(216 days)
The Sandman Elite software is intended for Polysomnography studies on pediatric and adult patients, and allows recording, displaying, analysis, printing and storage of physiological signals to assist in the diagnosis of various sleep disorders. The Sandman software also allows:
- Sleep report templates which summarize recorded and scored sleep data using simple measures including count, average, maximum and minimum values as well as data ranges for trended values;
- An optional automated analysis of physiological signals that is intended for use only in adults;
- An optional audio/visual alert for user defined threshold on calibrated DC input. These alerts are not intended for use as life support such as vital signs monitoring or continuous medical surveillance in intensive care units.
The Sandman software is intended for use only by qualified and trained medical practitioners in research and clinical environments, who evaluate the software output with their clinical experience and judgment to provide diagnostic conclusions about the patient's condition.
The Sandman Elite Application is a software product that runs on a desktop or laptop computer and requires no specialized hardware. It is a Windows based application used at sleep labs by trained clinicians to investigate sleep disorders. The Sandman Elite application collects and digitizes the electrical voltages of patient physiological signals. After collecting and saving the signals, it provides tools and modules to analyze the signals, which aid in the interpretation of a sleep study. The software consists of four main applications: Collection, Analysis, Data Management, and Configuration. The Sandman Elite application also includes a separate independent Report Builder module. All data are stored either locally or on a remote hard disk (network server). Provisions exist for archiving to several appropriate types of digital media, most frequently CD ROM. The Sandman Elite application software contains a number of computer-assisted scoring modules for analysis of adult patient data only.
Here's a summary of the acceptance criteria and the study proving the device meets them, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state pre-defined acceptance criteria for the PPA and False Detection Rate per Hour. Instead, it presents the results from the clinical study and concludes that the device performance is "clinically equivalent to the Reference standard (majority rule)" and "comparable to the manual markings of expert reviewers." Therefore, the reported performance values implicitly serve as the demonstrated acceptable performance.
| Event | Performance Metric | Reported Value (Mean) | 95% Confidence Interval (Lower) | 95% Confidence Interval (Upper) |
|---|---|---|---|---|
| Central apnea | Positive Percent Agreement (PPA) | 95.1% | 88.1% | 97.4% |
| False Detection Rate Per Hour | 3.8 | 2.4 | 6.4 | |
| Mixed apnea | Positive Percent Agreement (PPA) | 97.6% | 88.7% | 99.5% |
| False Detection Rate Per Hour | 0.8 | 0.4 | 1.4 | |
| Obstructive apnea | Positive Percent Agreement (PPA) | 92.0% | 86.0% | 94.1% |
| False Detection Rate Per Hour | 7.7 | 6.1 | 9.6 | |
| Hypopnea | Positive Percent Agreement (PPA) | 85.9% | 79.8% | 88.2% |
| False Detection Rate Per Hour | 15.4 | 13.3 | 17.8 | |
| Limb movement | Positive Percent Agreement (PPA) | 86.0% | 83.0% | 88.5% |
| False Detection Rate Per Hour | 16.8 | 14.0 | 20.5 | |
| Snoring | Positive Percent Agreement (PPA) | 82.0% | 78.3% | 84.7% |
| False Detection Rate Per Hour | 21.6 | 18.3 | 26.0 |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: 56 diagnostic PSG sleep studies were collected. Data from 54 subjects were evaluated for respiratory, limb movement, and snore events.
- Total Number of Subjects: 54 per event evaluated
- Total Number of scored Epochs (30 Sec): > 49,704
- Total Number of Hours: > 411.99
- Mean number of epochs per subject: > 920.4
- Minimum number of epochs per subject: 711
- Maximum Number of epochs per subject: 1,147
- Data Provenance: The document does not explicitly state the country of origin. It indicates that "All patients involved in this study were adult patients (>18 years old) with a clinical indication for a sleep study." The studies were collected for diagnostic purposes and then de-identified. It appears to be a retrospective collection of diagnostic PSG sleep studies.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
- Number of Experts: Three (3) experienced and certified PSG specialists.
- Qualifications of Experts: Included one board-certified sleep specialist, along with other experienced and certified PSG specialists.
4. Adjudication Method for the Test Set
- Adjudication Method: "Majority rule," defined as "at least two out of three expert scorings (medical professionals certified on PSG recording and analysis) agree on the presence of an event within an epoch."
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- The document describes a study comparing the Sandman assisted-scoring modules to a "Reference standard" established by expert manual markings. This is a standalone performance study of the algorithm against expert consensus, not a comparative effectiveness study of human readers with vs. without AI assistance. Therefore, no effect size of human readers improving with AI vs without AI assistance is reported.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
- Yes, a standalone performance study was done. The study evaluated the Sandman assisted-scoring modules (algorithm only) against the ground truth established by expert consensus. The reported PPA and False Detection Rate per Hour reflect the algorithm's performance.
7. Type of Ground Truth Used
- Expert Consensus: The "Reference standard" was defined using the majority rule of three experienced and certified PSG specialists.
8. Sample Size for the Training Set
- The document does not provide information regarding the sample size used for the training set. It only details the clinical validation study for the assisted-scoring modules. The phrasing "Sandman assisted-scoring modules at default values" suggests these modules were pre-trained or configured, but no details on training data are given.
9. How the Ground Truth for the Training Set Was Established
- As the document does not provide information on the training set, it does not describe how the ground truth for the training set was established.
§ 882.1400 Electroencephalograph.
(a)
Identification. An electroencephalograph is a device used to measure and record the electrical activity of the patient's brain obtained by placing two or more electrodes on the head.(b)
Classification. Class II (performance standards).