Search Results

The Cardiologs Holter Platform is intended for use by qualified healthcare professionals for the assessment of arrhythmias using ECG data in the adult and pediatric population.

The product supports downloading and analyzing data recorded in compatible formats from any device used for the arrhythmia diagnostics such as Holter, event recorder, 12 lead ambulatory ECG devices, or other similar devices indicated for recording heart rhythm.

The Cardiologs Holter Platform can also be electronically interfaced and perform analysis with data transferred from other computer-based ECG systems, such as an ECG management system.

The Cardiologs Holter Platform provides ECG signal processing and analysis, QRS and Ventricular Ectopic Beat detection, QRS feature extraction, interval measurement, heart rate measurement and rhythm analysis. The Cardiologs Holter Platform is not for use in life supporting or sustaining systems or ECG monitor and physiological alarm devices.

The product can be integrated into computerized ECG monitoring devices. In this case, the medical device manufacturer will identify the indication for use depending on the application of their device.

Cardiologs Holter Platform interpretation results are not intended to be the sole means of diagnosis. It is offered to physicians and clinicians on an advisory basis only in conjunction with the physician's knowledge of ECG patterns patient background, clinical history, symptoms, and other diagnostic information.

Cardiologs Holter Platform is comprised of:

• An interface, which provides tools to measure, analyze and review numerous ECGs;
• An automated proprietary ECG interpretation support algorithm using artificial intelligence (AI) to analyze ECGs to provide clinicians with supportive information for ECG diagnosis.

Cardiologs Holter Platform is an online portal that can be accessed through a network connection and allows the clinician to review and annotate the ECG signals. Alternatively, the Cardiologs Holter Platform can be accessed via an Application Programming Interface (API) connection. The API connection allows a digital ECG upload from a connected device and allows the connected device to receive the output of the Cardiologs ECG interpretation support algorithm and further process and display its output in their system.

Cardiologs Holter Platform is intended to analyze recordings from devices used for the arrhythmia diagnostics such as Holter, event recorder, 12 lead ambulatory ECG devices, or other similar devices for the assessment of heart rhythm in adult and pediatric populations.

Cardiologs Holter Platform works in the following way:

1. Upload of a digital ECG file to Cardiologs' secure hosting databases;

   • i. Manual upload: via the web-interface
   • ii. Direct upload: no manual intervention required, upload occurs whenever the third-party hardware or software system is connected to the Cardiologs' Application Programming Interface (or API) and the ECG is automatically sent to the Cardiologs' servers.

2. Processing of the uploaded ECG file;

3. Analysis and annotation of the uploaded ECG performed by Cardiologs' proprietary algorithm;

4. Display the analysis of the ECG, along with the original signal, to the clinician for review of patient data. The algorithm output may be accessed/displayed through the following interfaces:

   • i. The clinician can access the algorithm output directly within Cardiologs using Cardiologs' user interface.
   • ii. The clinician can access the algorithm output in their own downstream system. The downstream system receives the output of the algorithm via Cardiologs' Application Programming Interface (API).
   • The Cardiologs Holter Platform allows for editing and/or validation of the measurements and parameters by the analyzing clinician.

5. A PDF report is generated as the result of the analysis.

The provided FDA 510(k) clearance letter for the Cardiologs Holter Platform (K250569) does not contain the detailed information required to describe the acceptance criteria and the specific study proving the device meets these criteria.

The letter states:

• "Performance testing demonstrates that the proposed device is as safe and effective and performs as well as the predicate." (Page 6 & 7)
• "No clinical testing was performed in support of this premarket notification." (Page 7)
• "The modified device includes performance updates to enhance the accuracy of the currently cleared abnormalities and measurements and expanded pediatric indications." (Page 6)

This indicates that internal performance testing was conducted, likely against the predicate device's performance, but the details of these tests (acceptance criteria, performance results, sample sizes, ground truth establishment, etc.) are not included in this public facing letter. Such information would typically be found in the full 510(k) submission document, which is not provided here.

Therefore, I cannot fulfill your request with the given input. The document is a clearance letter, which summarizes the outcome of the FDA's review, but does not detail the technical studies and their results.

Ask a specific question about this device

ZBPro Diagnostic is a cloud-based medical device intended for use by qualified healthcare professionals in the detection and analysis of common cardiac arrhythmias in Holter ECG data in the adult, non-paced population.

The product supports downloading and analyzing Lead II, CM5 (Ch 1), or Modified-MLII (Ch 2+) on retrospective 3-lead and 5-lead 24/48-hour Holter ECG recordings collected using standard Ag/AgCl wet electrodes in adult, non-paced patients. ZBPro is not intended for use with multi-lead analysis, wearable patches, or pediatric/paced recordings.

ZBPro Diagnostic can also be electronically interfaced and perform analysis with data transferred from other computer-based ECG systems, such as an ECG management system.

ZBPro Diagnostic provides ECG signal processing and analysis, QRS and Ventricular Ectopic Beat detection, QRS feature extraction, R-R interval measurement, heart rate measurement, and rhythm analysis.

ZBPro Diagnostic is not for use in life-supporting or sustaining systems or ECG monitor and Alarm devices.

The product can be integrated into computerized ECG monitoring devices. In this case, the medical device manufacturer will identify the indication for use depending on the application of their device.

ZBPro Diagnostic interpretation results are not intended to be the sole means of diagnosis. It is offered to physicians and clinicians on an advisory basis only in conjunction with the physician's knowledge of ECG patterns, patient background, clinical history, symptoms, and other diagnostic information.

ZBPro is cloud-based Software as a Medical Device which aids healthcare professionals in interpreting ambulatory ECG recordings. The software comprises a secure web interface and a backend server hosted on Amazon Web Server (AWS). Authenticated users upload compatible 24-48 hour Holter ECG recordings via a web browser through an Application Programming Interface (API). ZBPro's proprietary ECG interpretation algorithm analyzes and annotates ECGs to provide supportive information for ECG and arrhythmia analysis.

