Search Results

The CardioNet Ambulatory ECG Monitor with Arrhythmia Detection intended use is for:

• 1. Patients who have a demonstrated need for cardiac Monitoring. These may include but are not limited to patients who require Monitoring for: a) non-life threatening arrhythmias such as supraventricular tachycardias (e.g. atrial fibrillation, atrial flutter, PACs, PSVT) and ventricular ectopy; b) evaluation of bradyarrhythmias and intermittent bundle branch block, including after cardiovascular surgery and myocardial infarction; and c) arrhythmias associated with co-morbid conditions such as hyperthyroidism or chronic fung disease.
• 2. Patients with symptoms that may be due to cardiac arrhythmias. These may include but are not limited to symptoms such as: a) dizziness or lightheadedness; b) syncope of unknown etiology in which arrhythmias are suspected or need to be excluded: c) dyspnea (shortness of breath).
• 3. Patients with palpitations with or without known arrhythmias to obtain correlation of rhythm with symptoms.
• 4. Patients who require outpatient monitoring of antiarrhythmic therapy: a) Monitoring of therapeutic and potential proarrhythmic effects of membrane active drugs, b) Monitoring of effect of drugs to control ventricular rate in various atrial arrhythmias (e.g. atrial fibrillation).
• 5. Patients recovering from cardiac surgery who are indicated for outpatient arrhythmia Monitoring.
• 6. Patients with diagnosed sleep disordered breathing including sleep apnea (obstructive, central) to evaluate possible nocturnal arrhythmias
• 7. Patients requiring arrhythmia evaluation of etiology of stroke or transient cerebral ischemia, possibly secondary to atrial fibrillation or atrial flutter.
• 8. Patients requiring measurement, analysis and reporting of QT interval, excluding patients with a documented history of sustained atrial fibrillation or atrial flutter
• 9. Patients who require monitoring for potential arrhythmias based on risk factors (e.g. atrial fibrillation).
• 10. Patients requiring measurement of ST segment changes. The device is not intended to sound any alarms for ST segment changes.

The CardioNet ECG Monitor with Arrhythmia Detection CN1006 is an ambulatory ECG monitor with capability to detect cardiac arrhythmias and transmit ECG data to a CardioNet staffed monitoring center.

The subject device is comprised of three (3) main components: 1) a patient-worn Sensor, 2) a Monitor and 3) a charging Base.

A Sensor acquires the ECG signal from the patient's body and transmits the signal to PDA sized monitor where the data is stored and analyzed by an automated arrhythmia analysis algorithm residing in the Monitor. When events are detected by the analysis algorithm or when indicated by the patient pressing the event key on the Monitor, the Monitor will transmit the data to the Monitoring Center. Data can be uploaded to the Monitoring Center in a variety of ways -Transmitted via Cellular RF modem or via RF to the Base for transmission via the patient's landline telephone. The data is received and reviewed by trained technicians using the Monitoring Services Application.

This document describes the CardioNet Ambulatory ECG Monitor with Arrhythmia Detection, Model CN1006.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for the CardioNet ECG Monitor with Arrhythmia Detection are based on various performance standards. The document states that the "subject device meets the requirements of the following performance standards in accordance with Class II Special Controls Guidance document: Arrhythmia Detector and Alarm." No specific numerical acceptance criteria or detailed device performance metrics are provided in the document beyond this general statement.

The performance standards met are:

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

The document does not expressly state the sample size used for the test set or the data provenance (e.g., country of origin, retrospective/prospective). It only refers to complying with the listed performance standards, which would imply that the device was tested against relevant data as prescribed by those standards.

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

The document does not specify the number of experts used or their qualifications for establishing ground truth for the test set. Given the reference to AAMI/ANSI EC 57, which often involves expert review of arrhythmias, it is likely that experts were involved, but details are not provided.

4. Adjudication Method for the Test Set

The adjudication method for the test set is not mentioned in the provided text.

