Search Results

DeepRhythmAI is a cloud-based software that utilizes AI algorithms to assess cardiac arrhythmias using a single- or two-lead ECG data from adult patients.

It is intended for use by a healthcare solution integrator to build web, mobile or another types of applications to let qualified healthcare professionals review and confirm the analytic result. The product supports downloading and analyzing data recorded in the compatible formats from ECG devices such as Holter, Event recorder, Outpatient Cardiac Telemetry devices or other similar recorders when the assessment of the rhythm is necessary.

The product can be electronically interfaced and perform analysis with data transferred from other computer-based ECG systems, such as an ECG management system. DeepRhythmAI can be integrated into medical devices. In this case, the medical device manufacturer will identify the indication for use depending on the application of their device.

DeepRhythmAI is not for use in life-supporting or sustaining systems or ECG Alarm devices. Interpretation results are not intended to be the sole means of diagnosis. It is offered to physicians and clinicians on an advisory basis only in conjunction with the physician's knowledge of ECG patterns, patient background, clinical history symptoms and other diagnostic information.

DeepRhythmAI is a cloud-based software utilizing CNN and transformer models for automated analysis of ECG data. It uses a scalable Application Programming Interface (API) to enable easy integration with other medical products. The main component of DeepRhythmAI is an automated proprietary deep-learning algorithm, which measures and analyzes ECG data to provide qualified healthcare professionals with supportive information for review. DeepRhythmAI can be integrated into medical devices. The product supports downloading and analyzing data recorded in compatible formats from ECG devices such as Holter, Event recorder, Outpatient Cardiac Telemetry devices or other similar recorders used when assessment of the rhythm is necessary.

The DRAI can also be electronically interfaced and perform analysis with data transferred from other computer-based ECG systems, such as an ECG management system. DeepRhythmAI doesn't have User Interface therefore it should be integrated with the external visualization software used by the ECG technicians for ECG visualization and analysis reporting.

DeepRhythmAI is not for use in life supporting or sustaining systems or ECG Alarm devices. Interpretation results are not intended to be the sole means of diagnosis. It is offered to physicians and clinicians on an advisory basis only in conjunction with the physician's knowledge of ECG patterns, patient background, clinical history, symptoms, and other diagnostic information.

DRAI consists of:

1. An API which allows the client to upload single- or two-lead ECG data and allows to download the results of the ECG analysis.
2. The automated proprietary deep-learning algorithm, which measures and analyzes ECG data to provide qualified healthcare professional with supportive information for review.

DRAI works in the following sequence:

1. Accept uploading digital ECG files via secure API;

2. Analyze the uploaded ECG data using a proprietary algorithm, which detects cardiac beats/arrhythmias and intervals including:

   • QRS
   • Heart rate determination
   • RR Interval measurements
   • Non-paced supraventricular rhythm and arrhythmia calls as specified by product's Instruction for Use
   • Non-paced ventricular rhythm and arrhythmia calls: as specified by product's Instruction for Use
   • Atrioventricular blocks (second or third degree)

3. Analyze detected individual Ventricular ectopic beats also known as Premature Ventricular Contractions (PVCs) to form groups and subgroups of similar beat morphology if product is configured to do so.

4. The results of the ECG analysis can be downloaded via secure API by the external visualization software used by healthcare professionals for the ECG visualization and analysis reporting.

This document describes the acceptance criteria and the study proving the device meets these criteria for DeepRhythmAI, a cloud-based software that utilizes AI algorithms to assess cardiac arrhythmias.

1. Table of Acceptance Criteria and Reported Device Performance

The provided 510(k) summary does not explicitly list quantitative acceptance criteria in terms of specific performance metrics (e.g., sensitivity, specificity, accuracy thresholds). Instead, it states that the device's performance was evaluated against recognized consensus standards and a proprietary database, and that the PVC grouping algorithm meets "predefined requirements for accuracy." Without specific numerical targets, the table below will summarize the types of performance evaluations conducted and the reported outcomes as described.

2. Sample Size for the Test Set and Data Provenance

The 510(k) summary states that "the algorithm was tested against the proprietary database (MDG validation db) that includes a large number of recordings captured among the intended patient population."

• Test Set Sample Size: The exact numerical sample size for the test set is not specified beyond "a large number of recordings."
• Data Provenance:
  • Country of Origin: Not explicitly stated. It refers to a "proprietary database (MDG validation db)."
  • Retrospective or Prospective: Not explicitly stated. Given it's a "validation db," it's likely retrospective data collected over time.

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

This information is not provided in the given 510(k) clearance letter. The document mentions "qualified healthcare professionals review and confirm the analytic result" in the context of the device's intended use and that the AI provides "supportive information for review." However, it does not detail how ground truth was established for the validation dataset, nor the number or qualifications of experts involved in that process.

4. Adjudication Method for the Test Set

The adjudication method used for establishing the ground truth for the test set is not provided in the document.

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

An MRMC comparative effectiveness study, comparing human readers with AI assistance versus without AI assistance, is not explicitly mentioned or described in the provided 510(k) summary. The device's indication for use states that "Interpretation results are not intended to be the sole means of diagnosis. It is offered to physicians and clinicians on an advisory basis only," suggesting it functions as an assistive tool, but a formal MRMC study demonstrating improvement is not detailed.

6. Standalone (Algorithm Only) Performance Study

Yes, a standalone performance study was done. The document states, "the algorithm was tested against the proprietary database (MDG validation db)" and that DeepRhythmAI "measures and analyzes ECG data to provide qualified healthcare professional with supportive information for review." The performance assessment of the "automated proprietary deep-learning algorithm" and the "hierarchical Premature Ventricular Contraction (PVC) clustering algorithm" implies a standalone evaluation of the algorithm's capabilities.

7. Type of Ground Truth Used for the Test Set

The type of ground truth used is not explicitly stated. However, given the nature of ECG analysis for arrhythmias, it is highly probable that the ground truth was established through expert consensus or manual expert annotation of the ECG recordings in the "proprietary database (MDG validation db)."

8. Sample Size for the Training Set

The sample size for the training set is not provided in the document. The document mentions the use of "CNN and transformer models for automated analysis of ECG data," which implies a machine learning approach requiring a training set, but its size is not disclosed.

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

The method for establishing ground truth for the training set is not provided in the document. As with the test set, it is likely that expert consensus or manual expert annotation was used to label the data for training the deep learning algorithms.

Ask a specific question about this device