Search Results

MoMe ARC® is indicated for:

1. Patients who experience transient symptoms that may suggest cardiac arrhythmia.
2. Patients who require monitoring of effect of drugs to control ventricular rate in various atrial arrhythmias (e.g. atrial fibrillation)
3. 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)
4. Patients recovering from cardiac surgery or interventional procedures who are indicated for outpatient arrhythmia monitoring.
5. ECG data recorded by the device can be analyzed by other processing systems to provide Holter style reports.

MoMe ARC® is contraindicated for:

1. MoMe ARC® is contraindicated for those patients requiring attended, in hospital monitoring for life threatening arrhythmias.
2. MoMe ARC® is not intended for use on infants weighing less than 10kg (22lbs.). Clinical judgement is necessary to determine if the MoMe ARC® is appropriate for specific pediatric patients.
3. The patch configuration of the MoMe ARC® is contraindicated for monitoring QT intervals for patients taking Class III antiarrhythmic drugs.

Note: MoMe ARC® does not provide interpretive statements. Interpretation and diagnosis is the responsibility of a physician.

The MoMe ARC® device consists of a Sensor Pod, Leads, Gateway, and Charging Cradle with accessories. The body worn Sensor Pod acquires, stores and forwards electrocardiogram (ECG) data from Leads in a Wired Lead-Set or in a Patch to the Gateway using a 2.4GHz BLE wireless link. The Gateway consists of an OTS mobile device running the MoMe ARC® Gateway Mobile App. The Gateway is a Medical Device Data System (MDDS) which stores and forwards the ECG signal data to the MoMe Software Platform (K152491) via a wireless cellular link.

The MoMe ARC® communicates with the MoMe Software Platform (K152491), a web-based remote server software with proprietary algorithms for analysis, using the MoMe Device Communications Protocol. The MoMe Software System (K152491) analyzes the data via the embedded algorithm and, when indicated, data identified by the algorithm is flagged for physician review.

Once activated and operating normally, the system requires no patient intervention to capture or analyze data. However, the MoMe ARC® has an optional patient triggered event feature that allows for manual selection and recording of patient symptoms, if and when desired.

The device is intended for use under prescription only (Rx only) for monitoring patients with suspected cardiac arrhythmias.

The MoMe ARC®:

• Is non-invasive and poses no significant safety issues;
• Uses existing electrode and patch ECG technology; and
• Is used in an adjunctive fashion, where physicians also use patient symptoms and other tests, in the diagnosis or monitoring of patients with suspected cardiac arrhythmias.

MoMe ARC® is not an emergency service. If the patient is experiencing symptoms that he/she is concerned about, the patient needs to seek immediate medical attention.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) clearance letter for the MoMe ARC® Wireless Ambulatory ECG Monitoring and Detection System:

1. Table of Acceptance Criteria and Reported Device Performance

The document explicitly states that the device's performance met "predefined acceptance criteria" for sensitivity and positive predictivity, and provided a "mean absolute error" for heart-rate accuracy. However, the precise numerical values for the acceptance criteria thresholds themselves for sensitivity and positive predictivity are not explicitly stated in the provided text. We only have the reported performance.

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

• Sample Size: 87 adult subjects.
  • Inpatient cohort: 75 subjects
  • Outpatient cohort: 12 subjects
• Data Provenance:
  • Country of origin: United States ("single U.S. clinic").
  • Retrospective or Prospective: Prospectively collected.

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

• Number of Experts: Not explicitly stated as a number of individual experts. However, the ground truth was established by "Certified Cardiac Technicians (CCTs)". This implies multiple CCTs were likely involved in adjudicating the data.
• Qualifications of Experts: Certified Cardiac Technicians (CCTs). The document doesn't provide further detail on their experience level (e.g., years of experience).

4. Adjudication Method for the Test Set

• The data from all 87 subjects were "adjudicated by Certified Cardiac Technicians (CCTs) using Holter software, with beat locations, morphologies, and arrhythmia annotations serving as the reference standard."
• This suggests a single-reader adjudication process per case by a CCT to establish the ground truth, rather than a multi-reader consensus method like 2+1 or 3+1.

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 comparative effectiveness study was not reported. The study focused on the performance of the "Software Platform's sensitivity and positive predictivity" against a CCT reference, which is a standalone performance evaluation, not a human-in-the-loop study comparing human performance with and without AI assistance.

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

• Yes, a standalone performance evaluation was done. The "Software Platform's sensitivity and positive predictivity were calculated using ANSI/AMI/IEC EC57:2012 methods" against the CCT-adjudicated reference standard. This directly assesses the algorithm's performance.

7. The Type of Ground Truth Used

• The ground truth was established through "expert consensus" in the form of "adjudication by Certified Cardiac Technicians (CCTs) using Holter software, with beat locations, morphologies, and arrhythmia annotations serving as the reference standard." This is a form of expert consensus based on established clinical procedures (Holter analysis).

8. The Sample Size for the Training Set

• The document does not specify the sample size for the training set. It only describes the clinical validation study (test set).

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

• The document does not state how the ground truth for the training set was established. It only describes the ground truth process for the independent test set used for performance validation.

Ask a specific question about this device

The Zio AT device is intended to capture and transmit symptomatic and asymptomatic cardiac events and record continuous electrocardiogram (ECG) data for long-term monitoring. It is indicated for use on patients 18 years or older who may be asymptomatic or who may suffer from transient symptoms such as palpitations, shortness of breath, dizziness, light-headedness, pre-syncope, syncope, fatigue, or anxiety. It is not intended for use on critical care patients.

The Zio AT® Electrocardiogram (ECG) Monitoring System is intended for continuous, long-term monitoring of a patient's ECG data with the ability to provide symptomatic and asymptomatic transmissions of potential arrhythmias during wear time. The Zio AT ECG Monitoring System enables ambulatory Mobile Cardiac Telemetry (MCT) services for non-critical care patients by providing the following devices for use. The Zio AT device consists of the Zio AT patch and Zio AT wireless gateway. The Zio AT patch is a single-use ECG monitor applied to the patient's chest, in-clinic or at home, and worn for up to 14 days without any required patient interaction for maintenance, such as replacing or charging a battery. The patch continuously records ECG data and transmits symptomatic and asymptomatic cardiac events through the Zio AT wireless gateway during the wear period. After the wear period concludes, the patient removes and returns the patch to the monitoring center, an Independent Diagnostic Testing Facility (IDTF), for analysis and end-of-wear reporting. The Zio AT wireless gateway securely receives ECG data from the Zio AT patch using Bluetooth technology. The gateway securely transmits ECG data through cellular technology for subsequent processing. The Zio AT device is designed to be used with the interoperable Zio ECG Utilization Service (ZEUS) SaMD which provides an arrhythmia detection algorithm for analysis and reporting.

