Search Results

The physlQ Heart Rhythm Module is intended for use by a physician or other qualified medical professionals for the calculation of heart rate and heart rate variability and the detection of atrial fibrillation using ambulatory ECG data. The physlQ Heart Rhythm Module supports receiving and analyzing single-lead ECG signals recorded in a compatible format from FDA-cleared ECG biosensor devices using "wet" electrode technology when assessment of rhythm is desired. The phys\Q Heart Rhythm Module is for use in subacute clinical settings for remote patient monitoring. The physlQ Heart Rhythm Module is not for use in patients requiring or life-sustaining systems or ECG Alam devices.

The physIQ Heart Rhythm Module (Version 1.0) is a computerized all-software callable function library in the Python programming language that is designed for calculating heart rate and heart rate variability and for detecting atrial fibrillation determined by automated analysis of any single electrocardiogram (ECG) channel collected by commercially-available ECG biosensor devices. This Heart Rhythm Module will be integrated by the customer organization into an end-to-end system (biosensor data collection to clinician display) that makes calls into the product, most typically via a Python middleware script. The "middleware" accesses the source ECG data from a customer's data collection system, most likely via its own application programming interface (API), and makes calls to the physIQ Heart Rhythm Module to input ECG for processing into the vital sign outputs of the product. These outputs are returned to the middleware, which may insert these results into a downstream monitoring system for clinical use.

Here's an analysis of the acceptance criteria and supporting studies for the physIQ Heart Rhythm Module (Version 1.0), based on the provided FDA 510(k) document:

phyIQ Heart Rhythm Module (Version 1.0) Acceptance Criteria and Performance

1. Table of Acceptance Criteria and Reported Device Performance

The provided document states that "Performance testing following guidelines of ANS/AAMI EC572012: Testing and Reporting Performance Results of Cardiac Rhythm and ST segment Measurement Algorithms has been applied to each of the algorithms. The performance testing results for all algorithms were compared to physIQ's defined acceptance criteria for performance testing. All algorithms met their corresponding acceptance criteria."

However, the specific quantitative acceptance criteria (e.g., sensitivity, specificity, accuracy thresholds) for each algorithm (Heartbeat Detector, Heart Rate, Heart Rate Variability, and Atrial Fibrillation Detector) are not explicitly detailed in the provided text. Similarly, the exact reported performance metrics (e.g., the achieved sensitivity/specificity values) are also not provided in a summarized table within this document. The document only confirms that "All algorithms met acceptance criteria."

Therefore, an exact table with numerical acceptance criteria and reported performance cannot be generated from the given text.

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

The document states:
"further supportive clinical validation testing of the physIQ Heart Rhythm Module was performed using electrocardiography (ECG) signals captured from ambulatory patients using a wearable single-lead biosensor device which were annotated by medical experts in cardiology."

• Sample Size for Test Set: Not explicitly stated. The document only refers to "ambulatory patients" without specifying the number of patients or the duration/amount of ECG data.
• Data Provenance: The ECG signals were "captured from ambulatory patients" using two commercially available FDA-cleared patches: HealthPatch (K152139) manufactured by VitalConnect Inc. and BodyGuardian (K121197; K151188) manufactured by Preventice Inc. The country of origin of the data is not specified, but the use of FDA-cleared devices typically implies data collected in regions where such devices are marketed, often the US. The data appears to be retrospective, as it was "captured from ambulatory patients" and then annotated.

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

• Number of Experts: Not explicitly stated. The document mentions "medical experts in cardiology."
• Qualifications of Experts: They were described as "medical experts in cardiology." Specific experience level (e.g., "10 years of experience") is not provided.

4. Adjudication Method for the Test Set

• Adjudication Method: Not explicitly stated. The document only says the data was "annotated by medical experts in cardiology." It does not specify if multiple experts independently annotated and then reached consensus, or if a single expert provided the ground truth, or if a specific adjudication process (like 2+1 or 3+1) was used.

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

• MRMC Study: No, a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance was not mentioned or described in the provided text. The testing focused on the standalone performance of the algorithm against expert annotations.
• Effect Size of Human Improvement with AI Assistance: Not applicable, as no MRMC study was described.

6. Standalone (Algorithm Only Without Human-in-the-Loop) Performance

• Standalone Performance: Yes, a standalone performance evaluation was conducted. The document states: "this testing did not use any patch-generated vitals, but instead compared physIQ Heart Rhythm Module outputs to annotations by cardiology experts using ECG captured from two commercially-available patches..." This indicates the algorithm's output was directly compared to the expert-derived ground truth without human intervention in the device's output.

7. Type of Ground Truth Used

• Type of Ground Truth: Expert Consensus (or Expert Annotation). The document explicitly states the ECG signals were "annotated by medical experts in cardiology."

8. Sample Size for the Training Set

• Sample Size for Training Set: Not mentioned in the provided text. The document focuses on the performance testing and clinical validation rather than the development and training details of the algorithms.

