Search Results

EKG-PLUS II Software is a Window-based program intended to receive, display, store and print out in network environment the ECG data monitored, recorded and analyzed by a Bionet's ECG device-CardioCare-2000 (Formerly, CardioCare EKG-2000) or CardioTouch-3000. The software can also store the ECG data as JPEG file.

The EKG-PLUS II Software is a program which receives, displays, stores and prints out in network environment the ECG data monitored, recorded and analyzed by a Bionet's ECG device.

The provided text describes a 510(k) submission for the EKG-PLUS II Software. However, it does not include detailed information regarding discrete acceptance criteria, a specific study proving the device meets those criteria, sample sizes for test/training sets, expert qualifications, or ground truth methodologies that would typically be found in a performance study section.

Based on the provided text, here's what can be extracted and what is missing:

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

The document states: "The performance of the EKG-PLUS If Software was comprehensively tested with the CardioCare-2000 and CardioTouch-3000. All functions as defined in the specifications were completely verified and validated."

This indicates that internal specifications for the software's functions served as the acceptance criteria. However, the document does not provide specific quantitative acceptance criteria (e.g., accuracy thresholds, sensitivity/specificity targets) or the reported performance metrics against those criteria. It only states that the functions were "completely verified and validated."

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

This information is not provided in the given text.

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 given text. The device is an ECG analysis system, implying it processes data from ECG devices. While it might perform some interpretive functions (like its predicate), the text does not detail a study where human experts independently establish a ground truth to evaluate the device's diagnostic accuracy.

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

This information is not provided in the given text.

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

There is no mention of an MRMC comparative effectiveness study or any assessment of human reader improvement with or without AI assistance. The device is described as "EKG-PLUS II Software ECG Analysis System," an "algorithm only" product for displaying, storing, and printing ECG data, and performing analysis. It's not presented as an AI-powered assistive tool for human interpretation in the context of this submission.

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

Yes, the described "EKG-PLUS II Software" is a standalone algorithm as it is an "ECG Analysis System" intended to "receive, display, store and print out in network environment the ECG data monitored, recorded and analyzed by a Bionet's ECG device." The "Non-clinical tests" section focuses on the performance of the software itself in conjunction with the specified ECG devices. The conclusion states it is "as effective, and performs as well as the CARDIOVIEW ECG Interpretive Software" (predicate device), implying a standalone, algorithmic comparison.

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

The document states "All functions as defined in the specifications were completely verified and validated." This implies an engineering-centric verification and validation against internal functional and technical specifications, rather than a clinical ground truth like expert consensus on diagnostic interpretations, pathology, or outcomes data. If there were interpretive capabilities, the ground truth methodology for those specific functions is not detailed.

8. The sample size for the training set

This information is not provided in the given text.

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

This information is not provided in the given text. As a pre-2009 submission, it's less likely to extensively detail machine learning training sets in the way more recent AI/ML device submissions would. The "analysis" capabilities are likely based on established ECG interpretation algorithms rather than a trained machine learning model in the contemporary sense.

Ask a specific question about this device

CardioView32 Review Module is a Window's based program intended to be called from a host application/database in a Hospital or in a Physician's Office.

CardioView32 Review Module receives, analyzes, displays, stores and prints ECG *.scp files generated from a standard 12-lead ECG recording. Cardio View 32 Review Module provides interpretive statements for which the physician renders his/her own medical opinion.

• Patient Population: Male/Female, Adults .
• Environment of Use: Hospital and Clinic .
• Prescription Device by a Physician ●

CardioView32 Review Module is a Window's based program intended to be called from a host application/database in a Hospital or in a Physician's Office.

CardioView32 Review Module receives, analyzes, displays, stores and prints ECG *.scp files generated from a standard 12-lead ECG recording. Cardio View 32 Review Module provides interpretive statements for which the physician renders his/her own medical opinion.

The provided document describes a 510(k) premarket notification for the CardioView 32 Review Module, an ECG interpretive software. The focus of the submission is to demonstrate substantial equivalence to a previously cleared predicate device, the CardioView 3000.