Here's an analysis of the provided text regarding the acceptance criteria and study for the Zio AT device, organized as requested:

Device: Zio AT® device (A100A1001)

This premarket notification (K240177) is for an updated version of an already cleared device (Zio® AT ECG Monitoring Device [K240029]). Therefore, the submission primarily focuses on demonstrating substantial equivalence to the predicate device through non-clinical testing rather than presenting new clinical study data with detailed acceptance criteria and performance metrics for the device's diagnostic capabilities. The document explicitly states: "No clinical testing was performed in support of this premarket notification."

As such, many of the requested details related to clinical performance, such as detailed acceptance criteria tables, sample sizes for test sets, expert qualifications, and MRMC studies, are not available in this 510(k) summary. The acceptance criteria described here pertain to safety and engineering standards, not clinical accuracy for arrhythmia detection.

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

Since this is a 510(k) for substantial equivalence based on non-clinical testing for an updated device, the "acceptance criteria" are predominantly for engineering and safety standards, and the "reported performance" is that the device conforms to these standards.

Regarding the study that proves the device meets the acceptance criteria:

The study referenced is a comprehensive set of nonclinical performance testing. The document states: "All necessary performance testing was conducted on the Zio AT device to ensure performance as intended per specifications and to support a determination of substantial equivalence to the predicate device."

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Sample Size for Test Set: Not applicable/not provided for clinical performance. The nonclinical testing involves evaluating the physical device and its software against engineering standards. The sample size would refer to the number of devices or components tested to ensure compliance with specific technical standards (e.g., a certain number of units for electrical safety testing, material samples for biocompatibility), but specific quantities are not detailed in this summary.
• Data Provenance: Not applicable, as this is nonclinical (engineering/safety) testing.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

Not applicable, as this document focuses on nonclinical testing and substantial equivalence, not clinical diagnostic performance requiring expert interpretation as ground truth.

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

Not applicable, as this document focuses on nonclinical testing, not clinical performance where adjudication of "ground truth" labels would be necessary.

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 was done or reported in this 510(k) summary. This submission explicitly states "No clinical testing was performed in support of this premarket notification." The Zio AT device uses an arrhythmia detection algorithm (provided by the interoperable ZEUS SaMD), but the evaluation here is for the physical device's safety and engineering, not the diagnostic performance of the AI component.

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

This document does not provide details on standalone algorithm performance. The "Zio AT device is designed to be used with the interoperable Zio ECG Utilization Service (ZEUS) SaMD which provides an arrhythmia detection algorithm for analysis and reporting." While an algorithm exists, its performance is not detailed or assessed in this specific 510(k) submission as the focus is on the physical hardware's substantial equivalence to a predicate. Evaluations of the ZEUS SaMD's algorithm (which likely includes standalone performance) would have been part of previous submissions for that software.

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

For the nonclinical testing described, the "ground truth" would be the defined standards and specifications (e.g., a device passes the electrical safety test if it meets the voltage and current limits specified in IEC 60601-1). This is not clinical ground truth.

8. The sample size for the training set

Not applicable/not provided. This submission does not discuss the training of any AI algorithm, as it's a 510(k) for an updated physical device and primarily addresses nonclinical performance and substantial equivalence based on engineering and safety standards.

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

Not applicable/not provided for the same reasons as #8.

Ask a specific question about this device

MoMe® ARC is indicated for:

1. Patients who experience transient symptoms that may suggest cardiac arrhythmia.
2. Patients who require monitoring of effect of drugs to control ventricular rate in various atrial arrhythmias (e.g. atrial fibrillation)
3. 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)
4. Patients recovering from cardiac surgery or interventional procedures who are indicated for outpatient arrhythmia monitoring.
5. ECG data recorded by the device can be analyzed by other processing systems to provide Holter style reports.

MoMe® ARC is contraindicated for:

1. MoMe® ARC is contraindicated for those patients requiring attended, in hospital monitoring for life threatening arrhythmias.
   Note: MoMe® ARC does not provide interpretive statements. Interpretation and diagnosis is the responsibility of a physician.

MoMe® ARC is a wireless, remote monitoring system designed to aid physicians in their diagnosis of cardiac arrhythmias in patients with a demonstrated need for cardiac monitoring.

The MoMe® ARC device primarily consists of a Sensor, Gateway, and Charging dock with accessories. The body worn Sensor acquires, stores, and forwards ECG data to the Gateway using a 2.4GHz BLE wireless link; and the Gateway stores and forwards ECG signal data to the MoMe® Software Platform (K152491) over a 4G LTE cellular link.

The Sensor and Gateway incorporate non-removable, rechargeable batteries, with the Gateway battery being wirelessly charged by the charging dock and the sensor battery being wirelessly charged by Gateway. The user interface is composed of a mechanical button, display with touch screen, vibrator, and a speaker on the Gateway and a vibrator and LED on the Sensor.

The MoMe® ARC communicates with the MoMe® Software System (K152491), a web-based remote server software with proprietary algorithms for analysis, using the MoMe® Device Communications Protocol. The MoMe® Software System analyzes the data via the embedded algorithm and when indicated, data identified by the algorithm is flagged for physician review.

Once activated and operating normally the system requires no patient intervention to capture or analyze data. However, the MoMe® ARC has a patient triggered Event feature that allows for selection and recording of their symptoms if desired.

The device is intended for use under prescription only for monitoring patients with suspected cardiac arrhythmias.

MoMe® ARC:

• Is non-invasive and poses no significant safety issues
• . Uses existing electrode and ECG technology
• ls used in an adjunctive fashion, where physicians also use patient symptoms and other tests, in the diagnosis or monitoring of patients with cardiac arrhythmias.

MoMe® ARC is not an emergency service. If the patient is experiencing symptoms that he/she is concerned about, the patient needs to seek immediate medical attention.

The intended use of the MoMe® ARC is for ECG reporting and arrhythmia detection in patients with non-life threatening arrhythmias.

