Search Results

The Silent Night II is indicated for use in the diagnostic evaluation of adults with possible Obstructive Sleep Apnea. It is intended to record a patient's respiratory pattern during sleep. The device is designed for prescription use in home screening of adults with possible sleep disorders. Information provided by the device includes the numbers of apneic and hypopneic events and the proportion of these events to the total sleep duration; and snoring levels (in decibels). The device is capable of recording four nights or up to 40 hours for an individual patient, after which time the sleep data are downloaded for provision to the prescribing physician.

The Silent Night™ II is a modified version of the legally marketed Silent Night I. The device is a portable, line-powered ventilatory effort recorder intended for use in the home screening of possible sleep disorders. The metal box has two receptacle connectors: one for input power and another for the microphone cable. The sensing microphone and the ambient noise microphone are located at the distal end of the cable, and are attached to the user by means of a modified conventional plastic oxygen cannula. The sensing microphone, located directly beneath the patient's nose, senses respiratory sounds during sleep. The ambient microphone, angled to the side of the patient's nose, senses room ambient noise and measures snoring levels. The Silent Night II is capable of recording up to four nights of sleep study data. The beginning and end of the sleep study are controlled by the use of the START and STOP buttons, located on the front of the unit. An LCD indicates operational status and has a sound level bar, used by the patient at the beginning of the study to verify adequate sensing of breathing sounds by the device.

The device operates by sensing the sound field (breathing sounds + room ambient noise) via the two microphones. Breathing sounds are extracted from all sounds received. The signals are filtered, analyzed, and processed to differentiate between types of sounds and to classify sounds as regular snoring or breathing, hypopnea, or annes. When beep study is completed, the cumulatively logged data are downloaded by Local Site a personal computer. Specialized software and provides, for each night of the sleep study, information about apneas, hypopneas, and snoring levels.

Here's an analysis of the provided text regarding the acceptance criteria and study for the Silent Night™ II device, formatted to include the requested information:

Acceptance Criteria and Device Performance Study for Silent Night™ II

1. Table of Acceptance Criteria and Reported Device Performance

The provided document describes the clinical evaluation of the Silent Night™ II by comparing it to a predicate device, the Sensormedics Model 4100 Somnostar system, for detecting sleep disordered breathing events. The acceptance criteria are implicitly derived from the "high positive correlation" and "strong positive linear association" stated. Specific numeric thresholds for sensitivity and specificity are not precisely defined in the text, but the study indicates the device met these criteria.

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

• Test Set Sample Size: The document does not explicitly state the number of patients or the exact sample size used for the clinical evaluation. It only mentions "Patients were subjected to sleep laboratory evaluation."
• Data Provenance: The study appears to be prospective as patients were "subjected to sleep laboratory evaluation" where both the Silent Night II and the Sensormedics system were used simultaneously. The country of origin of the data is not specified, but given the submitter is based in San José, CA, USA, and the FDA review, it is highly likely the study was conducted in the USA.

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

• Number of Experts: The document does not specify the number of experts used.
• Qualifications of Experts: The document does not explicitly state the qualifications of the experts. However, given that the ground truth was established by a "standard polysomnograph (the Sensormedics Model 4100 Somnostar system)" and involved simultaneous data gathering, it can be inferred that medical professionals trained in polysomnography and sleep disorder diagnosis (e.g., sleep physicians, registered polysomnographic technologists) would have been involved in interpreting and scoring the Sensormedics data.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method (e.g., 2+1, 3+1). The ground truth was established by the Sensormedics Model 4100 Somnostar system, which is a standard polysomnograph. This implies that the output of this established device served as the reference standard.

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

A multi-reader multi-case (MRMC) comparative effectiveness study was not done or described in the provided text. The study compares the device's measurements directly against those of a gold-standard polysomnograph, not against human readers using or not using AI.

6. Standalone (Algorithm Only) Performance Study

Yes, a standalone performance study was done. The clinical evaluation directly compared the measurements (number of Apneas and Respiratory Disturbance Index - RDI) calculated by the Silent Night II device to those gathered simultaneously by the Sensormedics standard polysomnograph. This assesses the algorithm's performance without direct human interaction for interpretation of the Silent Night II's raw data, although human expertise would be involved in interpreting the Sensormedics output (ground truth).