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

The document does not indicate that an MRMC comparative effectiveness study was performed, nor does it discuss the effect size of human readers with vs. without AI assistance. The device is an "Ambulatory ECG Monitor with Arrhythmia Detection," implying an automated detection system primarily, rather than an AI-assisted human reading system.

6. Standalone (Algorithm Only) Performance Study

The information provided suggests that a standalone performance study of the algorithm was conducted, as the device is described as having an "automated arrhythmia analysis algorithm residing in the Monitor" and the "subject device meets the requirements of the following performance standards in accordance with Class II Special Controls Guidance document: Arrhythmia Detector and Alarm." Compliance with standards like AAMI/ANSI EC 57 typically involves evaluating the performance of the algorithm itself. However, explicit details of a standalone study (e.g., specific metrics and experimental setup) are not provided beyond the statement of compliance with standards.

7. Type of Ground Truth Used

The document implies that the ground truth for evaluating arrhythmia detection would be established according to the methodologies defined by the AAMI/ANSI EC 57 standard, which often involves expert consensus on annotated ECG recordings. For other aspects, like biocompatibility (ISO 10993-1), the ground truth would relate to biological responses. No specific details are given, but compliance with these standards points to established scientific methods for ground truth creation.

8. Sample Size for the Training Set

The document does not provide information about the sample size used for the training set of the arrhythmia detection algorithm.

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

The document does not detail how the ground truth for the training set was established.

Ask a specific question about this device

The CardioNet Ambulatory ECG Monitor with Arrhythmia Detection intended use is for:

• Patients who have a demonstrated need for cardiac monitoring. These may include but are not limited to patients who require monitoring for: a) non-life threatening arrhythmias such as supraventricular tachycardias (e.g. atrial fibrillation, atrial flutter, PACs, PSVT) and ventricular ectopy; b) evaluation of bradyarrhythmias and intermittent bundle branch block, including after cardiovascular surgery and myocardial infarction; and c) arrhythmias associated with co-morbid conditions such as hyperthyroidism or chronic lung disease.
• Patients with symptoms that may be due to cardiac arrhythmias. These may include but are not limited to symptoms such as: a) dizziness or lightheadedness; b). syncope of unknown etiology in which arrhythmias are suspected or need to be excluded; and c) dyspnea (shortness of breath).
• Patients with palpitations with or without known arrhythmias to obtain correlation of rhythm with symptoms.
• Patients who require monitoring of effect of drugs to control ventricular rate in various atrial arrhythmias (e.g. atrial fibrillation).
• Patients recovering from cardiac surgery who are indicated for outpatient arrhythmia monitoring.
• Patients with diagnosed sleep disordered breathing including sleep apnea (obstructive, central) to evaluate possible nocturnal arrhythmias
• Patients requiring arrhythmia evaluation of etiology of stroke or transient cerebral ischemia, possibly secondary to atrial fibrillation or atrial flutter
• 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 interval changes

The CardioNet ECG Monitor with Arrhythmia Detection Model CN1005 is an ambulatory ECG monitor with capability to detect cardiac arrhythmias and transmit ECG data to a CardioNet staffed monitoring center.

The subject device is comprised of three (3) main components: 1) a patient-worn Sensor, 2) a Monitor and 3) a charging Base.

A Sensor acquires the ECG signal from the patient's body and transmits the signal to PDA sized monitor where the data is stored and analyzed by an automated arrhythmia analysis algorithm residing in the Monitor. When events are detected by the analysis algorithm or when indicated by the patient pressing the event key on the Monitor, the Monitor will transmit the data to the Monitoring Center. Data can be uploaded to the Monitoring Center in a variety of ways - Transmitted via Cellular RF modem or via RF to the Base for transmission via the patient's landline telephone.

The data is received and reviewed by trained technicians using the Monitoring Services Application.

The provided document is a 510(k) premarket notification for the CardioNet Ambulatory ECG Monitor with Arrhythmia Detection, Model CN1005. It describes the device, its indications for use, and a comparison to predicate devices, but it does not contain the detailed acceptance criteria or the specific study results proving the device meets those criteria.