ZBPro provides beat-by-beat ECG signal processing and analysis, QRS detection, Ventricular Ectopic Beat detection, R-R interval measurement, heart rate and Heart Rate Variability measurement, and rhythm analysis.

ZBPro consists of:

1. A web interface which provides tools to upload data, measure, analyze and review numerous ECGs and patient diary logs, make manual annotation and generate ECG reports.
2. An automated proprietary ECG interpretation algorithm which measures and analyzes ECGs to provide adjunct information for ECG diagnosis.

The backend application is established in Amazon Web Services (AWS) and accessed through an Internet connection and a web browser to perform ECG analysis and generate reports.

The provided FDA 510(k) clearance letter and summary for ZBPro Diagnostic contains information related to the device's acceptance criteria and the study conducted to prove it meets them. However, it does not provide explicit details for all the requested points, particularly numerical metrics for acceptance criteria and specific performance results. Instead, it refers to compliance with standards and successful completion of validation.

Here's an extraction of the available information, with notes on what is not explicitly stated:

Acceptance Criteria and Reported Device Performance

The document states that "All clinical input requirements were validated against a gold standard," and "Performance validation testing included comprehensive rhythm classification analyses on an adjudicated database in accordance with ANSI/AAMI EC57 and IEC 60601-2-47 reporting conventions." This implies the acceptance criteria were defined by these standards. However, the exact numerical thresholds for sensitivity, specificity, accuracy, etc., for each specific arrhythmia or beat type, are not explicitly stated in the provided text. Similarly, the reported numerical device performance (e.g., specific percentages for sensitivity or specificity) is also not given.

The table below reflects what can be inferred or is directly mentioned regarding the device's performance against its expected functions, without specific quantitative results.

Study Details:

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

   • Test Set Sample Size: The document mentions "an adjudicated database" for performance validation testing but does not specify the sample size (number of patients or recordings) used for this test set.
   • Data Provenance: The document does not specify the country of origin of the data. It states the testing was done on "retrospective 3-lead and 5-lead 24/48-hour Holter ECG recordings." This confirms the data was retrospective.

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

   • The document states "Performance validation testing included comprehensive rhythm classification analyses on an adjudicated database." This implies that experts were involved in adjudication to establish ground truth. However, the number of experts used and their specific qualifications (e.g., radiologist with X years of experience) are not explicitly stated.

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

   • The term "adjudicated database" is used, indicating that a formal process was followed to establish ground truth. However, the specific adjudication method (e.g., 2+1, 3+1) is not explicitly described in the provided text.

4. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

   • No MRMC comparative effectiveness study involving human readers with and without AI assistance is mentioned. The study described focuses on the standalone performance of the algorithm against an adjudicated ground truth and user interface usability.

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

   • Yes, a standalone performance evaluation of the algorithm was conducted. The document states: "Performance validation testing included comprehensive rhythm classification analyses on an adjudicated database." This refers to the algorithm's performance independent of a human-in-the-loop scenario.

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

   • The ground truth was established through expert consensus/adjudication, as indicated by the phrase "adjudicated database."

7. The sample size for the training set:

   • The document does not provide any information regarding the sample size of the training set used for the ZBPro Diagnostic algorithm.

8. How the 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. It only refers to the "adjudicated database" for performance validation testing (typically the test set).

Ask a specific question about this device

Masimo W1™ and the integrated Masimo W1 Module are intended to record, store and transfer single-channel electrocardiogram (ECG) rhythms. The Masimo W1 also displays ECG rhythms, and the Masimo W1 Module detects the presence of atrial fibrillation. The Masimo W1 and the integrated Masimo W1 Module are intended for use by healthcare professionals, patients with known or suspected heart conditions, and health-conscious individuals.

Masimo W1 Module ECG software is an over-the-counter (OTC) software that operates on the Masimo W1 Module that can be used with compatible watches (e.g., Masimo W1). The software is intended to create, record, store, transfer, and display a single channel electrocardiogram (ECG) for informational use only in adults 22 years and older. It supports the classification of either atrial fibrillation (AFib) or sinus rhythm with the intention of aiding heart rhythm identification; it is not intended to replace traditional methods of diagnosis or treatment. The software is not intended for users with other known arrhythmias and users should not interpret or take clinical action based on the device output without consultation of a qualified healthcare professional.

The Masimo W1™ and the integrated Masimo W1 Module are also intended for the spot-checking of functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate (PR). The Masimo W1 and the integrated Masimo W1 Module are indicated for adults in hospitals, clinics, long-term care facilities, and homes.

The Masimo W1 is a watch that incorporates the Masimo W1 Module, which is the device that is responsible for the physiological signal detection and algorithm used to support the different parameters. The Masimo W1 Module incorporates spot check ECG functionality and Masimo SET Pulse Oximetry technology so that it can provide both ECG and Masimo SET pulse oximetry parameters. As part of this submission, Masimo is requesting clearance for an automated atrial fibrillation "AFib" Classification Feature that is used to analyze the single channel ECG waveform.

The parameter outputs from the Masimo W1 Module are communicated and displayed on the watch screen so that the data can be viewed and recorded. Masimo W1 also supports wireless communication of monitored data to a compatible smart device application. The sharing of the parameter data to the applications allows the users to see and track their data using their smart phones. Smart phone applications can also help to share information to caregivers and healthcare professionals.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided FDA 510(k) Clearance Letter for the Masimo W1 with the Atrial Fibrillation (AFib) Classification Feature:

1. Table of Acceptance Criteria and Reported Device Performance

For the Atrial Fibrillation Classification Feature:

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

• Test Set Sample Size: The document states "Prospective clinical testing was conducted to validate the AFib Classification Feature on adult subjects from 4 different sites." While a specific number of subjects is not provided, it indicates a multi-site study.
• Data Provenance: Prospective clinical testing. The country of origin is not explicitly stated in the provided text.

