(111 days)
Somnolyzer 24x7 is a computer program (software) intended for use as an aid for the diagnosis of sleep and respiratory disorders.
Somnolyzer 24x7 is intended to be used for analysis (automatic scoring and manual re-scoring), display, redisplay (retrieve), summarize, reports generation and networking of data received from monitoring devices typically used to evaluate sleep and respiratory related sleep disorders.
This device is to be used under the supervision of a physician.
Somnolyzer is a polysomnography scoring application that provides automated analysis of sleep, respiratory and movement information recorded during sleep studies. It processes information recorded during sleep by electrodes and sensors attached to the body. It then generates results that include quantitative sleep, breathing and motion parameters, used to evaluate sleep and respiratoryrelated disorders. Somnolyzer 24x7 scoring is applicable to adult patient populations only.
Somnolyzer 24x7 version 2.5 provides an update to the currently released Somnolyzer 24x7 (K083620), which enables Somnolyzer to score sleep recordings according to the American Academy of Sleep Medicine (AASM) Manual 2007 and 2012 editions.
Here's an analysis of the provided information regarding the Somnolyzer 24x7, focusing on acceptance criteria and the study used to demonstrate compliance.
Based on the provided text, there is no explicit table of acceptance criteria or a detailed study description with performance metrics for the Somnolyzer 24x7. This submission (K131994) is a 510(k) for a modified device, and the primary claim is substantial equivalence to a previously cleared predicate device (Somnolyzer 24x7, K083620).
The submission relies on a non-clinical test approach, specifically focusing on verification and validation activities to ensure the modifications did not adversely affect safety and effectiveness.
Here's what can be extracted and inferred from the text regarding the requested information:
1. Table of Acceptance Criteria and Reported Device Performance
As stated, no explicit table of acceptance criteria or detailed performance metrics are provided in the document. The submission focuses on verification that the modifications performed as intended and did not impact safety and effectiveness.
The document implicitly states that "Testing confirmed that the Somnolyzer 24x7 software version 2.5 performs equivalently to the device predicate Somnolyzer 24x7 software (K083620). All tests had passing results or minor resolved defects." This implies the acceptance criteria were met, but the specific criteria and performance values are not detailed.
Inferred "Acceptance Criteria" (based on nature of submission):
| Acceptance Criteria (Inferred) | Reported Device Performance (Inferred) |
|---|---|
| Functional Equivalence: The modified software must correctly implement the AASM 2007 and 2012 scoring rules for sleep staging and respiratory events. | The algorithms were updated to add inputs (additional EEG leads, CPAP flow sensor, pressure transducer, RIPflow). Sleep staging and respiratory event scoring rules were updated. The software confirmed to support sub-classification of hypopneas and detect Cheyne Stokes breathing patterns. |
| Accuracy of Automated Scoring: The automated scoring results of the modified device should be comparable to human manual scoring. (Implied for substantial equivalence to predicate) | Automated validation testing "compared the performance of human manual scoring against Somnolyzer 24x7 version 2.5 and previous versions of Somnolyzer." The testing confirmed that the device "performs equivalently to the device predicate." |
| Safety and Effectiveness: The modifications must not introduce new safety concerns or decrease effectiveness. | "Respironics has determined that the modifications have no impact on the safety and effectiveness of the device." "The verification and validation testing demonstrates that all new requirements have been satisfied and safety and effectiveness has not been inadvertently affected by modifications to the system." |
| Software Quality: The software should be free of significant defects. | "All tests had passing results or minor resolved defects." |
| Configuration Options: New clinician configurability features should function as intended. | Modifications were made "to provide clinician configurability of several scoring parameters, accept ECG input for signal processing... and identify and select the EMG channel with the most viable data for scoring." The verification test would have assessed these. |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: Not specified. The document mentions "automated validation testing compared the performance of human manual scoring against Somnolyzer 24x7 version 2.5 and previous versions of Somnolyzer," but does not provide details on the number of cases or studies used.
- Data Provenance: Not specified. The country of origin of the data (e.g., retrospective or prospective) is not mentioned.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: Not specified. The document refers to "human manual scoring" as the benchmark for automated validation testing but doesn't quantify how many human scorers were involved or how their results were consolidated.
- Qualifications of Experts: Not specified. The qualifications of the "human manual scorers" are not detailed (e.g., board-certified sleep physicians, polysomnographic technologists, experience level).
4. Adjudication Method for the Test Set
- Adjudication Method: Not specified. Given that multiple "human manual scorers" may have been involved in establishing the benchmark (though not quantified), the method for resolving discrepancies or establishing a consensus (e.g., 2+1, 3+1) is not mentioned. It's possible a single expert's scoring was used as the ground truth if only one manual scorer was involved, or if the "previous versions of Somnolyzer" acted as a reference point.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- No MRMC study was done or reported. The submission does not mention a comparative effectiveness study involving human readers with and without AI assistance to quantify an effect size of improvement. The testing compared the algorithm's performance to human scoring, not human performance with/without the algorithm.
6. Standalone Performance Study
- Yes, a standalone algorithm performance evaluation was done. The "automated validation testing" involved comparing the performance of the Somnolyzer 24x7 version 2.5 (algorithm only) against human manual scoring. This is a standalone performance assessment for the algorithm.
7. Type of Ground Truth Used
- Expert Consensus / Expert Interpretation. The "human manual scoring" served as the ground truth against which the automated scoring algorithm's performance was compared. This indicates an expert interpretation or potentially an expert consensus if multiple human scorers were used. The document does not mention pathology or outcomes data as ground truth.
8. Sample Size for the Training Set
- Not applicable / Not specified. This submission is for modifications to an existing device. The training set for the original Somnolyzer 24x7 (K083620) is not discussed, and there is no indication that the modifications (which primarily involve updating algorithms to AASM rules) required a new or re-training with a distinct training set. The changes were algorithmic adjustments rather than training a new deep learning model from scratch.
9. How Ground Truth for the Training Set Was Established
- Not applicable / Not specified. Similar to the above, as this is a modification submission focused on rule implementation rather than re-training a new model, the establishment of ground truth for a training set is not discussed. For the original predicate device, it is presumed to have been established through expert manual scoring in accordance with relevant sleep scoring guidelines at that time.
§ 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).