Search Results

The Zio monitor is a prescription-only, single-use, ECG monitor that continuously records data for up to 14 days. It is indicated for use on patients, 18 years and older, who may be asymptomatic or who may suffer from transient symptoms such as palpitations, shortness of breath, dizziness, lightheadedness, pre-syncope, syncope, fatigue, or anxiety.

The Zio monitor is a non-sterile, single-use, continuously recording, long-term ambulatory ECG monitor that is adhered to a patient's left pectoral region in a modified Lead II orientation. The goal of the Zio monitor is to help physicians initiate long-term, patient-compliant ECG monitoring utilizing proprietary technology. The Zio monitor is applied and activated by the patient at home or at a clinic. Once activated, the device provides continuous, uninterrupted ECG recording into memory with minimal patient interaction. There is a button on the surface of the Zio monitor, which serves to activate the device and may be pressed by the patient during wear to indicate when he or she is experiencing a symptom. Additionally, there is a surface LED light that blinks green to confirm proper activation or that the device is working, and orange to indicate loss of connection with the skin or the presence of error conditions.

The Zio monitor utilizes firmware that captures single-channel ECG data into memory, there is no wireless transmission of data during the wear period of the device. After the prescribed monitoring period is complete, the Zio monitor is returned to iRhythm where the ECG data is then analyzed and annotated by the ZEUS System (K222389). ECG data is then presented to the Qualified Cardiac Technicians (QCT) at the Independent Diagnostic Testing Facility (IDTF) for review and subsequent creation and posting of the end-of-wear report with preliminary findings. Zio monitor device is not intended for real-time patient monitoring.

The provided text is an FDA 510(k) clearance letter and summary for the Zio® monitor. It details the device, its indications for use, comparison to a predicate device, and nonclinical testing performed to establish substantial equivalence. However, it explicitly states:

"No clinical testing was performed in support of this premarket notification."

Therefore, I cannot provide a table of acceptance criteria and reported device performance based on a clinical study, nor specific details about sample size, data provenance, ground truth establishment, expert qualifications, or MRMC studies, as these aspects relate to clinical testing which was not conducted for this submission.

Here's what I can extract and state based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance:

Based on the provided document, the acceptance criteria and device performance are established through nonclinical testing, demonstrating conformance to recognized standards and performance specifications, rather than through a clinical study with specific performance metrics like sensitivity or specificity for detecting arrhythmias.

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

• Sample Size for Test Set: Not applicable as no clinical testing was performed. The nonclinical testing would have used various test samples, components, or simulated data as appropriate for each specific engineering and performance test (e.g., system testing, electrical testing).
• Data Provenance: Not applicable for clinical data. For nonclinical testing, the data is generated in-house or by accredited testing laboratories as part of the device's design verification and validation.

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

• Not applicable as no clinical testing with human-established ground truth was reported. Ground truth in nonclinical testing refers to established engineering specifications or reference standards.

4. Adjudication method for the test set:

• Not applicable as no clinical testing requiring expert adjudication was performed.

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 as no clinical testing was performed. The device, Zio monitor, is described as recording ECG data which is then "analyzed and annotated by the ZEUS System (K222389)" and "presented to the Qualified Cardiac Technicians (QCT) at the Independent Diagnostic Testing Facility (IDTF) for review." This implies an existing workflow with a human-in-the-loop, but this submission specifically states no clinical testing was performed to evaluate its effectiveness in combination with human readers.

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

• The document implies that the "ZEUS System (K222389)" performs initial analysis and annotation of the ECG data, but this specific 510(k) is for the Zio® monitor hardware device. Performance data for the ZEUS System itself would be found in its own 510(k) clearance (K222389). This submission does not provide standalone algorithm performance metrics.

7. The type of ground truth used:

• For the nonclinical testing, the ground truth would be based on:
  • Engineering Specifications: Device design requirements and intended performance.
  • Recognized Consensus Standards: Compliance with international standards (e.g., IEC 60601 series, ISO 10993 series).
  • Internal Product Specifications: How the device is designed to function and its measurable outputs.

8. The sample size for the training set:

• Not applicable. This submission is for a hardware device and relies on nonclinical testing for substantial equivalence, not a machine learning model's training set. While the ZEUS System (K222389) likely uses a training set, details for that system are outside the scope of this document.

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

• Not applicable as no training set for an algorithm is discussed in this submission for the Zio® monitor hardware.

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

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 provided document, a 510(k) Summary for the Zio AT® device (K240029), states that no clinical testing was performed in support of this premarket notification. The submission relies solely on nonclinical testing to demonstrate substantial equivalence to the predicate device (Zio® AT ECG Monitoring Device [K163512]).

Therefore, based on the provided text, I cannot provide details regarding acceptance criteria, reported device performance, sample sizes for test sets, data provenance, expert ground truth establishment, adjudication methods, MRMC studies, or standalone performance that would typically be associated with clinical studies.

The document indicates that the device's acceptance criteria were based on its conformance to established performance specifications and FDA-recognized consensus standards. The study that proves the device meets these acceptance criteria is the nonclinical testing described.

Here's an overview of the information available:

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

The document does not provide a specific table of quantitative acceptance criteria and reported device performance metrics in the format typically seen with clinical study results (e.g., sensitivity, specificity, accuracy for arrhythmia detection). Instead, it states that "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."

The acceptance criteria implicitly relate to the successful completion of the following nonclinical tests and their conformance to specified standards:

• System performance testing: This would ensure the device functions as designed in various operational aspects.
• Biocompatibility testing: This confirms the materials used in the device are safe for contact with the human body.
• Firmware verification testing: This validates the software operating the device.
• Electrical safety and EMC testing: This ensures the device is electrically safe and does not interfere with other electronic devices, and vice versa.