This document only discusses the substantial equivalence of the MoMe® ARC device to its predicate device, MoMe® Kardia (K160064), based on non-clinical performance testing. It explicitly states that "No clinical tests were required to demonstrate substantial equivalence." Therefore, the document does not contain information about acceptance criteria for device performance based on clinical outcomes or a study proving the device meets such criteria through human-in-the-loop or standalone algorithm performance metrics.

However, it does address the performance testing against non-clinical standards and the equivalence of its features to the predicate device. I can extract information related to the device's technical specifications and the testing conducted to ensure it meets general safety and performance standards for ECG monitoring devices.

Here's what can be extracted based on the provided text, focusing on the available performance and testing information where applicable, and explicitly stating what information is not present regarding clinical performance:

The MoMe® ARC Wireless Ambulatory ECG Monitoring and Detection System's acceptance criteria and proven performance, as described in this 510(k) summary, are primarily focused on non-clinical performance testing and substantial equivalence to a predicate device, rather than a clinical study demonstrating specific performance metrics for arrhythmia detection by the device's algorithm or human readers.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not provide a table with specific, quantifiable acceptance criteria for arrhythmia detection performance (e.g., sensitivity, specificity, accuracy for various arrhythmias) and reported device performance from a clinical study. Instead, the performance testing described is against general medical device and ECG standards.

Note: The document explicitly states, "No clinical tests were required to demonstrate substantial equivalence." Therefore, there is no information on clinical performance metrics like sensitivity, specificity, or accuracy for arrhythmia detection in patients using the AI algorithm.

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

As no clinical efficacy study or specific test set for AI algorithm performance against clinical ground truth was conducted or reported for this 510(k), there is no information on sample size or data provenance (e.g., country of origin, retrospective/prospective) related to an AI performance test set. The non-clinical tests were conducted in a lab or testing facility setting.

3. Number of Experts Used to Establish Ground Truth and Qualifications

Since no clinical study evaluating the performance of the device's arrhythmia detection algorithm was conducted, there is no mention of experts being used to establish a ground truth for a clinical test set.

4. Adjudication Method for the Test Set

Given the lack of a clinical test set for algorithmic performance, no adjudication method (e.g., 2+1, 3+1) is described.

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

No MRMC comparative effectiveness study was done or reported. The submission explicitly states, "No clinical tests were required to demonstrate substantial equivalence." Therefore, there is no information on how much human readers improve with AI vs. without AI assistance. The device is intended to flag data for physician review, implying a human-in-the-loop process, but no study on the impact of this assistance is provided.

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

No standalone algorithmic performance study was done or reported in this document. The focus of the submission is on substantial equivalence based on non-clinical performance and the device's technical specifications.

7. Type of Ground Truth Used

For the technical performance of the device and its compliance with standards, the ground truth would be the defined parameters and specifications within the voluntary FDA recognized standards (e.g., IEC 60601-2-47 for ambulatory ECG systems). For the "Arrhythmia Detection Algorithm," it is noted as "Proprietary/Server Side" and "Identical" to the predicate, implying it relies on previously established and validated algorithms, but no details on their independent validation or the ground truth used for that validation are provided in this specific document.

8. Sample Size for the Training Set

The document does not provide information on the sample size used for training the proprietary arrhythmia detection algorithm. This information is typically proprietary to the device manufacturer and not directly required for a 510(k) submission focused on substantial equivalence to a predicate, especially when no new clinical performance claims are being made for the algorithm's accuracy.

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

The document does not provide information on how the ground truth was established for the training set of the proprietary arrhythmia detection algorithm. Similar to the sample size, this is typically part of the internal development and validation of the algorithm, rather than a requirement for this type of FDA submission.

Ask a specific question about this device

The SmartCardia 7L Platform is a prescribed device used for the purpose of identifying non-lethal arrhythmias. The SmartCardia 7L Platform is intended for:

1. Patients who experience transient symptoms that may suggest cardiac arrhythmia.
2. Patients who require monitoring of effect of drugs to control ventricular rate in various atrial arrhythmias (e.g., atrial fibrillation).
3. 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).
4. Patients recovering from cardiac surgery or interventional procedures who are indicated for outpatient arrhythmia monitoring.
5. ECG data recorded by the device can be analyzed by other processing systems to provide Holter style reports. Measurements include: electrocardiogram (ECG signal), R-R interval, Heart Rate. Notification alerts can be set for one or more of these measures.
   The SmartCardia 7L Platform is indicated for use on patients who are 18 years of age or older to provide monitoring of physiological information. It is intended for use in a physician office, outpatient facility, or in the patient's home.
   SmartCardia 7L Platform contraindications:
6. The SmartCardia 7L Platform is contraindicated for use in a critical care setting where an immediate response to life threatening conditions such as lethal arrhythmias is required.
7. The SmartCardia 7L Platform is contraindicated for use during external defibrillation.

The SmartCardia 7L Platform is a body worn Holter monitoring product that is designed with a disposable adhesive 7L Patch and reusable 7L Sensor. It is designed to be worn by the patient for up to 14 days. If longer monitoring is necessary, the 7L Patch is removed from the body, the 7L Sensor is removed from the worn 7L Patch which is discarded. The 7L Sensor is inserted into a new 7L Patch and the new assembly is placed on the patient for monitoring to continue.
The 7L Sensor/7L Patch assembly communicates to the SmartCardia Phone via Bluetooth technology and shows the patient's heart rate and ECG on its display and allows the patient to input symptoms (Mark Event) which are shown in the patient record. The SmartCardia Phone has a medical grade mains powered charger and uses its cellular technology to act as a gateway to the SmartCardia Cloud Service provided by Amazon Web Services. The SmartCardia Phone is pre-configured by SmartCardia and placed in a kiosk mode. Data stored in the SmartCardia cloud can be viewed in the SmartCardia Web Browser application by a clinician or healthcare provider. The SmartCardia 7L Platform incorporates two modes of Holter monitoring:

1. Holter Monitoring (up to 48 hours) and Extended Holter Monitoring (>48 hours and up to 14 days),
2. Event Monitoring (up to 48 hours, and >48 hours up to 14 days)
   During any of the selected modes of Holter monitoring, a clinician or healthcare provider can use the SmartCardia Web Browser and continuously monitor the patient.
   The SmartCardia 7L Platform provides alarm notifications for heart rate and atrial fibrillation. As stated in the Intended Use statement, the system is contraindicated for use in a critical care setting where an immediate response to life threatening conditions such as lethal arrhythmias is required. There are no alarm signals presented to the clinician for conditions other than heart rate and atrial fibrillation.
   The SmartCardia 7L Platform, like most Holter monitoring systems performs retrospective analysis and identifies events which it shows the clinician when they are reviewing historical data. The clinician must then review these events and determine if they are indeed valid and should be included in a physician's report. These events are things like 'Ventricular Bigeminy', 'Supraventricular Couplet', etc. A full list is included in the Clinician Instructions for Use.

