteria) and the corresponding reported device performance values are not detailed in this summary.

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

The document states, "Bench testing included battery performance testing and particle size distribution (PSD) testing." It also references "Software verification and validation testing." However, no specific sample sizes for these test sets are provided, nor is the data provenance (e.g., country of origin, retrospective or prospective) mentioned.

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

This information is not provided. The testing mentioned (software, electrical safety, biocompatibility, battery, PSD) does not typically involve expert review for ground truth establishment in the same way as performance studies for diagnostic algorithms.

4. Adjudication Method

This information is not applicable and therefore not provided. The testing described does not involve an adjudication process.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No MRMC comparative effectiveness study was done or reported. The device is a sensor for monitoring inhaler usage, not a diagnostic tool requiring human reader interpretation in comparison to AI assistance. The document explicitly states: "Clinical Testing No clinical testing was required."

6. Standalone (Algorithm Only) Performance Study

The device is a hardware sensor that passively records inhalation events and transmits data. Its "performance" is primarily about accurately detecting these events and transmitting them reliably. While software verification and validation were performed, no standalone "algorithm-only" performance study in the context of, for example, diagnostic image analysis, is described. The core function is sensing and data transmission, for which specific accuracy metrics are implied to be part of the "predetermined specifications" but are not detailed.

7. Type of Ground Truth Used

For the various tests mentioned:

• Software verification and validation: Ground truth would be defined by the software requirements and specifications.
• Compliance to standards (IEC, ISO): Ground truth is the adherence to the requirements outlined in those standards.
• EMC, Wireless Coexistence: Ground truth is defined by the technical limits and requirements of relevant standards and regulations.
• Battery performance, PSD: Ground truth would be the expected physical or electrical characteristics defined by the manufacturer's specifications.

8. Sample Size for the Training Set

This information is not provided and likely not relevant in the conventional sense of machine learning training data for this type of device. The device is a hardware sensor primarily. While there is a "Propeller System" that includes mobile and web applications, the document focuses on the sensor itself. Any "training" for the sensor would be during its design and calibration, not typically described as a "training set" in this context.

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

Not applicable/Not provided given the nature of the device and the absence of a distinct "training set" as understood in AI/ML performance studies.

Ask a specific question about this device

The Propeller System includes the Propeller Sensor is an accessory device intended for singlepatient use to assist physicians and patients in recording and monitoring the actuations of prescribed DPI usage for the Diskus devices.

The Propeller Mobile Application records, stores, and transmits usage events from Propeller Sensors, or via manual user entry, to a remote storage system. With the Propeller Mobile Application the user can review information collected from the DPI sensor, and review symptoms and other information about their disease management and its impact. The user may also share their information with their caregivers, physician, and healthcare providers.

The Propeller Web Application is software that, like the Propeller Mobile Application, is intended to allow users to review the collected information and characteristics of their DPI and its use, to capture other patient-reported information and outcomes, and to allow that information to be shared with their caregivers, physicians, and health care providers.

When used with a prescribed DPI, the system can report on information captured during the normal course of use, such as the time between actuations that can be helpful in assessing DPI technique.

The Propeller System is intended to be used in populations from Child (>2 years) to Adult.

The Propeller System can be used both indoors home, work, and clinical settings, as well as on aircraft.

The Propeller System may also be used in clinical trials where researchers need to know information about the use of DPI medication(s) by a participant.

The output of the Propeller System is not intended to diagnosis provided by a licensed physician. The Propeller System is not intended for use as an DPI dose counter, nor is it intended to indicate the quantity of medication remaining in an DPI.

Dry Powder Inhaler (DPI) / Diskus Accessory that monitors inhaler usage. The portable sensor mounts on top of a DPI and records inhalation events when the medication is used.

This document (K152882) describes the 510(k) premarket notification for the Propeller Sensor Model 2014-D. It explicitly states that no new testing was performed for the OTC indication, and no clinical testing was required. The device's substantial equivalence is based on its identity to a previously cleared predicate device (K143671) and another (K142516) with only a change from MDI to DPI.

Therefore, the detailed information requested regarding acceptance criteria, study sample sizes, ground truth establishment, expert involvement, and MRMC studies are not available in this specific regulatory submission as no new performance studies were conducted for this 510(k) clearance.

