CARDIONET AMBULATORY ECG MONITOR WITH ARRHYTHMIA DETECTION, MODEL CN1001

• K Number: K012241
• Device Name: CARDIONET AMBULATORY ECG MONITOR WITH ARRHYTHMIA DETECTION, MODEL CN1001
• Manufacturer: CARDIONET, INC
• Date Cleared: 2002-02-01 ( 199 days)
• Product Code: DSI
• Regulation Number: 870.1025
• Type: Traditional
• Panel: CV
• Reference & Predicate Devices: K003576 , K000882 , K003707 , K982803

Intended Use

1. Patients who have demonstrated a need for cardiac monitoring and are at low risk of developing primary ventricular fibrillation or sustained ventricular tachycardia.
2. Patients with dizziness or lightheadedness
3. Patients with palpitations
4. Patients with syncope of unknown etiology
5. Patients who require monitoring for non life-threatening arrhythmias, such as atrial fibrillation, other supra-ventricular arrhythmias, evaluation of various bradvarrhythmias and intermittent bundle branch block. This includes post operative monitoring for these rhythms
6. Patients recovering from coronary artery bypass graft (CABG) surgery who require monitoring for arrhythmias
   7 . Patients requiring monitoring for arrhythmias inducing co-morbid conditions such as hyperthyroidism or chronic lung disease
7. Patients with obstructive sleep apnea to evaluate possible nocturnal arrhythmias
8. Patients requiring arrhythmia evaluation for etiology of stroke or transient cerebral ischemia, possibly secondary to atrial fibrillation
9. Data from the device may be used by another device to analyze, measure or report QT interval. The device is not intended to sound any alarms for QT changes.

Device Description

The CardioNet Arrhythmia Detector which is also referred to as the subject device, is a modification to the CardioNet Ambulatory ECG monitor cleared by FDA under 510(k) number K003707, in May 2001. The subject device includes the addition of an ECG analysis capability that allows detection of cardiac arrhythmia. As described in the previous 510(k) the subject device is comprised of three components: 1) a patient-worn Sensor, 2) a Monitor and 3) a charging Base. The Sensor acquires the ECG signal from the patient's body. It is connected to electrodes attached to the patient's skin. It is suspended in place by a neck strap. The ECG signal is conditioned, filtered, digitized and transmitted to the Monitor via Radio Frequency bi-directional communications. The Sensor utilizes a disposable AAA battery. The Monitor receives, analyzes, stores and transmits the ECG data. The Monitor has an LCD display and handles the user interaction for the system. The Monitor has an integrated cellular modem to allow communications with and without physical connection to a phone line. The Monitor has a re-chargeable battery. When an ECG threshold is exceeded or if the patient initiates a call, the ECG data is transmitted to the CardioNet Monitoring Center where trained clinical personnel review the data. The Monitor Center can also request data from the Monitor, the Monitor will transmit ECG data are requested. All ECG data for the past 24 hours is resident on the Monitor and can be transmitted to the Monitoring Center as requested by Monitoring Center Personnel. The subject device utilizes the proven Mortara ECG analysis algorithm that is currently used in the Quinton Q-tel telemetry system, 510(k) number K003576, 807.1025, Procode DSI, Class III; and the Datex-Ohmeda CS/3 telemetry system, 510(k) number K000882, 807.1025, Procode DSI, Class III. The Quinton Q-tel telemetry system and the Datex-Ohmeda telemetry system are both Class III Preamendments devices for which FDA has not yet requested PMAs. The Base provides power, RS232, and telephone communication connectivity to allow telephone transmission of ECG data when in the Monitor is charging. The Base does not include any software; it is a passive component that provides input to the Monitor.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study information for the CardioNet ECG Monitor with Arrhythmia Detection, based on the provided 510(k) summary:

Acceptance Criteria and Device Performance

The provided 510(k) summary does not present a table of specific acceptance criteria (e.g., specific sensitivity/specificity thresholds for arrhythmia detection) alongside reported device performance. Instead, it indicates that the device's ECG analysis algorithm and viewing station "meets the requirements of ANSI/AAMI EC57:1998 'Testing and reporting performance results of cardiac rhythm and ST segment algorithms'".