The reported device performance, in this context, is that the device "meets the requirements of established conformance standards and performance specifications necessary for its intended use."

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

Not applicable, as no clinical testing was performed. The nonclinical testing would use various test samples and equipment as dictated by the specific standards and internal protocols, but these are not disclosed in terms of number or provenance in the provided summary.

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 no clinical testing with expert ground truth establishment was performed.

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

Not applicable, as no clinical testing requiring adjudication was performed.

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

Not applicable, as no clinical testing or MRMC study was performed. The Zio AT device itself functions as a monitoring and transmission system, not an AI-powered diagnostic aid that assists human readers in real-time interpretation.

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

The device is described as "intended to capture and transmit symptomatic and asymptomatic cardiac events and record continuous electrocardiogram (ECG) data." While it transmits events, the overall system for diagnosis involves a monitoring center for analysis and end-of-wear reporting, which would typically involve human oversight. The provided text does not suggest a standalone algorithm-only diagnostic performance evaluation in a clinical setting. The nonclinical testing focused on the device's functional performance and compliance with relevant standards.

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

Not applicable, as no clinical testing that would require such ground truth for diagnostic accuracy was performed. For nonclinical tests, the "ground truth" would be the specified parameters and expected outputs defined by the relevant engineering and safety standards.

8. The sample size for the training set

Not applicable, as no clinical testing or development of an AI algorithm based clinical data was detailed as part of this submission for demonstrating substantial equivalence. The device is an updated version of a previously cleared device, focusing on hardware and firmware changes.

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

Not applicable for the same reasons as #8.

Ask a specific question about this device

The device is intended to capture, and report symptomatic and asymptomatic cardiac events and continuous electrocardiogram information for long-term monitoring. After wear, ECG data from compatible monitoring devices is processed and analyzed by the ZEUS System. A final report is generated on the beat-to-beat information from the entire ECG recording. For the Zio AT service, the ZEUS System supports the capture and analysis of automatically-detected arrhythmia events, as well as the analysis of uploaded patient-triggered events.

The ZEUS System 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, fatigue, or anxiety and patients who are asymptomatic. The reports are provided for review by the intended user to render a diagnosis based on clinical judgment and experience. It is not intended for use on critical care patients.

The Zio® Service consists of single-patient-use monitoring devices and the Zio ECG Utilization Software (ZEUS) System, the subject device of this submission, for analysis and reporting of cardiac information derived from ECG data. The ZEUS System is a software system consisting of a collection of software modules designed to store and analyze data from compatible cardiac monitoring devices to curate a report of preliminary findings intended for use by clinicians as an aid in arrhythmia diagnosis and management.

The subject ZEUS System utilizes an artificial intelligence (AI) Al-based AutoTrigger Engine (ATE) software application for processing requests originating from the Gateway Service as part of the Zio AT system enabling asymptomatic ECG triggers, and Al-based ECG Analysis Software (ECGDL) to generate the initial ECG-based cardiac information.

The output of ECG Analysis Software of the ZEUS System is used by Certified Cardiographic Technicians (CCTs) prior to publishing the cardiac information in the patient report and is not utilized directly by the prescribing clinician or patient. The reported cardiac information includes beats, ectopic runs, ECG segments, rhythms, and heart rate measurements. Recorded ECG is processed by an automated ECG analysis platform; results are quality reviewed by CCTs, findings and associated ECG are captured in a report provided to clinicians via a secure website. For the Zio® AT Patch/Gateway, the ZEUS System provides capabilities to automatically detect clinically actionable arrhythmia during the monitoring period, as well as receive baseline, scheduled, symptomatic, and asymptomatic transmissions.

The subject of this 510(k) are proposed software modifications to the ZEUS System to allow AF/AFL burden estimate reporting in the daily reports. In addition, software modifications were made to the ECGDL software of the ZEUS System to target modest performance improvements.

The ZEUS System, subject of K222389, is substantially equivalent to its predicate device (K202527), based on non-clinical performance data. Here's a summary of the available information:

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

The provided document refers to non-clinical verification and performance testing that established the device meets its design requirements. However, it does not explicitly list specific acceptance criteria thresholds (e.g., sensitivity, specificity, accuracy targets) for arrhythmia detection or AF burden estimation, nor does it provide a table of reported device performance against such specific criteria.

Instead, it states: "The nonclinical verification and performance test results established that the device meets its design requirements and intended use, that the design differences with the cleared device do not raise new questions of safety and efficacy." And, "The verification and validation testing demonstrate that the device meets all predetermined specifications."

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

The document does not provide details on the sample size used for the test set in terms of the number of ECG recordings or patients, nor does it specify the data provenance (country of origin, retrospective/prospective). It only mentions "nonclinical verification and performance test results."

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)

The document states that the output of the ECG Analysis Software is "quality reviewed by CCTs" (Certified Cardiographic Technicians) before publishing the report. However, it does not specify:

• The number of CCTs or other experts involved in establishing ground truth for the test set used in the non-clinical performance evaluation.
• The specific qualifications or experience levels of these CCTs or any other experts who might have been involved in a ground truth process for testing.

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

The document does not describe any specific adjudication method (e.g., 2+1, 3+1) for the test set. It mentions CCTs perform a "quality review," but the procedure for resolving discrepancies or establishing a "ground truth" for formal testing purposes is not detailed.