However, based solely on the provided document, here's what can be inferred and what remains unknown regarding device performance validation:

1. Table of Acceptance Criteria and Reported Device Performance:

Since no new performance testing was conducted, there are no specific numeric acceptance criteria or reported device performance metrics presented in this document for the Propeller Sensor Model 2014-D in its OTC indication. The primary "performance" assessed was functional equivalence to the predicate.

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

• Sample Size: Not applicable/not provided for new performance testing, as none was conducted specific to this 510(k). The functional testing performed was "bench testing."
• Data Provenance: Not applicable/not provided for new performance testing. The document refers to prior testing for predicate devices.

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

• Not applicable, as no new performance studies with ground truth establishment were conducted for this 510(k). Hazard analysis involved review by (unspecified) experts during the predicate device clearance process.

4. Adjudication Method for the Test Set:

• Not applicable, as no new performance studies were conducted.

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

• No, an MRMC study was not done. The device does not involve human interpretation of medical images or data that would necessitate such a study. It is an accessory to monitor inhaler usage.

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

• The "functional testing" performed would be considered analogous to standalone performance, as it tests the device's ability to record actuations independently. However, no specific metrics like accuracy, sensitivity, or specificity are provided for this functional test for the current submission, as it relied on the established performance of the predicate. The device's primary function is data acquisition and transmission, not algorithmic interpretation requiring performance metrics typical of AI/ML devices.

7. The Type of Ground Truth Used:

• For the predicate device's original clearance, functional ground truth would have been established by comparing the device's recorded actuations against directly observed or mechanically triggered actuations of the DPI/MDI. This document relies on the ground truth established for the predicate device.

8. The Sample Size for the Training Set:

• Not applicable. This device is not described as utilizing a machine learning algorithm that requires a training set in the context of this 510(k). Its function is based on sensor detection, not pattern recognition learned from data.

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

• Not applicable, as there is no mention of a training set for a machine learning algorithm in this submission.

In summary, this 510(k) clearance (K152882) for the Propeller Sensor Model 2014-D focused on demonstrating substantial equivalence to previously cleared predicate devices (K143671 and K142516) and a change in indication (Prescription Use to OTC). It explicitly states that no new clinical or performance testing was required or performed for this specific submission. The acceptance criteria were implicitly met by demonstrating that the device is identical in technology and functionality to the predicate and that the change to OTC status did not introduce new safety concerns based on hazard analysis and bench testing.

Ask a specific question about this device

The Propeller System includes the Propeller Sensor Model 2014-R. The sensor is an accessory device intended for single-patient use to assist physicians and patients in recording and monitoring the actuations of prescribed SMI usage.

The Propeller Mobile Application records, stores, and transmits usage events from Propeller Sensors, or via manual user entry, to a remote storage system. With the Propeller Mobile Application the user can review information collected from the SMI sensor, and report and review symptoms and other information about their disease management and its impact. The user may also share their information with their caregivers, physician, and healthcare providers.

The Propeller Web Application is software that, like the Propeller Mobile Application, is intended to allow users to review the collected information and characteristics of their SMI and its use, to capture other patient-reported information and outcomes, and to allow that information to be shared with their caregivers, physicians, and health care providers.

When used with a prescribed SMI, the system can report on information captured during the normal course of use, such as the time between actuations that can be helpful in assessing SMI technique.

The Propeller System is intended to be used in populations from Child (>2 years) to Adult.

The Propeller System can be used both indoors and outdoors; home, work, and clinical settings, as well as on aircraft.

The Propeller System may also be used in clinical trials where researchers need to know information about the use of SMI medication(s) by a participant.

The output of the Propeller System is not intended to diagnose or replace a diagnosis provided by a licensed physician. The Propeller System is not intended for use as an SMI dose counter, nor is it intended to indicate the quantity of medication remaining in an SMI.

Electronic Soft-Mist Inhaler (SMI) Accessory. The Propeller Sensor Model 2014-R keeps track of medication use, with a record when a soft mist inhaler is used. The sensor is a small device that attaches to the top an existing inhaler. Both the subject device and the predicate device use technology that includes bluetooth wireless connectivity which connects to the same previously cleared Propeller Health software system together with a mobile phone or wireless gateway.

The provided document is a 510(k) summary for the Propeller Sensor Model 2014-R, focusing on its reclassification for Over-The-Counter (OTC) use. It does not describe an AI/ML-based medical device. Therefore, the questions related to AI/ML model performance, such as acceptance criteria based on AI metrics, sample sizes for test and training sets, expert ground truth establishment, adjudication methods, or MRMC studies, are not applicable.

