Search Results

Fetal & Maternal Monitor (Model: F15A, F15A Air) is intended for providing Non-Stress testing or fetal monitoring for pregnant women from the 28th week of gestation. It is intended to be used only by trained and qualified personnel in antepartum examination rooms, labor and delivery rooms.

Fetal & Maternal Monitor (Model: F15A, F15A Air) is intended for real time monitoring of fetal and maternal physiological parameters, including non-invasive monitoring and invasive monitoring:

Non-invasive physiological parameters:

• Maternal heart rates (MHR)
• Maternal ECG (MECG)
• Maternal temperature (TEMP)
• Maternal oxygen saturation (SpO2) and pulse rates (PR)
• Fetal heart rates (FHR)
• Fetal movements (FM)
• FTS-3

Note: SpO2 and PR are not available in F15A Air.

Invasive physiological parameters:

• Uterine activity
• Direct ECG (DECG)

The F15A series fetal and maternal monitor can monitor multiple physiological parameters of the fetus/mother in real time. F15A series can display, store, and print patient information and parameters, provide alarms of fetal and maternal parameters, and transmit patient data and parameters to Central Monitoring System.

F15A series fetal and maternal monitors mainly provide following primary feature:

Non-invasive physiological parameters:

• Maternal heart rates (MHR)
• Maternal ECG (MECG)
• Maternal temperature (TEMP)
• Maternal oxygen saturation (SpO2) and pulse rates (PR)
• Fetal heart rates (FHR)
• Fetal movements (FM)
• FTS-3

Note: SpO2 and PR are not available in F15A Air.

Invasive physiological parameters:

• Uterine activity
• Direct ECG (DECG)

The provided FDA 510(k) clearance letter and summary for the Fetal & Maternal Monitor (F15A, F15A Air) do not contain the detailed information necessary to fully answer all aspects of your request regarding acceptance criteria and the study that proves the device meets them.

The document focuses primarily on demonstrating substantial equivalence to a predicate device (Edan Instruments, Inc., F9 Express Fetal & Maternal Monitor, K173042) through comparison of intended use, technological characteristics, and conformance to various safety and performance standards. It mentions "functional and system level testing to validate the performance of the devices" and "results of the bench testing show that the subject device meets relevant consensus standards," but it does not specify quantitative acceptance criteria for each individual physiological parameter (e.g., FHR accuracy, SpO2 accuracy) nor the specific results of those tests beyond stating that they comply with standards.

Specifically, the document does not include information on:

• A table of acceptance criteria with specific quantitative targets for each parameter and the reported device performance values against those targets. It only states compliance with standards.
• Sample sizes used for a "test set" in the context of clinical performance evaluation (it mentions "bench testing," but this is typically laboratory-based and doesn't involve patient data in a "test set" sense for AI/algorithm performance validation).
• Data provenance for such a test set (e.g., country of origin, retrospective/prospective).
• Number or qualifications of experts used to establish ground truth.
• Adjudication methods.
• Multi-Reader Multi-Case (MRMC) studies or human reader improvement data with AI assistance.
• Standalone (algorithm-only) performance, as this is a monitoring device, not a diagnostic AI algorithm.
• Type of ground truth (beyond "bench testing" which implies engineered signals or controlled environments).
• Sample size for a training set or how ground truth for a training set was established. This device is a traditional medical device, not an AI/ML-driven diagnostic or interpretative algorithm in the way your request implies.

Therefore, based solely on the provided text, I can only address what is present or infer what is missing.

Here's a breakdown based on the available information:

Analysis of Acceptance Criteria and Performance Testing based on Provided Document

The provided 510(k) summary focuses on demonstrating substantial equivalence to a predicate device (F9 Express Fetal & Maternal Monitor, K173042) by showing that the new device (F15A, F15A Air) has the same intended use and fundamentally similar technological characteristics, with any differences not raising new safety or effectiveness concerns.