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

• Number of Experts: Unspecified (referred to as "qualified clinicians" for the qualitative assessment of ECG waveforms).
• Qualifications of Experts: "Qualified clinicians" were used for the qualitative assessment of the ECG waveforms. Further specific qualifications (e.g., cardiologist, years of experience) are not detailed in the provided text.

4. Adjudication Method for the Test Set

The document does not explicitly state the adjudication method used for establishing the ground truth for the test set (e.g., 2+1, 3+1). It only mentions that "qualified clinicians" made an agreement assessment.

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

• Was it done? No, a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with AI assistance versus without AI assistance was not described in the provided text. The study focused on the standalone performance of the AI AFib classification feature and the quality of its ECG waveform compared to a gold standard.
• Effect Size: Not applicable, as an MRMC study was not described.

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

• Was it done? Yes, a standalone performance study was clearly conducted for the AFib Classification Feature. The "Masimo W1 ECG AFib Classification feature Performance" section directly reports sensitivity, specificity, and PPV for the algorithm's output. The "Masimo W1 Module ECG software" is described as supporting the classification, indicating an algorithmic assessment.

7. Type of Ground Truth Used

• For AFib Classification: The gold standard for AFib classification is not explicitly stated, but clinical validation for ECG rhythm typically uses expert-adjudicated 12-lead ECG recordings. The document mentions "comparing similarity between Masimo W1 and gold-standard 12 lead ECG as reference" for waveform quality, which strongly implies 12-lead ECGs were used as a reference for rhythm classification as well.
• For ECG Waveform Quality: Gold-standard 12-lead ECG as reference.

8. Sample Size for the Training Set

The document does not specify the sample size for the training set. It only describes the test set used for clinical validation.

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 focuses solely on the validation/test set.

Ask a specific question about this device

The Inmedix® CloudHRV™ System is intended to acquire, display, and record electrocardiographic (ECG) information to measure heart rate variability (HRV) in adult patients (age 22 or above) with normal sinus rhythm and resting heart rate within 40 - 110 bpm. These measurements are not intended for any specific clinical diagnosis. The clinical significance of HRV must be determined by the physician.

Assessment is indicated for patients in a healthcare facility including a physician office or a hospital outpatient clinic where the patient is able to remain supine and still. The CloudHRV™ System is not indicated for use in a surgical suite or during transport.

Normal sinus rhythm is determined by the physician. The ECG is not intended to be used to diagnose or monitor cardiovascular conditions. The device does not provide assessments of cardiovascular abnormalities/arrhythmias.

The Inmedix® CloudHRV™ System acquires approximately 5 minutes of 3-lead electrocardioaraphic (ECG) data from a patient lying supine and at rest to measure heart rate variability (HRV). The raw cardiac electrical signals are detected using four standard ECG electrodes applied to the wrists and ankles of the patient and a custom 4-lead wire (one reference) ECG cable assembly.

The ECG data collected from the patient are transmitted to a cloud-based service hosted by Inmedix. where proprietary mathematical algorithms calculate HRV. The CloudHRV™ System outputs are used as an aid by clinicians who are accustomed to evaluating HRV as a part of their overall medical assessment.

The provided text does not contain detailed acceptance criteria and the results of a specific study to prove the device meets these criteria. Instead, it lists the standards and guidance documents used for design verification and validation, along with a high-level statement that testing demonstrates the device's safety and effectiveness compared to the predicate.

Therefore, many of the requested details cannot be extracted from the given information.

However, I can provide what is available, noting the limitations.

Missing Information:

• Specific quantitative acceptance criteria for device performance.
• The results of a specific study that quantitatively demonstrates the device meets acceptance criteria.
• Sample size used for a dedicated test set for performance evaluation (only general mention of "validation testing").
• Data provenance for any test set.
• Number and qualifications of experts for ground truth establishment.
• Adjudication method for any test set.
• Information on a multi-reader multi-case (MRMC) comparative effectiveness study.
• Information on a standalone algorithm performance study.
• The type of ground truth used for performance assessment.
• Sample size for the training set.
• How ground truth for the training set was established.

Information that can be extracted or inferred:

1. Table of Acceptance Criteria and Reported Device Performance

As specific quantitative acceptance criteria and their corresponding reported performance values are not detailed in the document for HRV measurement accuracy or related metrics, this table cannot be populated as requested. The document primarily focuses on regulatory compliance through adherence to standards and safety/EMC testing, and a functional comparison to a predicate device.

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

• Sample Size: Not specified for any performance-specific test set. The document refers generally to "Design validation testing" and "Design verification testing" but does not give sample sizes for subjects or data records.
• Data Provenance: Not specified.

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

• Not specified.

4. Adjudication method for the test set

• Not specified.

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 specified. The CloudHRV™ System calculates HRV indices and displays results, which are "used as an aid by clinicians." It does not appear to be an AI-assisted diagnostic or interpretation tool in the context of human reader improvement.

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

• The document implies standalone algorithm performance for HRV calculation: "The raw cardiac electrical signals are detected...The ECG data collected from the patient are transmitted to a cloud-based service hosted by Inmedix. where proprietary mathematical algorithms calculate HRV." However, no specific performance metrics (e.g., accuracy, precision) are provided for just the algorithm, nor is a dedicated study described.

7. The type of ground truth used

• Not specified for the performance of the HRV calculation itself. The compliance testing for standards likely uses reference devices or simulated signals as ground truth for ECG parameters.

8. The sample size for the training set

• Not specified.

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

• Not specified.

Ask a specific question about this device

The Cardiac Workstation is intended to acquire multi-channel ECG signals from adult and pediatric patients from body surface ECG electrodes, and to record, display, analyze and store these ECG signals for review by the user. They are to be used in healthcare facilities by trained healthcare professionals. Analysis of the ECG signals is accomplished with algorithms that provide measurements, data presentations, graphical presentations and interpretations for review by the user.

The interpreted ECG with measurements and interpretive statements is offered to the clinician on an advisory basis only. It is to be used in conjunction with the clinician's knowledge of the patient, the results of the physical examination, the ECG tracings, and other clinical findings. A qualified physician is asked to over-read and validate (or change) the computer-generated ECG interpretation.