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 is mentioned in the provided text. The document explicitly states: "No clinical testing was performed in support of this premarket notification." The system's output is intended for review by clinicians, but the document does not describe any studies on the impact of the AI on human reader performance.

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

Yes, a standalone performance of the algorithm is implied for the "ECGDL software of the ZEUS System to target modest performance improvements" and the "Al-based AutoTrigger Engine (ATE) software application." The non-clinical performance testing would evaluate the algorithm's output prior to human review, to ensure it meets design specifications. However, specific standalone performance metrics (e.g., sensitivity, specificity for various arrhythmias) are not provided in this document.

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

The document indicates that "the output of ECG Analysis Software of the ZEUS System is used by Certified Cardiographic Technicians (CCTs) prior to publishing the cardiac information in the patient report." This strongly suggests that for the operational process, the ground truth is essentially expert consensus/review by CCTs. For the non-clinical performance testing, it is implied that a similar expert review or a reference standard based on expert interpretation of ECG data would be used to establish ground truth, but this is not explicitly detailed.

8. The sample size for the training set

The document does not provide any information regarding the sample size used for the training set of the AI-based AutoTrigger Engine (ATE) and ECGDL software.

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

The document does not specify how the ground truth for the training set was established. It describes the general function of the system and its review process by CCTs, but details concerning training data annotation are absent.

Ask a specific question about this device

The ZEUS System (Zio Watch), as part of the Zio Watch Service, is intended to process and analyze electrocardiogram (ECG) and photoplethysmogram (PPG) based data to detect and report on the presence of Atrial Fibrillation (AF) over the monitoring period. The report provides ECG information for the intended user to diagnose AF and contextual information for AF, both to be interpreted based on clinical judgment and experience. It is indicated for use on adult patients 22 years or older who are susceptible to developing or who have been diagnosed with AF. It is not intended for use on critical care patients.

The ZEUS System (Zio Watch), the subject device of this 510(k) submission, is a software as a medical device (SaMD) system consisting of a collection of modules designed to process and analyze data from the Zio Watch into a curated report of preliminary findings intended for use by clinicians to aid in AF diagnosis.

The subject ZEUS System utilizes an artificial intelligence (Al) based ECG Analysis Software (ECGDL) to generate the initial ECG-based cardiac information provided to the clinician in Transmission Reports. In addition, continuously recorded PPG-based data is processed by a separate artificial intelligence (AI) based analysis software, the AF Context Engine (ACE), that detects the presence of AF. Specifically, the subject ZEUS System (Zio Watch) utilizes machine learning techniques for both the ECGDL and AF Context Engine algorithms.

These results are also presented along with the ECG data in the Zio Watch Transmission Reports. The reported cardiac information includes AF detection (including PPG-based AF summary) and heart rate measurements. The ECG-based preliminary findings in the Zio Watch Transmission Reports are quality reviewed by Certified Cardiographic Technicians (CCTs) prior to publishing. After CCT review, the report containing the preliminary findings and associated ECG are provided to clinicians via a secure website.

Here's a breakdown of the acceptance criteria and the study used to prove the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

The document doesn't explicitly state numerical acceptance criteria in a table format for a specific performance study. Instead, it focuses on demonstrating substantial equivalence to predicate devices and adherence to recognized standards. However, the core performance is related to AF detection. The acceptance criteria can be inferred as the device successfully performing its intended function of detecting and reporting AF from ECG and PPG data, with sufficient accuracy for clinical interpretation.

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

• Verily Prospective Study (ACE validation set):

  • Sample Size: Not explicitly stated as a number of patients or recordings. It describes "multi-day PPG recordings" from the Zio Watch along with "ECG-based, CCT-reviewed reference rhythm labels" obtained from simultaneously worn Zio XT Patches. Patient demographics are provided (see below).
  • Provenance: Prospective study.
  • Country of Origin: Regional Demographics (USA): Midwest: 8.0%, Mountain: 32.1%, West: 32.1%, Northeast: 14.3%, South: 13.4%.

• ZWAF Database (ECGDL validation set):

  • Sample Size: Not explicitly stated as a number of recordings. It consists of "ECG data obtained from Zio Watch as used in the Study Watch AF Detection At Home study ('Verily Prospective Study')". Patient demographics are provided (see below).
  • Provenance: This dataset is derived from the "Study Watch AF Detection At Home study" (Verily Prospective Study), which is noted as retrospective in reference to its use for the ZWAF database for ECGDL validation.
  • Country of Origin: Regional Demographics (USA) from the Verily Prospective Study (Midwest: 8.0%, Mountain: 32.1%, West: 32.1%, Northeast: 14.3%, South: 13.4%).

Demographics for both validation sets:

• Patients: At least 22 years or older who are at risk of having an AF event, as determined by having a diagnosis of paroxysmal AF.
• Age: Median = 67 [25%, 75%] = [59, 73]
• Gender: 45.5% Female

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

• Number of Experts: Not explicitly stated as a specific number. The text refers to "Certified Cardiographic Technicians (CCTs)". It implies multiple CCTs were involved in reviewing the reference ECG data to establish ground truth.
• Qualifications of Experts: "Certified Cardiographic Technicians (CCTs)". No further details on their years of experience are provided in this document.

4. Adjudication Method for the Test Set:

• The document states that the ground truth for the validation sets was based on "ECG-based, CCT-reviewed reference rhythm labels". This suggests that the CCTs' review served as the gold standard.
• No specific multi-expert adjudication method (like 2+1 or 3+1) is mentioned for resolving discrepancies among CCTs, if any. The phrasing "CCT-reviewed" implies their consensus or, at minimum, their expert determination.

