(90 days)
Sleep Data Recorder: The M1 sleep data recording device is intended for use by a physician or a trained technician for the collection of physiological (Actigraphy) and Electrocardiogram (ECG) recordings during sleep that will be used for screening different sleep associated disorders.
CPC WEB Application Software: The CPC application software (and associated modules) is intended for use by a physician or a trained technician for the analysis, manipulation and final presentation of physiological (Actigraphy) and Electrocardiogram (ECG) recordings during sleep.
Cardiopulmonary coupling (CPC) is currently a functional module included as one of many features in Embla's polysomnographic (PSG) presentation software of the predicate device. This can be invoked by the user to provide a CPC analysis from the EKG signals provided by the current multi-channel recorders in Embla's hardware product line. It has been decided to duplicate this presentation software module into its own product line with a separate web based application using a dedicated recorder. Therefore. MyCardio and Embla have developed a single channel (EKG) hardware recording device (M1 Sleep Data Recorder) and associated WEB site (CPC Web Application Software) to present the data and provide graphs and reports for manual diagnosis.
The model M1 Sleep Data Recorder is intended to be used as a sleep quality screening device. The M1 is a small palm size data recorder used with two commercially available EKG patient electrodes. One electrode snaps directly onto the recorder body. while the second electrode snaps onto a short cable in turn connected to a connector on the M1. The M1 is to be attached to the patient at home by the two electrodes and used to record multiple individual sleep periods. Following the home study, the M1 is returned to the clinic and the data is uploaded by the clinician to the CPC Web Application Software.
The CPC Application Software consists of three separate software programs working as a system. (1) CPC Console software - this software is similar to the predicate device presentation software CPC module and receives the data uploaded from the M1 recorder and performs the actual data graphing and reporting. (2) CPC Client software - this software manages the interaction between the user and the M1 device and uploads the analyzed M1 data from the CPC Console to the CPC Web software. (3) CPC Web software - this software creates the user interface screens, manages the data inputted by the user, keeps track of the studies and patient demographics, and provides charts, graphs and reports for manual evaluation of sleep quality screening.
A trained physician would typically review and analyze the charts, graphs and reports created and presented by the CPC Web Application Software. After this screening evaluation, the patient may require further testing and examination for possible treatment.
The battery operated M1 device will be capable of 72 hours (representing approximately 10 overnight studies) of recording to an internal memory.
The general intended environment is the patient home but the device is capable of functioning in any environment where patients can sleep reasonably comfortably.
The users are the general public, trained physicians, trained sleep technicians (RPGST) or people working under the supervision of one of these professionals. The user may or may not possess knowledge of the physiological signals or test criteria.
The M1 Sleep Data Recorder and CPC Web Application Software do not provide any alarms and are not intended as a monitor.
The provided 510(k) summary does not contain details about acceptance criteria or a specific study proving the device meets them, in the format typically required for performance claims of AI/ML-driven devices related to diagnostic accuracy.
However, based on the information provided, I can infer the implied acceptance criteria and describe the comparative study that was partially described.
Here's an analysis based on your requirements, highlighting what's present and what's missing:
Acceptance Criteria and Device Performance Study
The M1 Sleep Data Recorder and CPC Application Software are designed to be "clinically equivalent" to a predicate device (Embletta Gold) regarding their ability to record and present EKG signals and subsequently analyze them for sleep quality screening.