7. Type of Ground Truth Used

The ground truth used was polysomnography data, specifically from the "Sensormedics Model 4100 Somnostar system," which is described as a "standard polysomnograph." This is a highly accepted clinical standard for diagnosing sleep disorders.

8. Sample Size for the Training Set

The document does not provide any information regarding a training set sample size. This suggests that if machine learning was involved in the device's development (which is not explicitly clear from the description of signal processing and classification), the details of its training were not part of this 510(k) summary. Given the date of the document (1998), early machine learning techniques might have been used, but explicit "training set" reporting was less common compared to modern AI/ML device submissions.

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

As no training set is mentioned, no information is provided on how its ground truth would have been established.

Ask a specific question about this device

The Silent Night I is indicated for use in the diagnostic evaluation of adults with possible Obstructive Sleep Apnea. It is intended to record a patient's respiratory pattern. The device is designed for use in home screening of adults with possible sleep disorders.

The Silent Night I (SNI) consists of a metal box measuring approximately 23 centimeters wide by 17 centimeters deep by 7.5 centimeters high. The device is portable, line-powered and weighs approximately three pounds. The box contains the operational components of the device and has two receptacle connectors: one for input power and another for the sensing microphone. This microphone is attached to the SNI by means of an eight-foot flexible cable and connector. Another microphone is built into the rear of the box and senses room ambient noise. A POWER switch is located on the back of the unit. A switch enabling the user to PAUSE and RESUME device operation is located on the side of the unit.

The device operates as follows: the sound field (breathing sounds + room ambient noise) is sensed by the two microphones and sent to the controller, which extracts breathing sounds from all sounds received. These signals are then sent through bandpass filters and the amplitude characteristics of the signals in the frequency realm are analyzed. The signals are then processed by the pattern recognizer, which differentiates between types of sounds and classifies them as regular snoring or breathing, hypopnea, or apnea. These classified events are logged cumulatively and shown on a liquid crystal display as Disordered Breathing Events (DBE) on the front control panel of the device.

Here's an analysis of the acceptance criteria and study information for the Silent Night I device, 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

• Sample Size: The document does not explicitly state the specific number of patients included in the clinical study. It only mentions "Patients were subjected to sleep laboratory evaluation."
• Data Provenance: The document does not specify the country of origin. The study appears to be prospective as it involved patients being simultaneously evaluated by both the Silent Night I and a standard polysomnograph.

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

• The document does not explicitly mention the number of experts or their qualifications for establishing ground truth.
• The "ground truth" was established by a standard polysomnograph (the Grass Model 7P511 High Performance AC Amplifier), which is considered a benchmark device in sleep studies. While experts would interpret polysomnography data, the document doesn't detail this process for the ground truth establishment itself.

4. Adjudication Method for the Test Set

• The document does not describe a formal adjudication method. The comparison was statistical, correlating the measurements between the Silent Night I and the Grass polysomnograph. It doesn't mention multiple readers independently assessing data and then having an adjudication process.

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, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly described.
• The study focuses on the device's standalone performance compared to a gold standard, not on how it assists human readers. The device performs the analysis and displays the results directly ("These classified events are logged cumulatively and shown on a liquid crystal display"). Therefore, there is no mention of effect size related to human reader improvement with AI assistance.

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

• Yes, a standalone study was done. The Silent Night I is described as a device that "extracts breathing sounds from all sounds received," "processes... by the pattern recognizer," and "differentiates between types of sounds and classifies them as regular snoring or breathing, hypopnea, or apnea." The classified events are then "logged cumulatively and shown on a liquid crystal display." This indicates the device autonomously performs the detection and classification. The clinical study compares these device-generated results directly to the polysomnograph.

7. The Type of Ground Truth Used

• The ground truth used was data from a standard polysomnograph (the Grass Model 7P511 High Performance AC Amplifier). This is considered a clinical gold standard for measuring respiratory events during sleep.

8. The Sample Size for the Training Set

• The document does not specify a sample size for a training set. This device predates widespread explicit mention of "training sets" in regulatory submissions for AI/ML devices in the way we understand them today. The device uses "pattern recognizer" technology, implying some form of internal logic or learning, but the details of its development data are not provided.

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

• As the document does not specify a training set sample size, it also does not describe how the ground truth for any potential training set was established.

Ask a specific question about this device