Search Results

The Hailie® sensor is intended for single-patient multiple use in the home environment as an electronic data capture accessory for monitoring and recording actuation, inspiratory flow and inhaler shake for prescribed inhaler usage.

The Hailie® sensor may be used in the following applications: in clinical trials, where specialists, general practitioners, nurses, and educators need to know if a patient has used their prescribed medication, or assess inspiratory flow and inhaler technique; and in patient self-management.

The Hailie® sensor is compatible only with the Teva HFA MDIs like ProAir, Albuerol Sulphate inhalers. The Hailie® sensor is not intended to indicate remaining quantity of medication in an inhaler and does not include a dose counting function. The Hailie® sensor is not intended to provide spirometry measurements.

The subject device Hailie® Sensor (Hailie® sensor) NF0110 model, is a modification to the Hailie® sensor NF0109 model (the predicate device) and is used to provide medication actuation monitoring, shake and airflow recording functions, for use as an accessory to the inhaler specified on the device label. The Hailie® sensor is indicated for use only with the following TEVA MDIs: ProAir® HFA & Albuterol Sulphate HFA.

The Hailie sensor NF0110 is a clip-on device that attaches externally around the housing of the inhaler. The optical sensor and induction coil sensor are used to detect the inhaler presence and monitor actuation. Motion and flow sensors are used to record inhaler usage technique parameters. The Haile sensor contains an electronic clock and calendar that are used to log the date and time of inhaler usage events.

The user interface consists of a single Status Button and a multi-color LED indicator to check device status and initiate communications functions. The Hailie sensor has a Bluetooth interface to wirelessly exchange medication usage data with a paired communications device and compatible mobile software applications.

The Adherium Hailie Sensor (model NF0110) is an electronic data capture accessory that records actuation, inspiratory flow, and inhaler shake for prescribed inhaler usage in the home environment. It is compatible with Teva HFA MDIs like ProAir and Albuterol Sulphate inhalers.

Here's an analysis of its acceptance criteria and the supporting study:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not explicitly define specific numerical acceptance criteria for performance metrics (e.g., a specific percentage for accuracy of actuation detection). Instead, the performance testing section generally states that tests were conducted to "establish correct functionality and compatibility" and "confirmed performance." The conclusions state that the device "meets design, safety, and performance requirements" and that "inhaler usage parameters are measured with sufficient accuracy for monitoring inhaler use equivalent to reference device."

Therefore, the table below will summarize the areas of performance evaluated and the reported outcome in terms of meeting requirements or confirming functionality, rather than specific numerical criteria and results.

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

The document does not detail the specific sample sizes for tests related to optical detection, airflow, motion, or general performance. It mentions "non-clinical testing" and "finished device testing" but does not provide numbers of devices tested or iterations.

The and data provenance is not specified in terms of country of origin or whether it was retrospective or prospective. Given it's non-clinical performance testing of a device, it would typically be conducted in a laboratory setting.

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

This information is not provided. The study is primarily non-clinical device performance testing. Ground truth for device functionality would be established by validated test equipment and measurement standards, not typically by human experts in this context.

4. Adjudication Method for the Test Set

This is not applicable as the performance testing described is objective measurement against specified standards/functionality, not subjective assessment requiring adjudication.

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

No. A MRMC comparative effectiveness study was not done. The Hailie sensor is a data capture accessory, not an AI diagnostic tool that would typically involve human readers. Clinical testing was explicitly stated as "not required for a determination of substantial equivalence."

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

Yes, in essence, the performance testing described is a standalone evaluation of the device's functionality. The device's ability to detect inhaler use parameters (actuation, flow, shake) and its general functionality (shelf life, Bluetooth range, UI) were assessed independently of a human user's interpretation or interaction beyond basic usability. The device itself is designed to operate autonomously in recording data, which is then accessed by users/clinicians.

7. Type of Ground Truth Used

For the non-clinical performance tests, the "ground truth" would be established by:

• Validated measurement equipment and sensors: For parameters like inspiratory flow, shake detection, and actuation.
• Engineering specifications and design requirements: To confirm optical detection limits, Bluetooth range, battery life, etc.
• Industry standards: For biocompatibility (ISO 10993), electrical safety (ANSI/AAMI ES60601-1, IEC 60601-1-11), and EMC (IEC 60601-1-2).
• Known device behavior/calibration: For confirming the effect on the airflow path.