Here's an analysis of the acceptance criteria and study information, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of "acceptance criteria" with quantitative performance metrics for diagnostic accuracy (e.g., sensitivity, specificity for specific ECG abnormalities) for the device. Instead, the "Performance Standards" section indicates compliance with a general standard:

The submission relies on demonstrating that the modified CardioView 32 Review Module is as safe and effective as the unmodified CardioView 3000 predicate device, largely by showing that the fundamental interpretation algorithm (Cardionics Algorithm) remains the same, and that other modifications are related to software functionality, display, and operating system compatibility, rather than core diagnostic performance.

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

The document does not provide any specific information regarding a test set (e.g., ECG recordings used for validation), its sample size, or the provenance of the data (e.g., country of origin, retrospective or prospective). The "Summary of Performance Testing" only states that the device "has been tested or found otherwise to comply with applicable sections of the following standards: AAMI EC11-1991 (R/2007)." This suggests compliance through technical evaluation against the standard's requirements rather than a clinical performance study using a medical dataset.

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

Since no specific test set or clinical performance study is described, there is no information about the number of experts used to establish ground truth or their qualifications.

4. Adjudication Method for the Test Set

Again, given the absence of a described test set or clinical performance study, there is no information regarding an adjudication method.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

No, a multi-reader multi-case (MRMC) comparative effectiveness study is not mentioned or described in the provided document. The submission focuses on substantial equivalence based on technical specifications and adherence to a general standard, rather than a clinical comparison of human readers with and without AI assistance.

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

The document states that the CardioView 32 Review Module "provides interpretive statements for which the physician renders his/her own medical opinion." This indicates that the software is not intended for standalone diagnostic use; it produces interpretations that are reviewed by a physician. While the underlying "Cardionics Algorithm" performs the primary interpretation, the submission does not detail a standalone performance study where the algorithm's output alone was assessed against a ground truth without human review. The claim is that the algorithm itself is the same as the predicate.

7. The Type of Ground Truth Used

As there is no detailed performance study described, there is no explicit mention of the type of ground truth used. If the predicate device's algorithm was validated, it would likely have been against expert consensus or possibly outcomes data, but this submission does not provide those details for the modified device.

8. The Sample Size for the Training Set

The document does not provide any information about the training set sample size. The "Cardionics Algorithm" is a pre-existing component, and no details regarding its development or training are included in this 510(k) summary.

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

Similar to the above, the document does not provide any information on how the ground truth for the algorithm's training set was established, as the algorithm itself pre-dates this submission and is considered a "Same" component as the predicate device.

Ask a specific question about this device

To analyze multi-channel ECG signals from adult and pediatric patients 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.

Where the clinician decides to evaluate the electrocardiogram of adult and pediatric patients as part of decisions regarding possible diagnosis, potential treatment, effectiveness of treatment or to rule-out causes for symptoms.

The Philips ECG algorithm Software Release PH100B is a modification to a previously cleared device. The modification is a change that provides interpretive analysis capability for additional posterior and right sided heart lead placement locations beyond the standard lead placements used with a 12 lead ECG. The modification also incorporates a subset of the diagnostic statement changes recommended in the Journal of the American College of Cardiology Volume 49, No.10, 2007, pages 1128-1135. "Recommendations for the Standardization and Interpretation of the Electrocardiogram".

The provided text does not contain detailed information about specific acceptance criteria or the study used to prove the device meets these criteria. It focuses on regulatory aspects, substantial equivalence to predicate devices, and general statements about verification and validation.

However, based on the input provided, here's what can be extracted and inferred:

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

This information is not provided in the given text. The document states "Verification, validation, and testing activities establish the performance, functionality, and reliability characteristics of the new algorithm with respect to the predicate," but it does not specify what those performance characteristics are (e.g., sensitivity, specificity for certain conditions) or what the acceptance criteria for those characteristics were.

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

The text mentions "Testing involved use of standard ECG databases," but it does not specify the sample size of the test set or the data provenance (e.g., country of origin, retrospective or prospective nature).

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

This information is not provided in the given text.

4. Adjudication method for the test set

This information is not provided in the given text.

