Search Filters

Search Results

Found 3 results

510(k) Data Aggregation

    K Number
    K990093
    Date Cleared
    1999-05-11

    (120 days)

    Product Code
    Regulation Number
    870.1025
    Reference & Predicate Devices
    N/A
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use
    • Assessment of symptoms that may be related to rhythm disturbances of the heart: Patients with . palpitations; The evaluation of arrhythmia's in patients from pediatric to adult age.
    • . Assessment of risk in patients with or without symptoms of arrhythmia.
    • . Assessment of efficacy of Antiarrhythmic therapy.
    • . Assessment of Pacemaker Function.
    • . Assessment of real time ST segment analysis
    • . Assessment of symptomatic or asymptomatic patients, to evaluate for, ischemic heart disease and arrhythmia analysis during exercise testing.
    • . Assessment of transferred SpO2 level date from an MDE Escort Bedside monitor to EasiView for display and alarm.
    • . Assessment of transferred Invasive and Non-Invasive blood pressure, both systolic and diastolic, data from an MDE Escort Bedside monitor to EasiView for display and alarm.
    • Assessment of transferred temperature parameter data from an MDE Escort Bedside monitor to ● EasiView for display and alarm.
    • Assessment of transferred respiration data from an MDE Escort Bedside monitor to Easi View for display.
    • Assessment is for single-hospital environment.
    Device Description

    A Zymed Telemetry monitoring system consists of a series of interface devices to include ECG transmitters, multi-parameter transmitters, a central Telemetry monitoring computerized unit with a strip chart recorder, Easi 5 lead and laser printer. The Zymed central monitor supports up to eight patients for real time cardiac monitoring. The system displays each patient's ECG continuously on the screen while performing real time ECG waveform analysis for all eight patients. This analysis permits immediate detection and classification of abnormal beats, cardiac rhythm disturbances and variations. The system will also display each patient's Oxygen Saturation, Respiration, Non-Invasive Blood Pressure, Invasive Blood Pressure and Temperature.

    Each ECG transmitter's frequency can be programmed to operate at any frequency within the entire VHF band. For US domestic sites, the transmitters will comply with FCC band allocations (174-216 Mhz). In addition to ECG data, the transmitters also detect and transmit cardiac pacemaker information. Other information including transmitter status and individual lead impedance is also transmitted to the Zymed system for overall system safety and efficacy.

    The Zymed system presents the user with a number of clinical tools such as visual and audible alarms for the diagnosis of patients with various heart conditions. The system also provides tools to review a patient's cardiac performance. On-line review mechanisms as well as detailed analysis screens have been designed into the system to facilitate and to enhance the patient's diagnosis and treatment. Features such as individual ECG printouts, multi-channel automatic ST analysis, trend data analysis, and Full Disclosure data further enhance the system's qualities as a valuable and practical clinical tool.

    The Zymed system presents the user with a number of clinical tools such as visual and audible alarms for multi-parameter monitoring of the patient. The Zymed system provides a means to monitor multiple patients from a central monitoring station for ECG, Oxygen Saturation, Non-Invasive Blood Pressure, Invasive Blood Pressure, Temperature, and Respiration.

    The system has the following options available:

    Choice of 4, 6, or 8 bed central monitor Full disclosure screen and printout (full resolution programmable from 0 to 168 hours) Choice of 6 lead sets, based on transmitter capability Full arrhythmia analysis to include multi-channel automatic ST Analysis Laser Printer, print server options Strip Chart Networking

    AI/ML Overview

    The provided text describes the Zymed Telemetry System: Model EasiView Telemetry Central Station Monitor and its performance evaluation for 510(k) clearance. Here's an analysis of the acceptance criteria and study as requested:

    1. Table of Acceptance Criteria and Reported Device Performance

    The document doesn't explicitly state "acceptance criteria" in a quantitative manner for all metrics. However, it implicitly uses the performance of industry-accepted databases and comparison to predicate devices as a benchmark for equivalence. The reported device performance is presented as being "typical" and "nearly identical data" to the comparator.