This document describes the device's technical characteristics and bench testing summary but does not provide complete details on a clinical study that proves the device meets the acceptance criteria, particularly for AI/algorithm performance. The information provided is primarily focused on hardware and basic signal acquisition validation against regulatory standards.

Here's an attempt to answer your questions based on the provided text, with explicit notes where information is missing or unclear for a comprehensive AI/algorithm study:

1. Table of Acceptance Criteria and Reported Device Performance

The document mentions "Pass criteria is compliance with the claimed range and precision provided in the labeling for the SmartCardia 7L Platform" and that the device "met the pass/fail criteria established by the appropriate standards." However, it does not explicitly list specific numerical acceptance criteria or performance metrics for arrhythmia detection beyond stating that "the SmartCardia 7L Platform algorithm detection and reported results for the stated output arrhythmia were satisfactory and met industry norms."

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

The document states, "SmartCardia developed a protocol and database for evaluating the analysis algorithm" for the EC57 testing. However, it does not specify the sample size of this database (test set). It also does not mention the country of origin of the data or whether it was retrospective or prospective.

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

This information is not provided in the document. For an algorithm evaluation, expert review is crucial for establishing ground truth, but no details are given.

4. Adjudication Method for the Test Set

This information is not provided in the document.

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

The document does not indicate that a MRMC comparative effectiveness study was done. The testing described is primarily focused on the device's technical performance and algorithm's standalone detection capabilities, not the improvement in human reader performance with AI assistance.

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

Yes, a standalone performance evaluation of the algorithm was conducted. The document states: "The ECG detection algorithm was tested per ANSI/AAMI EC57 standard for testing and reporting performance results of cardiac rhythm... SmartCardia developed a protocol and database for evaluating the analysis algorithm. The results show that the SmartCardia 7L Platform algorithm detection and reported results for the stated output arrhythmia were satisfactory and met industry norms."

7. Type of Ground Truth Used

The document mentions "SmartCardia developed a protocol and database for evaluating the analysis algorithm" per the ANSI/AAMI EC57 standard. This standard provides guidelines for performance reporting of cardiac rhythm algorithms, which typically implies comparison against known, validated arrhythmia events within the ECG recordings. The source of this ground truth (e.g., expert consensus, independent adjudication, or a pre-validated dataset) is not explicitly stated, but for EC57, it's generally based on highly accurate reference annotations.

8. Sample Size for the Training Set

The document does not mention any details about a training set or its sample size. The focus of this submission is on the testing and validation of the device, not its development or algorithm training.

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

Since no training set details are provided, information on how its ground truth was established is not available in this document.

Ask a specific question about this device

The PocketECG IV is intended to be used by:

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 bradyarhythmias 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 without known arrhythmias to obtain a correlation of rhythm with symptoms.

4. Patients who require monitoring of the 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 arrial fibrillation or atrial flutter.

Data from the device may be used by another device to analyze. measure or report OT interval. The device is not intended to sound any alarms for QT interval changes.

Contraindications:

The PocketECG IV is not intended to be used by:

1. Patients who have been diagnosed with life-threatening arrhythmias and require hospitalization.

2. Patients who require inpatient monitoring using a life-saving device.

The Medicalgorithmics Unified Arrhythmia Diagnostic System PocketECG IV, type P4TR-AA-ADS is an ambulatory ECG monitor which analyzes electrographic signal, classifies all detected heart beats and recognizes rhythm abnormalities. All detection results, including annotations for every detected heart beat and the entire ECG signal are transmitted via cellular telephony network to a remote server accessible by a Monitoring Center for reviewing by trained medical staff.

Here's a breakdown of the acceptance criteria and study information for the Unified Arrhythmia Diagnostic System PocketECG IV, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The submission references compliance with the IEC 60601-2-47:2012 standard for arrhythmia detection algorithms. The text explicitly states: "Test results were considered to be in complaint with standard requirements." However, concrete numerical acceptance criteria and specific performance metrics (e.g., sensitivity, specificity, accuracy for various arrhythmia types) from this standard are not detailed in the provided document. The document implies that the device meets the standard but doesn't provide the standard's exact requirements or the device's specific results against those requirements.

Similarly, for wireless transmission, the document states: "Wireless transmission performance has been tested according to Verizon Open Development (based on CTIA) requirements for LTE data transmissions." Again, the specific numerical acceptance criteria and detailed performance results are not provided.

Therefore, I can only create a table that states the areas tested and the general conclusion of compliance, not a detailed comparison of specific numerical acceptance criteria versus reported performance.

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

• Sample Size for Test Set: Not explicitly stated. The document mentions "performance testing according to IEC 60601-2-47:2012" but doesn't provide any details about the dataset used for this testing, including the number of patients, recordings, or specific arrhythmias.
• Data Provenance: Not explicitly stated. There is no mention of the country of origin of the data or whether it was retrospective or prospective.

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

• Number of Experts: Not explicitly stated. The document does not describe how ground truth was established for the performance testing, nor does it mention the involvement or qualifications of experts for this purpose.

4. Adjudication Method for the Test Set

• Adjudication Method: Not explicitly stated. The document does not describe any adjudication method used for the test set.

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

• MRMC Study: No indication of an MRMC comparative effectiveness study being performed or reported in the provided text. The submission focuses on device performance against standards, not on human-AI collaboration or improvement metrics.

6. Standalone Performance Study (Algorithm Only)

• Standalone Performance: Yes, a standalone performance study was implicitly done for the arrhythmia detection algorithms. The text states: "Arrhythmia detection algorithms implemented in PocketECG IV have been subject for performance testing according to IEC 60601-2-47:2012 (AAMI / ANSI / IEC 60601-2-47:2012)." This refers to the algorithm's performance in detecting arrhythmias against established standards, without human intervention as part of the testing methodology described. While the overall system involves human review, the specific performance testing mentioned here would be for the automated algorithm's accuracy.

7. Type of Ground Truth Used

• Type of Ground Truth: Not explicitly stated. While performance testing against IEC 60601-2-47:2012 implies a comparison to a known, verified "true" state of cardiac rhythms, the method by which this ground truth was established (e.g., expert consensus, pathology, other validated methods) is not detailed in the document.