The document primarily addresses the substantial equivalence of the Propeller Sensor Model 2014-R for OTC use to its previously cleared prescription-use version (K142960) and another OTC predicate (K142516).

Here's a breakdown of the relevant information provided:

1. Table of Acceptance Criteria and Reported Device Performance:

The document focuses on compliance with established medical device standards and the device's functional equivalence to its predicate. There isn't a table presenting specific acceptance criteria and reported device performance in the context of an AI/ML device (e.g., sensitivity, specificity, or AUC). Instead, the "performance" is demonstrated by adherence to safety and functional standards.

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

• Sample Size: Not applicable. The testing described is primarily focused on engineering validation, safety, and functional equivalence, not on a data-driven performance evaluation with a "test set" in the context of AI/ML.
• Data Provenance: Not applicable for AI/ML. The device's functionality involves recording SMI usage events, but the testing described is not based on patient data in this context.

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

Not applicable. The ground truth concept for an AI/ML test set is not relevant here as this is not an AI/ML device.

4. Adjudication method for the test set:

Not applicable. There is no mention of an adjudication method, as it doesn't apply to the type of testing described (engineering, safety, functional equivalence).

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 study was not done. This is not an AI/ML device, and its purpose is not to assist human readers in interpretation.

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

No, a standalone algorithm performance study was not done. This is not an AI/ML device. The device itself is a physical sensor and associated software for tracking inhaler use.

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

Not applicable. Ground truth for AI/ML models is not relevant here. The "ground truth" for the device's function is simply the actual actuation of the SMI, which the sensor is designed to detect and record. The testing confirmed the sensor's ability to accurately record these events and its compliance with safety and electrical standards.

8. The sample size for the training set:

Not applicable. There is no AI/ML model described that would require a training set.

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

Not applicable. There is no AI/ML model described that would require a ground truth for a training set.

Ask a specific question about this device

The Propeller System includes the Propeller Model 2014-D Sensor is an accessory device intended for singlepatient use to assist physicians and patients in recording and monitoring the actuations of prescribed DPI usage for the Diskus devices.

The Propeller Mobile Application records, stores, and transmits usage events from Propeller Sensors, or via manual user entry, to a remote storage system. With the Propeller Mobile Application the user can review information collected from the DPI sensor, and report and review symptoms and other information about their disease management and its impact. The user may also share their information with their caregivers, physician, and healthcare providers.

The Propeller Web Application is software that, like the Propeller Mobile Application, is intended to allow users to review the collected information and characteristics of their DPI and its use, to capture other patient-reported information and outcomes, and to allow that information to be shared with their caregivers, physicians, and health care providers.

When used under the care of a physician with a prescribed DPI, the system can report on information captured during the normal course of use, such as the time between actuations that can be helpful in assessing DPI technique.

When used under the care of a physician with a prescribed DPI, the system can be used to reduce the frequency of respiratory health symptoms and exacerbations by increasing adherence to DPI medications through the use of feedback such as reminders and notifications, and self-management education.

The Propeller System is intended to be used in populations from Child (>2 years) to Adult.

The Propeller System can be used both indoors; home, work, and clinical settings, as well as on aircraft.

The Propeller System may also be used in clinical trials where researchers need to know information about the use of DPI medication(s) by a participant.

The output of the Propeller System is not intended to diagnose or replace a diagnosis provided by a licensed physician. The Propeller System is not intended for use as an DPI dose counter, nor is it intended to indicate the quantity of medication remaining in an DPI.

Dry Powder Inhaler (DPI) / Diskus Accessory

The subject device uses technology similar to the predicate device including Bluetooth wireless connectivity which connects to the same previously cleared Propeller Health software system together with a mobile phone or wireless gateway. The Sensor Model 2014-D is different from the Sensor Model 2 in that it contains enclosure size differences required to install on the DPI inhaler and electronic sensors to detect Propeller Sensor 2014-D use rather than a button which was used in the predicate device.

The provided text describes the Propeller Sensor Model 2014-D, an accessory device for Dry Powder Inhalers (DPIs), and its comparison to a predicate device. However, the document does not contain specific acceptance criteria values or a detailed study explicitly proving the device meets these criteria in the format requested.

The text generally states that "Test results indicate that the Propeller Sensor Model 2014-D and its predicate Propeller System Model 2 complies with predetermined specifications. Software verification and validation testing confirms this result." and "the subject device meets the predetermined performance specifications as was the case with the predicate device." without providing the actual specifications or the detailed results of the tests in a quantitative manner.