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 text mentions that "Results from interpretive ECG analysis programs are used as in an advisory nature. Physicians are required to over read each ECG report and also consider the ECG waveforms, the patient's clinical history before agreeing with the ECG analysis program statement." This implies that the device is intended to be used with human-in-the-loop. However, a formal MRMC comparative effectiveness study to quantify human reader improvement with versus without AI assistance and its effect size is not explicitly described in the provided text.

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

The text strongly emphasizes the advisory nature of the algorithm and the requirement for physician over-read. It states, "Results from interpretive ECG analysis programs are used as in an advisory nature. Physicians are required to over read each ECG report and also consider the ECG waveforms, the patient's clinical history before agreeing with the ECG analysis program statement." This suggests that the device is not intended for standalone use, and thus, a standalone performance study in the context of clinical decision-making is unlikely to have been performed or prioritized for this regulatory submission. However, the "verification, validation, and testing activities" would have evaluated the algorithm's performance on its own before integrating it into the system.

7. The type of ground truth used

The text mentions "standard ECG databases." For ECG interpretation algorithms, the ground truth for such databases is typically established by expert consensus of cardiologists or other qualified physicians, often based on a combination of ECG findings and clinical context. However, the specific method of ground truth establishment is not detailed in the provided text.

8. The sample size for the training set

The text mentions "standard ECG databases" for testing but does not specify the sample size for the training set of the algorithm.

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

The text mentions using "standard ECG databases" for testing, but it does not describe how the ground truth for the training set was established. It's generally assumed that algorithms trained on such databases would have their ground truth established by expert consensus or a similar rigorous annotation process, but this is not explicitly stated for this device's training data.

Ask a specific question about this device

The CARDIOTOUCH-3000 is intended to be used under the direct supervision of a licensed healthcare practitioner. The CARDIOTOUCH-3000 is intended to be used by trained operators in a hospital or medical professional's facility environment to record ECG signals from surface electrodes. The device is intended to acquire, analyze, display, and record electrocardiographic information from adult population. The device is not intended for home use. The device is not designated for intracardial use.

As an electrocardiograph with 12-channel, CARDIOTOUCH-3000 does not only provide parameters and diagnose a patient automatically for patient's electrocardiogram, but also it improves chart management by printing information on an operator as well as on the patient. Furthermore, for the convenience of operators, it is designed so that an operator needs to press a button once to let the machine measure and record patient's electrocardiogram, apply a filter, extract parameters, diagnose a patient automatically then print out a result on an A-4- size report. In addition, the built-in battery helps an operator carry and use CARDIOTOUCH-3000 easily and conveniently for a hospital on wheel and an emergency.

Acceptance Criteria and Device Performance for CARDIOTOUCH-3000

This submission for the CARDIOTOUCH-3000 is a "SPECIAL type" 510(k), claiming substantial equivalence to the predicate device, Bionet's EKG-2000 Cardio Care (K011328). The submission focuses on comparing technological characteristics rather than presenting new clinical study data with specific acceptance criteria. Therefore, the "acceptance criteria" are implicitly met by demonstrating identical or similar performance to the legally marketed predicate device.

Here's a breakdown based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly list quantitative acceptance criteria in terms of performance metrics (e.g., sensitivity, specificity, accuracy) for a diagnostic output. Instead, it relies on demonstrating technological equivalence to the predicate device. The "acceptance criteria" are therefore qualitative statements of similarity or identicality to the predicate device across various features and performance aspects.

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

The document does not describe a specific test set, sample size, or data provenance for evaluating the CARDIOTOUCH-3000's performance against clinical acceptance criteria. The submission relies on demonstrating substantial equivalence to a predicate device based on technological characteristics and shared intended use. This type of 510(k) (Special 510(k)) often focuses on design control changes and verification/validation activities to ensure the new device meets its own specifications, which are aligned with the predicate. There is no mention of a clinical performance study using patient data to prove diagnostic accuracy.

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

As no specific test set or clinical performance study for diagnostic accuracy is described, there is no information regarding experts, ground truth establishment, or their qualifications.