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

The document does not provide a specific table with quantitative acceptance criteria for each physiological parameter (e.g., FHR accuracy, SpO2 accuracy) and the corresponding reported performance values obtained in testing. Instead, it states that the device was assessed for conformity with relevant consensus standards. For example, it lists:

• IEC 60601-2-37:2015: Particular requirements for the basic safety and essential performance of ultrasonic medical diagnostic and monitoring equipment (relevant for FHR).
• ISO 80601-2-61:2017+A1:2018: Particular requirements for basic safety and essential performance of pulse oximeter equipment (relevant for SpO2).
• ISO 80601-2-56:2017+A1:2018: Particular requirements for basic safety and essential performance of clinical thermometers for body temperature measurement (relevant for TEMP).
• IEC 60601-2-27:2011: Particular requirements for the basic safety and essential performance of electrocardiographic monitoring equipment (relevant for MECG/DECG).

Acceptance Criteria (Inferred from standards compliance): The acceptance criteria are implicitly the performance requirements specified within these listed consensus standards. These standards set limits for accuracy, precision, response time, and other performance metrics for each type of measurement.

Reported Device Performance: The document states: "The results of the bench testing show that the subject device meets relevant consensus standards." This implies that the measured performance statistics (e.g., accuracy, bias, precision) for each parameter fell within the acceptable limits defined by the respective standards. However, the specific measured values are not provided in this summary.

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

The document mentions "Bench Testing" which implies laboratory-based testing using simulators, controlled signals, or phantoms, rather than a "test set" involving patient data. There is no information provided regarding:

• Sample size (e.g., number of recordings, duration of recordings, number of simulated cases) for the bench tests for each parameter.
• Data provenance (e.g., country of origin, retrospective or prospective) as this is not a study involving patient data collection for performance validation.

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 is not applicable and not provided. For a traditional physiological monitor, ground truth for bench testing is typically established using:

• Calibrated reference equipment/simulators: e.g., ECG simulators to generate known heart rates, SpO2 simulators to generate known oxygen saturation levels.
• Physical standards/phantoms: e.g., temperature baths at known temperatures.
• Known physical properties: e.g., precise weights for pressure transducers.

Clinical experts are not involved in establishing ground truth for bench performance of these types of physiological measurements.

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

This is not applicable and not provided. Adjudication methods are relevant for human expert review of complex clinical data (e.g., medical images for AI validation) to establish a consensus ground truth. For bench testing of physiological monitors, ground truth is objectively determined by calibrated instruments or defined physical parameters.

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

This is not applicable and not provided. An MRMC study is typically performed to evaluate the diagnostic accuracy of AI-assisted human interpretations versus unassisted human interpretations for AI-driven diagnostic devices. The Fetal & Maternal Monitor is a physiological monitoring device, not an AI-assisted diagnostic imaging or interpretation system. It measures and displays physiological parameters; it does not provide AI-driven assistance for human "readers" to interpret complex clinical information.

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

The device is a monitor that directly measures physiological parameters. It is not an "algorithm only" device in the sense of an AI model providing a diagnostic output. Its performance (e.g., FHR accuracy) is its standalone performance, as it directly measures these parameters. The document states "functional and system level testing to validate the performance of the devices," which would represent this type of standalone performance for the measurement functionalities. However, specific quantitative results are not given, only compliance with standards.

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

As explained in point 3, the ground truth for bench testing of physiological monitors is established using calibrated reference equipment/simulators and physical standards.

8. The sample size for the training set

This is not applicable and not provided. This device is a traditional physiological monitor, not a machine learning model that requires a "training set." Its algorithms for parameter measurement are based on established physiological principles and signal processing techniques, not on statistical learning from large datasets.

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

This is not applicable and not provided for the same reasons as point 8.

Ask a specific question about this device

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

The monitors are intended to be used for monitoring, storing, recording, and reviewing of, and to generate alarms for, multiple physiological parameters of adults and pediatrics (including neonates). The monitors are intended for use by trained healthcare professionals in hospital environments.

The monitored physiological parameters include: ECG, respiration (RESP), temperature (TEMP), functional oxygen saturation of arterial hemoglobin (SpO₂), pulse rate (PR), non-invasive blood pressure (NIBP), invasive blood pressure (IBP), carbon dioxide (CO2), and cardiac output (C.O.).

The arrhythmia detection and ST Segment analysis are intended for adult patients.