8. Sample Size for the Training Set

• Sample Size for Training Set: Not explicitly stated. The document makes no mention of a training set or its size, which is common for submissions primarily focused on verification and validation of a developed product rather than describing the entire development process of an AI model from scratch.

9. How Ground Truth for the Training Set Was Established

• Ground Truth for Training Set: Not explicitly stated. Since a training set isn't mentioned, the method for establishing its ground truth is also not provided.

Ask a specific question about this device

The BodyGuardian System detects and monitors cardiac arrhythmias in ambulatory patients, when prescribed by a physician or other qualified healthcare professional. Not for use with patients requiring attended, in-hospital monitoring for life threatening arrhythmias.

The Preventice BodyGuardian Remote Monitoring System is intended for use with adult and pediatric patients in clinical and non-clinical settings to collect and transmit health parameters to healthcare professionals for monitoring and evaluation. Health parameters are collected from a variety of commercially available, external plug in devices such as ECG sensors, weight scales, blood pressure meters and pulse oximeters, and parameters such as ECG, heart rate, body weight, temperature, respiration rate, blood pressure, and SpO2.

The Preventice BodyGuardian Remote Monitoring System does not provide any diagnosis.

Arrhythmia Detector and Alarm; Patient Physiological Monitor (with arrhythmia detection)

The predicate device's ECG Unit is a small, ambulatory cardiac monitor that records and transmits ECG data. The subject device's ECG Unit is also a small, ambulatory cardiac monitor that records and transmits ECG data.

Both products, the predicate and subject devices, provide a data hub function that connects to commercially available devices such as weight scales, blood pressure monitors, pulse oximeters, ECG Units and other plug-in devices.

For both devices, the predicate and subject devices, data is transmitted to an external device or server, depending model. If not a server, this device sends the data to a remote computer server that allows healthcare professionals to access and review the data.

This document is a 510(k) summary for the BodyGuardian Remote Monitoring System (K192732). It focuses on demonstrating substantial equivalence to a predicate device (BodyGuardian Remote Monitoring System, K151188) rather than providing detailed acceptance criteria and performance data from a new clinical study.

Here's an analysis based on the provided text, addressing your points where possible, and noting where information is explicitly stated as not present (e.g., clinical testing was not performed):

Key Takeaway: The submission relies on non-clinical testing and comparison to a predicate device, asserting that the technology is not new and therefore a clinical study was not necessary. This means many of your requested details about acceptance criteria directly tied to a clinical performance study are not available in this document.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not provide a table of quantitative acceptance criteria for clinical performance (e.g., sensitivity, specificity for arrhythmia detection) because no clinical study was conducted for this submission. The "acceptance criteria" discussed are implicitly related to demonstrating substantial equivalence through non-clinical means.

The non-clinical "performance testing" mentioned includes:

• EMC and electrical safety testing
• Electrical and mechanical safety testing
• System safety testing
• Software verification and validation
• Performance testing (general statement, no specific metrics provided)
• Predicate device comparison tests
• Usability Testing
• Biocompatibility for patient contact materials

The document states, "We conclude that the results of testing show the Preventice BG RMS to be substantially equivalent to the predicate device." This implies the performance observed during these non-clinical tests met the unstated internal acceptance criteria for substantial equivalence.

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

• Test Set Sample Size: Not applicable for clinical performance, as "a clinical study was not considered necessary."
• Data Provenance: Not applicable for clinical performance. The non-clinical tests would have been performed in a lab setting by the manufacturer.

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

• Not applicable as no clinical study with a test set requiring expert ground truth establishment for arrhythmia detection was performed.

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

• Not applicable for the same reason as above.

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 MRMC or comparative effectiveness study involving human readers and AI assistance was conducted or described. The device's primary function is described as detecting and monitoring, rather than assisting human readers in interpreting images or patterns.

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

• The document implies the device has an algorithmic component for "detects and monitors cardiac arrhythmias." However, no specific standalone performance metrics (e.g., sensitivity, specificity, accuracy) for this algorithm are provided, nor is a dedicated "standalone study" described in the context of clinical performance. The focus is on the device as a whole system.

7. The type of ground truth used:

• For the non-clinical "performance testing," the ground truth would typically be established based on engineering specifications, known signal inputs, and reference standards for electrical, mechanical, and software verification. For biocompatibility, it would be based on ISO standards. For usability, it would involve direct observation and user feedback against defined usability goals. No clinical ground truth (e.g., expert consensus, pathology, outcome data) for arrhythmia diagnosis is mentioned.

8. The sample size for the training set:

• Not applicable, as no mention of a training set for an AI/ML algorithm (in the context of clinical performance) is made. The device is referred to using existing technology ("This technology is not new").

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

• Not applicable for the same reason as above.

Summary of what the document does state regarding validation:

The validation for this 510(k) submission primarily relies on:

• Bench Testing: EMC, electrical/mechanical safety, system safety, software V&V, general performance testing, and predicate device comparison tests.
• Biocompatibility: Testing to ensure patient contact materials are safe.
• Quality Assurance Measures: FMEA, Design FMEAs, Performance Requirements Testing (including Final System Verification and Validation Testing), ISO 60601 Testing.
• Usability Testing: Performed, including a pediatric usability study to show "no new hazards or risk associated with pediatric use."
• Comparison to Predicate Device (BodyGuardian Remote Monitoring System, K151188): The core argument for substantial equivalence is that the new device has "the same technological characteristics" and "the same intended uses" as the predicate device. "There are no fundamental differences between their technological characteristics."
• Waiver of Clinical Testing: Explicitly states, "This technology is not new, therefore a clinical study was not considered necessary prior to release. Additionally, there was no clinical testing required to support the medical device as the indications for use is equivalent to the predicate device. The substantial equivalence of the device is supported by the non-clinical testing."

Ask a specific question about this device

The Patient Assistant model PA97000 initiates the recording of cardiac event data in the device memory of a Medtronic insertable cardiac monitor. The Patient Assistant is intended for unsupervised patient use away from a hospital or clinic.

The PA97000 Patient Assistant (hereinafter referred to as PA97000) is a hand-held, battery operated, Bluetooth Low Energy (BLE) device used by patients to mark symptoms in the memory of their implantable device, as illustrated in Figure 1: Image of PA97000. It is intended for unsupervised use away from a hospital or clinic.