4. Adjudication Method for the Test Set

Since no specific test set or clinical performance study is described, there is no information regarding an adjudication method.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, an MRMC comparative effectiveness study was not done or at least not described in the provided summary. The submission focuses purely on demonstrating technological equivalence to a predicate device, not on comparing human reader performance with or without AI assistance. The device is a standalone ECG analysis system, not an AI-assisted interpretation tool for human readers in the context of this submission.

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

The device itself includes "automatic diagnosis" as a feature ("Twenty-five diagnoses are available through auto diagnosis"). However, the document does not describe a standalone performance study for this automatic diagnosis algorithm with explicit metrics (e.g., sensitivity, specificity, accuracy against a reference standard). The performance claims are limited to the technical specifications of ECG signal acquisition and analysis, stating they are "Identical" to the predicate.

7. The Type of Ground Truth Used

As no specific clinical performance study for diagnostic accuracy is described, there is no mention of the type of ground truth used. The "ground truth" for the submission is effectively the established performance and safety profile of the predicate device.

8. The Sample Size for the Training Set

The document does not mention a training set or its sample size. ECG analysis algorithms can be developed using large datasets, but this information is not part of this 510(k) summary, which focuses on hardware and basic functionality equivalence.

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

Since no training set is mentioned, there is no information on how its ground truth was established.

Ask a specific question about this device

Ask a specific question about this device

The Cardio-Card interpretation program analyzes and reports abnormal and normal ECGs and possible classifications of what kind of abnormals may have been detected from ECG data sent to it. The ECG statements reported assist the user in knowing what problems may exist in the ECG. These statements are to be overread by a Physician trained in the art of ECG interpretation as no automated analysis is completely reliable.

It is intended to be used by or on the order of a physician or similarly qualified health care professional in any environmental setting that the ECG acquisition device is suitable for. These environments include hospitals, physician offices, and clinical settings.

It is intended to be used on the adult patient population.

Cardio-Card Interpretive System I

This is a 510(k) clearance letter from the FDA for a device called "Cardio-Card Interpretation System I". This type of letter generally does not contain detailed study information, acceptance criteria, or performance metrics. It primarily states that the device has been found substantially equivalent to a legally marketed predicate device.

Therefore, based on the provided text, I cannot extract the requested information. The document focuses on regulatory approval and provides indications for use, but no specific performance study data, acceptance criteria, sample sizes, expert qualifications, or ground truth details.

Here's a breakdown of why each point cannot be addressed:

1. A table of acceptance criteria and the reported device performance: Not present in the document.
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective): Not present 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): Not present in the document.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not present 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: Not present in the document.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The document mentions "automated analysis" and states "These statements are to be overread by a Physician trained in the art of ECG interpretation as no automated analysis is completely reliable," implying it's not standalone or requires human oversight. However, no specific study proving this or measuring standalone performance is provided.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): Not present in the document. It only states the system "analyzes and reports abnormal and normal ECGs and possible classifications."
8. The sample size for the training set: Not present in the document.
9. How the ground truth for the training set was established: Not present in the document.

To obtain this information, one would typically need to refer to the full 510(k) submission (if it's publicly available and unredacted), or scientific publications related to the device's validation.

Ask a specific question about this device

The OxyconAlpha with option ECG is a software-driven, medical device for exercise measurements, including ECG ST Segment Analysis and/or ECG Stress Analysis. It measures the human response to increasing workloads with emphasis on the gas exchange parameters. Measurements include ventilation, oxygen uptake, carbon dioxide excretion, heart rate and derived parameters. The results of the tests, including the ECG wave forms, can be viewed on the computer screen and can be printed during the test. The test results can be saved on the computer hard disk for further referral or report generation purposes.

The OxyconAlpha with option ECG interfaces to a testsubject via a mouthpiece or a face mask and ECG electrodes. The OxyconAlpha with option ECG interfaces to a peripheral ergometer or treadmill. The patient population is 4 age and older,

The OxyconAlpha with option ECG is capable of performing computerized ECG interpretation during resting condition.

The intended use locations are either in a physician office, hospital exercise rehabilitation facilities, or similar areas. It is intended to be used by or on the order of a physician or similar qualified health care professional. This device is intended for use in the hospital environment, physician's office, or similar settings. This device is not intended for home use.