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

• No MRMC comparative effectiveness study was mentioned or performed. The document explicitly states: "No clinical testing was performed in support of this premarket notification." The focus was on the performance of the algorithm itself against expertly reviewed ground truth.

6. Standalone (Algorithm Only) Performance:

• Yes, standalone performance was done for both algorithms. The validation studies described for the "AF Context Engine (ACE)" and "ECG Deep Learned (ECGDL)" algorithms assessed their performance in detecting AF and analyzing ECG data, respectively, against CCT-reviewed ground truth, without a human-in-the-loop component during the performance evaluation for substantial equivalence. The "ZEUS System (Zio Watch)" itself is described as a "software as a medical device (SaMD) system consisting of a collection of modules designed to process and analyze data".

7. Type of Ground Truth Used:

• Expert Consensus (CCT-reviewed ECG data): The primary ground truth for both the ACE and ECGDL algorithm validation was derived from "ECG-based, CCT-reviewed reference rhythm labels". For ACE, these were from simultaneously worn Zio XT Patches. For ECGDL, it was ECG data obtained from the Zio Watch itself, which was also subject to CCT review to establish ground truth.

8. Sample Size for the Training Set:

• Not explicitly stated as a number of recordings or patients. The text mentions "thousands of recordings" for both ECGDL and ACE algorithms.

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

• The training data for both the ECGDL and ACE algorithms came from "continuous cardiac recordings from compatible cardiac monitors" that "have already undergone Certified Cardiographic Technician (CCT) review." This indicates that the ground truth for the training data was also established by CCTs.

Ask a specific question about this device

The Zio Monitor is a prescription-only, single-patient-use, ECG monitor that continuously records data for up to 14 days. It is indicated for use on patients who may be asymptomatic or who may suffer from transient such as palpitations, shortness of breath, dizziness, lightheadedness, pre-syncope, syncope, fatigue or anxiety.

The Zio monitor is a non-sterile, single-patient-use, long-term ambulatory ECG monitor that is adhered to a patient's left pectoral region in a modified Lead II orientation. The goal of the Zio monitor is to help physicians initiate long-term, patient-compliant ECG monitoring utilizing proprietary technology.

The Zio monitor is applied and activated by the patient at home or at a clinic. Once activated, the device provides continuous, uninterrupted ECG recording into memory with minimal patient interaction. There is a button on the surface of the Zio monitor, which serves to activate the device and may be pressed by the patient during wear to indicate when he or she is experiencing a symptom. Additionally, there is a surface LED light that blinks green to confirm proper activation or that the device is working, and orange to indicate loss of connection with the skin or the presence of error conditions.

Although the provided document is a 510(k) summary for the Zio Monitor, it explicitly states that no clinical testing was performed in support of this premarket notification. Therefore, the document does not contain information about acceptance criteria based on clinical performance, a study proving device performance against such criteria, sample sizes for test sets, expert qualifications, adjudication methods, MRMC studies, standalone performance, or grand truth details for either test or training sets.

The document focuses on demonstrating substantial equivalence to a predicate device (Zio XT Patch) through nonclinical testing, changes in technological characteristics (reduced weight and power), and adherence to recognized consensus standards and guidance documents.

Here's an analysis of the provided information, noting the absence of the requested clinical performance details:

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

   • The document states: "There are no required FDA performance standards for the Zio monitor. All necessary performance testing was conducted on the Zio monitor to ensure performance as intended per specifications and to support a determination of substantial equivalence to the predicate device."
   • It lists several nonclinical tests (Mechanical verification, Biocompatibility, Firmware verification, Electrical safety and EMC, and packaging tests conforming to ASTM standards) and mentions conformance to various ISO/AAMI/IEC standards (Table 2).
   • However, specific quantitative acceptance criteria and their corresponding reported device performance values from these nonclinical tests are not detailed in this summary. The summary only asserts that the device meets these standards and specifications.

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

   • Not applicable / Not provided. No clinical test set was used as no clinical testing was performed.

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 / Not provided. No clinical test set requiring expert ground truth was used.

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

   • Not applicable / Not provided. No clinical test set requiring adjudication was used.

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

   • Not applicable / Not provided. No clinical testing, including MRMC studies, was performed. The device itself is an ECG monitor, not explicitly described as having AI assistance for human readers in this document.

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

   • Not applicable / Not provided. No clinical or algorithm-only performance study was conducted or reported in this summary.

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

   • Not applicable / Not provided. No clinical ground truth was established as no clinical testing was performed. For the engineering/nonclinical tests, the "ground truth" would be the specifications and standards themselves.

8. The sample size for the training set

   • Not applicable / Not provided. No machine learning or AI algorithm requiring a training set is discussed or implied to have been evaluated clinically in this document.

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

   • Not applicable / Not provided. As no training set is mentioned, its ground truth establishment is also not applicable.

In summary, the provided 510(k) summary for the Zio Monitor focuses on demonstrating substantial equivalence through nonclinical conformity and engineering specifications rather than clinical performance data. Therefore, the requested information regarding acceptance criteria derived from clinical studies and their supporting evidence is not present in this document.

Ask a specific question about this device

The device is intended to capture, and report symptomatic and asymptomatic cardiac events and continuous electrocardiogram information for long-term monitoring. After wear, ECG data from compatible monitoring devices is processed and analyzed by the ZEUS System. A final report is generated on the beat-to-beat information from the entire ECG recording. For the Zio AT service, the ZEUS System supports the capture and analysis of automatically-detected arrhythmia event, as well as the analysis of uploaded patient-triggered events.