Therefore, I cannot populate the table and answer all questions directly from the provided input. I will extract what information is present and indicate where the information is missing.

Here's the breakdown based on the provided document:

1. Table of acceptance criteria and the reported device performance:

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

• Sample size: Not specified.
• Data provenance: The testing appears to be bench testing and software verification/validation conducted by the manufacturer, Reciprocal Labs Corporation, as part of their 510(k) submission. No specific country of origin for test data or whether it was retrospective/prospective is mentioned, but it generally refers to pre-market testing.

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. The document outlines bench testing, software testing, and compliance with standards, but does not refer to expert-established ground truth in the context of diagnostic accuracy for this type of device. The ground truth for actuation detection would likely be based on physical detection during bench tests.

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

• Not applicable/Not provided. This type of adjudication is typically used in clinical studies for diagnostic devices, which was stated as "No clinical testing was required" for this device.

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. The device is a sensor system for recording DPI actuations and providing user information/feedback, not an AI-assisted diagnostic tool for human readers. "No clinical testing was required."

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

• Yes, implicitly. The listed tests (bench testing, software verification/validation, compliance to standards) would evaluate the device's performance independently of human interaction in the loop, beyond basic usability. The device's primary function (recording actuations) is automated.

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

• For the core function of detecting DPI actuations, the ground truth would have been established through controlled physical actuations on the bench, likely using mechanical or human operation with direct observation or other validated measurement methods (e.g., measuring force, movement, etc.). For software and system functionality (data transmission, app features), ground truth would be established against documented functional requirements.

8. The sample size for the training set:

• Not applicable/Not provided. The document describes a "sensor" and "system" that perform specific functions (recording actuations, transmitting data, providing reminders), rather than a machine learning or AI model that requires a training set in the typical sense.

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

• Not applicable/Not provided, as there is no mention of a training set for an AI/ML model.

Ask a specific question about this device

The Propeller System includes the Propeller MDI Model 2 OTC Sensor is an accessory device intended for single-patient use to assist physicians and patients in recording and monitoring the actuations of prescribed MDI usage.

The Propeller Mobile Application records, stores, and transmits usage events from Propeller Sensors, or via manual user entry, to a remote storage system. With the Propeller Mobile Application the user can review information collected from the MDI sensor, and report and review symptoms and other information about their disease management and its impact. The user may also share their information with their caregivers, physician and healthcare providers.

The Propeller Web Application is software that, like the Propeller Mobile Application, is intended to allow users to review the collected information and characteristics of their respiratory medication(s) and its use, to capture other patientreported information and outcomes, and to allow that information to be shared with their caregivers, physicians and health care providers.

When used with a prescribed MDI, the system can report on information captured during the normal course of use, such as the time between actuations that can be helpful in assessing MDI technique.

When used under the care of a physician with a prescribed MDI, or other inhaled medication, the system can be used to reduce the frequency of respiratory health symptoms and exacerbations by increasing adherence to MDI or other inhaled medications through the use of feedback such as reminders and notifications, and self-management education.

The Propeller System is intended to be used in populations from used in populations from Child (>2 years) to adult.

The Propeller system can be used both indoors; home, work and clinical settings, as well as on aircraff.

The Propeller System may also be used in clinical trials where researchers need to know information about the use of MDI or other inhaled medication(s) by a participant.

The output of the Propeller System is not intended to diagnose provided by a licensed physician. The Propeller System is not intended for use as an MDI or inhaled medication dose counter, nor is it intended to indicate the quantity of medication remaining in an MDI or inhaled medication.

The Propeller System includes the Propeller MDI Model 2 OTC Sensor is an accessory device intended for single-patient use to assist physicians and patients in recording and monitoring the actuations of prescribed MDI usage.

The Propeller Mobile Application records, stores, and transmits usage events from Propeller Sensors, or via manual user entry, to a remote storage system. With the Propeller Mobile Application the user can review information collected from the MDI sensor, and report and review symptoms and other information about their disease management and its impact. The user may also share their information with their caregivers, physician and healthcare providers.

The Propeller Web Application is software that, like the Propeller Mobile Application, is intended to allow users to review the collected information and characteristics of their respiratory medication(s) and its use, to capture other patientreported information and outcomes, and to allow that information to be shared with their caregivers, physicians and health care providers.