The OxyconAlpha with option ECG is a software-driven, medical device for exercise measurements, including ECG ST Segment Analysis and/or ECG Stress Analysis. It measures the human response to increasing workloads with emphasis on the gas exchange parameters. Measurements include ventilation, oxygen uptake, carbon dioxide excretion, heart rate and derived parameters. The results of the tests, including the ECG wave forms, can be viewed on the computer screen and can be printed during the test. The test results can be saved on the computer hard disk for further referral or report generation purposes.

The OxyconAlpha with option ECG interfaces to a testsubject via a mouthpiece or a face mask and ECG electrodes. The OxyconAlpha with option ECG interfaces to a peripheral ergometer or treadmill.

This document is a marketing clearance letter for a medical device (OxyconAlpha with Option ECG) and does not contain the specific information required to complete your request about acceptance criteria and a study that proves the device meets those criteria.

Therefore, I cannot provide:

1. A table of acceptance criteria and the reported device performance.
2. Sample size used for the test set and data provenance.
3. Number of experts used to establish ground truth and their qualifications.
4. Adjudication method.
5. MRMC comparative effectiveness study results.
6. Standalone algorithm performance.
7. Type of ground truth used.
8. Sample size for the training set.
9. How ground truth for the training set was established.

This letter primarily focuses on the FDA's determination of substantial equivalence (510(k) clearance) to a legally marketed predicate device, indicating that the device can be marketed. It describes the device's intended use and classification but does not detail the specific performance studies and their results.

Ask a specific question about this device

The CASE 8000 exercise testing system is a diagnostic device intended to monitor and record electrocardiographic data from the patient during exercise, as well as perform resting ECG analysis.

The intended use of the CASE 8000 exercise testing system is to acquire, process, record, archive, analyze, and output data during a period of physiologic stress or during a resting ECG condition. The CASE 8000 exercise testing system has the ability to calculate prognostic scores. A user selectable option can provide printout of prognostic scores on select reports. A vector loops report is also available.

Ancillary functions include control of an external device (typically a treadmill or ergometer) and communications with centralized electronic/digital storage system.

This device uses a computerized analysis program, which can be used as a tool in ECG tracing interpretation.

The device records 12 lead ECG data taken in resting and exercise modes, as well as real-time rhythm and median morphology recordings. The device can perform a 12 lead interpretive analysis on the resting ECG, providing the user with statements of morphology, rhythm and conduction.

The CASE 8000 exercise testing system is intended to be used by trained operators under the direct supervision of a licensed health care practitioner when exercise or resting ECG records are required.

The CASE 8000 exercise testing system is intended to be used primarily in hospital based exercise testing laboratories, but can be used in clinics, physician offices, outreach centers or wherever exercise testing is performed. This device is not intended for use with high frequency surgical units.

The CASE 8000 system is not intended to be used as a vital signs physiological monitor.

This equipment will not cause abnormal operation of a patient's cardiac pacemaker or other electronic stimulator.

The CASE 8000 exercise testing system is a PC-based device capable of being operated as a stand-alone system or in conjunction with a centralized electronic/digital storage system such as the MUSE CV Information System - K980495 (MUSE). Major components include a CPU, display, modem, mouse, printer, keyboard, power supply, acquisition module and a cart. It is intended to be used primarily in hospital based exercise testing laboratories. It can also be used in clinics and outreach centers or wherever exercise testing is performed.

The primary application of the device is to acquire, process, record, archive, analyze and output data during a period of physiologic stress or during rest. Ancillary functions include control of an external exercise device, typically a treadmill or ergometer, and communication with a centralized electronic/digital storage system such as the MUSE.

When used in conjunction with MUSE, the CASE 8000 exercise testing system is capable of bringing computerized information management to the exercise laboratory. Demographic and order information can be downloaded to the system to simplify order management and data entry operation. Results from previous tests can be reviewed on the system after network download from the MUSE. New results can be quickly sent to the MUSE for long term storage.