The NIBP monitoring supports iCUFS algorithm and iFAST algorithm. The iCUFS algorithm is intended for adult, pediatric and neonatal patients. The iFAST algorithm is intended for adult and pediatric patients (≥3 years of age). Both measurement algorithms are also intended for use with pregnant women, including pre-eclamptic patients. NIBP MAP is not applicable to pregnant women.

The Spot Temp with T2A module can only measure temperature of adult and pediatric (> 1 year of age) patients.

The monitors are not intended for MRI environments.

The cardiac output (C.O.) is only intended for adult patients.

The CX&UX series Patient Monitor including CX10/CX12/CX15/UX10/UX12/UX15 can perform long-time continuous monitoring of multiple physiological parameters. Also, it is capable of storing, displaying, analyzing and controlling measurements, and it will indicate alarms in case of abnormalities so that doctors and nurses can respond to the patient's situation as appropriate.

Minor differences from the predicate device are limited to some modifications of monitoring parameter specifications. These updates do not change the fundamental scientific technology of the cleared predicate device and thus do not raise any questions about the safety and effectiveness of the subject device.

The provided FDA 510(k) clearance letter details the device's technical specifications and comparisons to predicate devices, along with the non-clinical performance data and adherence to various IEC and ISO standards. However, it explicitly states: "Clinical data: The subject device did not require new clinical studies to support substantial equivalence."

This means that the submission for this Patient Monitor device (CX10, CX12, CX15, UX10, UX12, UX15) relies on demonstrating substantial equivalence to a legally marketed predicate device (Edan Instruments, Inc., Patient Monitor Model iX10, iX12, iX15, K232962) through non-clinical performance testing and software verification/validation, rather than new clinical trials or studies involving human patients.

Therefore, the requested information regarding acceptance criteria and studies that prove the device meets acceptance criteria through clinical performance (e.g., sample size for test set, expert involvement, MRMC studies, ground truth establishment for test/training sets, effect size of human reader improvement with AI) cannot be extracted from this document, as such clinical studies were explicitly not required for this 510(k) submission.

The document focuses on demonstrating that the new device's technical specifications and performance are similar to the predicate device, and that it complies with relevant safety and performance standards through bench testing.

Here's what can be extracted from the provided text regarding acceptance criteria and the type of study performed, specifically focusing on the non-clinical aspects:

Device: Patient Monitor (CX10, CX12, CX15, UX10, UX12, UX15)

The acceptance criteria for this device are implicitly tied to its performance meeting the standards and accuracy specifications of the predicate device and relevant international standards. Since no new clinical studies were conducted, the "proof" comes from non-clinical bench testing and software validation.

1. Table of Acceptance Criteria and Reported Device Performance (Non-Clinical/Bench Testing)

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

• Sample Size: Not applicable in terms of human subjects or patient data test sets, as "new clinical studies" were not required. The "test set" refers to bench testing and functional system-level validation. The specific number of test cycles or a detailed breakdown of test cases for bench testing is not provided in this summary.
• Data Provenance: The data primarily originates from Edan Instruments Inc. (Shenzhen, Guangdong, China) through internal engineering and quality assurance processes for non-clinical bench testing and software validation. It is not patient data, so concepts like "retrospective or prospective" do not apply.

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

• Not applicable for clinical ground truth: Since no clinical studies were performed requiring human interpretation or diagnosis for a test set, no medical experts (e.g., radiologists) were used to establish ground truth in this context.
• Internal experts: Bench testing and software validation would have involved engineers and quality assurance professionals, whose qualifications are implicit in the quality system (21 CFR Part 820) but not specified in detail here.

4. Adjudication Method for the Test Set:

• Not applicable: Adjudication methods (e.g., 2+1, 3+1) are relevant for clinical studies involving multiple readers. This was not a clinical study. Bench testing relies on established technical specifications and standard compliance.

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

• No: No MRMC study was performed as no new clinical studies were required or conducted. Therefore, there's no effect size of human readers improving with AI assistance. The device is a patient monitor, not an AI-assisted diagnostic tool.