The ZEUS System 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, fatigue, or anxiety and patients who are asymptomatic. The reports are provided for review by the intended user to render a diagnosis based on clinical judgment and experience. It is not intended for use on critical care patients.

The Zio® Service consists of single-patient-use monitoring devices and the Zio ECG Utilization Software (ZEUS) System, the subject device of this submission, for analysis and reporting of cardiac information derived from ECG data. The ZEUS System is a software system consisting of a collection of software modules designed to store and analyze data from compatible cardiac monitoring devices to curate a report of preliminary findings intended for use by clinicians as an aid in arrhythmia diagnosis and management. The ECG Analysis Software of the ZEUS System is used by Certified Cardiographic Technicians (CCTs) prior to publishing the reported cardiac information in the Final Report and is not utilized directly by the prescribing clinician or patient. The reported cardiac information includes beats, ectopic runs, ECG segments, rhythms, and heart rate measurements. Recorded ECG is processed by an automated ECG analysis platform; results are quality reviewed by CCTs, findings and associated ECG are captured in a report provided to clinicians via a secure website. For the Zio® AT Patch/Gateway, the ZEUS System provides capabilities to automatically detect clinically actionable arrhythmia during the monitoring period, as well as receive baseline, scheduled, symptomatic and asymptomatic transmissions.

This FDA 510(k) summary for the Zio ECG Utilization Software (ZEUS) System (K202527) does not provide the detailed acceptance criteria and the comprehensive study results typically found in performance studies for AI/ML devices. Instead, it focuses on demonstrating substantial equivalence to a predicate device (K190593) primarily through non-clinical testing and comparison of technological characteristics.

Therefore, many of the requested details about acceptance criteria, specific performance metrics, sample sizes, ground truth establishment, expert qualifications, and MRMC studies are not explicitly stated within this document. The document explicitly states: "No clinical testing was performed in support of this premarket notification."

However, I can extract the available information and highlight what is missing based on your request.

Summary of Available Information and Missing Details:

1. Table of Acceptance Criteria and Reported Device Performance: This information is not provided in a table format within the document. The document states that "nonclinical verification and performance test results established that the device meets its design requirements and intended use." It also mentions "design specifications" which would contain acceptance criteria, but these are not enumerated. The "reported device performance" is not quantified in terms of metrics like sensitivity, specificity, or F1-score for arrhythmia detection.

2. Sample Size Used for the Test Set and Data Provenance: Not specified. The document only mentions "nonclinical testing" and "verification and system-level regression testing." It does not detail specific test sets for performance evaluation in terms of ECG data or patient population, nor does it mention data provenance (country, retrospective/prospective). Given that no clinical testing was performed, any "test set" would likely refer to internal validation data, which is not described.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications: Not specified. Since no clinical testing was performed and no specific test set based on expert-labeled data is described, this information is not present. The document mentions that "results are quality reviewed by CCTs" (Certified Cardiographic Technicians) as part of the overall Zio Service operation, but this refers to the workflow, not the establishment of ground truth for a predefined test set used for regulatory submission.

4. Adjudication Method: Not specified. No clinical study or expert-based ground truth establishment is detailed.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done, and Effect Size: No. The document explicitly states, "No clinical testing was performed in support of this premarket notification." Therefore, no MRMC study was conducted or reported here.

6. If a Standalone (algorithm only without human-in-the-loop performance) was done: The document describes the ZEUS System as a "software system consisting of a collection of software modules designed to store and analyze data... to curate a report of preliminary findings intended for use by clinicians... The ECG Analysis Software of the ZEUS System is used by Certified Cardiographic Technicians (CCTs) prior to publishing the reported cardiac information in the Final Report." This indicates a human-in-the-loop system where the algorithm's output is reviewed by CCTs. The document does not provide standalone performance metrics for the algorithm prior to CCT review.

7. The Type of Ground Truth Used: Not specified. Given the lack of clinical testing and detailed performance evaluation, the method for establishing ground truth for any internal validation is not described.

8. The Sample Size for the Training Set: Not specified. The document does not describe the development or training of any AI/ML components in detail, nor does it specify the size of any training data used. It only mentions "ECGDL" (ECG Deep Learning?) as the rhythm detection algorithm, replacing "ECGML + ECGDL" from the predicate.

9. How the Ground Truth for the Training Set was Established: Not specified.

Available Information from the Document:

While the direct answers to your questions are largely "not specified" due to the nature of this 510(k) submission focusing on substantial equivalence based on non-clinical testing, here's what the document does provide:

• Device: Zio ECG Utilization Software (ZEUS) System (K202527)
• Intended Use: "capture, analyze and report symptomatic and asymptomatic cardiac events and continuous electrocardiogram information for long-term monitoring." Reports are "provided for review by the intended user to render a diagnosis based on clinical judgment and experience."
• Predicate Device: iRhythm Technologies, Inc. Zio® ECG Utilization Software (ZEUS) System (K190593).
• Technological Change: The subject device introduces "ECG segment detection" (specifically QT interval detection) and uses "ECGDL" for rhythm detection, whereas the predicate used "ECGML + ECGDL." It also expands interoperability to include the Zio® Monitor.
• Performance Evaluation Method: "Safety and performance... has been evaluated and verified in accordance with design specifications and to support a determination of substantial equivalence... Nonclinical testing summarized in Table 2 demonstrates that the ZEUS System is in conformance with FDA-recognized consensus standards and FDA guidance documents."
• Standards/Guidance Documents Used for Nonclinical Testing:
  • AAMI ANSI ISO 14971:2012(R)2010 (Risk Management)
  • IEC 62304 Edition 1.1 2015-06 (Medical device software - Software life cycle processes)
  • AAMI ANSI IEC 60601-2-47:2012 (Ambulatory Electrocardiographic Systems)
  • AAMI ANSI EC57:2012 (Testing and reporting performance results of cardiac rhythm and ST segment measurement algorithms)
  • U.S. FDA October 2, 2014 Guidance (Cybersecurity in Medical Devices)
  • U.S. FDA May 5, 2005 Guidance (Software Contained in Medical Devices)
• Conclusion of Performance: "The nonclinical verification and performance test results established that the device meets its design requirements and intended use... The verification and system-level regression testing demonstrate that the device meets all its specifications."