The "Summary of Performance Testing" section broadly states that the device meets the requirements of certain performance standards (ANSI/AAMI EC 38:1998, ANSI/AAMI EC 57:1998, and IEC 60601-1), but it does not provide the specific metrics or the actual performance data from any particular study.

Therefore, I cannot fulfill your request for:

• A table of acceptance criteria and the reported device performance: This information is not present in the document.
• Sample size used for the test set and the data provenance: Not specified.
• Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not specified.
• Adjudication method for the test set: Not specified.
• If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and the effect size of how much human readers improve with AI vs without AI assistance: Not specified. This device is an arrhythmia detection algorithm, not explicitly marketed as AI assistance for human readers in the context of an MRMC study described.
• If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The document states data is analyzed by an automated algorithm and then reviewed by trained technicians, implying human-in-the-loop, but specific standalone performance data is not provided.
• The type of ground truth used: Not specified.
• The sample size for the training set: Not specified.
• How the ground truth for the training set was established: Not specified.

The closest information related to performance is the mention of adherence to standards like ANSI/AAMI EC 57:1998, which outlines methods for "Testing and Reporting Performance Results of Cardiac Rhythm and ST Segment Measurement Algorithms." To find the specifics of the acceptance criteria and study results, one would need to refer to the full 510(k) submission, which is not provided in this document.

Ask a specific question about this device

The CardioNet Ambulatory ECG Monitor with Arrhythmia Detection intended use is for:

1. Patients who have a demonstrated need for cardiac monitoring. These may include but are not limited to patients who require monitoring for: a) non-life threatening arrhythmias such as supraventricular tachycardias (e.g. atrial fibrillation, atrial flutter, PACs, PSVT) and ventricular ectopy; b) evaluation of bradyarrhythmias and intermittent bundle branch block, including after cardiovascular surgery and myocardial infarction; and c) arrhythmias associated with co-morbid conditions such as hyperthyroidism or chronic lung disease
2. Patients with symptoms that may be due to cardiac arrhythmias. These may include but are not limited to symptoms such as: a) dizziness or lightheadedness; b) syncope of unknown etiology in which arrhythmias are suspected or need to be excluded; and c) dyspnea (shortness of breath).
3. Patients with palpitations with or without known arrhythmias to obtain correlation of rhythm with symptoms.
4. Patients who require monitoring of effect of drugs to control ventricular rate in various atrial arrhythmias (e.g. atrial fibrillation).
5. Patients recovering from cardiac surgery who are indicated for outpatient arrhythmia monitoring.
6. Patients with diagnosed sleep disordered breathing including sleep apnea (obstructive, central) to evaluate possible nocturnal arrhythmias
7. Patients requiring arrhythmia evaluation of etiology of stroke or transient cerebral ischemia, possibly secondary to atrial fibrillation or atrial flutter
8. 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 interval changes

The CardioNet ECG Monitor with Arrhythmia Detection Model CN1004 is an ambulatory ECG monitor with capability to detect cardiac arrhythmias and transmit ECG data to a CardioNet staffed monitoring center.
The subject device is comprised of three (3) main components: 1) a patient-worn Sensor, 2) a Monitor (communications Gateway) and 3) a charning Base.
A Sensor acquires two (2) channels of ECG data from the patient's body. This ECG in the Sames Will in the Sensor. When events are detected by the analysis algorithm or when indicated by the patient pressing the event key on the Monitor, the Sensor will upload the data to the Monitor. The ECG data is then uploaded to the Monitoring Center. Data can be uploaded to the Monitoring Center in a variety of ways - Transmitted via Cellular RF modem or via RF to the Base for transmission via the patient's landline telephone.
The data is received and reviewed by trained technicians using the Monitoring Services Application.