The Cardiac Workstation 5000 (aka: CW 5000) and Cardiac Workstation 7000 (aka: CW 7000) are intended to acquire multi-channel ECG signals from adult and pediatric patients from body surface ECG electrodes, and to record, display, analyze and store these ECG signals for review by the user. They are to be used in healthcare facilities by trained healthcare professionals. Analysis of the ECG signals is accomplished with algorithms that provide measurements, data presentations, graphical presentations for review by the user.

The interpreted ECG with measurements and interpretive statements are offered to the clinician on an advisory basis only. They are to be used in conjunction with the clinician's knowledge of the results of the physical examination, the ECG tracings, and other clinical findings. A qualified physician is asked to over-read and validate (or change) the computer-generated ECG interpretation.

The CW 5000 and CW 7000 are mid- and high-range interpretive cardiographs, differing primarily in display size, the number of standard options. Both devices offer a full array of features built on the Linux operating system, with touch screen operation, a configurable feature set, and interpretation from the clinically proven Philips DXL ECG Algorithm (K132068). They provide a cardiograph solution for hospitals and cardiology clinics in processing large volumes of ECGs. The DXL ECG algorithm in the software analyzes up-to 18 leads of simultaneously acquired ECG waveform to interpret rhythm and morphology for a variety of patient populations. The measurements are then analyzed by the DXL ECG Algorithm. The resulting ECG reports may include ECG measurements, reasons, or analysis statements. The algorithm covers both adult and pediatric populations.

The CW 5000 and CW 7000 consist of the following:

• An electrocardiograph device with integrated display and printer. CW 5000 provides 12.1'' display panel. CW 7000 provides 15.6″ and 18.5″ options for the display panel.
• Optional Trolley (ordered via a separate part number)

The subject devices are further structured with options relating to software. Ul language, keyboard locale, and a wide range of other configuration choices to optimize the user's experience with the devices.

The Philips Cardiac Workstation 5000 and 7000 are ECG devices designed to acquire, record, display, analyze, and store multi-channel ECG signals for review. The analysis is performed by algorithms providing measurements, data presentations, graphical representations, and interpretations.

The study presented in the provided context for the Cardiac Workstation 5000 and 7000 is a non-clinical bench testing study, primarily focused on demonstrating substantial equivalence to a predicate device (PageWriter TC70 Cardiograph, K210560).

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are generally framed as compliance with harmonized standards and successful completion of various bench tests, aiming to show performance similar to the predicate device. Specific quantitative performance metrics for the standalone algorithm are not detailed in the provided text, as the focus is on overall device equivalence.

2. Sample Size for the Test Set and Data Provenance

The document does not detail specific sample sizes for a 'test set' in the traditional sense of a clinical or algorithm performance study. The evidence provided is primarily focused on bench testing against harmonized standards and comparison to a predicate device. Therefore, the "test set" would refer to the tests and evaluations conducted on the devices themselves rather than a dataset of patient ECGs.

The data provenance for any internal testing is not explicitly stated in terms of country of origin or retrospective/prospective nature regarding patient data. However, the harmonized standards (e.g., IEC, ANSI/AAMI, ISO, ASTM) are international or US-based.

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

No information is provided about experts establishing ground truth for a test set. This type of information would typically be present in a clinical or algorithm validation study. Since this is a substantial equivalence submission based on non-clinical bench testing, the ground truth refers to compliance with established technical specifications and standards rather than clinical diagnoses.

4. Adjudication Method for the Test Set

Not applicable, as the provided document describes non-clinical bench testing and compliance with standards, not a study involving expert adjudication of clinical outcomes.

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. The document explicitly states: "The Cardiac Workstation 5000 and Cardiac Workstation 7000, like the predicate device (K210560), did not require clinical studies to demonstrate substantial equivalence." The algorithm ("Philips DXL ECG Algorithm", K132068) is mentioned as previously cleared. This submission focuses on the hardware device's equivalence and updated features, not new claims about AI performance or human-AI interaction.

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

The document states that the devices use the "clinically proven Philips DXL ECG Algorithm (K132068)" or "same cleared ECG algorithm (PH110C) for ECG measurement and interpretation." This implies that the algorithm's standalone performance was likely established in its original K132068 submission. This current submission for the Cardiac Workstation 5000/7000 leverages that existing clearance and does not provide new standalone algorithm performance data. The mention of the algorithm being "advisory basis only" and requiring "a qualified physician to over-read and validate (or change) the computer-generated ECG interpretation" confirms it is not intended for standalone diagnostic use without human oversight.

7. The Type of Ground Truth Used

For the specific non-clinical bench tests described in this document, the "ground truth" is compliance with harmonized technical standards and internal specifications. For the underlying DXL ECG algorithm, its original clearance (K132068) would have established its ground truth, likely using expert consensus ECG interpretations, and potentially clinical outcomes or pathology, but details are not provided in this document.

8. The Sample Size for the Training Set

The document does not provide a sample size for the training set. This information would pertain to the development of the DXL ECG algorithm, which was already cleared under K132068. This submission is for the Cardiac Workstation devices incorporating the already cleared algorithm.

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

This information is not provided in the document. It would have been part of the original submission for the Philips DXL ECG Algorithm (K132068).

Ask a specific question about this device

Masimo W1 and the integrated Masimo W1 module are intended for the spot-check determination of Heart Rate using a single-channel electrocardiogram (ECG). The Masimo W1 and the integrated Masimo W1 module records, stores, transfers, and displays the single-channel ECG for the manual interpretation of heart rate. It is worn on the wrist and also provides the spot-checking of other continuous parameters (e.g., pulse oximetry).

The Masimo W1 and the integrated Masimo W1 module are also intended for the spot-checking of functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate (PR). The Masimo W1 and the integrated Masimo W1 Module are indicated for adults in hospitals, clinics, long-term care facilities, and homes.