This document is a 510(k) premarket notification for the Propeller System Model 2 OTC. It is primarily focused on seeking approval for over-the-counter (OTC) use of a device previously approved for prescription use. As such, the information provided relates more to the comparison with a predicate device and the validation for the change in use status, rather than a detailed study proving performance against new, specific acceptance criteria for a novel device.

Given the information provided, it states: "No clinical testing was required" and "The device is identical to the predicate device." Therefore, a traditional study proving the device meets acceptance criteria as would be for a de novo or novel device is not present here. The focus is on demonstrating that the previously established performance and safety remain valid for OTC use.

However, I can extract information related to the validation testing for OTC and the conclusion regarding safety, which can be interpreted as fulfilling new "acceptance criteria" for the change in intended use.

Here's an attempt to structure the information based on your request, acknowledging the limitations of the provided text:

Acceptance Criteria and Study to Prove the Device Meets Acceptance Criteria

The provided document describes a 510(k) premarket notification for the Propeller System Model 2 OTC, which is a re-marketing of a previously approved prescription-use device (Propeller System Model 2) for over-the-counter (OTC) use. The primary goal of this submission is to demonstrate that the device continues to meet specified requirements for the change in status from "Prescription Use" to "OTC". Therefore, the "acceptance criteria" and "study" are framed around this change in intended use, rather than a de novo evaluation of the device's fundamental performance.

1. Table of Acceptance Criteria and Reported Device Performance

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

The document explicitly states: "No clinical testing was required". This indicates that the validation for OTC use did not involve a study with human subjects or a test set in the traditional sense of a clinical trial. The testing performed was likely bench testing, software validation, and a hazard analysis related to the change in labeling and intended use. Therefore, a "sample size for the test set" is not applicable in the context of clinical performance data, and "data provenance" (country of origin, retrospective/prospective) is not relevant to this type of regulatory submission.

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

Not applicable. As no clinical testing was required and the device is stated to be identical to its predicate, there was no "test set" requiring expert ground truth establishment in a clinical performance study. The "ground truth" here is the established safety and performance of the predicate device and the assessment that these characteristics are maintained for OTC use.

4. Adjudication Method (e.g., 2+1, 3+1, none) for the Test Set

Not applicable, as no clinical test set requiring adjudication was performed.

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. The Propeller System is an electronic MDI accessory for recording and monitoring inhaler actuations, not an AI-powered diagnostic imaging tool. Therefore, an MRMC study and effects on "human readers" are not relevant to this device.

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

The device itself (the Propeller MDI Model 2 OTC Sensor) operates in a standalone manner to record actuations. The accompanying mobile and web applications also process and display data. The document confirms that "Completed EMC, electrical, safety, mechanical durability, software verification and validation testing confirms this result." This implies that the device's core functions (including its algorithms for detecting actuations) were validated. However, the document does not provide details on the performance metrics of these algorithms (e.g., accuracy of actuation detection) as this was likely established and accepted with the predicate device. The focus here is on the transition to OTC.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc)

For the validation of the device itself (as opposed to its OTC reclassification), the ground truth for actuation detection would typically be established against physical measurements or manual observations of MDI actuations. However, this information pertains to the predicate device's initial approval and is not detailed in this 510(k) submission which focuses on the OTC change. For the OTC reclassification, the "ground truth" was essentially the confirmed safety and effectiveness of the identical predicate device and the absence of new hazards identified through the hazard analysis for OTC.

8. The Sample Size for the Training Set

Not applicable. This device is an electronic MDI accessory, not an AI/machine learning model that typically requires a training set of data. Its function is based on sensor data interpretation, not predictive modeling from a large dataset.

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

Not applicable, as there is no "training set" in the context of this device's function as described.

Ask a specific question about this device

The Propeller System includes the Propeller SMI Model 2014-R Sensor is an accessory device intended for single-patient use to assist physicians and patients in recording and monitoring the actuations of prescribed SMI usage.

The Propeller Mobile Application records, stores, and transmits usage events from Propeller Sensors, or via manual user entry, to a remote system. With the Propeller Mobile Application the user can review information collected from the SMI sensor, and report and review symptoms and other information about their disease management and its impact. The user may also share their information with their caregivers, physician, and healthcare providers.

The Propeller Web Application is software that, like the Propeller Mobile Application, is intended to allow users to review the collected information and characteristics of their SMI and its use, to capture other patient-reported information and outcomes, and to allow that information to be shared with their caregivers, physicians, and health care providers.