8. Sample Size for the Training Set

This information is not applicable. The Hailie sensor is a hardware device with embedded software designed for data capture, not a machine learning or AI model that requires a separate training set in the conventional sense. The "software verification and validation testing" refers to ensuring the embedded software functions correctly, not training a predictive algorithm from a dataset.

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

This information is not applicable, as there is no mention of a training set for an AI/ML algorithm within the provided document. The software validation is against expected functional requirements, not through a training process with ground truth data.

Ask a specific question about this device

The Hailie@ sensor is intended for single-patient multiple use in the home environment as an electronic data capture accessory for monitoring and recording actuation, inspiratory flow and inhaler shake for prescribed inhaler usage.

The Hailie® sensor may be used in the following applications: in clinical trials, where specialists, general practitioners, nurses, and educators need to know if a patient has used their prescribed medication, or assess inspiratory flow and inhaler technique; and in patient self-management including medication reminders.

The Hailie@ sensor is compatible only with the Ventolin, Advair, Flovent inhaler. The Hailie® sensor is not intended to indicate remaining quantity of medication in an inhaler and does not include a dose counting function. The Hailie® sensor is not intended to provide spirometry measurements.

The Hailie® sensor is intended for single-patient multiple use in the home environment as an electronic data capture accessory for monitoring and recording actuation, inspiratory flow and inhaler shake for prescribed inhaler usage.

This appears to be a 510(k) clearance letter from the FDA for the Hailie® Sensor. These letters typically grant market clearance based on substantial equivalence to a predicate device and do not usually include extensive details about the performance study that would generate acceptance criteria and detailed performance metrics as one might find in an AI/ML device submission.

Based on the provided text, there is no specific information regarding acceptance criteria and a study that proves the device meets those criteria in the way described in your request (e.g., performance metrics, sample sizes for test/training sets, expert adjudication methods, MRMC studies, or standalone performance).

The document primarily focuses on:

• Confirming the device's substantial equivalence to a predicate.
• Indications for Use of the Hailie® Sensor.
• Regulatory classifications and general controls.

Therefore, I cannot fulfill your request for the specific details listed because they are not present in the provided FDA clearance letter.

To fully answer your request, you would typically need access to the full 510(k) submission, which would contain the performance testing data and clinical study details (if any were required beyond basic functionality and safety testing for substantial equivalence).

Ask a specific question about this device

The Hailie@ sensor is intended for single patient, multiple use, in the home environment, as an electronic data capture accessory for monitoring and recording actuations, inspiratory flow, and inhaler orientation, for prescribed inhaler usage.

The Hailie@ sensor may be used in the following applications: in clinical trials, where specialists, general practitioners, nurses, and educators need to know if a patient has used their prescribed medication or assess inspiratory flow and inhaler technique; and in patient self-management including medication reminders.

The Hailie® sensor is compatible only with the following ELLIPTA® DPI inhalers: Breo™, Incruse™, Trelegy™ and Arnuity™. The Hailie@sensor is not intended to indicate remaining quantity of medication in an inhaler and does not include a dose counting function. The Hailie® sensor is not intended to provide spirometry measurements.

The Hailie® Sensor (Hailie® sensor) NF0106 model, is a modification to the Hailie® sensor NF0109 model, and is used to provide medication reminder, actuation monitoring, orientation and airflow recording functions, for use as an accessory to the inhaler specified on the device label. The Haili® sensor is indicated for use only with the following ELLIPTA® DPI inhalers: Breo™, Anoro™, Incruse™, Trelegy™ and Arnuity™.

The Hailie® sensor is a clip-on device that attaches externally around the housing of the inhaler. Optical sensors are used to detect the inhaler presence and monitor actuation. Motion and flow sensors are used to record inhaler usage technique parameters. The Hailie® sensor contains an electronic clock and calendar that are used to log the date and time of inhaler usage events.