The provided text describes the CardioNet Ambulatory ECG Monitor with Arrhythmia Detection, Model CN1004. Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the given information:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not provide details on the specific sample size, country of origin, or whether the data was retrospective or prospective for any "test set" demonstrating the device's arrhythmia detection performance. Instead, it refers to compliance with industry standards.

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

This information is not provided in the document. The substantial equivalence claim is based on compliance with standards, not on a specific clinical performance study against expert-derived ground truth.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

This information is not provided in the document.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done

No, a multi-reader multi-case (MRMC) comparative effectiveness study is not mentioned. The document focuses on the device's technical specifications and compliance with performance standards, rather than comparing human reader performance with and without AI assistance.

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

The document states that the proprietary algorithm "resides in the Sensor and detection of events is performed in the Sensor" and that it analyzes the ECG real time. This implies that the algorithm (the "Arrhythmia Detector") operates in a standalone fashion to detect events before trained technicians review the data in the Monitoring Services Application. However, no specific standalone performance metrics (e.g., sensitivity, specificity) for this algorithm are provided in the summarized information, only that it "meets the requirements of" relevant standards.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

The document references compliance with "ANSI/AAMI EC 57: 1998 - Testing and Reporting Performance Results of Cardiac Rhythm and ST Segment Measurement Algorithms." This standard typically outlines methodologies for evaluating such algorithms, often involving reference databases with expert-annotated ground truth for various arrhythmias. However, the document does not explicitly state the specific ground truth types used for the testing of this particular device.

8. The sample size for the training set

The document does not provide information regarding the sample size of any training set used for the device's arrhythmia detection algorithm.

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

The document does not provide information on how the ground truth for any training set was established.

Ask a specific question about this device

The CardioNet Ambulatory ECG Monitor with Arrhythmia Detection intended use is for:

1. Patients who have a demonstrated need for cardiac monitoring. These may include but are not limited to patients who require monitoring for: a) non-life threatening arrhythmias such as supraventricular tachycardias (e.g. atrial fibrillation, atrial flutter, PACs, PSVT) and ventricular ectopy; b) evaluation of bradyarrhythmias and intermittent bundle branch block, including after cardiovascular surgery and myocardial infarction; and c) arrhythmias associated with co-morbid conditions such as hyperthyroidism or chronic lung disease
2. Patients with symptoms that may be due to cardiac arrhythmias. These may include but are not limited to symptoms such as: a) dizziness or lightheadedness; b) syncope of unknown etiology in which arrhythmias are suspected or need to be excluded; and c) dyspnea (shortness of breath).
3. Patients with palpitations with or without known arrhythmias to obtain correlation of rhythm with symptoms.
4. Patients who require outpatient monitoring of antiarrhythmic therapy: a) monitoring of therapeutic and potential proarrhythmic effects (e.g. QT prolongation) of membrane active drugs b) monitoring of effect of drugs to control ventricular rate in various atrial arrhythmias (e.g. atrial fibrillation).
5. Patients recovering from cardiac surgery who are indicated for outpatient arrhythmia monitoring.
6. Patients with diagnosed sleep disordered breathing including sleep apnea (obstructive, central) to evaluate possible nocturnal arrhythmias
7. Patients requiring arrhythmia evaluation of etiology of stroke or transient cerebral ischemia, possibly secondary to atrial fibrillation or atrial flutter
8. Patients requiring measurement, analysis and reporting of the QT interval, excluding patients with a documented history of sustained atrial fibrillation or atrial flutter.

The CardioNet ECG Monitor with Arrhythmia Detection is an ambulatory ECG monitor with capability to detect cardiac arrhythmias and transmit ECG data to a CardioNet staffed monitoring center.

The subject device is comprised of three (3) main components: 1) a patient-worn Sensor, 2) a Monitor and 3) a charging Base.

A Sensor acquires the ECG signal from the patient's body and transmits the signal to PDA sized monitor where the data is stored and analyzed by an automated arrhythmia analysis algorithm. When an arrhythmic event is detected the monitor can transmit the ECG data to the monitoring center utilizing a cellular modem or telephone data line. The patient can also initiate the recording and transmission of ECG data if symptoms are felt. The data is received and reviewed by trained technicians using the Monitoring Services Application.