When used under the care of a physician with a prescribed SMI, the system can report on information captured during the normal course of use, such as the time between actuations that can be helpful in assessing SMI technique.

The Propeller System is intended to be used in populations from Child (>2 years) to Adult.

The Propeller System can be used both indoors; home, work, and clinical settings, as well as on aircraft.

The Propeller System may also be used in clinical trials where researchers need to know information about the use of SMI medication(s) by a participant.

The output of the Propeller System is not intended to diagnosis provided by a licensed physician. The Propeller System is not intended for use as an SMI dose counter, nor is it intended to indicate the quantity of medication remaining in an SMI.

Electronic Soft-Mist Inhaler (SMI) Accessory

The provided text is a 510(k) Premarket Notification for the Propeller System Model 2014-R, which is an accessory device intended to assist physicians and patients in recording and monitoring the actuations of prescribed Soft-Mist Inhaler (SMI) usage. The document focuses on establishing substantial equivalence to a legally marketed predicate device (Propeller System K140638) rather than presenting a detailed study proving the device meets specific acceptance criteria related to its direct performance as a diagnostic or therapeutic tool.

Therefore, much of the requested information, particularly regarding diagnostic performance metrics, expert adjudication, ground truth establishment for a test set, and multi-reader multi-case studies, is not applicable or cannot be extracted from this type of regulatory submission. The device is primarily a data collection and transmission accessory.

However, based on the Test Summary provided, some information can be inferred or directly stated regarding the device's functional performance and safety.

Here's the breakdown of what can be extracted:

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

The document states: "Test results indicate that the Propeller Sensor Model 2014-R and its predicate Propeller System Model 2 complies with predetermined specifications. Completed EMC, electrical, safety, mechanical durability, software verification and validation testing confirms this result."

While specific numerical acceptance criteria and reported performance values are not provided in this summary, the statement implies that the device met all established specifications within these categories.

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

The document does not specify the sample size (e.g., number of devices tested, number of actuations recorded) for the various tests mentioned (EMC, electrical, safety, mechanical durability, software V&V). It also does not mention the data provenance in terms of country of origin or whether the tests were retrospective or prospective, as these are typically part of a detailed test report not included in this summary.

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 and not provided. The device (Propeller Sensor Model 2014-R) is not a diagnostic device that requires expert-established ground truth for its core function of recording SMI actuations. The "ground truth" for its performance would likely be a known physical actuation or a simulated event, verified by test equipment or direct observation, not expert clinical consensus.

4. Adjudication method for the test set

This information is not applicable and not provided for the same reasons as #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

No such study was mentioned or required. The device is an accessory to an SMI, primarily for data collection and monitoring, not for AI-assisted human reading of medical images or diagnostic tests. The document explicitly states: "No clinical testing was required."

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

The device itself is a sensor that records physical events (SMI actuations). Its "standalone performance" would be its accuracy in detecting and transmitting these events. The software verification and validation testing would cover the algorithm's performance within the system, but the document does not detail specific metrics like recall, precision, or F1-score for this function as it's not a diagnostic algorithm.

7. The type of ground truth used

For the functional aspects (e.g., detecting an actuation), the ground truth would likely be a direct physical actuation of the SMI, verified by mechanical means or direct observation during testing. For electrical, EMC, and safety, the ground truth would be established by reference to relevant industry standards and objective measurements. The document does not specify this in detail.

8. The sample size for the training set

This is not applicable and not provided. The device is a hardware sensor with associated software for data collection. It does not appear to involve machine learning models that require a "training set" in the traditional sense for diagnostic prediction. Its software performs data capture, storage, and transmission, which are typically validated through testing against requirements, not trained on extensive datasets.

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

Not applicable, as there is no mention of a training set for a machine learning model.

Ask a specific question about this device

The Propeller System includes the Propeller MDI Model 2 Sensor is an accessory device intended for single-patient use to assist physicians and patients in recording and monitoring the actuations of prescribed MDI usage.

The Propeller Mobile Application records, stores, and transmits usage events from Propeller Sensors, or via manual user entry, to a remote storage system. With the Propeller Mobile Application the user can review information collected from the MDI sensor, and review symploms and other information about their disease management and its impact. The user may also share their information with their caregivers, physician and healthcare providers.