The user interface consists of a single Status Button and a multi-color LED indicator to check device status, initiate communications functions, and provide reminder features. The Hailie® sensor has a Bluetooth interface to wirelessly exchange medication usage data and reminder setting data with a paired communications device and compatible mobile software applications.

This document, a 510(k) summary, describes the Hailie® Sensor NF0106, a medical device intended to monitor and record inhaler usage. The information provided heavily emphasizes equivalence to a predicate device (Hailie® Sensor NF0109) and reference devices rather than detailing a standalone acceptance criteria study with specific performance metrics and corresponding results for the NF0106 model itself.

Based on the provided text, a comprehensive table of acceptance criteria and reported device performance, as well as a detailed description of an MRMC or standalone study with specific performance metrics (like sensitivity, specificity, accuracy, etc.) for the detection of inhaler usage parameters, cannot be fully constructed or extracted. The document focuses on demonstrating that the modified Hailie® Sensor (NF0106) performs equivalently to prior cleared devices and meets general safety and performance requirements through a series of non-clinical testing.

Therefore, I will extract and synthesize the information that is available regarding testing and performance, and note where specific details for the requested categories are either not present or are presented in a comparative rather than quantitative manner.

Summary of Acceptance Criteria and Study to Prove Device Meets Them

Note: The provided text is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device through non-clinical testing. It does not present a standalone clinical performance study with explicit acceptance criteria for metrics like accuracy, sensitivity, or specificity of the device's core functions (actuation, inspiratory flow, orientation detection) in a quantitative, per-metric format. Instead, it describes general performance testing and states that the device offers "equivalent performance to the predicate" or "sufficient accuracy" without providing specific numerical targets or results for these equivalencies.

Due to the nature of this document (a 510(k) summary for a modified device), specific enumerated acceptance criteria with corresponding performance numbers for each function are not explicitly listed in a table format. The performance data section describes the types of tests conducted and their general conclusions of compliance or equivalence.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: The document does not specify exact sample sizes (e.g., number of devices or number of tests performed) for the performance testing. It states that "Non-clinical testing and evaluation of the Hailie® sensor has been carried out..."
• Data Provenance: The tests were non-clinical, conducted by "external laboratories" for electrical safety and EMC. No specific country of origin for the data or whether it was retrospective or prospective is mentioned beyond it being "non-clinical testing." This implies laboratory-based, controlled testing rather than patient data.

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

• The document describes non-clinical testing. Therefore, there is no mention of experts establishing a "ground truth" for a test set in the clinical sense (e.g., radiologists reviewing images). The ground truth for performance testing would likely be based on controlled laboratory conditions and measurement equipment.

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

• Not applicable as this was non-clinical performance testing, not a clinical study requiring adjudication of expert interpretations.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• No. The document explicitly states: "Clinical testing was not required for a determination of substantial equivalence of the Hailie® sensor. The product functionality has been adequately assessed by non-clinical testing as outlined above." Therefore, no MRMC study was conducted.

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

• The device itself is a standalone sensor that operates to detect and record events. The performance testing described (optical detection, airflow, motion, general performance) effectively serves as "standalone" performance evaluation of the device's core functions, as it does not involve a human in the loop for the actual detection mechanism of the device. The device's output (logged data) is what a human would then review.
• However, no specific quantitative metrics (e.g., "95% accuracy in detecting actuations") are provided from such a standalone assessment. Instead, the performance is described as "equivalent to the predicate" or "sufficient accuracy."

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

• For the non-clinical performance testing, the ground truth would have been established through instrumentation, controlled experimental setups, and engineering specifications. For example, a known flow rate would be introduced to test the airflow sensor, or a known orientation change to test the motion sensor.

8. The sample size for the training set:

• This device is not an AI/ML algorithm that requires a "training set" in the conventional sense of machine learning model development. It's a sensor-based electronic device. Therefore, the concept of a "training set" for model development does not apply here.

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

• Not applicable, as there is no "training set" for an AI/ML model.

Ask a specific question about this device

The Hailie® sensor is intended for single-patient use in the home environment as an electronic data capture accessory for monitoring and recording actuations, inspiratory flow, and inhaler shake, for prescribed inhaler usage.