In essence, this 510(k) clears the device based on demonstrating that its changes from the predicate device do not raise new questions of safety or effectiveness, supported by non-clinical engineering and software validation testing, rather than a clinical performance study with detailed acceptance criteria for diagnostic accuracy metrics.

Ask a specific question about this device

The Zio ECG Utilization Service (ZEUS) System is intended to analyze and report symptomatic and asymptomatic cardiac events and continuous electrocardiogram information for long-term monitoring by Zio XT or Zio AT Patch, a final report is generated based on the beat information from the entire ECG recording. 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, fatigue, or anxiety and patients who are asymptomatic. The reports are provided for review by the intended user to render a diagnosis based on clinical judgment and experience. It is not intended for use on critical care patients.

The ZEUS System is an electrocardiogram (ECG) processing and analysis system, designed to handle continuously recorded, single-lead ECG data. It downloads, stores, analyzes and aggregates the ECG data for a Certified Cardiographic Technician (CCT) to review and generate a report of the findings contained within the data; thereby enabling the provision of a complete ECG processing and analysis service.

The provided text is a truncated 510(k) submission summary for the Zio® ECG Utilization Service (ZEUS) System. Unfortunately, it does not contain the detailed information necessary to answer all parts of your request regarding acceptance criteria and the specific study that proves the device meets those criteria.

Specifically, the document states: "Automated ECG analysis performance was quantified for any claimed analysis metrics. The resulting statistics demonstrate sensitivity and positive predictivity levels which satisfy requirements and minimize safety or efficacy concerns." However, it does not present the specific acceptance criteria (e.g., target sensitivity/predictivity values) nor does it provide a table of acceptance criteria alongside reported device performance. It also explicitly states, "No clinical testing was performed in support of this premarket notification." Therefore, the detailed study information you requested (sample sizes, ground truth establishment, expert qualifications, MRMC studies, standalone performance details, training set info) is not present in this document.

Based on the available text, here's what can be extracted:

1. Table of acceptance criteria and the reported device performance:

   • Acceptance Criteria (Implied): The device was expected to demonstrate sensitivity and positive predictivity levels that "satisfy requirements and minimize safety or efficacy concerns" for "any claimed analysis metrics."
   • Reported Device Performance: The document states, "The resulting statistics demonstrate sensitivity and positive predictivity levels which satisfy requirements..." However, no specific numerical values or a table comparing criteria to performance are provided.

2. Sample sized 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 in the document.

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 in the document. The text mentions that a "Certified Cardiographic Technician (CCT) to review and generate a report of the findings contained within the data," but this refers to the intended use of the device for clinical review, not the establishment of ground truth for a performance study.

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, 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 is not mentioned or implied. The document explicitly states, "No clinical testing was performed in support of this premarket notification."

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

   • The document states, "Automated ECG analysis performance was quantified for any claimed analysis metrics." This suggests standalone algorithm performance was evaluated, but the results and methodology are not detailed.

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

   • This information is not explicitly provided. Given the nature of ECG analysis, it would typically be expert annotation/consensus, but the document does not confirm this.

8. The sample size for the training set:

   • This information is not provided in the document.

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

   • This information is not provided in the document.

Summary of available information regarding performance evaluation:

• Device Name: Zio® ECG Utilization Service (ZEUS) System
• Purpose of Evaluation (Implied): To quantify automated ECG analysis performance for claimed metrics, demonstrating sensitivity and positive predictivity.
• Type of Testing: "Automated ECG analysis performance was quantified." This was part of "Overall system performance testing" and "Software verification testing" as "nonclinical testing."
• Result (General): "The resulting statistics demonstrate sensitivity and positive predictivity levels which satisfy requirements and minimize safety or efficacy concerns."
• Lack of Detail: The document explicitly states "No clinical testing was performed" and does not provide specific numerical results, acceptance thresholds, sample sizes, methodology for ground truth, or details of expert involvement in performance studies.

Ask a specific question about this device

The device is intended to capture, and report symptomatic and asymptomatic cardiac events and continuous electrocardiogram information for long-term monitoring. While continuously recording patient ECG, both patient-triggered and automatically-detected arthythmia events are transmitted to a monitoring center for reporting. After wear, a final report is generated based on the beat information from the entire ECC recording. 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, fatigue, or anxiety and patients who are asymptomatic. The reports are provided for review by the intended user to render a diagnosis based on clinical judgment and experience. It is not intended for use on critical care patients.

The ZEUS System is an electrocardiogram (ECG) analysis and reporting software system, designed to process continuously recorded, signal-lead ECG data. The ZEUS System downloads, stores, analyzes and sorts the ECG data to allow iRhythm's Certified Cardiographic Technicians (CCTs) to generate and distribute a report of the findings contained within the data, thereby enabling the provision of a complete ECG processing and analysis service.