The provided text describes the GE Marquette Medical Systems' CASE 8000 exercise testing system and its 510(k) submission (K991014) to the FDA. However, the document does not contain specific acceptance criteria or a detailed study report that quantitatively proves the device meets such criteria.

The "Test Summary" section {2} mentions general quality assurance measures applied during development but lacks concrete metrics, study designs, sample sizes, or performance results. The "Conclusion" states "The results of these measures demonstrate that the CASE 8000 exercise testing system is as safe, as effective, and performs as well as the predicate devices," but provides no data to support this.

Therefore, I cannot fulfill your request for a table of acceptance criteria and reported device performance, nor can I provide details about sample sizes, data provenance, expert ground truth establishment, adjudication methods, MRMC studies, standalone performance, or training set information.

Based on the provided text, the following information is either not available or only vaguely mentioned:

1. Table of acceptance criteria and the reported device performance: Not provided. The document states the device "complies with the voluntary standards as detailed in Section 9 Specific Standards and Guidances of this submission" and that "the results of these measures demonstrate that the CASE 8000 exercise testing system is as safe, as effective, and performs as well as the predicate devices." However, no specific performance metrics or their comparison against acceptance criteria are presented.
2. Sample sized used for the test set and the data provenance: Not provided.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not provided.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set: Not provided.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and the effect size of how much human readers improve with AI vs. without AI assistance: Not provided. The device performs "12SL Analysis" which is a computerized interpretive analysis on resting ECGs, but no MRMC study details are given. The document does not describe AI assistance for human readers.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: The device performs a "12 lead interpretive analysis on the resting ECG" {2}. This implies standalone algorithmic performance, but no specific study or metrics for this standalone performance are provided.
7. The type of ground truth used: Not explicitly stated. For the 12-lead interpretive analysis, it would typically be compared against expert cardiologist interpretations, but this is not confirmed or detailed in the document.
8. The sample size for the training set: Not provided.
9. How the ground truth for the training set was established: Not provided.

Ask a specific question about this device

The MAC Series Resting ECG Analysis Systems (Includes the MAC PC, MAC 6, MAC VU, MAC 8, and MAC 5000) are intended to acquire, analyze, display, and record electrocardiographic information from adult and pediatric populations. Basic systems deliver 3, 6, 12, or 15 lead interpretive analysis, vector loops, and can be upgraded to provide software analysis options such as high resolution signal averaging of QRS and P wave portions of the electrocardiogram. Transmission and reception of ECG data to and from a central ECG cardiovascular information system is optional.

The MAC Series is intended to be used under the direct supervision of a licensed healthcare practitioner, by trained operators in a hospital or medical professional's facility.

The Mac Series consists of electrocardiograph models designed to acquire, analyze, display, and record ECG signals from surface ECG electrodes. The devices consist of two basic components: the processing unit and patient acquisition module. Models provide rechargeable battery operation and/or optional trolley for transporting the equipment.

The MAC 5000 can deliver 3, 6, 12, or 15 lead ECG's, 12 lead interpretive analysis, vector loops, and can be upgraded to provide software analysis options such as high resolution signal averaging of ORS and P wave portions of the electrocardiogram. Transmission and reception of ECG data to and from a central ECG cardiovascular information system is optional.

The provided document describes a 510(k) submission for the GE Marquette Medical Systems MAC Series Resting ECG Analysis Systems. This submission is focused on demonstrating substantial equivalence to predicate devices, rather than a de novo approval requiring a detailed clinical study with pre-defined acceptance criteria and reported performance metrics. Therefore, the information typically requested regarding acceptance criteria and a study proving device adherence to these criteria is not fully available in this type of submission.

However, based on the provided text, we can infer some aspects and extract relevant information.

1. Table of Acceptance Criteria and Reported Device Performance

The submission does not explicitly state quantitative acceptance criteria or a dedicated performance study with specific metrics like sensitivity, specificity, or accuracy that would be typical for a de novo device. Instead, the focus is on the device's technological characteristics not raising "new questions of safety or effectiveness" compared to predicate devices. This indicates that the performance is implicitly expected to be at least equivalent to the predicate devices.

