Search Results
Found 1 results
510(k) Data Aggregation
(294 days)
The Silent Night V is indicated for use in the diagnostic evaluation of adults with possible sleep disorders. The Silent Night V can score obstructive apneas, which includes mixed apneas.
The Silent Night V is a portable, line-powered ventilatory effort recorder for use in the home for the diagnostic evaluation of the patient. The device consists of a bedside unit which is positioned on the patient and the sensors are placed on the patient's body and connect into the patient module. The Silent Night V contains the same functions as its predecessor, Silent Night II, with the addition of two other functions. The functionality of Silent Night V has been expanded from the previous estimation device, (Silent Night II K973902) to include ventilatory effort monitoring. The Silent Night V provides the following data:
- Arterial oxygen saturation level (SP02)
- Pulse rate
- Respiration effort signal
- Respiration sound corrected for ambient room noise.
Throughout a typical sleep study, sleep-disordered breathing information and statistics are stored into the memory. The stored information includes time and duration of apneas and hypopneas, block apneas, number of apneas and hypopneas, number of central apneas, number of mixed apneas, number of obstructive apneas, number of desaturation events, number of pulse events, number of respiratory effort events, number of sound events, minimum saturation levels, pulse rate, respiratory effort level, sound measurement level, open in intervals, pulse rate, respiratory effort level, sound measurement level, open in intervals. Current storage capacity is 512 Kbytes, which is sufficient to retain three 8-hour studies. Software has been developed to retrieve, score, display and print the collected data on a personal computer. The collected data is provided to the physician to view the sleep data.
Here's a summary of the acceptance criteria and the study proving the Silent Night V device meets those criteria, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
Metric | Acceptance Criteria (Implied) | Reported Device Performance |
---|---|---|
Apnea Detection: | High sensitivity for apnea detection (relative to PSG) | Sensitivity: 83.2% |
False Positive Apnea Events per Hour | Low number of false positive apneas (relative to PSG) | False Positives: 3.5 events/hour |
Overall Event Detection (Apneas + Hypopneas): | High overall sensitivity for events (relative to PSG) | Overall Sensitivity: 90.7% |
False Positive Events per Hour | Low number of false positive events (apneas + hypopneas) | False Positives: 3.8 events/hour |
RDI Correlation (PSG vs. Silent Night V): | High correlation coefficient | Correlation Coefficient: 97.7% |
RDI Classification (RDI=15 cutoff): | High sensitivity and specificity for RDI classification | Sensitivity (RDI=15): 95% |
Specificity (RDI=15): 91% |
Note: The document doesn't explicitly state "acceptance criteria" but rather presents performance metrics from the clinical study as evidence of equivalence to the predicate device. Therefore, the "acceptance criteria" column is populated with implied targets based on the documented performance.
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: The document does not explicitly state the total number of patients/studies in the clinical test set. It mentions "using the overall number of patients as the basis of calculation" for RDI, but a specific number is not provided.
- Data Provenance: Prospective. The study involved patients undergoing a sleep laboratory evaluation with a standard polysomnograph, and the Silent Night V was used "concomitantly for a side-by-side comparison." This indicates a prospective collection of data in a clinical setting. The country of origin is not explicitly stated, but the company address is Palo Alto, CA, USA, suggesting the study was conducted in the US.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
The document does not provide details on the number of experts or their qualifications used to establish the ground truth. It states that the ground truth was derived from "a standard polysomnograph" and that "The data were compared on an event-by-event basis." This implies that the PSG data was expertly scored, but no specifics about the scorers are given.
4. Adjudication Method for the Test Set
The document does not explicitly describe an adjudication method. It states, "The data were compared on an event-by-event basis." This suggests a direct comparison, likely by an expert, between the PSG and Silent Night V outputs. However, specific methods like 2+1 or 3+1 for resolving discrepancies are not mentioned.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done
No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly described. The study compared the device against a standard polysomnograph (PSG), not an AI-assisted human reader vs. a human reader without AI assistance. Therefore, there is no effect size reported for human readers improving with AI.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
Yes, a standalone study was performed. The reported performance metrics (sensitivity, false positives, correlation) represent the performance of the Silent Night V device itself in detecting and classifying respiratory events, directly compared to the PSG. This is "algorithm only without human-in-the-loop performance" for the device under evaluation.
7. The Type of Ground Truth Used
The ground truth used was expertly interpreted polysomnography (PSG) data. This is considered a gold standard for sleep disorder diagnosis. The document states, "Patients underwent a sleep laboratory evaluation with a standard polysomnograph." The Silent Night V's data was then compared directly to this PSG data.
8. The Sample Size for the Training Set
The document does not provide any information regarding a training set sample size. This suggests that if the device utilizes a machine learning algorithm, the training data details were not included in this 510(k) summary. Alternatively, the device may be based on traditional signal processing rather than machine learning, eliminating the need for a "training set" in that context.
9. How the Ground Truth for the Training Set was Established
Since no information about a training set is provided, there is no information on how its ground truth was established.
Ask a specific question about this device
Page 1 of 1