The Masimo W1 is a watch that incorporates the W1 Module, which is the device that is responsible for the physiological signal detection and algorithm in providing the supported parameters. The W1 Module incorporates ECG functionality and Masimo SET Pulse Oximetry technology so that it can provide both ECG parameters and Masimo SET pulse oximetry parameters.

As part of this submission, Bluetooth connectivity has been added to the Masimo W1 to support the wireless communication of monitored data to a compatible smart device application, such as the Masimo SafetyNet. The sharing of the parameter data to applications like the Masimo SafetyNet allows for users to see and track their data using their smart phone applications can also help to share information to caregivers and healthcare professionals.

This document is a 510(k) premarket notification from the FDA, indicating that the Masimo W1 device, with the addition of Bluetooth connectivity, has been found substantially equivalent to its predicate device (K232512). It does not contain detailed acceptance criteria and study results for the device's original performance claims (e.g., accuracy of Heart Rate, SpO2, and Pulse Rate measurements), but rather focuses on demonstrating that the addition of Bluetooth connectivity does not introduce new safety or effectiveness concerns.

Therefore, the requested information regarding acceptance criteria and performance studies for the core functionalities (like ECG heart rate, SpO2, and PR accuracy), multi-reader multi-case studies, ground truth establishment, and training set details, are not available in the provided document. The document primarily focuses on explaining that the Bluetooth addition was tested and found to not negatively impact the device's safety and effectiveness.

Here's an attempt to answer the questions based only on the information provided, highlighting what is not available:

Device: Masimo W1 (with added Bluetooth connectivity)
Device Name: Electrocardiograph (also measures SpO2 and Pulse Rate)
K Number: K240229

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

The document states that the Masimo W1 maintains the same performance specifications as its predicate device (K232512) for its core functionalities, implying these specifications were met in previous testing for the predicate. For the new Bluetooth functionality, the acceptance criterion was effectively that its addition does not degrade the existing performance or introduce new safety/effectiveness issues.

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 mentions "non-clinical testing" including "Bench testing," "Software Verification and Validation Testing," "Wireless Testing," "Cybersecurity Testing," and "Human Factors and Usability Testing" to support the Bluetooth addition.
However, specific sample sizes for these tests are not provided.
Data provenance (country of origin, retrospective/prospective) is not specified. The studies are non-clinical and focus on functional performance and safety.

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. This type of information is typically relevant for studies involving human interpretation (e.g., diagnostic imaging AI). The tests described here are primarily technical and performance-based for a vital signs monitoring device. The ground truth for SpO2, PR, and HR measurement accuracy would have been established using reference standards (e.g., arterial blood gas analysis, ECG machine) during the original clearance of the predicate device, but details are not included here for this new submission (which focuses on Bluetooth).

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

Not applicable/Not provided. Adjudication methods are typically used in clinical studies where expert consensus is required for ground truth, particularly in diagnostic or AI-assisted interpretation. This document describes technical and performance validation.

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 study was performed or described. The device is a vital signs monitor, not an AI diagnostic tool that assists human readers in interpreting images or data. The focus of this submission is adding Bluetooth connectivity.

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

The device itself operates without a human in the loop for the measurement of parameters (Heart Rate, SpO2, PR). The "manual interpretation of heart rate" mentioned in the Indications for Use refers to a human looking at the displayed ECG and determining the rate, not the device performing an interpretation for diagnosis. The performance specifications listed (e.g., SpO2, PR, HR accuracy) are standalone claims for the device's measurement capabilities. However, details of the studies proving these specific accuracies were part of the predicate device's clearance and are not reiterated here, as this submission focuses on the addition of Bluetooth.
The document states: "The Masimo W1 and the integrated Masimo W1 module records, stores, transfers, and displays the single-channel ECG for the manual interpretation of heart rate." This implies the device provides the data, and a human performs the interpretation.

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

For the core measurements (SpO2, PR, HR), the ground truth for the predicate device's original clearance would likely have been established using reference medical devices/methods (e.g., CO-oximeter for SpO2, reference ECG for HR, reference pulse oximeter for PR) in controlled clinical or laboratory settings. This document does not detail how the ground truth was established, as it focuses on the new Bluetooth feature. For the Bluetooth feature, the ground truth would relate to successful data transfer, communication security, and non-interference with primary functions.

8. The sample size for the training set

Not applicable/Not provided. This device is not described as using machine learning models that require a "training set" in the conventional sense. The "algorithm" for physiological signal detection and parameter determination would be deterministic or signal-processing based, not a learned model from a training set.

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

Not applicable/Not provided (as no training set is described).

Ask a specific question about this device

The DeepRhythm Platform is intended for use by qualified healthcare professionals for the assessment of arthythmias using ECG data in adult patients.

The product supports downloading and analyzing data recorded in compatible formats from 1-channel and 2-channel ambulatory ECG recording devices used for the arthythmia diagnostics such as Holter, event recorder or other similar devices when retrospective assessment of the rhythm is necessary.

The DeepRhythm Platform is intended for the storage, analysis, visualization, review and reporting of arthythmias. The DeepRhythm Platform utilizes DeepRhythmAl (FDA-cleared device) for QRS and arrhythmia detection on the received signal. The DeepRhythm Platform provides further ECG signal annotations processing on a beat-by-beat basis, heart rate measurement and rhythm analysis, for both symptomatic and asymptomatic events.

The DeepRhythm Platform is not for use in life supporting or sustaining systems or ECG monitor and Alarm devices. The product can be integrated with computerized ECG monitoring devices compatible with DeepRhythmAI.

The DeepRhythm Platform interpretation results are not intended to be the sole means of diagnosis. It is offered to physicians and clinicians on an advisory basis only in conjunction with the physician's knowledge of ECG patterns, patient background, clinical history, symptoms, and other diagnostic information.

The DeepRhythm Platform system is a cloud-based software with microservice architecture and browser-based user interface. It provides arrhythmia diagnosis process and monitoring session management capabilities.