The provided text describes the 510(k) premarket notification for the Zio AT ECG Monitoring System, specifically focusing on the modifications made to the ZEUS System's rhythm classification algorithm from a rule and machine-learning implementation to a deep-learning basis.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

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

The document states that "Safety and performance of the modified ZEUS System has been evaluated and verified in accordance with design specifications and applicable performance standards." and "The nonclinical verification and performance test results established that the device meets its design requirements and intended use, that the modifications to the originally cleared device do not raise new questions of safety and efficacy."

However, there is no specific table of acceptance criteria with corresponding performance metrics provided in the text. The document broadly refers to compliance with standards like AAMI ANSI EC57: 2012 and IEC 60601-2-47:2012. These standards typically outline performance requirements for ECG analysis systems (e.g., sensitivity, specificity for various arrhythmias), but the specific numerical targets set as acceptance criteria by iRhythm and the reported device performance against those targets are not detailed in this public FDA letter.

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

The document mentions that "The modified device's arrhythmia algorithm detection was tested in accordance to AAMI ANSI EC57: 2012". While AAMI ANSI EC57: 2012 provides guidelines for testing and reporting performance, it does not explicitly state the sample size (number of patients or recordings) used for the test set.

Data Provenance: The document does not specify the country of origin of the data, nor does it explicitly state whether the data was retrospective or prospective.

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

The document mentions that the ZEUS System enables "iRhythm's Certified Cardiographic Technicians (CCTs) to generate and distribute a report of the findings contained within the data". However, it does not specify the number of experts used to establish the ground truth for the test set used to validate the deep-learning algorithm, nor does it explicitly state their qualifications (e.g., number of years of experience, specific certifications beyond "Certified Cardiographic Technicians").

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

The document does not describe any adjudication method used for the test set to establish ground truth. It implies that CCTs generate reports, but not the process for an independent adjudicated ground truth for testing.

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:

The document does not mention an MRMC comparative effectiveness study where human readers' performance with and without AI assistance was evaluated. The focus of this submission is on the technological change to the algorithm itself and demonstrating its substantial equivalence to the predicate device.

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

Yes, the document implies that standalone performance testing of the algorithm was done. It states: "The modified device's arrhythmia algorithm detection was tested in accordance to AAMI ANSI EC57: 2012" and "The ZEUS System is an electrocardiogram (ECG) analysis and reporting software system, designed to process continuously recorded, signal-lead ECG data." This suggests that the algorithm's performance in detecting arrhythmias was evaluated independently.

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

The document indicates that "iRhythm's Certified Cardiographic Technicians (CCTs) generate and distribute a report of the findings contained within the data". This implies that the ground truth for the data used in the system's operation is established by CCTs. For the testing data, it's highly probable that expert review (likely by CCTs, and potentially also by cardiologists as part of a gold standard process not explicitly detailed here) was used to establish ground truth for the arrhythmias. However, it does not explicitly state "expert consensus" or provide details on how many experts.

8. The sample size for the training set:

The document does not specify the sample size for the training set used for the deep-learning algorithm. It only states that the algorithm was updated "from a rule and machine-learning implementation to a deep-learning basis."

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

The document does not explicitly state how the ground truth for the training set was established. Given that the "ZEUS System downloads, stores, analyzes and sorts the ECG data to allow iRhythm's Certified Cardiographic Technicians (CCTs) to generate and distribute a report of the findings," it is highly probable that the training data and their corresponding labels (ground truth) were derived from previous ECG recordings marked up by these Certified Cardiographic Technicians or similar qualified personnel.

Ask a specific question about this device

The Zio QX ECG Monitoring System is intended to capture, analyze and report symptomatic and asymptomatic cardiac events and continuous electrocardiogram (ECG) information for long-term monitoring. While continuously recording patient ECG, both patient-triggered and automatically detected arrhythmia events are transmitted to a monitoring center for reporting. After wear, a final report is generated based on beat-to-beat information from the entire ECG recording. 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, fatigue, or anxiety. The reports are provided for review by the intended user to render a diagnosis based on clinical judgment and experience. It is not intended for use on critical care patients.

The Zio® QX ECG Monitoring System consists of three key device components: (1) Zio QX Patch Recorder with Bluetooth technology, (2) Zio QX Wireless Gateway with both Bluetooth and cellular technology, and (3) the Zio ECG Utilization Service (ZEUS) System for data analysis and reporting.

The Zio® QX Patch is a non-sterile, single-patient-use ECG monitor that provides a continuous, single-channel recording in addition to asymptomatic and symptomatic data transmission for up to 14 days. The Zio® QX Patch is applied and activated by the patient. Once activated, the Patch records ECG without patient interaction, with the goal of improving patient compliance via simplicity of operation. The Zio® QX Patch, in conjunction with the Wireless Gateway and the ZEUS System, has arrhythmia auto-detection capabilities. Additionally, patients have the option of pressing a convenient trigger button which marks the continuous record and initiates the wireless transfer of a 90-second ECG strip. The wireless transfer of data is enabled by the Zio® QX Gateway, which requires Bluetooth proximity to the Patch and cellular network reception but no patient interaction to transmit to the monitoring center. The patient is encouraged to document symptomatic events in either the provided booklet, mobile medical app (iOS 9+, Android 4.4+) or via a patient website, which will support symptom-rhythm correlation in the Zio QX Report.

At the conclusion of the wear period (up to 14 days), the patient removes the Zio® QX Patch and returns it by mail to an iRhythm data processing center.