The "Test Summary" section states: "The MAC Series complies with the voluntary standards as detailed in Section 9 Test Summary." This implies that the device was tested against applicable industry standards, and compliance with these standards serves as the primary "acceptance criteria" for this type of submission. Without Section 9, the specific standards and their associated performance thresholds cannot be detailed.

Inferred "Acceptance Criteria" (Compliance with Predicate Devices and Standards):

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

The provided text does not specify a distinct "test set" sample size or its data provenance (country of origin, retrospective/prospective). This is common for 510(k) submissions focusing on substantial equivalence, where the "study" often involves comparison to predicate device specifications and internal verification/validation testing against standards, rather than a large-scale clinical trial with patient data for performance metrics.

For an ECG analysis system, testing would typically involve a database of ECG recordings used to validate the accuracy of the interpretive algorithms, but details of such a dataset are not provided here.

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

The submission does not detail the number or qualifications of experts used to establish ground truth for any specific "test set." The device is intended to provide "computerized ECG analysis program which can be used as a tool in ECG tracing interpretation" and explicitly states: "All computer-generated tracings should be overread by a qualified physician." This indicates that the ultimate "ground truth" in clinical practice for individual patient care rests with a qualified physician.

If the underlying "Marquette 12SL Analysis Program" (K964750) predicate device underwent rigorous validation, that would have involved expert consensus for ground truth, but those details are not in this document.

4. Adjudication Method for the Test Set

No details on an adjudication method (such as 2+1 or 3+1) are provided, as a specific "test set" and a corresponding expert-adjudicated ground truth study are not explicitly described in this 510(k) summary.

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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study evaluating how much human readers improve with AI vs. without AI assistance is not mentioned or described in the provided text. This type of study is more common for novel diagnostic algorithms where human-AI interaction is being specifically assessed. The MAC Series system is presenting an "interpretation" to be "overread by a qualified physician," implying a supportive role rather than an assistive AI system in the modern sense that mandates MRMC studies.

6. Standalone Performance Study (Algorithm Only)

While the device incorporates a "computerized ECG analysis program" (likely the Marquette 12SL Analysis Program), the provided text does not describe a standalone performance study (i.e., algorithm only, without human-in-the-loop performance) for this specific 510(k) submission.

The fact that it mentions "Marquette 12SL Analysis Program - K964750" as a predicate device suggests that the performance of the core analysis algorithm would have been established during the clearance of K964750. This current submission likely concerns updates to the hardware (MAC Series devices) and the integration of this established analysis program, ensuring that the integration does not degrade its performance.

7. Type of Ground Truth Used

The type of ground truth used for any internal validation of the "computerized ECG analysis program" in the underlying 12SL program is not specified in this document. For ECG interpretive algorithms, ground truth is typically established through:

• Expert Consensus: A panel of cardiologists independently reviewing ECGs and patient records to reach a consensus diagnosis.
• Clinical Outcomes/Follow-up: Correlating ECG findings with subsequent clinical events or diagnoses.
• Pathology/Other Definitive Tests: For certain conditions, correlation with more definitive diagnostic procedures.

The caution explicitly stating that the "computerized interpretation is only significant when used in conjunction with clinical findings" and must be "overread by a qualified physician" underscores that the device's output is an aid, not a definitive diagnosis, and relies on clinical context and expert review for ultimate truth.

8. Sample Size for the Training Set

The document does not provide any information regarding the sample size used for the training set of the ECG analysis algorithms. As noted, this is a 510(k) for a device incorporating an existing analysis program (12SL), so details about the training of that program would reside with its original submission (K964750) or internal development documentation.

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

Similar to the training set sample size, the method for establishing ground truth for any training set used for the ECG analysis algorithms is not described in this document. This information would be specific to the development and validation of the "Marquette 12SL Analysis Program" (K964750) that is integrated into the MAC Series systems.

Ask a specific question about this device

The ECG-9010K and ECG-9020K Cardiofax GEM electrocardiographs are intended for medical purposes to process the electrical signals transmitted through two or more electrocardiograph electrodes to produce a visual display and/or to prepare a record of the electrical signals produced by the heart.