The DeepRhythm Platform's functionality consists of:

• enrolling a patient for an ECG monitoring session in a medical facility (performed . by Healthcare Professionals users),
• receiving the signal from a compatible monitoring device worn by the patient, .
• using an external AI service for signal analysis and classification (not a part of the . subject device),
• processing signal and annotations received from the external Al service, including . statistics computation,
• · reviewing the signal and annotations by an ECG Technician user,
• generating and publishing a report for a single ECG episode (Urgent report) and . for the entire monitoring session (End of Study report), performed by an ECG Technician user,
• reviewing a published report back at the medical facility that ordered the monitoring . session in the first place (performed by a Physician user).

The provided text does not contain detailed acceptance criteria or a comprehensive study report proving the device meets specific performance criteria. It primarily focuses on the regulatory submission information for FDA 510(k) clearance, asserting substantial equivalence to a predicate device.

Therefore, I cannot populate all the requested information. However, I can extract what is available and note the missing information.

Here's an analysis based on the provided text:

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

The document does not provide a specific table of acceptance criteria with corresponding performance metrics. It generally states that "All necessary testing was conducted on the DeepRhythm Platform to support a determination of substantial equivalence to the predicate device. Test results confirm that DeepRhythm Platform meets 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)

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 document mentions that the DeepRhythm Platform "utilizes DeepRhythmAI (FDA-cleared device) for QRS and arrhythmia detection on the received signal." This suggests that the AI component's ground truth establishment might have been part of its own prior clearance, but details for the DeepRhythm Platform's specific testing are absent.

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

This information is not provided in the document. The DeepRhythm Platform's role is described as "interpretation results are not intended to be the sole means of diagnosis. It is offered to physicians and clinicians on an advisory basis only." This suggests it's an assistive tool, but a comparative effectiveness study with human readers is not detailed.

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

The document states that "DeepRhythm Platform utilizes DeepRhythmAI (FDA-cleared device) for QRS and arrhythmia detection on the received signal." This implies that the core algorithmic performance for detection is handled by the pre-cleared DeepRhythmAI. The DeepRhythm Platform "provides further ECG signal annotations processing on a beat-by-beat basis, heart rate measurement and rhythm analysis," and processes statistics from DeepRhythmAI. However, specific standalone performance metrics for the DeepRhythm Platform's unique contributions (beyond DeepRhythmAI) are not detailed.

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

The type of ground truth used for this specific submission's testing is not explicitly stated. Given that it leverages a previously cleared AI for detection, the ground truth for the DeepRhythmAI algorithm itself would have been established during its clearance, likely through expert consensus with ECG interpretation. For the DeepRhythm Platform's own capabilities (processing, visualization, reporting), it would likely involve verification against established ECG processing standards and internal validation, but the ground truth method is not described.

8. The sample size for the training set

The document states that the DeepRhythm Platform "utilizes DeepRhythmAI (FDA-cleared device) for QRS and arrhythmia detection on the received signal." This means the training of the core AI algorithm (DeepRhythmAI) would have been done prior to this submission as part of its own clearance. The sample size for the training of DeepRhythmAI is not provided in this document.

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

As in point 8, the ground truth for the DeepRhythmAI algorithm's training would have been established during its separate FDA clearance. Details on this ground truth establishment are not provided in this document.

Ask a specific question about this device

The Digital Electrocardiograph ME3 is intended to acquire ECG signals from adult and pediatric patients through body surface ECG electrodes. The electrocardiograph is only intended to be used in hospitals or healthcare facilities by doctors and trained healthcare professionals. The carded by the electrocardiograph can help users to analyze and diagnose heart disease. The proposed device has analysis feature, however the ECG with measurements and interpretive statements is offered to clinician on an advisory basis only.

The ME6 is intended to acquire ECG signals from adult and pediatric patients through body surface ECG electrodes. The obtained ECG records can help users to analyze and disease. Digital Electrocardiographs shall be used in healthcare facilities by doctors and/or trained healthcare professionals.

Digital Electrocardiographs ME12P is intended to acquire ECG signals from adult and pediatric patients through body surface ECG electrodes. The obtained ECG records can help users to analyze and diagnose heart disease. Digital Electrocardiographs shall be used in healthcare facilities by doctors and/or trained healthcare professionals.

Digital Electrocardiograph ME15P is intended to acquire ECG signals from adult and pediatric patients through body surface ECG electrodes. The obtained ECG records can help users to analyze and diagnose heart disease. Digital Electrocardiographs shall he used in healtheare facilities by doctors and/or trained healthcare professionals.

The Mediblu ME3 Digital Electrocardiograph is intended to acquire, display and record ECG signals from adult and pediatric patients through body surface ECG electrodes. ECG data result and patient information could be stored in the memory of the device. The obtained ECG records can help users to analyze and diagnose heart disease.

The Mediblu ME6P Digital Electrocardiograph is intended to acquire, display and record ECG signals from adult and pediatric patients through body surface ECG electrodes. ECG data result and patient information could be stored in the memory of the device. The obtained ECG records can help users to analyze and diagnose heart disease.

The Mediblu ME12P Digital Electrocardiograph is designed to acquire ECG signals from adult and pediatric patients through body surface ECG electrodes. After been amplified and filtered, the ECG signal waveforms are displayed in the LCD and recorded in the paper through thermal printer. ECG data result and patient information could be stored in the memory of the device.

The Mediblu ME15P Digital Electrocardiograph is designed to acquire, display and record ECG signals from adult and pediatric patients through body surface ECG electrodes. After been amplified and filtered, the ECG signal waveforms are displayed in the LCD and recorded in the paper through thermal printer. ECG data result and patient information could be stored in the memory of the device.

The provided document is a 510(k) Premarket Notification for the Mediblu ECG System Models ME3, ME6P, ME12P, ME15P. This type of submission aims to demonstrate substantial equivalence to a predicate device, rather than proving the safety and effectiveness of a device from scratch through clinical studies with specific acceptance criteria and performance metrics.