The provided text is a summary of the 510(k) submission for the Medtronic Patient Assistant Model PA97000. It describes the device, its intended use, and the testing performed to support its substantial equivalence to a predicate device. However, it does not contain a table of acceptance criteria and reported device performance in the typical sense of a clinical or analytical performance study with specific metrics like sensitivity, specificity, or accuracy.

The information primarily focuses on design verification and validation, rather than a study with a test set, ground truth, or expert adjudication for determining performance against clinical acceptance criteria.

Therefore, I cannot fulfill all parts of your request as the specific information is not present in the provided text.

Here's what can be extracted based on the document:

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

This information is not explicitly provided in the document in the format requested (specific performance metrics against acceptance criteria). The text states that "Device verification testing was performed to demonstrate the PA97000 meets established performance criteria" but does not detail what those criteria are or the quantitative results against them. The listed tests are primarily engineering design verification and validation.

2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective):

This information is not provided. The text mentions "extensive testing" and "design verification testing" but does not specify sample sizes for any test sets that would typically be used for evaluating clinical or analytical performance.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience):

This information is not provided. As there's no mention of a clinical or analytical performance study with a test set requiring ground truth, there's no information about experts or their qualifications.

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

This information is not provided for the same reasons as above.

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:

This is not applicable to this device. The Patient Assistant Model PA97000 is a hardware device (a hand-held, battery-operated device) that initiates recording of cardiac event data. It is not an AI-based diagnostic tool, nor does it involve "human readers" in the context of an MRMC study.

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

This is not applicable to this device. It is a physical device, not an algorithm, and its function involves user interaction (a patient pressing a button) to mark symptoms. While it operates "unsupervised" in terms of clinical oversight, it's not an "algorithm-only" performance in the sense of AI.

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

This information is not provided. No clinical or analytical ground truth is mentioned in the context of performance evaluation, as the focus is on engineering verification.

8. The sample size for the training set:

This information is not provided. There is no mention of a "training set" as this is not an AI/machine learning device.

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

This information is not provided for the same reason as above.

Summary of Device and Testing (from the text):

The device under review is the Medtronic Patient Assistant Model PA97000.

Device Purpose: The PA97000 is a hand-held, battery-operated device that allows patients to mark symptoms in the memory of their implanted cardiac device (an Insertable Cardiac Monitor). It provides feedback to the user about searching for the implanted device and successful symptom marking.

Study Type and Goal (as described): The submission aimed to demonstrate substantial equivalence to the predicate device, Patient Assistant Model PA96000. This was supported by "design verification testing" and "hazard analysis." The primary change from the predicate was an update in the communication protocol from Telemetry B to Bluetooth Low Energy (BTLE).

Tests Performed (Design Verification and Validation):

• Safety Design Verification
• EMC Design Verification
• Environmental Design Verification
• Mechanical Design Verification
• Firmware Design Verification
• Packaging Design Verification
• Security Design Validation
• System Design Validation
• Human Factors Testing
• Biocompatibility

Conclusion of the Submission: The intended use, design, materials, and performance of the PA97000 are substantially equivalent to the predicate PA96000, supported by thorough hazard analysis and extensive testing.

Ask a specific question about this device

The Liba3 ™ System is an ambulatory cardiac monitoring system prescribed by a physician or other qualified healthcare professional for out-patient individuals with known non-lethal arrhythmias such as:

• · Atrial Fibrillation
• · Bradycardia
• · Tachycardia
  · Pause
  It continuously monitors, records, and stores electrocardiographic (ECG) data. If equipped with a transmitter, the Liba3™ will also periodically transmit ECG Cardiac Event to a remote computer server. Both recorded and transmitted ECG data are available to HealthCare Providers for analysis and reporting.
  Liba3™ is intended to be used with adult patients 22 years and older, but not designed for pediative patients.

The Liba3™ System is a wearable, wireless arrhythmia detection system that provides continuous cardiac monitoring functionality for an extended period of time. Each Sensor can be worn for up to 7.5 days. If the prescribed monitoring period exceeds 7.5 days. National Cardiac. Inc. will provide additional sensors. For a 30-day monitoring period, the patient would be required to use four (4) Sensor components. The Liba3 System is prescribed by healthcare providers to monitor, record, and report on a patient's electrocardiographic (ECG) data.
The Liba3 system consists of: (1) a wearable electronic component that collects and monitors a patient's single lead ECG data referred to as a Liba3TM Sensor; (2) an optional transmitting device, referred to as the Liba3 transmitting device, that is used for ECG data transmission while the patient is wearing the sensor and for transmission of patient triggered events; and (3) a Remote Data Management System (RDMS) which is a remote server with software that will allow qualified healthcare providers to receive, analyze, interpret, and report on the results of the ECG test.

I am sorry, but the provided text does not contain detailed information about the acceptance criteria for device performance and the specific study that proves the device meets those criteria, particularly in the context of an AI-powered medical device and the requested elements:

• A table of acceptance criteria and reported device performance: This is not present, nor are specific performance metrics related to AI algorithm accuracy provided. The document focuses on regulatory compliance and substantial equivalence to a predicate device.
• Sample size and data provenance for the test set: There is no mention of a test set, its size, or the origin of the data.
• Number and qualifications of experts for ground truth: No information is provided about expert involvement in establishing ground truth for a test set.
• Adjudication method: Not discussed.
• MRMC comparative effectiveness study: There is no mention of a multi-reader multi-case study or the effect size of AI assistance on human readers. The document primarily concerns the device as an ambulatory cardiac monitoring system, not specifically an AI-assisted diagnostic tool in the typical sense of imaging AI.
• Standalone algorithm performance: While the device has an "Arrythmia detection algorithm (Proprietary / Server side)", there are no specific performance metrics (e.g., sensitivity, specificity, accuracy) provided for this algorithm in a standalone capacity.
• Type of ground truth: Not specified for any performance evaluation.
• Sample size for training set: No information is provided about a training set or its size.
• How ground truth for training set was established: Not discussed.

The document is a 510(k) summary, which focuses on demonstrating "substantial equivalence" to a predicate device (NowCardio™ System). It highlights technological characteristics, compliance with various medical device standards (e.g., electrical safety, biocompatibility, risk management, software life cycle), and general design verification activities. However, it does not provide the specific performance study details, acceptance criteria, and ground truth methodologies typically expected for a detailed AI device performance evaluation.