Here's an analysis of the CardioNet Arrhythmia Detector based on the provided text, focusing on acceptance criteria and study details:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative "acceptance criteria" in a typical numerical format (e.g., sensitivity of X%, specificity of Y%). Instead, it refers to performance standards and comparison to human-annotated data, particularly for QT detection.

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

• Sample Size: Not explicitly stated for either the overall arrhythmia detection or the QT detection algorithm. The text only mentions "human annotated ECG data" for QT, without specifying the number of ECGs or patients.
• Data Provenance: Not specified. It's unclear if the data was retrospective or prospective, or the country of origin.

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

• Number of Experts: Not specified. The data for QT detection was "human annotated," implying at least one expert, but the exact number isn't provided.
• Qualifications of Experts: Not specified. The term "human annotated" is broad and does not detail the expertise (e.g., cardiologists, certified ECG technicians, years of experience) of those who provided the annotations.

4. Adjudication Method for the Test Set

• Not specified. There is no mention of how disagreements among multiple annotators (if any were used) were resolved.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done, and the effect size of how much human readers improve with AI vs without AI assistance

• No. The provided text does not describe an MRMC comparative effectiveness study where human readers' performance with and without AI assistance was evaluated. The performance assessment mentioned for QT detection was a standalone comparison of the algorithm and a predicate device against human-annotated ground truth.

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

• Yes, for the QT detection algorithm. The text states: "The performance of the QT detection algorithm was assessed by comparing the performance of both the subject and predicate devices against human annotated ECG data." This indicates an algorithm-only evaluation against established ground truth.
• For the general arrhythmia detection, the device is described as having an "automated arrhythmia analysis algorithm" which performs analysis on the monitor. While it transmits data to a monitoring center for review by "trained technicians," the initial analysis is algorithmic. The performance testing against standards (EC 38, EC 57) implies standalone algorithm performance evaluation.

7. The Type of Ground Truth Used

• For the QT detection algorithm: Expert Consensus/Human Annotation. The text explicitly states "human annotated ECG data."
• For general arrhythmia detection: Implied to be derived from expert-reviewed "gold standard" datasets that conform to standards like ANSI/AAMI EC 57, which outlines methods for testing and reporting performance results of cardiac rhythm algorithms. However, the specific method for establishing ground truth for the entire arrhythmia detection suite isn't detailed beyond conforming to these standards.

8. The Sample Size for the Training Set

• Not specified. The document focuses on performance testing (validation) and does not provide details about the training data used to develop the algorithms.

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

• Not specified. As with the training set size, the method for establishing its ground truth is not mentioned in the provided summary.

Ask a specific question about this device

The CardioNet Ambulatory ECG Monitor with Arrhythmia Detection intended use is for:

• Patients who have a demonstrated need for cardiac monitoring. These may include but are not limited to patients who require monitoring for: a) non-life threatening arrhythmias such as supraventricular tachycardias (e.g. atrial fibrillation, atrial flutter, PACs, PSVT) and ventricular ectopy; b) evaluation of bradyarrhythmias and intermittent bundle branch block, including after cardiovascular surgery and myocardial infarction; and c) arrhythmias associated with co-morbid conditions such as hyperthyroidism or chronic lung disease
• Patients with symptoms that may be due to cardiac arrhythmias. These may include but are not limited to symptoms such as: a) dizziness or lightheadedness; b) syncope of unknown etiology in which arrhythmias are suspected or need to be excluded; and c) dyspnea (shortness of breath).
• Patients with palpitations with or without known arrhythmias to obtain correlation of rhythm with symptoms.
• Patients who require monitoring of effect of drugs to control ventricular rate in various atrial arrhythmias (e.g. atrial fibrillation).
• Patients recovering from cardiac surgery who are indicated for outpatient arrhythmia monitoring.
• Patients with diagnosed sleep disordered breathing including sleep apnea (obstructive, central) to evaluate possible nocturnal arrhythmias
• Patients requiring arrhythmia evaluation of etiology of stroke or transient cerebral ischemia, possibly secondary to atrial fibrillation or atrial flutter
• 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 interval changes

The CardioNet ECG Monitor with Arrhythmia Detection is an ambulatory ECG monitor with capability to detect cardiac arrhythmias and transmit ECG data to a CardioNet staffed monitoring center.

