Search Results

The SleepImage System is medical software that establishes sleep quality. The SleepImage system analyzes, displays and summarizes ECG data, typically collected during sleep that is intended for use by or on the order of a Health Care Professional to aid in the evaluation of sleep disorders, where it may inform or drive clinical management.

The SleepImage System consists of an operator-independent process that automatically analyzes Electrocardiography data using a general purpose computing platform. When provided in addition to the ECG data, the SleepImage System can optionally 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.

The data output establishes sleep quality and allows the healthcare professional 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.

The clinician can create unique patient reports for the patient being evaluated, and configure parameters in the software.

The SleepImage System is a standalone, sleep health evaluation application that provides automated analysis of cardiovascular and respiratory waveforms. Like the predicate device, it processes information recorded during sleep. The SleepImage System is considered to be medical software.

The SleepImage System is being updated from the predicate device, the M1 Sleep Data Recorder and CPC Application Software to operate independent of the dedicated M1 Sleep Data Recorder cleared under K092003.

The provided text describes the 510(k) submission for the SleepImage System. While it states that a study was conducted, it does not provide detailed acceptance criteria and performance data in the structured format requested (e.g., specific metrics like sensitivity, specificity, or accuracy with threshold values). The document focuses on demonstrating substantial equivalence to a predicate device, rather than proving performance against predefined clinical criteria for a novel device.

Therefore, many of the requested sections regarding acceptance criteria and detailed study results cannot be fully extracted from the provided text. However, based on the information available, here's what can be provided:

Acceptance Criteria and Study to Prove Device Meets Acceptance Criteria

Summary: The SleepImage System is medical software that analyzes ECG data to establish sleep quality for the evaluation of sleep disorders. The primary "study" mentioned is a comparison study to demonstrate substantial equivalence to a predicate device, specifically the M1 Sleep Data Recorder and CPC Application Software (K092003). The core of the evidence relies on the claim that the SleepImage System software is "identical in specifications and performance" to the previously cleared CPC Application Software and that its analysis of ECG signals from alternate sources is "statistically equivalent" to the predicate device.

1. Table of Acceptance Criteria and Reported Device Performance:

Based on the provided text, the acceptance criteria are not explicitly defined with numerical targets (e.g., "sensitivity > X%"). Instead, the acceptance is based on demonstrating substantial equivalence to a predicate device.

• A study compared ECG analysis and results of the SleepImage System based on simultaneous recordings with alternate ECG collection sources (typical hospital PSG study and home-use ECG sensors) and the predicate M1 Sleep Data Recorder.
• The result of this comparison is that the output from the ECG signals from the alternate recordings are "in every respect statistically equivalent" to the output from ECG signals recorded by the predicate M1 Sleep Data Recorder predicate device. |

2. Sample Size Used for the Test Set and Data Provenance:

• Sample Size: The exact sample size for the comparison study is not specified in the provided text. It only states "A study was conducted to compare electrocardiography (ECG) analysis and results of the SleepImage System based on simultaneous recordings with alternate ECG collection sources...".
• Data Provenance: Not explicitly stated. The text mentions "typical hospital PSG study" which suggests clinical data, but details like country of origin or whether it was retrospective/prospective are not provided.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:

• This information is not provided in the document. The study described is a comparison of instrument outputs (ECG analysis results) for "statistical equivalence," rather than a clinical ground truth established by expert review.

4. Adjudication Method for the Test Set:

• Not applicable/Not provided. The study described compares computational outputs, not human interpretations requiring adjudication.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:

• No. The document describes a study comparing the device's output across different ECG signal sources to a predicate device, not a human reader study (MRMC) evaluating AI assistance.

6. If a Standalone (algorithm only without human-in-the-loop performance) was done:

• Yes, indirectly. The study described evaluates the SleepImage System's standalone analytical performance by comparing its ECG analysis results from different sources to the predicate device's results. The device itself is described as "operator-independent" and providing "automated analysis."

7. The Type of Ground Truth Used:

• Comparison to a predicate device's output. The "ground truth" for this study is implicitly the output from the previously cleared M1 Sleep Data Recorder predicate device. The study aimed to show that the SleepImage System's outputs using various ECG sources were "statistically equivalent" to the predicate device's outputs. There is no mention of an independent clinical ground truth (e.g., pathology, outcomes data, or fully independent expert consensus) against which the device's diagnostic accuracy was measured.