For non-interpretive applications, the ECG-9010K and ECG-9020K are intended for use with a full range of patient populations as determined by a clinician. The devices also provide an interpretive ECG program intended for use with patients age 3 years to adult.

The interpretation program is intended to provide an assessment of ECG waveform rhythm and morphology to assist the physician in diagnosis. Assessments provided by the interpretation program are not intended as the sole basis for diagnosis. All assessments provided by the interpretation program are recommended for review by qualified physicians trained in electrocardiography.

The ECG-9010K and ECG-9020K have been classified as Class III by the Division of Cardiovascular. Respiratory, and Neurological Devices and the Cardiovascular Device Classification Panel under 21 CFR Part 870.2340 "Electrocardiograph" as per 74 LOS.

Common names for the ECG-9010K and ECG-9020K include ECG and electrocardiograph.

Nihon Kohden's model ECG-9010K and ECG-9020K are intended for medical purposes to process the electrical signals transmitted through two or more electrocardiograph electrodes and to produce a visual display and/or prepare a record of the electrical signals produced by the heart.

The ECG-9010K and ECG-9020K devices comply with the IEC 601-1 standard including subclause 56.3(c) implemented by 21 CFR Part 868 Performance Standard for Electrode Lead Wires and Patient Cables. To date, no other special controls or performance standards are known or established for these devices. The devices are also in compliance with the following voluntary industrial standards: IEC 601-2-25 and CSA 601-1. Defibrillator Discharge Protection: Class I, Type CF.

The ECG-9010K and ECG-9020K are not intended to be sterile.

The devices were determined to be non-contacting. Therefore, good laboratory practice studies were not required per 21 CFR part 58.

The ECG-9010K and ECG-9020K were subjected to electromagnetic, environmental, safety and performance testing procedures. These tests verified the operation of the device. Software validation is performed to test the operation of the device software. The results confirm that the device performs within specifications.

The provided text describes the 510(k) notification for the Nihon Kohden ECG-9010K and ECG-9020K Cardiofax GEM electrocardiographs. However, this document does not contain the detailed information needed to completely fill out all sections of your request regarding acceptance criteria and the study proving device performance.

Here's what can be extracted and what is missing:

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

The document states: "The ECG-9010K and ECG-9020K were subjected to electromagnetic, environmental, safety and performance testing procedures. These tests verified the operation of the device. Software validation is performed to test the operation of the device software. The results confirm that the device performs within specifications."

However, specific acceptance criteria values and the reported performance values are not provided in this document. It only confirms that tests were done and the device met its specifications.

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

This information is not explicitly provided in the document. The document mentions "performance testing procedures" but doesn't specify the details of the test set for these procedures, especially for the interpretive ECG program.

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. For the "interpretive ECG program," it states that "All assessments provided by the interpretation program are recommended for review by qualified physicians trained in electrocardiography," but it doesn't describe how ground truth was established for the device's validation.

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

This information is not provided.

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. The document describes a standalone device that provides an interpretive program but does not detail comparative studies with human readers or AI assistance.

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

Yes, the document implies standalone performance testing for the device's "interpretive ECG program" as it is designed to provide an assessment. It states, "The interpretation program is intended to provide an assessment of ECG waveform rhythm and morphology to assist the physician in diagnosis." It also clarifies: "Assessments provided by the interpretation program are not intended as the sole basis for diagnosis. All assessments provided by the interpretation program are recommended for review by qualified physicians trained in electrocardiography." This suggests an algorithm-only assessment component.

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

This information is not provided. While the device provides an interpretation, how the "ground truth" was established for validating this interpretation is not described.

8. The sample size for the training set

The document is a 510(k) summary for a medical device and does not delve into the specifics of the training data used for the interpretive algorithm. This information is not provided.

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

Similar to point 8, this information is not provided in the 510(k) summary.

Summary of available information vs. missing information:

In conclusion, this 510(k) document confirms that the device underwent various tests and met its specifications, and it has an interpretive ECG program. However, it lacks the detailed study methodology, sample sizes, and specific performance metrics that would typically be found in a detailed validation study report.

Ask a specific question about this device