The subject device is comprised of three (3) main components: 1) a patient-worn Sensor, 2) a Monitor and 3) a charging Base.

A Sensor acquires the ECG signal from the patient's body and transmits the signal to PDA sized monitor where the data is stored and analyzed by an automated arrhythmia analysis algorithm. When an arrhythmic event is defected the monitor can transmit the ECG data to the monitoring center utilizing a cellular modem or telephone data line. The patient can also initiate the recording and transmission of ECG data if symptoms are felt. The data is received and reviewed by trained technicians using the Monitoring Services Application.

Here's a breakdown of the acceptance criteria and study information for the CardioNet Ambulatory ECG Monitor with Arrhythmia Detection, Model 1002, based on the provided documents:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not explicitly present a table of quantitative acceptance criteria and corresponding reported device performance metrics in the format requested. However, it states that "Performance testing was performed in accordance with FDA Class II Special Controls Guidance Document: Arrhythmia Detector and Alarm" and that "The CardioNet Ambulatory ECG Monitor meets or intends to conform to the applicable standards suggested in the guidance document including:

• ANSI/AAMI EC 38: 1998 Ambulatory Electrocardiographs
• ANSI/AAMI EC 57: 1998 Testing and Reporting Performance Results of Cardiac Rhythm and ST Segment Measurement Algorithms
• International Electrotechnical Commission (IEC) 60601-1 Medical Electrical Equipment - Part 1: General Requirements for Safety"

Therefore, the acceptance criteria would be the specific quantitative and qualitative performance requirements outlined in these standards and the FDA guidance document for arrhythmia detectors. Without access to the full submission or these detailed standards, a precise table cannot be generated.

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

The document does not explicitly state the sample size used for the test set or the data provenance (e.g., country of origin, retrospective/prospective). It only mentions "Performance testing was performed..."

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

The document does not specify the number of experts used or their qualifications for establishing ground truth for the test set.

4. Adjudication Method for the Test Set

The document does not specify any adjudication method used for the test set.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs Without AI Assistance

The document does not mention a Multi-Reader Multi-Case (MRMC) comparative effectiveness study, nor does it discuss the effect size of human readers improving with or without AI assistance. This study appears to be focused on the standalone performance of the device's arrhythmia detection algorithm.

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

Yes, a standalone study was indicated. The document states: "The CardioNet ECG Monitor with Arrhythmia Detection differs from the predicate device only with respect to the arrhythmia analysis algorithm. The predicate device included an arrhythmia analysis algorithm licensed from Mortara Instrument. The new algorithm was developed by CardioNet and includes the same functions supplied by the previous algorithm." This implies that the performance testing described was primarily to validate the new, standalone arrhythmia analysis algorithm developed by CardioNet. The device transmits data to a "CardioNet staffed monitoring center" where data is "reviewed by trained technicians," suggesting human-in-the-loop for clinical use, but the performance testing refers specifically to the algorithm's capability.

7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)

The document does not explicitly state the type of ground truth used. For arrhythmia detection, it is common to use expert-annotated ECG recordings, often involving multiple cardiologists or electrophysiologists to establish consensus.

8. The Sample Size for the Training Set

The document does not provide any information regarding the sample size used for the training set for the CardioNet-developed algorithm.

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

The document does not provide information on how the ground truth for the training set was established.

Ask a specific question about this device

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.

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.

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.

Ask a specific question about this device