The Hailie® sensor may be used in the following applications: in clinical trials, where specialists, general practitioners, nurses, and educators need to know if a patient has used their prescribed medication, or assess inspiratory flow and inhaler technique; and in patient self-management including medication reminders.

The Hailie® sensor is compatible only with the Symbicort™ MDI inhaler. The Haile® sensor is not intended to indicate remaining quantity of medication in an inhaler and does not include a dose counting function. The Hallie® sensor is not intended to provide spirometry measurements.

The Hailie® sensor is a modification to the SmartTouch sensor, and is used to provide medication reminder, actuation monitoring, and shake and airflow recording for use as an accessory to the inhaler specified on the device label. The Hailie® sensor is indicated for use only with the Symbicort™ MDI inhaler.

The Hailie® sensor is a clip-on device that attaches externally around the housing of the inhaler. Mechanical and optical sensors are used to detect the inhaler presence and monitor actuation. Motion and flow sensors are used to record inhaler usage technique parameters. The Hailie® sensor contains an electronic clock and calendar that are used to log the date and time of inhaler usage events.

The user interface consists of a single Status Button and a multi-color LED indicator to check device status, initiate communications functions, and provide reminder features. The Hailie® sensor has a Bluetooth interface to wirelessly exchange medication usage data and reminder setting data with a paired communications device and compatible mobile software applications.

The provided text describes information related to the 510(k) premarket notification for the Hailie® Sensor, but it does not contain a table of acceptance criteria or a detailed study proving the device meets those criteria with specific performance metrics (e.g., sensitivity, specificity, accuracy).

The document primarily focuses on demonstrating substantial equivalence to a predicate device (SmartTouch) and reference devices (K183586 CapMedic, K181405 Hailie® Sensor) through non-clinical testing. It highlights the technological characteristics of the Hailie® sensor and its performance in various non-clinical tests.

Therefore, I cannot provide the requested information regarding acceptance criteria and a study proving the device meets them from the given text.

However, I can extract and summarize other relevant information you asked for:

Information Extracted from the Document:

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

  • The document states "Clinical testing was not required for a determination of substantial equivalence of the Hailie® sensor." This implies that no clinical test set with patient data was used for performance evaluation against ground truth in the way typically seen for AI/ML device validations for diagnostic or prognostic purposes. The performance assessment was based on non-clinical testing (e.g., mechanical, electrical, software functionality) in a lab setting.
  • Data provenance for these non-clinical tests is not specified in terms of country of origin or retrospective/prospective nature, as it relates to device functionality testing rather than patient data.

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

  • Not applicable, as no clinical test set using expert-established ground truth was presented for the device's core functionality of monitoring actuations, inspiratory flow, and inhaler shake. The ground truth for performance testing would have been established by engineering specifications and known physical principles.

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

  • Not applicable, as there was no expert review/adjudication of a clinical test set.

• If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

  • No, an MRMC comparative effectiveness study was not done. The device is an electronic data capture accessory, not an AI assisting human readers in diagnostic interpretation.

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

  • The "performance testing" described (optical inhaler presence detection, airflow detection sensor, motion detection sensor, general performance testing, user interface testing) essentially represents standalone testing of the device's core functions. However, these are functional tests, not "algorithm only" performance in the context of an AI/ML diagnostic or predictive algorithm. The device itself is an "algorithm" in the sense of executing programmed functions, and these tests verify its standalone performance.

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

  • The ground truth for the performance tests appears to be based on:
    • Engineering specifications and expected device behavior: e.g., accurate detection within defined calibration limits for optical detection.
    • Physical measurements: e.g., flow rate measurements, duration of shake.
    • Requirements from the inhaler manufacturer: for shake detection.
    • Regulatory standards: for biocompatibility, electrical safety, EMC.

• The sample size for the training set:

  • The document does not describe a "training set" in the context of machine learning. The device's functionality appears to be rule-based or engineered, rather than learned from a large dataset.