    Metric (Implicit Acceptance Criteria)Reported Device Performance
    Arrhythmia Analysis
    QRS Sensitivity (SE)"Typical for the real time monitoring environment"
    QRS Positive Predictivity (+P)"Typical for the real time monitoring environment"
    QRS False Positive Rate (FPR)"Typical for the real time monitoring environment"
    Ventricular Sensitivity (SE)"Typical for the real time monitoring environment"
    Ventricular Positive Predictivity (+P)"Typical for the real time monitoring environment"
    Ventricular False Positive Rate (FPR)"Typical for the real time monitoring environment"
    Couplets Sensitivity (SE)"Typical for the real time monitoring environment"
    Couplets Positive Predictivity (+P)"Typical for the real time monitoring environment"
    Couplets False Positive Rate (FPR)"Typical for the real time monitoring environment"
    Short runs Sensitivity (SE)"Typical for the real time monitoring environment"
    Short runs Positive Predictivity (+P)"Typical for the real time monitoring environment"
    Short runs False Positive Rate (FPR)"Typical for the real time monitoring environment"
    Long runs Sensitivity (SE)"Typical for the real time monitoring environment"
    Long runs Positive Predictivity (+P)"Typical for the real time monitoring environment"
    Long runs False Positive Rate (FPR)"Typical for the real time monitoring environment"
    ST Analysis
    Episode Sensitivity (ESE)"Typical for the real time monitoring environment"
    Episode Positive Predictivity (E+P)"Typical for the real time monitoring environment"
    Duration Sensitivity (DSE)"Typical for the real time monitoring environment"
    Duration Positive Predictivity (D+P)"Typical for the real time monitoring environment"
    High Heart Rates"Within recommended guidelines in excess of 300 bpm"
    Noise Performance"Equal to or better than the old system when looking at baseline, electrode or muscle as the cause of noise."

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

    • Sample Size: The document does not explicitly state a specific "sample size" in terms of number of patients or recordings. It refers to the AHA (American Heart Association), MIT (Massachusetts Institute of Technology), and European ST-T (EST) databases. These are public databases of ECG recordings used for algorithm testing, implying a collection of pre-recorded data.
    • Data Provenance:
      • Country of Origin: Not specified in the document, but the names (AHA, MIT, European ST-T) suggest origins in the US and Europe.
      • Retrospective or Prospective: The use of pre-existing, established databases (AHA, MIT, EST) indicates a retrospective study.

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

    The document does not provide information on the number or qualifications of experts used to establish the ground truth within the AHA, MIT, and EST databases. The ground truth for these databases is typically established by expert cardiologists or technicians during the creation of the databases themselves, often through manual annotation and consensus. This information is inherent to the databases, not detailed in this specific submission.

    4. Adjudication Method for the Test Set

    The document does not describe any specific adjudication method (e.g., 2+1, 3+1, none) for the test set. Given the use of established databases, the ground truth labels within those databases would have been pre-adjudicated during their creation.

    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, a Multi Reader Multi Case (MRMC) comparative effectiveness study was not done. The study focuses on the standalone performance of the device's algorithms against established databases and a comparison of the device's technical characteristics and overall performance (e.g., noise handling, high heart rate) to a predicate device ("EasiView (Old) telemetry system" and "MDE Escort Monitor System (Old)"). There is no mention of human readers or AI assistance in the context of improving human reader performance.

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

    Yes, a standalone (algorithm only) performance assessment was done. The performance evaluation was conducted against the AHA, MIT, and European ST-T databases, where the device's algorithms processed these pre-recorded ECGs and generated performance metrics (SE, +P, FPR, ESE, E+P, DSE, D+P) for arrhythmia and ST analysis.