Therefore, the document does not contain the information requested regarding acceptance criteria, a study proving the device meets those criteria, sample sizes for test/training sets, data provenance, expert qualifications, ground truth establishment, or multi-reader multi-case studies.

Instead, the submission focuses on comparing the subject devices to existing predicate devices to demonstrate that their indications for use, technological characteristics, and performance are substantially equivalent, implying that they are as safe and effective as the legally marketed predicate devices.

The document states:

• "We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices..." (Page 0)
• "The non-clinical test data demonstrates that the Mediblu ECG system models are substantially equivalent to digital electrocardiograph systems cleared for marketing in the US." (Page 15)
• "There are no differences between the subject devices and the predicate devices." (Page 15)

The acceptance criteria here is "substantial equivalence" to a predicate device, which is demonstrated by presenting a side-by-side comparison of technical specifications and intended use. The "study" proving this largely involves non-clinical testing to ensure the device meets specified technical performance (e.g., input impedance, frequency response, noise level) and safety standards (e.g., IEC60601-1), and then detailing how these align with the predicate device.

Here's a summary of what is provided, framed in relation to your request, and why it doesn't fit the typical "acceptance criteria and study" for a de novo or PMA submission:

Mediblu ECG System Models (ME3, ME6P, ME12P, ME15P) 510(k) Premarket Notification

This submission is to demonstrate substantial equivalence to existing, legally marketed predicate devices, not to prove de novo safety and effectiveness through clinical trials against specific performance acceptance criteria. The "acceptance criteria" for a 510(k) is that the device is as safe and effective as a predicate device.

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

• Acceptance Criteria (for 510(k)): Substantial equivalence to predicate devices, meaning the intended use and technological characteristics are the same, or if different, the differences do not raise new questions of safety or effectiveness.
• Reported Device Performance: Instead of a single "performance" score against an acceptance criterion, the document provides detailed technical specifications for each Mediblu model (ME3, ME6P, ME12P, ME15P) and directly compares them to their respective predicate devices. The "performance" is implicitly demonstrated by showing that all key technical specifications and features are "Same" as the predicate.

Example Table (Extracted from document for ME3 comparison):

Ask a specific question about this device

The intended use of ECG301 is to acquire ECG signals from adult and pediatric patients(above 3 years old) through body surface ECG electrodes. The electrocardiograph is intended to be used only in hospitals or healthcare facilities by doctors and trained healthcare professionals. The cardiogram recorded by ECG301 can help users to diagnose heart disease. ECG301 does not include any automated measurement or analysis of the ECG signal, and does not produce interpretative statements. The ECG recorded is not intended to be used for measurement or analysis of the ECG signal, or for the automated generation of interpretative statements.

Electrocardiograph, models: ECG301, is to acquire multi-channel ECG signals from adult and pediatric patients(above 3 years old) through body surface ECG electrodes. The device can gather and record ECG signals of 12 leads simultaneously. The cardiogram recorded by ECG301 can help users to diagnose heart disease. ECG301 does not include any automated measurement or analysis of the ECG signal, and does not produce interpretative statements. The ECG recorded is not intended to be used for measurement or analysis of the ECG signal, or for the automated generation of interpretative statements.

Electrocardiograph, models: ECG301, has LCD display with touchscreen and functional buttons. The device can be powered from AC power or through an embedded re-chargeable battery. The device contains built-in thermal dot-matrix recorder for ECG report printing. The Electrocardiograph includes main unit and an AC power cord.

The provided document is a 510(k) premarket notification for an ECG device. It outlines the device's technical characteristics and compares them to a predicate device to demonstrate substantial equivalence. However, it explicitly states in Section 8: "There was no clinical testing performed."

Therefore, I cannot provide the information requested in points 1 through 7, or 9, as no clinical study or performance testing against acceptance criteria was conducted for this specific submission to establish clinical accuracy or improvement with AI assistance. The document focuses on non-clinical tests (safety, EMC, software verification) to demonstrate substantial equivalence to a predicate device.

The requested information regarding acceptance criteria and study data would typically be found in a clinical study report or a different section of a more extensive submission for a device that relies on clinical performance data for clearance.

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

8. The sample size for the training set:
Not applicable. The document states, "There was no clinical testing performed." This implies no training set was used for performance validation in a clinical context for this submission. The device, an "Electrocardiograph," as described, does not appear to incorporate AI or machine learning that would typically require a training set for its core functionality of acquiring ECG signals. It explicitly states, "ECG301 does not include any automated measurement or analysis of the ECG signal, and does not produce interpretative statements."

9. How the ground truth for the training set was established:
Not applicable, as no training set (for clinical performance evaluation) was used or mentioned.

Ask a specific question about this device

Impala is intended to record, store, and transfer a 12-lead resting electrocardiogram (ECG). Impala acquires four standard diagnostic-bandwidth leads (Leads I, II, V2, V4, or Leads I, II, V1, V4). The device derives four standard diagnosticbandwidth, Lead-III and unipolar limb leads aVR, aVF and aVL. The device also synthesizes Leads V1 or V2, V3, V5, V6, which are similar to but not identical to the same leads of a standard diagnostic 12-lead. The 4 synthesized chest leads are not intended for diagnostic use and may fail to show important findings limited to those leads. This device is not a substitute for a diagnostic 12-lead ECG and is contraindicated for use in ruling out any condition (including but not limited to certain ischemia/infarcts, Brugada syndrome) for which the diagnosis may be solely dependent on the synthesized leads.

The device also provides ECG measurements and ECG analysis (rhythm and morphological interpretation) using the acquired leads. The automated ECG analysis results are provisional and should not be used for clinical action if it has not been reviewed by a qualified physician capable of interpreting the ECG signal in the context of the patient's condition. The automated analysis may then be confirmed, edited, or qualified physician. ECG analysis should be used only as an adjunct to clinical history, symptoms, and the results of other non-invasive tests.

Impala is intended for use with patients aged 18 years and older. Impala is intended for use by healthcare professionals, or trained personnel in healthcare facilities (e.g. the doctor's office or hospital) and in acute settings.

