(324 days)
The SleepImage System is Software as a Medical Device (SaMD) that establishes sleep quality. The SleepImage System analyzes, displays and summarizes Electrocardiogram (ECG) or Plethysmogram (PLETH) data, typically collected during sleep, that is intended for use by or on the order of a Healthcare Professional to aid in the evaluation of sleep disorders, where it may inform or drive clinical management for children, adolescents and adults.
The SleepImage Apnea Hypopnea Index (sAHI), presented when oximeter data is available, is intended to aid healthcare professionals in diagnosis and management of sleep disordered breathing.
The SleepImage System output is not interpreted or clinical action taken without consultation of a qualified healthcare professional.
The SleepImage System is a Class II Software as a Medical Device (SaMD), intended to aid in the evaluation of sleep disorders, where it may inform or drive clinical management.
The Sleeplmage System automatically analyzes and displays Electrocardiogram (ECG) and Plethysmogram (PLETH) data. When provided in addition to the ECG or PLETH data, the SleepImage System can optionally analyze and display accelerometer and oximeter data.
The results of the processed data are graphical and numerical presentations and reports of sleep latency, sleep duration, sleep quality and sleep pathology for the use by or on the order of physicians, trained technicians, or other healthcare professionals to evaluate sleep disorders where it may inform or drive clinical management taking into consideration other factors that normally are considered for clinical management of sleep disorders for children, adolescents and adults. When oximeter data is available, the Sleeplmage System will generate the Sleeplmage Apnea Hypopnea Index (sAHI) to aid healthcare professionals in diagnosis and management of sleep disordered breathing.
The SleepImage System reports results of the automated data analysis, including expected values for sleep quality, sleep duration and sleep pathology based on published peer-reviewed publications, and guidelines for sleep duration (National Sleep Foundation) and sleep apnea (American Academy of Sleep Medicine).
The clinician can view raw data for interpretation, adjust study duration, write clinical notes in the report and make recommendations to patients for further testing, recommend a referral to another clinician and/or recommendations for therapy.
The SleepImage System output is not intended to be interpreted or clinical action taken without consultation of a qualified healthcare professional. Due to the intra-night variability of sleep, it is recommended that patients track their sleep over time.
The SleepImage System is a sleep health evaluation application that is indicated for use on a general-purpose computing platform. Like the predicate device, it processes data typically recorded during sleep, using a cloud-based web application.
Here's a breakdown of the acceptance criteria and study information for the SleepImage System, based on the provided document:
1. Acceptance Criteria and Reported Device Performance
The document does not explicitly present a table of acceptance criteria with specific performance metrics (e.g., sensitivity, specificity, accuracy thresholds) for the modifications. Instead, it states that "All parameters tested exceeded the thresholds set for the tests."
However, we can infer the type of acceptance criteria based on the comparisons made:
| Acceptance Criteria Type | Reported Device Performance / Assessment |
|---|---|
| Modification #1: PLETH vs. ECG input for CPC Analysis | |
| Agreement between automated output from CPC analysis using PLETH input vs. ECG input (compared to predicate device). | "All parameters tested exceeded the thresholds set for the tests." The report references the average agreement for sleep stage scoring among expert scorers using PSG (82.6%) as a contextual benchmark for inter-scorer reliability. The clinical evaluation confirmed that CPC analysis with PLETH input is comparable to ECG input for clinical decisions. |
| Modification #2: SleepImage Apnea Hypopnea Index (sAHI) vs. Manual AHI | |
| Agreement between sAHI calculated by the device and manual human scoring of AHI using AASM criteria for mild, moderate, severe sleep apnea (pediatric & adult). | "All parameters tested exceeded the thresholds set for the tests." The clinical evaluation confirmed that sAHI auto-scoring algorithms generate comparable output to human manual scoring of AHI from PSG studies. |
| Sensitivity and Positive Likelihood Ratio (LR+) of sAHI against pre-determined thresholds for Out Of Center (OOC) diagnostic devices (based on AASM guidelines). | "All parameters tested exceeded the thresholds set for the tests." The document states that the sAHI demonstrated agreement levels compared to manually scored AHI from PSG studies to be used to aid clinical diagnosis. |
| No adverse impact on existing predicate device functionality due to software modifications. | "Validation and verification was performed to verify that the software modifications did not have any adverse impact on the functionality of the SleepImage System." "The verification and validation testing demonstrate that both new feature requirements have been satisfied and safety and effectiveness has not been inadvertently affected by modifications to the system." |
Study Details:
2. Sample Size and Data Provenance
- Test Set Sample Size: Over 2,000 sleep studies.
- Children: 1334 studies (all based on PSG studies).
- Adults: 761 studies (189 from PSG, 572 from HSAT).
- Data Provenance: The records were "obtained from prospective clinical trials," indicating prospective collection. The country of origin is not specified.
3. Number of Experts and Qualifications for Ground Truth
- The document mentions "manual human scoring of Apnea Hypopnea Index (AHI) using American Academy of Sleep Medicine (AASM) scoring criteria" as a comparator for the sAHI. It refers to the "average agreement for sleep stage scoring among expert scorers in accredited sleep centers using PSG" (82.6%) for contextual comparison but does not state the number or specific qualifications of experts who performed the manual scoring for this specific test set's ground truth. It implies that the human scoring adhered to AASM guidelines, suggesting qualified sleep experts/technicians.
4. Adjudication Method for the Test Set
- The document does not explicitly state an adjudication method (e.g., 2+1, 3+1). It refers to "manual human scoring" which typically implies one qualified scorer, but does not detail if multiple scorers or an adjudication process were used for discrepancies in the AHI ground truth.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- No, a formal MRMC comparative effectiveness study involving human readers with and without AI assistance is not explicitly described. The study compared the device's automated output to human manual scoring (for sAHI) and to the predicate device's performance (for CPC with different input). It did not assess human reader improvement with AI assistance.
6. Standalone Performance Study
- Yes, a standalone (algorithm only) performance study was done for both modifications:
- Modification #1 (PLETH vs. ECG for CPC): The study compared the automated output of CPC analysis using PLETH input directly against the automated output using ECG input (which was the basis of the predicate device).
- Modification #2 (sAHI calculation): The study compared the device's automatically calculated sAHI against manually scored AHI and evaluated its sensitivity and LR+ against AASM guidelines for OOC devices. This is a clear standalone performance evaluation.
7. Type of Ground Truth Used
- For Modification #1 (PLETH vs. ECG for CPC): The ground truth implicitly seems to be the performance of the predicate device's ECG-based CPC analysis. The comparison was to show agreement between the two automated methods.
- For Modification #2 (sAHI): The ground truth was "manual human scoring of Apnea Hypopnea Index (AHI) using American Academy of Sleep Medicine (AASM) scoring criteria" from Polysomnography (PSG) studies.
8. Sample Size for the Training Set
- The document does not specify the sample size used for the training set. The "over 2,000 sleep studies" are mentioned in the context of "clinical evaluation" which typically refers to validation/test data, not training data.
9. How the Ground Truth for the Training Set Was Established
- Since the training set size is not provided, the method for establishing its ground truth is also not detailed. However, it can be inferred that if AHI was part of the training, it would likely follow AASM scoring criteria, similar to the test set.
§ 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).