    7. The Type of Ground Truth Used

    The ground truth used was based on expert consensus annotations within the established AHA, MIT, and European ST-T databases. These databases are recognized in the field for providing annotated ECG waveforms that serve as the "true" events against which algorithms are measured.

    8. The Sample Size for the Training Set

    The document does not specify the sample size for any training set. It only discusses the evaluation of the device's performance against the AHA, MIT, and EST databases, which are typically used for testing, not training, of algorithms after their development.

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

    Since the document does not mention the use of a distinct training set or its associated ground truth establishment, this information is not available in the provided text. The submission focuses on the evaluation of the already developed device.

    Ask a Question

    Ask a specific question about this device

    K Number
    K984089
    Date Cleared
    1999-02-16

    (92 days)

    Product Code
    Regulation Number
    870.1025
    Reference & Predicate Devices
    N/A
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use
    • Assessment of symptoms that may be related to rhythm disturbances of the heart: Patients with . palpitations; The evaluation of arrhythmia's in patients from pediatric to adult age.
    • Assessment of risk in patients with or without symptoms of arrhythmia.
    • Assessment of efficacy of Antiarrhythmic therapy. .
    • . Assessment of Pacemaker Function.
    • Assessment of real time ST segment analysis .
    • . Assessment of symptomatic or asymptomatic patients, to evaluate for, ischemic heart disease and arrhythmia analysis during exercise testing.
    • Assessment is for single-hospital environment.
    • Assessment of EASI derived 12-lead ST measurements is recommended for patients that meet the . following parameters.
        1. Ages: 33 to 82 years
        1. Heights: 147 to 185 cm (58 to 73 in)
        1. Weights: 53 to 118 kg (117 to 2611b)
        1. Height to Weight Ratios: 1.41 to 2.99 cm/kg (0.25 to 0.54 in/b.)
    Device Description

    A Zymed Telemetry monitoring system consists of a series of interface devices to include ECG transmitters, a central Telemetry monitoring computerized unit with a strip chart recorder, Easi 5 (12 lead derived), and laser printer. The Zymed central monitor supports up to eight patients for real time cardiac monitoring. The system displays each patient's ECG continuously on the screen while performing real time ECG waveform analysis for all eight patients. This analysis permits immediate detection and classification of abnormal beats, cardiac rhythm disturbances and variations.

    Each ECG transmitter's frequency can be programmed to operate at any frequency within the entire VHF band. For US domestic sites, the transmitters will comply with FCC band allocations (174-216 Mbz). In addition to ECG data, the transmitters also detect and transmit cardiac pacemaker information. Other information including transmitter status and individual lead impedance is also transmitted to the Zymed system for overall system safety and efficacy.

    The Zymed system presents the user with a number of clinical tools such as visual and audible alarms and derived 12 lead display for the diagnosis of patients with various heart conditions. The system also provides tools to review a patient's cardiac performance. On-line review mechanisms as well as detailed analysis screens have been designed into the system to facilitate and to enhance the patient's diagnosis and treatment. Features such as individual ECG printouts, multi-channel automatic ST analysis, trend data analysis, and Full Disclosure data further enhance the system's qualities as a valuable and practical clinical tool.

    The system has the following options available:
    Choice of 4, 6, or 8 bed central monitor
    Full disclosure screen and printout (full resolution programmable from 0 to 168 hours)
    Choice of 6 lead sets, based on transmitter capability
    Full arrhythmia analysis to include multi-channel automatic ST Analysis
    12 lead ECGD
    Laser Printer, print server options
    Strip Chart
    Networking

    AI/ML Overview

    Here's an analysis of the provided text regarding the Zymed Telemetry System, Model EasiView:

    Device: Zymed Telemetry System: Model EasiView Telemetry Central Station Monitor

    1. Table of Acceptance Criteria and Reported Device Performance:

    The document doesn't explicitly define "acceptance criteria" in a quantitative, pass/fail manner. Instead, it states that "Performance was measured against industry accepted AHA (AHA), MIT (MIT) and European ST-T (EST) databases. Results were typical for the real time monitoring environment for the EasiView as targeted." It then lists the types of metrics examined.

