FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

The Suzanne System is composed of a data recorder that contains the electronics and software necessary to capture the physiological information of each sensor and to store this information in a Flash card it to a computer via a serial communication port.

The information that can be recorded by the Suzanne System is :

· EEG signals
· ECG signals
· Pressure signals
· Thoracic movements
Abdominal movements .
· Breath detection (through bucco-nasal thermistor)
· Flow (through pneumotachometer)
· Envelope of ambient sound
· Body position
· Ambient light detection

The signals are amplified by different amplifiers contained in elements of the system known as headboxes. When used in a home environment, the data is recorded in the flash card and the clinican uses a setup unit to check that the system works correctly and to set the recording starting time.

When used in a clinical environment, the system can be used as described above or data can be recorded to a computer with the use of a PC application software.

The system is powered by an internal battery.

AI/ML Overview

The provided text describes the regulatory clearance for the "Suzanne" Ventilatory Effort Recorder (K990565), not a study with detailed acceptance criteria and performance metrics typically associated with AI/ML devices. Therefore, much of the requested information cannot be extracted directly from this document.

However, based on the limited information available, here's a breakdown of what can be inferred or stated:

1. Table of Acceptance Criteria and Reported Device Performance

Acceptance Criteria Category	Specific Criteria/Tests	Reported Device Performance
Functional Performance	Ability to meet stated functional specifications and produce readable output.	"The Suzanne System passed all tests."
Regulatory Compliance	Compliance with the November 1993 draft "Reviewer Guidance for Premarket submissions" (Division of Cardiovascular, Respiratory, and Neurological Devices).	"The Suzanne System passed all tests."
Software Validation	Compliance with the May 29, 1998 "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" (Office of Device Evaluation).	"The Suzanne System passed all tests."
Basic Signal Generation	Verification of readable, appropriate signals when connected to a healthy person.	Implied as passing, as no further clinical studies were deemed necessary for substantial equivalence.
Intended Use Fulfillment	Collect physiological data for diagnosing sleep disorders.	"Nelloor Puritan Bennett concludes that the Suzanne meets its stated specifications, operates safely in its intended environment, and is effective in fulfilling its intended use."

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

Sample Size (Test Set): Not explicitly stated in terms of a formal test set for performance metrics. The document mentions "connecting the device to a healthy person and running the system to verify that readable, appropriate signals were generated." This suggests a very small, qualitative "test" rather than a statistically powered test set.
Data Provenance: Not specified, but given the nature of the test (connecting to a healthy person), it would be prospective data collection, likely from the manufacturer's location.

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

Number of Experts: Not mentioned.
Qualifications: Not mentioned.

4. Adjudication Method for the Test Set

Adjudication Method: Not applicable/not mentioned, as there was no formal expert-adjudicated test set described.

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

MRMC Study: No, an MRMC comparative effectiveness study was explicitly not done. The text states: "No clinical studies were required to support a substantial equivalence determination, except for connecting the device to a healthy person and running the system to verify that readable, appropriate signals were generated." The device is a data recorder, not an AI for interpretation, so such a study would not typically be relevant.

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

Standalone Performance: Not applicable in the context of an "algorithm only" device as described for AI. This device (Suzanne) is a data collection system. Its "performance" refers to its ability to accurately acquire and record physiological signals, not to produce diagnostic interpretations that would typically have a standalone algorithm performance measurement. The functional and software tests described confirm its ability to collect and store data reliably.

7. The Type of Ground Truth Used

Ground Truth: For the basic signal generation test, the "ground truth" was likely the expected physiological signals (e.g., a visibly clear ECG waveform, consistent respiratory patterns, etc.) that would be generated by a healthy person and observable by an engineer or technician. It was not expert consensus, pathology, or outcomes data.

8. The Sample Size for the Training Set

Training Set Sample Size: Not applicable. This device is a hardware and software system for data acquisition, not a machine learning algorithm that requires a training set in the conventional sense.

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

Training Set Ground Truth: Not applicable, as there is no training set for a machine learning model. The "ground truth" for the device's development would be its engineering specifications and the accurate reflection of known physical phenomena.

Summary

Regulation Number and Section

§ 868.2375 Breathing frequency monitor.

(a)
Identification. A breathing (ventilatory) frequency monitor is a device intended to measure or monitor a patient's respiratory rate. The device may provide an audible or visible alarm when the respiratory rate, averaged over time, is outside operator settable alarm limits. This device does not include the apnea monitor classified in § 868.2377.(b)
Classification. Class II (performance standards).