1. Table of Acceptance Criteria and Reported Device Performance
Note: The document does not explicitly state quantitative acceptance criteria (e.g., specific accuracy metrics, sensitivity, specificity, AUC, or concordance rates with defined thresholds). It focuses on qualitative "clinical equivalence."
| Acceptance Criteria Category | Acceptance Criteria (Implied) | Reported Device Performance (as stated in the conclusion) |
|---|---|---|
| EKG Signal Recording | The EKG signal recorded by the M1 Sleep Data Recorder should be "clinically equivalent" to the EKG signal recorded by the predicate Embletta Gold recorder in the context of screening. | "The EKG signal recorded by the M1 Sleep Data Recorder is in every respect clinically equivalent in the context of screening to the EKG signal currently recorded by the predicate device." |
| CPC Presentation & Analysis | The presentation, analysis, and reports generated by the CPC Web Application Software for EKG signals should be "clinically equivalent" to those generated by the CPC module of the predicate device's PSG application software for EKG signals, for sleep quality screening. | "The presentation, analysis and reports generated by the CPC Web Application Software... were compared by qualified sleep technicians... The result of the comparison is that the presentation, analysis and reports generated by the CPC Web Application Software are in every respect clinically equivalent to the presentation, analysis and reports generated by the predicate device." |
2. Sample Size for Test Set and Data Provenance
- Sample Size: This information is not provided in the summary.
- Data Provenance: This information is not provided in the summary. It's unclear if the data was retrospective or prospective, or from what country/clinical setting it originated.
3. Number and Qualifications of Experts for Ground Truth
- Number of Experts: This information is not explicitly stated. The conclusion mentions "qualified sleep technicians" performing the comparison of the CPC analysis and reports. It doesn't specify if these technicians established a ground truth from an independent source or simply compared the outputs of the new device against the predicate.
- Qualifications of Experts: The experts are described as "qualified sleep technicians." No further details (e.g., years of experience, specific certifications like RPGST) are given for those involved in the comparison mentioned in the conclusion. For the intended use, "trained physicians" and "trained sleep technicians (RPGST)" are mentioned as users.
4. Adjudication Method for the Test Set
- Adjudication Method: This information is not provided. The summary describes a comparison, but not an adjudication process involving multiple experts resolving discrepancies. It implies a direct comparison or verification by the "qualified sleep technicians."
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- Was an MRMC study done? No. The document does not describe a comparative effectiveness study involving human readers with and without AI assistance to quantify improvement. The study described is a comparison of the device's output to a predicate device's output, and the EKG signal itself.
- Effect Size: Not applicable, as an MRMC study was not described.
6. Standalone Performance Study
- Was a standalone study done? No, not in the traditional sense of measuring diagnostic accuracy against a clinical ground truth for only the algorithm. The device (M1 Recorder + CPC Software) was compared against a predicate system. The objective was to show clinical equivalence of the output, rather than the standalone diagnostic accuracy of the algorithm itself for a specific condition.
7. Type of Ground Truth Used for the Test Set
- Type of Ground Truth: The ground truth used was the output of the predicate device (Embletta Gold recorder and its CPC module software). The comparison was made against the EKG signal and the analysis/reports generated by the predicate, not against an independent clinical diagnosis, pathology, or direct patient outcomes. This implies a "reference standard" rather than a clinical ground truth for specific disease presence/absence.
8. Sample Size for the Training Set
- Sample Size: This information is not provided. The document makes no mention of a training set, which is typical for a device that is essentially porting an existing algorithm to a new platform/recorder.
9. How Ground Truth for Training Set Was Established
- How Ground Truth Was Established: This information is not provided as no training set or its associated ground truth establishment is described. The CPC algorithm itself appears to be a pre-existing module from the predicate device that was duplicated.
Summary of Gaps and Key Missing Information:
The provided 510(k) summary is typical for a predicate device comparison focusing on "clinical equivalence" of signal recording and output presentation rather than a de novo AI/ML diagnostic device with performance metrics based on diagnostic accuracy.
- No quantitative acceptance criteria are provided.
- No details on sample sizes (test or training sets) are given.
- No specific details on the number or detailed qualifications of experts involved in the comparison are provided beyond "qualified sleep technicians."
- No formal adjudication method is described.
- No MRMC or standalone diagnostic accuracy studies against a true clinical ground truth (e.g., sleep study diagnoses, pathology, outcomes) are described. The "ground truth" used for comparison was the predicate device's output.
§ 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).