    Given this, the table below will present the types of performance metrics used and a general summary of the findings as described in the submission.

    Metric CategorySpecific Metrics ExaminedReported Performance
    Arrhythmia Analysis (QRS, Ventricular, Couplets, Short runs, Long runs)Sensitivity (SE), Positive Predictivity (+P), False Positive Rate (FPR)"Results were typical for the real time monitoring environment for the EasiView as targeted."
    ST Analysis (European ST-T database)Episode Sensitivities (ESE), Episode Positive Predictivity (E+P), Duration Sensitivity (DSE), Duration Positive Predictivity (D+P)"Results were typical for the real time monitoring environment for the EasiView as targeted."
    High Heart Rates (incl. pediatric)Performance at high heart rates"Demonstrated to be within recommended guidelines in excess of 300 bpm."
    Noise PresencePerformance in the presence of baseline, electrode, or muscle noise"Indicates the new system is equal to or better than the old system."
    Overall Comparison to PredicateN/A (implicit comparison across all performance aspects)"Performance data between the two systems shows nearly identical data, and therefore, supports a claim of Substantial Equivalence."

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

    • Sample Size for Test Set: The document refers to "industry accepted AHA (AHA), MIT (MIT) and European ST-T (EST) databases." However, it does not explicitly state the specific number of cases or recordings from these databases used for testing this particular device.
    • Data Provenance: The document implies the use of pre-existing, standardized databases (AHA, MIT, EST). It does not specify the country of origin of the data within these databases or whether the data was retrospective or prospective. Given they are "industry accepted databases," it's highly likely they contain a mix of retrospective data collected over time from various sources.

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

    The document does not provide any information about the number or qualifications of experts used to establish the ground truth for the test sets (AHA, MIT, EST databases). For standardized databases like these, the ground truth is typically established by multiple expert cardiologists or arrhythmia technicians through a consensus process, but this submission does not detail that process for these specific databases.

    4. Adjudication Method for the Test Set:

    The document does not specify an adjudication method (e.g., 2+1, 3+1, none) for the ground truth of the test set. For pre-existing, standardized databases, the adjudication would have been part of the database creation process, but it's not described here.

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size:

    No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done or reported in this 510(k) summary. The submission focuses solely on the device's algorithmic performance against established databases and a comparison of its features and performance to a predicate device, not on human reader improvement with or without AI assistance.

    6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done:

    Yes, a standalone performance study was done. The entire section describing "Performance was measured against industry accepted AHA (AHA), MIT (MIT) and European ST-T (EST) databases" focuses on the algorithm's performance in detecting QRS, Ventricular events, Couplets, Short/Long runs, and ST analysis, without human intervention in the interpretation process.

    7. The Type of Ground Truth Used:

    The type of ground truth used was based on the annotations provided within the industry-accepted AHA, MIT, and European ST-T databases. These databases typically contain expert-adjudicated annotations for cardiac events (e.g., QRS complexes, arrhythmias) and ST segment changes, effectively representing expert consensus.

    8. The Sample Size for the Training Set:

    The document does not specify the sample size for the training set. It only discusses the performance evaluation against established test databases.

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

    The document does not provide information on how the ground truth for the training set (if any distinct training was performed using Zymed's own data) was established. It only refers to using "industry accepted databases" for performance testing. If the device was trained using these same databases, the ground truth would be from those databases, which is typically expert consensus.