• How the ground truth for the training set was established:

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

Summary of what CANNOT be provided from the text:

1. A table of acceptance criteria and reported device performance related to diagnostic accuracy (e.g., sensitivity, specificity, AUC). The document focuses on functional performance and substantial equivalence based on non-clinical tests.
2. Detailed information on clinical test set sample size, provenance, expert qualifications, or adjudication methods. The document explicitly states clinical testing was not required for determining substantial equivalence for this device.
3. Specific effect sizes for human reader improvement with AI assistance. The device is not an AI diagnostic aid.

Ask a specific question about this device

The Hailie™ sensor is intended for single-patient use in the home environment as a medication reminder and electronic data capture accessory for recording usage of prescribed inhaler medication. This may be used in the following applications:

· In clinical trials, where researchers need to know when a patient has used their trial inhaler medication.

· In clinical practice, where specialists, general practitioners, nurses, and educators need to know if a patient has used their prescribed inhaler medication.

· In self-management, where patients need to track their medication use as part of their management plan.

The Hailie™ sensor is compatible only with the HandiHaler® inhaler and is for use by adults.

The Hailie™ sensor is used to provide a medication reminder and actuation recording function for use as an accessory to the inhaler specified on the device label. Under the current 510(k), the Hailie™ sensor is indicated for use only with the HandiHaler® inhaler.

The Hailie™ sensor is a clip-on device that attaches externally around the housing of the inhaler. Mechanical, optical and acoustic sensors are used to detect the presence and actuation of the inhaler. The Hailie™ sensor contains an electronic clock and calendar that are used to log the date and time of inhaler actuation.

The user interface consists of a single Status Button and dual multi-color LED indicators to check device status, initiate communications functions, and provide reminder features. The Hailie™ sensor has a Bluetooth interface to wirelessly exchange medication and reminder setting data with a paired communications device and compatible mobile software applications.

The medical device in question is the Hailie™ Sensor, which is intended "for single-patient use in the home environment as a medication reminder and electronic data capture accessory for recording usage of prescribed inhaler medication."

Here's an analysis of the acceptance criteria and supporting studies based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present acceptance criteria in a tabular format with specific quantitative targets. Instead, it describes various tests and states that the device "meets design and performance functional requirements" and "meets standard requirements." Based on the provided text, the acceptance criteria are implicitly defined by the successful completion of the listed tests and adherence to relevant standards.

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

The document does not specify the sample size for any of the individual non-clinical tests (e.g., performance testing, usability evaluation). The provenance of the data is indicated as "non-clinical testing," performed by "external laboratories" for electrical safety and EMC. There is no mention of specific country of origin or whether the data was retrospective or prospective.

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

The document does not mention the use of experts to establish a "ground truth" for the non-clinical test set in the same way clinical studies use experts for diagnosis. The testing primarily involved engineering and technical evaluations against defined standards and functional requirements. For the usability evaluation, it states "summative usability validation testing was carried out," implying user participants, but it does not specify the number or qualifications of experts for establishing ground truth related to the device's functional outputs.

4. Adjudication Method for the Test Set

No adjudication method (e.g., 2+1, 3+1) is mentioned or relevant for the described non-clinical performance and safety testing. The evaluation focused on compliance with technical standards and functional requirements.

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

No MRMC comparative effectiveness study was done. The document explicitly states: "Clinical testing was not required for a determination of substantial equivalence of the Hailie™ sensor. The product functionality has been adequately assessed by non-clinical testing as above."

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

The device is a hardware sensor that captures data and provides reminders. Its core function is automated detection and recording of inhaler usage. Therefore, the "performance testing" described (optical, mechanical, acoustic sensor validation, spurious log prevention) inherently represents a standalone performance evaluation of the device's ability to accurately detect and log events without human intervention during the detection process. The usability evaluation, however, involves human interaction with the device for its intended purpose.

7. The Type of Ground Truth Used

The ground truth for the non-clinical performance tests was based on:

• Established Standards: For biocompatibility, electrical safety, and EMC.
• Defined Functional Requirements: Optical, mechanical, and acoustic sensor validation, spurious log prevention, general performance (shelf life, Bluetooth range), and user interface. These are likely based on engineering specifications and expected device behavior.
• Usability Risk Analysis: For the usability evaluation, focusing on "critical tasks."