Impala is a portable 12-Lead resting electrocardiograph (ECG) device that acquires 4 standard diagnostic-bandwidth ECG leads from a patient (I, II, V1 or V2, V4), derives 4 standard diagnostic-bandwidth leads (aVL, aVR, aVF, III), and using software generates the remaining leads (V2 or V1, V3, V5, V6) to create a 12-Lead ECG recording. The device can be used by healthcare professionals (HCPs) to record a reduced lead, diagnostic-bandwidth, resting ECG, where traditional 10 electrode, 12 lead ECG recorders are not practical to administer due to size, time, or need for specialized clinicians to administer. Examples may include physician offices, and remote and field locations.

The Impala hardware consists of the Impala ECG Module that connects to the Patient Lead Wire. The Patient Lead Wire is a single cable that includes five snap-on electrodes. Impala also consists of a mobile software application, the Impala App that executes on a mobile computing platform (MCP), such as an Apple iPhone smartphone. To record an ECG, the user positions standard off-the-shelf (OTS) ECG gel electrodes on the patient and snaps on the connectors in the Patient Lead Wire on to the electrodes. Impala allows for two options for which set of leads are acquired:

1. Lead Set 1: Leads {I, II, V2, and V4}, with electrodes on RA, LA, LL, V2, V4; and
2. Lead Set 2: Leads {I, II, V1, and V4} with electrodes on RA, LA, LL, V1, and V4.

Impala incorporates AliveCor's Corvair (K231010), a software as a medical device, to provide rhythm analysis, morphological analysis, and ECG measurements. Corvair has two modes of operation, Symptomatic Mode, which is used when the pre-test probability for a specific rhythm is high, and Asymptomatic Mode, which optimizes the PPV, by optimizing the specificity, to detect the various rhythms and morphologies. The user can choose which Impala Lead Set and which Corvair mode of determinations to utilize based on the target clinical application.

The Impala device, an electrocardiograph, underwent nonclinical testing to demonstrate its performance and substantial equivalence to a predicate device.

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

The document does not provide a specific table of acceptance criteria with corresponding performance metrics for the synthesized leads. However, it implicitly states an acceptance criterion related to the similarity of synthesized leads to standard 12-lead ECGs and the device's intended use.

| Acceptance Criteria (Implicit) | Reported Device Performance |
| :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Synthesized leads are similar to corresponding standard 12-leads, and their display is not likely to confuse human interpreters, while acknowledging that significant differences may exist and these leads are not for diagnostic use to rule out certain conditions. | Results suggest that the synthesized leads tend to be similar to the corresponding 12-leads, so the display of these leads is not likely to confuse human interpreter. However, significant differences exist in many cases. Thus, the 4 synthesized chest leads are not intended for diagnostic use and may fail to show important findings limited to those leads. Further, this device is contraindicated for the diagnosis of any condition (including but not limited to certain ischemia/infarcts, Brugada syndrome) for which the diagnosis may be solely dependent on the synthesized leads. |

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

• Sample Size: The test set for the performance of the synthesized leads utilized data from a proprietary AliveCor database described as consisting of 3,000 12-Lead ECGs. Additionally, two public databases (Physionet PTB-XL and the Common Standards for Quantitative Electrocardiography Standard Database (CSEDB) as referenced in IEC 60601-2-25) were used, though their specific sample sizes for this test are not explicitly stated.
• Data Provenance:
  • Proprietary Dataset: The 3,000 ECGs were acquired from clinical patients at the Mayo Clinic over several decades between 1985 and 2010.
  • Public Databases: Physionet PTB-XL and CSEDB. The origin countries are not specified for the public databases but are generally global or multi-center for such resources.
• Retrospective or Prospective: The proprietary dataset from the Mayo Clinic (1985-2010) is clearly retrospective. The nature of the public databases would also be retrospective.

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 mentions that each ECG in the proprietary dataset "has a physician overread confirmed diagnosis with multiple diagnostic codes." It does not specify the number of physicians or their specific qualifications (e.g., years of experience as cardiologists/ECG interpreters) for establishing the ground truth for the test set ECGs.

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

The term "physician overread confirmed diagnosis" suggests that a physician reviewed the ECGs and assigned diagnoses. However, the exact adjudication method (e.g., single physician, consensus of multiple physicians, tie-breaking by a senior expert) is not specified.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

No MRMC comparative effectiveness study involving human readers with and without AI assistance was reported. The testing focused on the bench performance of the synthesized leads and their similarity to standard leads, rather than a human-in-the-loop diagnostic accuracy study. The device's automated ECG analysis (Corvair) is explicitly stated to be "provisional and should not be used for clinical action if it has not been reviewed by a qualified physician." This implies a human-in-the-loop is always required for clinical action, but no study comparing human performance with/without AI assistance was described.

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

Yes, a standalone performance evaluation of the algorithm for lead synthesis was performed. The "Bench performance testing" section specifically describes the evaluation of "the 4 synthesized chest leads generated by Impala from the 4 recorded leads in comparison with the corresponding chest leads of a standard 10-electrode resting 12-lead ECG." This is an algorithm-only evaluation of the lead synthesis component.

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

The ground truth for evaluating the synthesized leads was the corresponding chest leads of a standard 10-electrode resting 12-lead ECG. For the underlying diagnoses of the ECGs in the proprietary dataset, the ground truth was "physician overread confirmed diagnosis with multiple diagnostic codes."

8. The sample size for the training set:

The machine learning model for lead synthesis was trained on a dataset of approximately 110,000 12-Lead ECGs.

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

The training dataset of 110,000 ECGs was "acquired from clinical patients at the Mayo Clinic over several decades between 1985 and 2010. Each ECG has a physician overread confirmed diagnosis with multiple diagnostic codes." This indicates that the ground truth for the training set's clinical characteristics was established by physician overread and confirmed diagnoses. For the lead synthesis part of the training, the direct 12-lead ECG itself would serve as the ground truth against which the synthesized leads were learned.

Ask a specific question about this device