The closest relevant statement is under "G. Non-Clinical Performance Data," which mentions "complete design verification activities which included verification of all design input requirements and ECG Analysis performance vs. recognized Databases, ECG analysis software validation". However, it does not elaborate on what these "recognized Databases" are, the specific performance metrics (e.g., sensitivity, specificity for arrhythmia detection), the acceptance criteria for these metrics, or the methodologies used to establish ground truth within those databases.

Therefore, I cannot fulfill your request for the specific details regarding acceptance criteria and performance study as outlined in your prompt based on the provided text.

Ask a specific question about this device

Configuration 1) Holter Mode: The MobileECG 2 BT is intended to record continuous data for 30+ days for the detection of arrhythmias in ambulatory patients. Such monitoring is frequently used for patient symptoms such as: Palpitations, shortness of breath, chest pain, syncope, evaluating pacemakers, heart rate variability's, and clinical studies. The MobileECG 2 BT device transmits all collected data to a call center for interpretation using the TM eCloud ECG Analysis System at the end of the completed study.

Configuration 2) Mobile Cardiac Telement Mode: The MobileECG 2 BT is intended to continuously monitor, transmit, and record data for up to 30 days for patient transient symptoms that may suggest cardiac arrhythmia. The MobileECG 2 BT device continuously transmits data to a call center for interpretation of ECG data using the TM eCloud ECG Analysis System.

Configuration 3) Event Mode: The MobileECG 2 BT is intended to monitor and record patient activated data for up to 30 days for patient transient symptoms that may suggest cardiac arrhythmia. The MobileECG 2 BT device transmits all patient event activated data to a call center for interpretation of ECG data using the TM eCloud ECG Analysis System.

The MobileECG 2 BT is intended for use in adults and children of any age from birth upwards.

The MobileECG 2 BT and the TM eCloud ECG Analysis System interpretation software is not intended as sole means of diagnosis and is offered to physicians and clinicians on an advisory basis only in conjunction with the physician's knowledge of ECG.

The MEMTEC MobileECG 2 BT digital Monitor provides high resolution recording of patient ECG data and pacemaker spike detection for a period of up to 30 Days. The 3 in 1 Multi - Function BT monitor provides Holter, Event, and MCT ambulatory use. The data is stored on a removable Micro SD Card and no data compression is used. The data can be downloaded by a USB 3.0 cable, BT, or removable Micro SD Card. The BLE 4.1 (Bluetooth) sends patient data to cell phone continuous for 30 days for use as an Event or MCT Monitor. The patient ID/Date/Time is stamped on the recording every 2 minutes preventing the mixing of data with another patients data. The large LCD provides real time patient ECG signals and confirms lead hook-ups. In Holter Mode the unit has selectable sample rates of 250, 500, or 1000 samples per second with resolution of 12bits. The MobileECG 2 BT operates on a single "AAA" alkaline or "AAA" lithium battery.

Configuration 1 (Holter Mode): MobileECG 2 BT is used with the TM eCloud Analysis System (K142349) for Holter monitoring. In Holter usage, data is recorded for the prescribed duration and then uploaded and analyzed after the recording period has ended. The TM eCloud algorithm suite is used to analyze and interpret the ECG data.

Configuration 2 (MCT Mode): MobileECG 2 BT is combined with a special purpose cell phone and Android APP to store and transmit real-time ECG to the TM eCloud Analysis System (K142349) to provide Mobile Cardiac Telemetry (MCT). The TM eCloud algorithm suite is used to analyze and interpret the ECG data.

Configuration 3 (Event Mode): MobileECG 2 BT is combined with a special purpose cell phone and Android APP to store and transmit real-time ECG on patient activated events to the TM eCloud Analysis System (K142349). The TM eCloud algorithm suite is used to analyze and interpret the ECG data.

The Memtec Corporation's MobileECG 2 BT device underwent testing to demonstrate its substantial equivalence to predicate devices. The study information is extracted from the provided text.

1. Acceptance Criteria and Reported Device Performance

The provided document describes a comparison of technical specifications and indications for use between the subject device (MobileECG 2 BT) and two predicate devices (Preventice BodyGuardian and Memtec Corporation Model 950-12L). The primary acceptance criteria for establishing substantial equivalence were that differences in technological specifications should not raise any new issues of safety or effectiveness. The document concludes that "the differences in the above "Technological Specifications" between the devices do not raise any new issues of safety or effectiveness, demonstrating that the subject device is as safe and as effective as the predicated devices."

A table comparing the technical specifications of the MobileECG 2 BT with the predicate devices is provided in the source document. Since the reported performance is largely a qualitative statement of "Same" or "Different" with a justification for why the difference does not affect safety or effectiveness, a direct quantitative comparison of acceptance criteria vs. specific reported device performance values for each technical specification is not explicitly detailed in a pass/fail format within this document. The conclusion states all criteria were met to establish substantial equivalence.

Conclusion: The provided document states that the MobileECG 2 BT's performance testing results demonstrate that the differences in "Technological Specifications" do not raise any new safety or effectiveness issues, and that the "Indications For Use" are substantially equivalent to the predicate devices.

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

The provided document does not specify a separate test set, its sample size, or data provenance (e.g., country of origin, retrospective/prospective). The assessment of substantial equivalence relies on comparison of technical specifications and indications for use against predicate devices validated against recognized FDA standards. The non-clinical tests mentioned are conformance to these standards.

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

The document does not mention the use of experts to establish ground truth for a test set. Substantial equivalence was determined through comparison to predicate devices and conformance to recognized standards.

4. Adjudication Method

The document does not mention any adjudication method as no expert review or human evaluation of a test set is described.

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

The document does not describe an MRMC comparative effectiveness study, nor does it provide information on human reader improvement with or without AI assistance. The device is a data acquisition system that transmits data to an existing analysis system (TM eCloud ECG Analysis System, K142349).

6. Standalone Performance Study

The document does not describe a standalone (algorithm only without human-in-the-loop performance) study for the MobileECG 2 BT itself in terms of diagnostic accuracy. Instead, it states that "The MobileECG 2 BT and the TM eCloud ECG Analysis System interpretation software is not intended as sole means of diagnosis and is offered to physicians and clinicians on an advisory basis only in conjunction with the physician's knowledge of ECG." The MobileECG 2 BT is primarily a data acquisition device, and its performance is evaluated through its conformity to established medical device standards and comparison of its technical specifications to predicate devices. The TM eCloud ECG Analysis System is a referenced device (K142349), suggesting its own performance would have been established separately.