8. The Sample Size for the Training Set

The document describes non-clinical testing for regulatory clearance (510(k)). This type of submission typically focuses on validation and verification of the final device, not on the training of machine learning models. There is no mention of a "training set" in the context of device development or performance evaluation. The device utilizes sensors and electronics, not a machine learning algorithm that would require a training set.

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

As no training set is mentioned or applicable to the device's stated technology (sensors and electronics rather than machine learning), there is no information on how a "ground truth for the training set" was established.

Ask a specific question about this device

The Hailie™ sensor is intended for single-patient use in the home environment as a medication reminder and electronic data capture accessory for recording usage of prescribed inhaler medication. This may be used in the following applications:

· In clinical trials, where researchers need to know when a patient has used their trial inhaler medication.

· In clinical practice, where specialists, general practitioners, nurses, and educators need to know if a patient has used their prescribed inhaler medication.

· In self-management, where patients need to track their medication use as part of their management plan.

The Hailie™ sensor is compatible only with the Advair® Diskus® inhalers. The Hailie™ sensor is not intended to indicate remaining quantity of medication in an inhaler and does not include a dose counting function.

The Hailie™ sensor is used to provide a medication reminder and usage recording function as an accessory to the inhalers specified on the device label. Under the current 510(k), the Hailie™ sensor is indicated for use only with the Advair® Diskus® (100/50, 250/50, 500/50 mcg) and Flovent® Diskus® (50, 100, 250 mcg) inhalers.

The Hailie™ sensor is a clip-on device that attaches externally around the housing of the inhaler. Optical sensors are used to detect the presence and usage of the inhaler. The Hailie™ sensor contains an electronic clock and calendar that are used to log the date and time of inhaler usage.

The user interface consists of a three control buttons and three LED indicators to check device status, initiate communications functions, and provide reminder features. The Hailie™ sensor has a Bluetooth interface to wirelessly exchange medication usage and reminder setting data with a paired communications device and compatible mobile software applications.

The provided text describes a medical device called the "Hailie™ Sensor," which is an accessory for inhalers, primarily for medication reminders and recording usage. The document is a 510(k) summary from the FDA, indicating a premarket notification for a medical device.

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

1. Table of Acceptance Criteria and Reported Device Performance:

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

The document states that clinical testing was not required for a determination of substantial equivalence. The device's functionality was "adequately assessed by bench testing" and "non-clinical testing." Therefore, there isn't a "test set" in the traditional sense of patient data. The provenance of any underlying data for the non-clinical tests is not specified, but it would have been generated in a laboratory setting as part of the device's verification and validation.

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

Since no clinical data or patient test set was used, there were no experts used to establish ground truth in this context. The "ground truth" for the non-clinical tests would have been established by engineering specifications and expected performance outcomes derived from the predicate device and regulatory standards.

4. Adjudication Method for the Test Set:

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

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

No MRMC study was conducted. The Hailie™ sensor is not an AI-powered diagnostic device, but rather a data capture and reminder accessory. The document explicitly states: "Clinical testing was not required for a determination of substantial equivalence of the Hailie™ sensor. The product functionality has been adequately assessed by bench testing as above."

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

The Hailie™ sensor itself is a standalone device in that it captures data independently. However, "standalone performance" in the context of AI often refers to an algorithm's diagnostic accuracy without human intervention. This device's primary function is not diagnostic, but rather data logging and reminders. Its "standalone performance" would refer to its ability to accurately detect and log inhaler usage, which was confirmed through non-clinical testing.

7. The Type of Ground Truth Used:

The ground truth used was based on engineering specifications, regulatory standards, and expected performance derived from the predicate device. For instance, the "accurate logging of inhaler usage" was verified against a known or simulated usage event. Biocompatibility was assessed against established ISO and AAMI standards.

8. The Sample Size for the Training Set:

Not applicable. This device is not an AI/ML device that requires a training set of data in the sense of supervised or unsupervised learning for making predictions or classifications. Its functionality is based on optical sensors and embedded logic.

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

Not applicable, as there was no training set for an AI/ML model.