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

• Ground Truth for Training Set: Not mentioned in the provided text. As with the training set size, the document does not delve into the methodology for establishing ground truth for any training data used for the algorithms.

Ask a specific question about this device

The Nuubo System is indicated for use on patients who may be asymptomatic or who may suffer from transient symptoms such as palpitations, shortness of breath, dizziness, light-headedness, presyncope, syncope, fatigue, or anxiety.

The Nuubo system continuously records and stores ECG and activity data for up to 30 days at a time. The Nuubo System detects arrhythmias at the end of the monitoring period upon download of the ECG data. The Nuubo System is Rx use device.

The Nuubo System, developed by Smart Solutions Technologies (SST), is a wearable device designed for ambulatory recording electrocardiogram (ECG) up to 30 days. The system is composed of 3 main components:

• Nuubo30 – The Nuubo30 wearable is a single patient textile like a chest-belt that contains 4 textile electrodes in the inner side that are used for sensing patient 's ECG.
• NuuboREC - The Nuubo recorder is a small, lightweight device that records ECG continuously. The device records 2 Leads of ECG data up to 30 days. The device also records data from a 3-axis accelerometer located inside the device.
• Nuubo Leonardo - The Leonardo Software is installed on a computer where the patient´s ECG data stored in the recorder will be downloaded for subsequent analysis and report.

This document is a 510(k) summary for the Nuubo System, submitted to the FDA. It details the device's indications for use, technological characteristics, and performance data to demonstrate substantial equivalence to a predicate device.

Here's an analysis based on the provided information:

1. Table of Acceptance Criteria and Reported Device Performance

The document explicitly states that "The results obtained validate the Nuubo Arrhythmia Algorithms and prove equivalence to Monebo Automated ECG Analysis And Interpretation Software Library, version 3.0 [manufacturer Monebo Technologies, 510(k) number K062282]." It further mentions that "All results are comparable to the results claimed by Monebo."

While specific numerical acceptance criteria (e.g., minimum sensitivity/specificity for each arrhythmia) and the Nuubo System's reported performance for each criterion are not directly listed in the provided text, the document indicates that the device's arrhythmia detection performance was validated and found comparable to the Monebo device, which was referenced by the predicate ZioPatch. The table below lists the arrhythmia functionalities and their detection criteria, implying these are the targets for the algorithm:

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

The arrhythmia detection algorithms were tested using:

• Public Databases: MIT-BIH, AHA, and MITAF. These are well-known, established retrospective ECG databases. The country of origin for these databases is primarily the United States.
• Private Database: Comprised of 90 ECG registries from 58 patients. The provenance (country of origin) is not explicitly stated, but the context of the submission to the FDA suggests it aligns with U.S. medical practice. This data is described as "anonymized," potentially retrospective, selected to contain all arrhythmias detected by the algorithm.

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

For the private database (90 ECG registries from 58 patients), the ground truth was established by "experienced medical professionals." The specific number of experts is not provided, nor are their detailed qualifications (e.g., specific sub-specialty or years of experience). For the public databases (MIT-BIH, AHA, MITAF), ground truth is typically established by consensus of multiple cardiologists or electrophysiologists based on established annotation guidelines, though the document doesn't detail this for these specific databases.

4. Adjudication Method for the Test Set

The document states that the private database "was annotated using experienced medical professionals, using prospectively defined guidelines, consistent with US medical practice." This suggests an expert review process. However, the exact adjudication method (e.g., 2+1, 3+1, or simple consensus from a single annotator if a single expert annotated) is not specified. For the public databases, adjudication methods are usually defined by the database creators, often involving multiple experts to establish consensus.

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 MRMC comparative effectiveness study involving human readers' improvement with AI vs. without AI assistance is reported in this document. The study focuses on the standalone performance of the algorithm.

6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was Done

Yes, a standalone performance study of the algorithm was done. The document states: "The Nuubo Arrhythmia detection algorithm was tested per requirements of AAMI/IEC60601-2-47. To validate the arrhythmia detection algorithms were used three public databases and one private database." The results of this testing were compared to the performance claimed by the Monebo Automated ECG Analysis And Interpretation Software Library (K062282), indicating a standalone comparison. The caveat is that "The Nuubo Arrhythmia Detection Algorithm is not intended to replace the Clinician review of signals. The software menu prompts the Clinician or trained technician to review events prior to generating a report," which implies that the intended use is with a human-in-the-loop for final review, even if standalone performance was tested.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

The type of ground truth used for the private database was expert annotation/consensus based on "experienced medical professionals, using prospectively defined guidelines." For the public databases (MIT-BIH, AHA, MITAF), the ground truth is also based on expert annotation (often expert consensus).

8. The Sample Size for the Training Set

The document does not explicitly state the sample size used for the training set for the Nuubo arrhythmia detection algorithm. It only mentions the databases used for validation/testing.

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

Since the training set size and specific databases are not mentioned, how the ground truth for any training set was established is also not described in this document. The description of ground truth establishment is specifically for the test/validation data.

Ask a specific question about this device