The Propeller Web Application is software that, like the Propeller Mobile Application, is intended to allow users to review the collected information and characteristics of their MDI and its use, to caplure other patient-reported information and outcomes, and to allow that information to be shared with their caregivers, physicians and health care providers.

When used under the care of a physician with a prescribed MDI, the system can report on information caplured during the normal course of use, such as the lime between actualions that can be helpful in assessing MDI technique. When used under the care of a physician will a prescribed MDI, the system can be used to reduce the frequency of respiratory health symploms and exacerbations by increasing adherence to MDI medications through the use of feedback such as reminders and notifications, and self-management education.

The Propeller System is intended to be used in populations from Child (>2 years) to adult."

The Propeller system can be used both indoors and ouldoors; home, work and clinical settings, as well as on aircraft.

The Propeller System may also be used in clinical trials where researchers need to know information about the use of MDI medication(s) by a participant. The Propeller System is not inlended to diagnose or replace a diaonosis provided by a licensed physician. The Propeller System is not intended for use as an MDI dose counter, nor is it intended to indicate the quantity of medication remaining in an MDI.

Electronic MDI Accessory

Here's an analysis of the Propeller System based on the provided 510(k) summary, structured to address your specific questions.

1. Table of Acceptance Criteria and Reported Device Performance

The 510(k) summary for the Propeller System (K140638) does not explicitly present a table of "acceptance criteria" with quantitative targets or thresholds for its performance. Instead, it focuses on demonstrating that the device functions as intended and is substantially equivalent to a predicate device (Asthmapolis, K121609) through various verification and validation tests. The reported device performance is largely described in terms of successful completion of these tests and compliance with relevant standards.

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

The summary does not specify a sample size for a "test set" or data provenance in the context of clinical performance data comparing human readers with and without the device, or studies involving a test set of patient data. The testing described is primarily non-clinical, focusing on device functionality, safety, and compliance with standards. It mentions "functional verification and device performance" and "performance testing of the MDI actuation sensor system to ensure data is logged accurately for MDI usage," but these are general descriptions of bench testing rather than studies involving patient data or a defined test set with associated sample size and provenance.

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

This information is not provided in the 510(k) summary. Given that the testing detailed is primarily non-clinical and focused on device functionality, there is no mention of "experts" establishing ground truth for a test set in a medical diagnostic or interpretive context.

4. Adjudication Method for the Test Set

This information is not provided in the 510(k) summary. As there's no mention of a test set involving medical interpretations, there's no adjudication method described.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and the effect size of how much human readers improve with AI vs without AI assistance

There is no mention of a Multi-Reader Multi-Case (MRMC) comparative effectiveness study comparing human performance with and without AI (or device) assistance in the provided 510(k) summary. The device's purpose is to record and monitor MDI usage, provide feedback, and aid in adherence and self-management, not to assist human readers in interpreting medical images or data diagnostically.

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

The summary describes the core functionality of the device as standalone in its data collection and transmission aspects: "The Propeller Mobile Application records, stores, and transmits usage events from Propeller Sensors..." and the "MDI actuation sensor system to ensure data is logged accurately for MDI usage." This implies that the sensor and associated software perform their function (recording actuations) without direct human intervention in the moment of data capture. However, the system's intended use is described as assisting physicians and patients, and empowering users to review and share information, implying a human-in-the-loop for interpretation and action based on the data. The testing primarily verifies the accuracy of this standalone data collection.

7. The Type of Ground Truth Used

For the functional verification of the MDI actuation sensor system, the ground truth would have been established through known, controlled MDI actuations performed during bench testing. For example, actuating an MDI a specific number of times and then verifying that the Propeller System accurately recorded that exact number. For compliance with standards (IEC, ISO, FCC), the "ground truth" is adherence to the technical specifications and requirements defined by those standards.

8. The Sample Size for the Training Set

The summary does not specify a sample size for a training set. The Propeller System is primarily a data capture and feedback system, not a device that relies on complex machine learning models trained on large datasets in the way an AI diagnostic tool would. Its functionality is based on sensors and software logic.

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

Since there is no mention of a training set for a machine learning model, the concept of establishing ground truth for a training set is not applicable in the context of the information provided for this device. The "training" for such a system would involve software development and engineering processes, with verification against design specifications and functional requirements.

Ask a specific question about this device

The Asthmapolis System includes the Asthmapolis Sensor which is an electronic accessory device intended for single-patient use to assist physicians and patients in recording and monitoring the actuations of prescribed MDI usage.