Upon receipt of both symptomatic/asymptomatic transmissions (during wear) and downloaded continuous ECG data (post wear) at iRhythm's Clinical Center (iCC), the data is processed through the ZEUS detection algorithm and delivered to the QA Tool module where the results are reviewed and/or adjusted by iRhythm's Certified Cardiographic Technicians (CCTs) for accuracy. iRhythm employed and trained Patch in-take and CCT personnel follow internal procedures for processing and are made aware of performance limitations and anomalies with both the detection algorithms and software workflow tools. All anomalies are visible to and, where appropriate, are manually corrected by iRhythm Technologies CCTs during the QA review and/or Patch Report edits. The CCT generates a final report (Zio QX Report) of the ECG findings contained within the data, thereby providing a complete ECG processing and analysis service.

Upon explicit request from a clinician responsible for the patient's healthcare, longer segments of ECG data from the continuous recording on the Patch can also be wirelessly retrieved during the wear period. Alternatively, such periods are also available for inclusion in the final report, where the entire ECG recording is available for review and selective inclusion based on clinical relevance.

The provided FDA 510(k) summary for the Zio® QX ECG Monitoring System (K163512) describes the device's acceptance criteria and the study conducted to prove it meets them.

Here's an analysis of the provided information:

1. Table of Acceptance Criteria and Reported Device Performance

The document states: "Automated ECG analysis performance was quantified for any claimed analysis metrics. The resulting statistics demonstrate sensitivity and positive predictivity levels which satisfy requirements."

However, the specific quantitative acceptance criteria (e.g., minimum sensitivity of X%, minimum PPV of Y% for specific arrhythmia types) and the actual reported performance metrics (e.g., Sensitivity = A%, PPV = B%) are NOT explicitly provided in the excerpt. The document only makes a general statement that the device satisfies requirements.

Without the actual numbers, a precise table cannot be constructed.

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

The document states: "No clinical testing was performed in support of this premarket notification." and "All necessary performance testing was conducted on the Zio® QX ECG Monitoring System to ensure performance as intended per specifications and to support a determination of substantial equivalence to the predicate devices."

This indicates that the primary performance evaluation for the automated ECG analysis was done as part of non-clinical testing. This likely means simulated or pre-recorded ECG datasets were used.

• Test Set Sample Size: Not explicitly provided.
• Data Provenance: The document does not specify the country of origin of the data or whether it was retrospective or prospective. Given "nonclinical testing," it's likely a retrospective analysis of existing datasets or simulated data.

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

The document describes the role of human experts in the data processing workflow:

• "...the data is processed through the ZEUS detection algorithm and delivered to the QA Tool module where the results are reviewed and/or adjusted by iRhythm's Certified Cardiographic Technicians (CCTs) for accuracy."
• "All anomalies are visible to and, where appropriate, are manually corrected by iRhythm Technologies CCTs during the QA review and/or Patch Report edits."
• "The CCT generates a final report (Zio QX Report) of the ECG findings contained within the data, thereby providing a complete ECG processing and analysis service."

From this, we can infer:

• Number of Experts: Not explicitly stated as a fixed number for establishing a ground truth dataset for the purpose of the regulatory submission's performance study. However, it implies that multiple CCTs are involved in the standard operational workflow for quality assurance and report generation. For the study proving acceptance criteria, the number of experts used to establish the "ground truth" for the test set is not specified.
• Qualifications of Experts: "iRhythm's Certified Cardiographic Technicians (CCTs)" are mentioned. Their specific experience (e.g., 10 years) is not provided. It also doesn't specify if a higher level of expertise (e.g., cardiologists) was involved in establishing the ground truth for the performance claim.

4. Adjudication Method for the Test Set

The document states that CCTs review and adjust the algorithm's results. This implies a human-in-the-loop system where the CCTs serve as a final arbiter. However, for the non-clinical performance testing used for the regulatory submission, the specific adjudication method to build the "ground truth" dataset is not described. General methods like "2+1" or "3+1" are not mentioned. It's possible that a single CCT or a panel of CCTs established the ground truth in the datasets used for testing.

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

The document explicitly states: "No clinical testing was performed in support of this premarket notification."

Therefore, a MRMC comparative effectiveness study involving human readers improving with AI vs. without AI assistance was NOT done for this submission. The device is a "monitoring system" with an automated analysis component that produces a report for human review; the study focuses on the algorithm's performance and the general process, not on human-AI collaboration effectiveness.

6. Standalone (Algorithm Only) Performance

Yes, a standalone performance evaluation of the algorithm was conducted. The document states:

• "Automated ECG analysis performance was quantified for any claimed analysis metrics."
• This falls under "Nonclinical testing."

The device description also clarifies the algorithm's role: "...the data is processed through the ZEUS detection algorithm...". This "ZEUS detection algorithm" is the standalone component whose performance was quantified.

7. Type of Ground Truth Used

The document indicates that CCTs review and "adjust" results to ensure "accuracy" and manually "correct" anomalies. This suggests the ground truth for the performance evaluation (or at least the operational ground truth for report generation) is established by expert consensus/adjudication by Certified Cardiographic Technicians (CCTs). It's not explicitly stated whether a higher level of ground truth (e.g., pathology, clinical outcomes, or adjudication by cardiologists) was used for the non-clinical test set.

8. Sample Size for the Training Set

The document does NOT provide any information regarding the training set's sample size. The focus of the 510(k) summary is on the testing that demonstrates substantial equivalence, not on the details of algorithm development (training, validation).

9. How Ground Truth for the Training Set Was Established

The document does NOT provide any information on how the ground truth for the training set was established. This is typical for a 510(k) submission, which focuses on the validation of the final product.

Ask a specific question about this device