Search Results

The ECG Check Universal family of devices is intended for self-testing by patients at home. These 1-lead cardiac monitors allow remote patients to display and transmit their ECG data to medical professionals via a communication device to a remote server.

Specifically, the ECG Check Universal models are indicated for patients who are concerned about their heart rhythm and have experienced the following symptoms that are suggestive of abnormal heart rhythms:

• · Skipped Beats
• · Pounding Heart (Palpitations)
• · Heart Racing or Irregular Pulse
• · Lightheadedness or Faintness
• · History of Arrhythmias

The new ECG CHECK – UNIVERSAL model devices are personal 1 lead ECG Event Monitors specifically designed to operate over the cellular network with iPhone & Android cellular phone handsets. The new ECG CHECK – UNIVERSAL model devices include two models. The ECG CHECK -UNIVERSAL (Model ECG01-U) and the ECG CHECK - UNIVERSAL PLUS (Model ECG01-UPLUS). Both models are designed to capture a user's ECG data and transmit the data via Bluetooth to a cellular device, which will ultimately transmit the ECG data over the cellular network to the ECG Check web center. The difference between the two models is that the new ECG CHECK -UNIVERSAL PLUS allows for the storage of recordings on the device and includes a button for the added capability of transmitting these ECG data transtelephonically using landlines to the ECG Check web center. The button also provides indication of the number of saved ECG recordings as well as the ability to delete saved recordings. Both new ECG CHECK - UNIVERSAL model devices will record a preselected amount of user ECG activity, as directed by the user. Typical configuration is to record 30 seconds of ECG per event.

The provided document is a 510(k) premarket notification for the ECG Check - Universal and ECG Check - Universal Plus devices. It outlines the company's claim of substantial equivalence to a predicate device (ECG Check K122184) and summarizes non-clinical testing.

However, the document states: "No clinical testing was conducted in support of this 510(k) submission." This means there is no study described in this document that proves the device meets specific acceptance criteria based on human or expert evaluation of its diagnostic performance. The submission relies on bench testing demonstrating performance equivalent or superior to the predicate and compliance with relevant IEC standards for safety and essential performance.

Therefore, I cannot provide a table of acceptance criteria and reported device performance related to diagnostic accuracy, nor can I answer questions about:

• Sample size used for a test set
• Number of experts used to establish ground truth
• Adjudication method for a test set
• MRMC comparative effectiveness study
• Standalone algorithm performance
• Type of ground truth used
• Sample size for the training set
• How ground truth for the training set was established

Based on the provided document, the acceptance criteria and study details are as follows:

1. A table of acceptance criteria and the reported device performance:

Since no clinical testing was performed to assess diagnostic performance of the new device models against specific clinical acceptance criteria, a table for this purpose cannot be created from the provided text. The submission focuses on demonstrating safety, essential performance, and equivalence to the predicate device through non-clinical bench testing and adherence to standards.

The closest analogue to "reported device performance" in this context is the successful passing of various safety and performance standards.

2. Sample size used for the test set and the data provenance:

• Sample size: Not applicable for a clinical test set, as no clinical testing was conducted. The non-clinical testing involved various bench tests on the device hardware and software.
• Data provenance: Not applicable to clinical data. For non-clinical testing, it would be laboratory-generated data from device testing.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Not applicable, as no clinical test set requiring expert ground truth for diagnostic accuracy was used.

4. Adjudication method for the test set:

• Not applicable, as no clinical test set was adjudicated.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• No, an MRMC study was not done. The device is a 1-lead cardiac monitor for self-testing and transmission of ECG data, not an AI diagnostic algorithm assisting human readers in interpreting complex images or signals in a clinical study setting.

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

• The document implies that the device captures and transmits ECG data to a "web center for analysis and assessment by qualified professionals," and that the web-based engine uses "standard analysis of ECG... in similar terms to a stoplight (Green, Yellow, Red)." While this suggests an algorithmic component to the "stoplight" assessment, the submission does not detail a standalone diagnostic performance study of this algorithm. The focus is on the device's ability to capture and transmit data reliably and safely.

7. The type of ground truth used:

• For demonstrating substantial equivalence and safety/performance: The ground truth was established by adherence to recognized national and international standards (e.g., IEC 60601 series, IEC 62366) and direct comparison of the new devices' technical specifications and bench performance against the predicate device.
• For diagnostic accuracy: Not applicable, as no clinical diagnostic accuracy study was conducted.

8. The sample size for the training set:

• Not applicable. The document does not describe the development or training of an AI algorithm in the context of a public-facing dataset, but rather the device's hardware and software for ECG acquisition and transmission.

9. How the ground truth for the training set was established:

• Not applicable.

Ask a specific question about this device