(117 days)
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 ground truth for the performance tests appears to be based on:
-
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:
- 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.
- 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.
- Specific effect sizes for human reader improvement with AI assistance. The device is not an AI diagnostic aid.
§ 868.5630 Nebulizer.
(a)
Identification. A nebulizer is a device intended to spray liquids in aerosol form into gases that are delivered directly to the patient for breathing. Heated, ultrasonic, gas, venturi, and refillable nebulizers are included in this generic type of device.(b)
Classification. Class II (performance standards).