8. The Sample Size for the Training Set:

• Not applicable/Not provided. The document describes the SleepImage System software as being "identical in specifications and performance" to the previously cleared CPC Application Software. This suggests it's an updated version of existing software, rather than a de novo AI model requiring a distinct training set. If it is an AI/ML model, the details of its training set are not disclosed.

9. How the Ground Truth for the Training Set was Established:

• Not applicable/Not provided. Similar to point 8, if this is an updated version of existing software, a "training set" might not be relevant in the same way it would be for a novel machine learning algorithm. If there was a training process for underlying algorithms, the ground truth establishment method is not described.

Ask a specific question about this device

The EZsleep Sleep Quality Recorder is to be placed on patient's chest for recording of heart rate signals while patient is asleep. The recorded data is for sleep quality analysis. The EZsleep Sleep Quality Recorder is not intended for monitoring purpose.

The EZsleep Sleep Quality Recorder is a small battery powered device designed to be simple and easy to use by a patient who suffers from sleep disorder. It is self-contained, with integrated microcontroller and LED displays and all necessary interface electronics for performing recording functions. The device has a storage function in which the recorded signals can be transmitted through a USB port to a computer for data analysis. The proposed device is intended for adults who suffer from sleep disorders such as abnormal pauses in breathing (apnea), or instances of abnormally low breathing during sleep (hypopnea). This device is not intended to substitute for a hospital device for diagnosis of sleep disorders. This device is also not intended for recording and transmission of user's heart rate signal simultaneously. Users with implanted pacemaker are not recommended to use this device.

This 510(k) premarket notification for the EZsleep Sleep Quality Recorder does not contain the detailed information typically found in a study report that directly establishes acceptance criteria and then proves the device meets those criteria through specific performance metrics. Instead, it focuses on demonstrating substantial equivalence to predicate devices and adherence to relevant safety and performance standards.

Here's an analysis based on the provided document, addressing your specific points where information is available or can be inferred:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria or a performance table in the format usually associated with clinical or analytical validation studies. Instead, it relies on general performance claims and adherence to standards.

2. Sample Size Used for the Test Set and Data Provenance

The document does not specify a sample size for a test set in the context of a clinical performance study. The "Performance Summary" primarily refers to bench tests for electrical safety, EMC, and biocompatibility. These types of tests typically involve a limited number of device units or specific materials rather than patient data.

Data Provenance: Not applicable based on the type of tests described.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications

This information is not provided in the document. The filing describes safety and engineering tests, not a clinical study involving expert interpretation of patient data to establish ground truth.

4. Adjudication Method for the Test Set

This information is not provided. As explained above, the document details engineering and safety tests, not clinical evaluations that typically employ adjudication methods.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

A multi-reader multi-case (MRMC) comparative effectiveness study was not conducted or reported in this 510(k) submission. The device is a "Sleep Quality Recorder" which records heart rate signals. The recorded data is intended for "sleep quality analysis using the software, Sleep Quality Apnea Examination System, which was already cleared by US FDA, as K070855." This implies the EZsleep device is a data acquisition tool, and its primary function being evaluated here is accurate signal recording and safe operation, not diagnostic efficacy compared to human readers.

6. Standalone Performance Study

A standalone performance study, in the sense of an algorithm-only diagnostic performance without human-in-the-loop, is not described for the EZsleep device itself. The EZsleep is a recorder. Its "performance" in this context is about accurately recording signals and meeting safety/EMC standards, not about making diagnostic interpretations. The document explicitly states the recorded data is for analysis by another cleared software (K070855), implying that diagnostic interpretation is handled by that separate system, not the EZsleep recorder in standalone mode.

7. Type of Ground Truth Used

For the bench tests mentioned:

• Electrical Safety & EMC: Ground truth would be defined by the specifications in IEC 60601-1 and IEC 60601-1-2. The "truth" is whether the device's electrical characteristics and electromagnetic compatibility fall within the limits set by these standards. This is generally determined by calibrated test equipment.
• Biocompatibility: Ground truth is established by ISO 10993 guidelines, which define acceptable levels of biological response to materials. Testing would involve observing biological reactions (e.g., irritation) to the device's materials.

No human expert consensus, pathology, or outcomes data is referenced for establishing ground truth for the EZsleep recorder's performance in this document.

8. Sample Size for the Training Set

The document does not mention a training set as this filing describes a hardware device (recorder) and its associated bench tests, not an AI/ML algorithm that would typically require a training set.

9. How the Ground Truth for the Training Set Was Established

Since no training set for an AI/ML algorithm is mentioned, this point is not applicable.

Ask a specific question about this device