7. Type of Ground Truth Used

For the MobileECG 2 BT device itself, the ground truth for performance assessment seems to be derived from compliance with FDA-recognized consensus standards (e.g., ANSI/AAMI ES60601-1-2005, IEC 60601-1-2:2014, ANSI/AAMI-IEC 60601-2-47-2012, ANSI/AAMI EC53:1995). The document does not describe a clinical study with pathology or outcomes data specifically for the MobileECG 2 BT's diagnostic performance for arrhythmias, as it functions as a data recorder for an analysis system.

8. Sample Size for the Training Set

The document does not mention a training set or its sample size. The MobileECG 2 BT is a hardware device for ECG data acquisition; it does not explicitly describe an AI algorithm or model that would require a training set. The referenced "TM eCloud ECG Analysis System" (K142349) would be the component that uses algorithms and would likely have had its own training set.

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

As no training set is described for the MobileECG 2 BT, there is no information provided on how its ground truth would have been established.

Ask a specific question about this device

PocketECG CRS is intended to be used for:

1. Cardiac monitoring of patients undergoing a cardiac rehabilitation program. Its main feature is patient monitoring during previously planned training sessions and training assistance to achieve desired intensity and duration of workout. Training session parameters such as heart rate threshold, session duration (time intervals and number of repetitions) are defined by the physician for each patient individually. Additionally, the transmitter allows continuous ECG monitoring between trainings, during patient daily activities.

2. All patients hospitalized with a primary diagnosis of an acute myocardial infarction (MI) or chronic stable angina (CSA), or who during hospitalization have undergone coronary artery bypass graft (CABG) surgery, a percutaneous coronary intervention (PCI), cardiac valve surgery, or cardiac transplantation, referred to an early outpatient cardiac rehabilitation or secondary prevention (CR) program.

3. All patients evaluated in an outpatient setting who within the past 12 months have experienced an acute myocardial infarction (MI), coronary artery bypass graft (CABG) surgery, a percutaneous coronary intervention (PCI), cardiac valve surgery, or cardiac transplantation, or who have chronic stable angina (CSA) and have not already participated in an early outpatient cardiac rehabilitation or secondary prevention (CR) program for the qualifying event or diagnosis, referred to such a program.

4. Patients who require monitoring for: a) non-life threatening arrhythmias such as supraventricular (e.g. atrial fibrillation, atrial flutter, PACs, PSVT) and ventricular ectopy; b) evaluation of bradyarrhythmias and internittent 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;

5. PocketECG CRS can be used to monitor the training session in hospital, rehabilitation center or physicians office under supervision of qualified staff.

Medicalgorithmics Unified Cardiac Rehabilitation System PocketECG CRS is an ambulatory system which can be used for patient monitoring during previously planned cardiac rehabilitation training sessions and training assistance to achieve desired intensity and duration of workout. The system measures patient's physical activity and ECG signal, classifies all detected heart beats and recognizes rhythm abnormalities. PocketECG CRS can be also used for patient's monitoring between training sessions as an ambulatory ECG monitor which analyzes electrographic signal, classifies all detected heart beats and recognizes rhythm abnormalities. All detection results, including annotations for every detected heart beats and the entire ECG signal are transmitted via cellular network to a remote server accessible by a Monitoring Center for review by trained medical staff.

The provided text is a 510(k) summary for the Medicalgorithmics Unified Cardiac Rehabilitation System PocketECG CRS. It details the device's indications for use, technological comparison to predicate devices, and adherence to various standards and guidance documents. However, it does not include specific tables of acceptance criteria with reported device performance, nor does it provide details on the study design elements such as sample sizes for test/training sets, data provenance, number or qualifications of experts for ground truth, adjudication methods, or MRMC comparative effectiveness study results.

The section titled "IX. Performance data" states:
"Arrhythmia detection algorithms implemented in PocketECG CRS (PECGT-III) and PocketECG III (PECGT-IIIR) have been subject for performance testing according to IEC 60601-2-47:2012 (AAMI / ANSI / IEC 60601-2-47:2012) Test results were considered to be in complaint with standard requirements."

This statement indicates that performance testing was conducted and met the requirements of the specified standard, but it does not provide the qualitative or quantitative results needed to populate the requested table or answer the specific questions about the study methodology.

Therefore, many of the requested details cannot be extracted from the provided text.

Here's a breakdown of what can and cannot be answered based on the provided document:

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

• Cannot be fully provided. The document states that "Test results were considered to be in complaint with standard requirements" (IEC 60601-2-47:2012), implying acceptance criteria from that standard were met. However, the specific acceptance criteria and the reported performance metrics (e.g., sensitivity, specificity for various arrhythmias) are not explicitly listed in a table.

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Cannot be provided. The document does not specify the sample size for the test set or the provenance of the data used for performance testing (e.g., country of origin, retrospective/prospective nature).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Cannot be provided. The document does not describe how ground truth was established for the performance testing, nor does it mention the number or qualifications of any experts involved.

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

• Cannot be provided. The document does not describe any adjudication method used for the test set.

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

• Cannot be provided. The document makes no mention of an MRMC comparative effectiveness study or human reader improvement with AI assistance. The performance testing described appears to be for the algorithm's standalone performance against a standard.

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

• Likely yes, based on the text. The statement "Arrhythmia detection algorithms implemented in PocketECG CRS (PECGT-III) and PocketECG III (PECGT-IIIR) have been subject for performance testing according to IEC 60601-2-47:2012" implies standalone algorithmic performance was assessed against a standard. There is no mention of human-in-the-loop performance studies described in this summary.

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

• Cannot be provided specifically. While it's implied that there was a ground truth or reference standard against which the arrhythmia detection algorithms were tested, the document does not specify the type of ground truth (e.g., whether it was expert consensus, manually annotated ECGs, etc.).

8. The sample size for the training set

• Cannot be provided. The document does not mention the training set or its size.

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

• Cannot be provided. As the training set is not mentioned, its ground truth establishment is also not described.

In summary, the provided 510(k) summary confirms that performance testing (specifically for arrhythmia detection algorithms) was conducted in accordance with IEC 60601-2-47:2012 and found to be "in complaint with standard requirements." However, it lacks the detailed quantitative and qualitative results, and the specifics of the study methodology (sample sizes, data provenance, ground truth establishment, expert involvement, or any human-in-the-loop studies) that your request entails.

Ask a specific question about this device