    Ask a Question

    Ask a specific question about this device

    K Number
    K980186
    Date Cleared
    1998-10-07

    (260 days)

    Product Code
    Regulation Number
    870.1025
    Reference & Predicate Devices
    N/A
    Predicate For
    N/A
    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use
    • Assessment of symptoms that may be related to rhythm disturbances of the hear. Parients with . palpitations; The evaluation of arrhythmia's in parients from pediatric to adult age.
    • Assessment of risk in pariems with or without symptoms of arrhythmia ♥
    • Assessment of efficacy of Antiarrhythmic therapy. .
    • Assessment of Pacemaker Function. .
    • Assessment of real time ST segment analysis .
    • Assessment of symptomatic or asymptomatic patients, to evaluate for, ischemic heart disease and . arrhythmia analysis during exercise testing
    • Assessment is for single-hospital environment ◆
    Device Description

    A Zymed Telement monitoring system consists of a series of interface devices to include ECG transmitters, a central Telementy monitoring computerized until a surin chart recorder, Easi 5 (12 lead derived), and laser printer. The Zymed central monutor supports up to eight parients for real time curdial monitoring. The system displays each patient's ECG community on the screen while performing real time ECG wave form analysis for all eight patients. Thus analysis permits immediate detection and classification of abnormal beats, cardiac rhythm disturbances and variations.

    Each ECG transmitter's frequency can be programmed to operate at any frequency within the entire VHF band For US domestic sites, the transmitters will comply with FCC band allocations (174-216 Mich. In addition to ECG data, the transmitters also detect and transmit cardiac pacemaker information. Other information including transminer status and individual lead impediated is the Zyned system for overall system safety and efficacy.

    The Zymed system presents the user with a number of clinical tools such as visual and audible alarms and derived 12 lead display for the diagnosis of parients with various heart conditions. The system also provides tools to review a patient's cardiac performance. Con-line review mechanisms as well as detailed analysis screens have been designed into the system to facilitate and to enhance the patient's diagnosis and treatment. Features such as individual ECG printous, multi-channel automatic ST analysis, trend data analysis, and Full Disclosure data further enhance the system's qualities as a valuable and practical clinical

    AI/ML Overview

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

    Acceptance Criteria and Device Performance Study (Zymed EasiView Telemetry System)

    1. Table of Acceptance Criteria and Reported Device Performance

    The document states, "Performance was measured against industry accepted AHA (AHA), MIT (MIT) and European ST-T (EST) databases. Results were typical for the real time monitoring environment for the EasiView as targeted." While specific numerical acceptance criteria (e.g., minimum sensitivity or specificity values) are not explicitly provided in the text, the study implies that the device met the generally understood "typical" performance for real-time monitoring against established cardiac databases. The document also states that performance data between the two Zymed systems (the new EasiView and the predicate) shows "nearly identical data."

    Based on the provided text, the criteria are implicitly derived from the established performance on these benchmark databases.

    Acceptance Criteria (Implicit)Reported Device Performance
    QRS detection performance (Sensitivity, Positive Predictivity, False Positive Rate) against AHA, MIT, and EST databases."Results were typical for the real time monitoring environment for the EasiView as targeted."
    Separate SE, +P, and FPR were "examined for each database and measured for QRS."
    "Performance data between the two systems shows nearly identical data."
    Ventricular arrhythmia detection performance (Sensitivity, Positive Predictivity, False Positive Rate) against AHA, MIT, and EST databases."Results were typical for the real time monitoring environment for the EasiView as targeted."
    Separate SE, +P, and FPR were "examined for each database and measured for... Ventricular."
    "Performance data between the two systems shows nearly identical data."
    Couplets detection performance (Sensitivity, Positive Predictivity, False Positive Rate) against AHA, MIT, and EST databases."Results were typical for the real time monitoring environment for the EasiView as targeted."
    Separate SE, +P, and FPR were "examined for each database and measured for... Couplers."
    "Performance data between the two systems shows nearly identical data."
    Short runs detection performance (Sensitivity, Positive Predictivity, False Positive Rate) against AHA, MIT, and EST databases."Results were typical for the real time monitoring environment for the EasiView as targeted."
    Separate SE, +P, and FPR were "examined for each database and measured for... Short runs."
    "Performance data between the two systems shows nearly identical data."
    Long runs detection performance (Sensitivity, Positive Predictivity, False Positive Rate) against AHA, MIT, and EST databases."Results were typical for the real time monitoring environment for the EasiView as targeted."
    Separate SE, +P, and FPR were "examined for each database and measured for... Long runs."
    "Performance data between the two systems shows nearly identical data."
    High heart rate performance (including pediatric patients)."High heart rates to include pediatric patients were demonstrated to be within recommended guidelines in excess of 300 bpm."
    "Performance data between the two systems shows nearly identical data."
    Performance in the presence of noise (baseline, electrode, muscle)."Performance in the presence of noise indicates the new system is equal to or better than the old system when looking at baseline, electrode or muscle as the cause of noise."
    "Performance data between the two systems shows nearly identical data."
    ST Segment Analysis/Alarm (Implicitly, that its performance is acceptable for the new feature and maintains overall system performance at par with the predicate).The only explicit discussion of this feature is that the "only difference between the two Zymed systems is the addition of automatic Multi-channel ST Analysis/alarm to the algorithm." The statement that overall "performance data between the two systems shows nearly identical data" implies that the ST Analysis feature did not negatively impact the device's overall performance to an unacceptable degree, and it's considered "substantially equivalent."