Ask a specific question about this device

The Hailie™ sensor is intended for single-patient use in the home environment as a medication reminder and electronic data capture accessory for recording actuations of prescribed inhaler usage. This may be used in the following applications:

• In clinical trials, where researchers need to know when a patient has actuated their trial inhaler medication.
  • In clinical practice, where specialists, general practitioners, nurses, and educators need to know if a patient has actuated their prescribed inhaler medication.

• In self-management, where patients need to track their medication use as part of their management plan.

The Hailie™ sensor is compatible only with Bevespi Aerosphere® and is for use by adults. The Hailie™ sensor is not intended to indicate remaining quantity of medication in an inhaler and does not include a dose counting function.

The Hailie™ sensor is used to provide a medication reminder and actuation recording function for use as an accessory to the inhaler specified on the device label. Under the current 510(k), the Hailie™ sensor is indicated for use only with the Bevespi Aerosphere®.

The Hailie™ sensor is a clip-on device that attaches externally around the housing of the inhaler. Optical and mechanical sensors are used to detect the presence and actuation of the inhaler. The Hailie™ sensor contains an electronic clock and calendar that are used to log the date and time of inhaler actuation.

The user interface consists of three control buttons and three LED indicators to check device status, initiate communications functions, and provide reminder features. The Hailie™ sensor has a Bluetooth interface to wirelessly exchange medication and reminder setting data with a paired communications device and compatible mobile software applications.

The provided text describes the Hailie™ Sensor, an accessory for inhalers, and its FDA 510(k) premarket notification. The document primarily focuses on demonstrating substantial equivalence to a predicate device through non-clinical testing. It explicitly states that clinical testing was not required for this determination. Therefore, the device performance and acceptance criteria are based on non-clinical, functional, and engineering tests rather than a multi-reader, multi-case (MRMC) comparative effectiveness study or a standalone AI algorithm performance study.

Here's the breakdown of the information requested, based on the provided document:

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

The document does not present a formal table of distinct acceptance criteria with corresponding performance metrics like a typical clinical trial. Instead, it describes various non-clinical tests and states that the device "meets design and performance functional requirements" and "complies" with relevant standards. The "performance" is generally described as "correct functionality and compatibility."

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

The document does not detail specific sample sizes for tests (e.g., how many devices were tested for electrical safety, how many users for usability). The performance tests appear to be laboratory-based and focused on device function rather than clinical data. Given that clinical testing was not required, there is no mention of patient data (retrospective or prospective) or country of origin for such data.

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. The ground truth for this device's performance is established through engineering and functional testing against defined technical specifications and regulatory standards, not through expert consensus on medical images or patient outcomes.

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

Not applicable. This type of adjudication method is relevant for studies involving human interpretation (e.g., reading medical images) where a consensus or majority opinion is needed to establish ground truth. For this device's non-clinical testing, the "ground truth" is determined by objective measurements and compliance with technical standards.

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 document explicitly states: "Clinical testing was not required for a determination of substantial equivalence of the Hailie™ sensor. The product functionality has been adequately assessed by non-clinical testing as above." Therefore, no MRMC study or AI assistance evaluation was performed as part of this submission. The Hailie™ sensor is an electronic data capture accessory for an inhaler, not an AI-powered diagnostic tool.

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

Not applicable in the context of an AI algorithm. The device has an "algorithm" in the sense of software processing, but its "standalone performance" refers to its ability to accurately detect inhaler presence and actuation, store data, and communicate via Bluetooth, as verified through performance testing, not as a diagnostic algorithm.

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

The "ground truth" for this device's non-clinical performance evaluation is based on:

• Compliance with recognized international and national standards (e.g., ISO 10993 for biocompatibility, IEC 60601 for electrical safety and EMC).
• Pre-defined engineering specifications and functional requirements for optical and mechanical sensor performance, data transfer, and user interface.
• Successful completion of usability tasks.

8. The sample size for the training set

Not applicable. This device is not an AI/machine learning model that requires a "training set" of data in the typical sense. Its functionality is based on direct sensor input and programmable logic.

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

Not applicable, as no training set (for an AI model) was used.

Ask a specific question about this device