Therefore, the acceptance criteria are implicitly defined by the standards referenced:

• ANSI/AAMI EC38:1998 'Ambulatory electrocardiographs': General requirements for ambulatory ECG monitors.
• ANSI/AAMI EC57:1998 "Testing and reporting performance results of cardiac rhythm and ST segment algorithms": Specifically for the performance of arrhythmia detection algorithms.

The summary does not include a table with reported device performance metrics (e.g., sensitivity, specificity, accuracy for various arrhythmias) against specific numerical acceptance criteria. It states that the device "meets or exceeds" these standards, implying compliance without providing raw performance numbers in this document.

The summary highlights that the device "utilizes the proven Mortara ECG analysis algorithm that is currently used in the Quinton Q-tel telemetry system... and the Datex-Ohmeda CS/3 telemetry system," both of which are Class III Preamendment devices. This suggests leveraging performance validated in previously cleared devices.

Study Information

Due to the nature of the 510(k) submission, specific detailed study information (like sample sizes, ground truth establishment for a new clinical study) related to the algorithmic performance is not explicitly provided in the summary. The summary refers to existing standards and leveraging a "proven" algorithm.

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

   • Test Set Sample Size: Not explicitly stated for a new, dedicated test. The summary indicates compliance with ANSI/AAMI EC57:1998, which would dictate testing methodologies and minimum data requirements for reporting performance. However, these details are not extracted here.
   • Data Provenance: Not explicitly stated. The algorithm is noted as "proven" from other existing devices (Quinton Q-tel telemetry system, Datex-Ohmeda CS/3 telemetry system), suggesting its performance was likely established on retrospective datasets during its original development and validation, or potentially during its application in those predicate devices.

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

   • Number of Experts & Qualifications: Not explicitly stated. For compliance with ANSI/AAMI EC57:1998, expert review (typically by cardiologists or electrophysiologists) would be standard practice for establishing ground truth on ECG databases. However, the details for this specific submission are not provided.

3. Adjudication method for the test set:

   • Adjudication Method: Not explicitly stated. If multiple experts were used, standard adjudication methods (e.g., 2+1, 3+1, majority vote, or expert consensus with discussion) would typically be employed.

4. 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:

   • MRMC Study: No MRMC comparative effectiveness study is mentioned in the provided 510(k) summary. The device focuses on standalone arrhythmia detection and subsequent review by "trained clinical personnel" at a monitoring center. It acts as an aid to detection and data transmission for human review, rather than a system directly augmenting a human reader's initial diagnostic accuracy on a given case.

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

   • Standalone Performance: Yes, the core of the submission focuses on the standalone performance of the "ECG analysis algorithm" in detecting cardiac arrhythmias. The summary states that "The ECG analysis algorithm... meets the requirements of ANSI/AAMI EC57:1998 'Testing and reporting performance results of cardiac rhythm and ST segment algorithms'." This standard specifically addresses the performance of algorithms. The device then transmits this data for review by clinical personnel, implying a human-in-the-loop for final interpretation, but the algorithm's detection capabilities are evaluated standalone.

6. The type of ground truth used:

   • Ground Truth Type: Not explicitly stated, but for arrhythmia detection algorithms reviewed under standards like ANSI/AAMI EC57, the ground truth is typically established by expert consensus (e.g., cardiologists, electrophysiologists) reviewing the ECG waveforms and annotations, often against well-curated public or private ECG databases. Pathology or outcomes data are generally not the direct ground truth for arrhythmia detection on an ECG.

7. The sample size for the training set:

   • Training Set Sample Size: Not specified. The algorithm is described as "proven" and used in other existing devices. Details about its original training are not part of this 510(k) summary.

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

   • Training Set Ground Truth: Not specified. For a "proven" algorithm, its ground truth for training would have been established during its initial development and validation, likely through expert consensus annotation of large ECG datasets.

Regulation Number and Section

§ 870.1025 Arrhythmia detector and alarm (including ST-segment measurement and alarm).

(a)
Identification. The arrhythmia detector and alarm device monitors an electrocardiogram and is designed to produce a visible or audible signal or alarm when atrial or ventricular arrhythmia, such as premature contraction or ventricular fibrillation, occurs.(b)
Classification. Class II (special controls). The guidance document entitled “Class II Special Controls Guidance Document: Arrhythmia Detector and Alarm” will serve as the special control. See § 870.1 for the availability of this guidance document.