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

    • Sample size: Not explicitly stated. The document only mentions using "industry accepted AHA (AHA), MIT (MIT) and European ST-T (EST) databases." The exact number of patients or ECGs from these databases used in the test set is not provided.
    • Data provenance: The data came from "industry accepted AHA (AHA), MIT (MIT) and European ST-T (EST) databases." These are well-known, publicly available, and extensively used retrospective ECG databases from various institutions. The specific countries of origin for each database are not mentioned in this document, but they are generally international in scope (e.g., MIT/BIH Arrhythmia Database from the US, European ST-T Database primarily from Europe). The data is retrospective.

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

    Not explicitly stated. For established public databases like AHA, MIT, and EST, the ground truth is typically established through a consensus of multiple cardiologists or expert reviewers, but the specific number and qualifications are not mentioned in this document.

    4. Adjudication method for the test set

    Not explicitly stated. For established public databases, the adjudication method for ground truth is usually a consensus process (e.g., multiple experts reviewing and agreeing, often with a tie-breaker if needed), but this document does not detail it.

    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, a multi-reader, multi-case (MRMC) comparative effectiveness study focusing on human reader improvement with AI assistance was not done. This device is a "Telemetry Central Station Monitor" performing "real time ECG wave form analysis" for "immediate detection and classification of abnormal beats, cardiac rhythm disturbances and variations." The study compared the device's performance against established databases and against its predicate device, not the performance of human readers using the device.

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

    Yes, a standalone performance study was done. The document states, "Performance was measured against industry accepted AHA (AHA), MIT (MIT) and European ST-T (EST) databases." This describes the algorithm's direct performance against annotated databases, without human intervention in the loop during the measurement of these specific metrics (SE, +P, FPR for various beat types and conditions). The comparison to the predicate device also focuses on the algorithmic performance.

    7. The type of ground truth used

    The ground truth used for the test sets (AHA, MIT, EST databases) would be expert consensus annotations. These databases are meticulously reviewed and labeled by cardiology experts to establish the "true" events (e.g., QRS complexes, ventricular beats, ST segment changes) against which algorithms are benchmarked.

    8. The sample size for the training set

    Not explicitly stated. The document refers to the evaluation being performed against the AHA, MIT, and EST databases, which are typically used for testing and benchmarking rather than for training a new algorithm. It's possible the new "automatic Multi-channel ST Analysis/alarm" algorithm was trained on proprietary data or a subset of these large databases, but the training set size is not provided.

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

    Not explicitly stated. Given that the training set size is not provided and the primary databases mentioned are benchmark testing databases, the ground truth establishment method for training data is unknown from this document. However, for medical algorithms, ground truth for training data would typically be established by expert review (e.g., cardiologists annotating ECG recordings).

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1