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

• Yes (for the technical components): The "performance testing-Bench" effectively represents a standalone evaluation of the device's functional components (ECG, NIBP, SpO2, etc.) and software against defined technical specifications and standards. The "software verification and validation testing" also represents a standalone evaluation of the algorithm and software functions. The specific algorithms (e.g., iCUFS, iFAST for NIBP, arrhythmia analysis logic) are tested independently for their accuracy against known inputs or reference standards as part of bench testing.

7. The Type of Ground Truth Used:

• Technical/Reference Standards: For the bench testing, the "ground truth" would be derived from:
  • Reference standards/simulators: Calibrated medical equipment, physiological simulators, and test signals (e.g., known ECG waveforms, simulated blood pressure readings, temperature standards) are used to provide the "true" values against which the device's measurements are compared.
  • Defined specifications: The device's internal design specifications and the requirements of the referenced IEC/ISO standards serve as the "ground truth" for compliance testing.
• Not clinical ground truth: No expert consensus, pathology, or outcomes data from real patients were used for establishing ground truth for this submission.

8. The Sample Size for the Training Set:

• Not applicable: The device is a patient monitor, not a machine learning/AI algorithm that typically undergoes a distinct "training" phase with a large dataset. Its functionality is based on established physiological measurement principles and programmed algorithms. Any internal calibration or algorithm refinement would be part of the product development process, not a dedicated "training set" in the AI/ML sense.

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

• Not applicable: As there was no "training set" in the context of an AI/ML model, the concept of establishing ground truth for it does not apply to this 510(k) submission.

In summary, this 510(k) clearance relies on demonstrating that the new Patient Monitor is substantially equivalent to a previously cleared predicate device, primarily through robust non-clinical bench testing and software validation, proving compliance with established medical device standards and functional specifications. No new clinical studies with patient data were required or conducted for this specific submission.

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

The TeleRehab® Aermos Cardiopulmonary Rehabilitation System is intended to acquire and condition the ECG signal from a patient so that it can be transmitted wirelessly from a radiofrequency transmitter to a workstation in a hospital or a clinical setting where the data is displayed and analyzed. This device also measures heart rate and provides visual and audible alarms if the patient's heart rate goes out of a prescribed range. This device is for use with ambulatory adult patients who need monitoring while undergoing cardiovascular and/or pulmonary rehabilitation. The physiological data from monitoring and other patient information (such as patient demographics, exercise protocol and medical information) is stored in a database for tracking and reporting of the patients' progress through rehabilitation.

The TeleRehab® Aermos Cardiopulmonary Rehabilitation System ("Aermos") provides the ECG monitoring functionality required for performing rehabilitation of cardiovascular and/or pulmonary patients. Patients' ECG may be monitored using the Aermos system during exercise under clinical supervision. During monitoring, Aermos provides both visual and audible alarms if the patient's heart rate goes out of a prescribed range. The heart rate alarm indication is one of multiple inputs a clinician may use to modify and adjust rehabilitation activities such as decreasing the patient's level of physical exertion or halting the exercise entirely.

Aermos also provides the ability to plan a patient's rehabilitation program and document the patient's progress through the creation of various types of reports. The report types supported in Aermos include individual treatment plan reports, daily exercise session reports and various patient information reports. Additionally, the Aermos system provides the ability to transfer various report types to the hospital Electronic Medical Records system.

The main components of Aermos are Argus ECG transmitters, the Aermos Workstation and associated networking equipment.

This FDA 510(k) clearance letter pertains to the TeleRehab Aermos Cardiopulmonary Rehabilitation System, which is a device for monitoring ECG signals and heart rate during patient rehabilitation. The provided documentation (the 510(k) Summary) details non-clinical bench testing for performance and safety but explicitly states that clinical testing was not applicable.

Therefore, based on the provided document, the following information regarding acceptance criteria and a study that proves the device meets those criteria, specifically concerning an AI/algorithm-driven component with clinical performance metrics, cannot be fully extracted or is explicitly stated as not performed:

Here's an analysis of the provided information relative to your request:

Acceptance Criteria and Device Performance (Based on Non-Clinical Bench Testing)

Since no clinical study was performed, the "reported device performance" would pertain to the results of non-clinical bench testing against established performance standards. The document does not provide specific quantitative acceptance criteria or reported numerical performance results for the device. Instead, it states that the device's specifications were "verified through internal verification testing" and its usability "evaluated through internal validation testing," and that it complies with various international standards.