The Asthmapolis Mobile Application records, stores, and transmits usage events from the Asthmapolis Sensor to a remote storage system.

The Asthmapolis Web Application is software intended to allow users to review the collected information and characteristics of MDI use, to add detail associated with a recorded usage event, and to share that information with their physician in order to provide additional information associated with the condition for which their MDI medication(s) are prescribed.

The Asthmapolis System may also be used in clinical trials where researchers need to know information about use of a MDI Medication(s) by a participant.

The output of the Asthmapolis System is not intended to diagnose or replace a diagnosis provided by a licensed physician. The Asthmapolis system is not intended for use as a MDI medication dose counter, nor is it intended to indicate the quantity of medication remaining in an MDI.

Electronic MDI Accessory

The Asthmapolis System is an electronic accessory device (Asthmapolis Sensor) paired with a mobile and web application. Its intended use is to record and monitor actuations of prescribed Metered Dose Inhaler (MDI) usage for physicians and patients, and for use in clinical trials to track MDI medication use. It is not intended for diagnosis, as a MDI dose counter, or to indicate remaining medication.

The device was determined to be substantially equivalent to the SmartTrack System (K091803).

Here's an analysis of the acceptance criteria and study information provided:

1. Table of Acceptance Criteria and Reported Device Performance

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

The provided text describes non-clinical performance and engineering testing (software, electrical safety, EMC, wireless). It does not mention a "test set" in the context of patient data or clinical data. The performance testing appears to be primarily bench testing and software validation. Therefore, there is no information provided regarding a sample size for a test set of patient data, nor its provenance (country of origin, retrospective/prospective).

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

As the testing described is primarily non-clinical (bench, software, electrical), the concept of "ground truth" derived from expert review in a clinical context does not apply here. The "ground truth" would be related to engineering specifications and functional requirements. Therefore, no information on the number or qualifications of experts for establishing ground truth for a clinical test set is provided.

4. Adjudication Method for the Test Set

Given that the document describes non-clinical, bench, and software testing, a clinical "adjudication method" like 2+1 or 3+1 is not relevant. The verification and validation processes would involve reviewing test results against predefined specifications and requirements.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done, and Effect Size

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. The device's primary function is to automatically record MDI actuations, not to aid human readers in interpreting clinical images or data in a way that would necessitate an MRMC study. The comparison is between the performance of the Asthmapolis System and its predicate device (SmartTrack System) in terms of fundamental technological characteristics and safety.

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

The performance testing described focuses on the standalone functionality of the device components:

• MDI actuation sensor system: "to ensure data is logged accurately for MDI usage."
• Software verification and validation: "device features are effective, and that the system configuration functions equivalently to the predicate device."
• Wireless/Bluetooth technology: "successfully completed performance testing... in accordance with specifications."

These tests evaluate the device's ability to perform its specified functions independently (e.g., accurately detecting an MDI actuation and transmitting data). While the system is intended to assist physicians and patients, the core performance validation relates to the device's inherent functional accuracy rather than its human-in-the-loop impact. So, yes, the described performance testing reflects a standalone evaluation of the device's core functionalities.

7. The Type of Ground Truth Used

The ground truth used for these non-clinical tests would be:

• Engineering Specifications/Requirements: For functional verification, software validation, electrical safety, EMC, and wireless performance, the "ground truth" is defined by the established technical specifications and performance requirements derived from applicable standards (e.g., IEC 60601-1, IEC 60601-1-2, FDA guidance for wireless technology) or internal design documentation.
• Predicate Device Performance: For demonstrating substantial equivalence, the "ground truth" for comparative technological characteristics is the known performance and characteristics of the legally marketed SmartTrack System (K091803).

In summary, the ground truth is based on engineering specifications, regulatory standards, and the characteristics of the predicate device's performance.

8. The Sample Size for the Training Set

The document describes non-clinical verification and validation testing, not a machine learning model that would require a "training set" in the sense of a large dataset for algorithm development. Therefore, no information is provided regarding a sample size for a training set. The "training" here refers to the software development process aligned with specific guidelines.

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

As there's no mention of a traditional machine learning "training set" in this context, the question of how its ground truth was established is not applicable. The software development process followed established guidelines ("Design Control Guidance for Medical Device Manufacturers," "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices," "Guidance for Off the Shelf Software Use in Medical Devices," and "General Principles of Software Validation"), which define the "ground truth" for compliant and effective software.

Ask a specific question about this device