Study Details (Based on the provided 510(k) Summary)

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

   • See the table above. Specific quantitative acceptance criteria beyond "compliance with standard" are not provided in this regulatory summary.

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

   • The document explicitly states "Clinical Testing: Not applicable."
   • For the non-clinical bench testing, specific sample sizes (e.g., number of devices tested, number of test cases) are not detailed in this 510(k) summary.
   • Data provenance for non-clinical testing would typically be internal laboratory data generated during device development and verification. There is no mention of geographical origin or retrospective/prospective nature as this was not clinical data.

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

   • Not applicable, as no clinical study with human interpretation/ground truth was performed. The "ground truth" for bench testing would be defined by validated test equipment and reference standards.

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

   • Not applicable, as there was no study involving human readers or interpretation requiring adjudication.

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 done, as clinical testing was "Not applicable." The device is a physiological signal monitor, not an AI-assisted diagnostic tool that interprets images or signals requiring human reader comparison.

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

   • The core functionality of the device (ECG acquisition, heart rate measurement, alarms) is algorithmic. The performance of these algorithms would have been assessed during the non-clinical bench testing, which is essentially "standalone algorithm" testing against known inputs and expected outputs. Specific quantitative results (e.g., algorithm accuracy for heart rate) are not provided in this summary beyond "compliance with IEC 60601-2-27" and "ANSI/AAMI EC57: 2012, Testing and Reporting Performance Results of Cardiac Rhythm and ST-Segment Measure Algorithms."

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

   • For non-clinical bench testing, the "ground truth" is typically established by:
     • Reference standards and calibrated test equipment: For electrical performance, signal acquisition accuracy, frequency response, etc.
     • Simulated physiological signals: For testing heart rate calculation and alarm thresholds.
     • Design specifications and established engineering principles: For software functionality and cybersecurity.

8. The sample size for the training set:

   • Not applicable. The device is a monitoring system and not primarily driven by a deep learning or machine learning algorithm that requires a "training set" in the sense of a large dataset for model development. The algorithms for heart rate calculation, etc., are likely traditional signal processing algorithms.

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

   • Not applicable, as there was no training set for a machine learning model.

Summary of Device Nature and Regulatory Pathway:

The TeleRehab Aermos Cardiopulmonary Rehabilitation System is a Class II device (Product Codes DRG, DRT) which functions as a physiological signal transmitter and receiver. It monitors ECG and heart rate and provides alarms. Its 510(k) clearance relied on demonstrating substantial equivalence to predicate devices primarily through non-clinical bench testing against recognized industry standards (e.g., IEC 60601 series, ANSI/AAMI, ISO standards) and adherence to FDA guidance documents (e.g., for software, cybersecurity, reprocessing). The explicit statement "Clinical Testing: Not applicable" indicates that the nature of the device and its intended use, combined with the comprehensive non-clinical data, satisfied the FDA's requirements for demonstrating safety and effectiveness without the need for a human-subject clinical study. This is common for devices that are evolutionary improvements on existing technologies with well-understood performance parameters.

Ask a specific question about this device

The Radius VSM and accessories are intended to be used as both a wearable multi-parameter patient monitor and an accessory to a multi-parameter patient monitor that is intended for multi-parameter physiological patient monitoring in hospital and healthcare facilities.

The Radius VSM and accessories are indicated for the monitoring of hemodynamic (including ECG, arrhythmia detection, non-invasive blood pressure, SpO2, Pulse Rate, PVi, heart rate, and temperature), and respiratory (e.g., impedance, acoustic, and pleth-based respiration rate) physiological parameters along with the orientation and activity of adults.

The Radius VSM and accessories are indicated for the non-invasive continuous monitoring of functional oxygen saturation of arterial hemoglobin (SpO2) and Pulse Rate (PR) of well or poorly perfused adults during both no motion and motion conditions.

The Radius VSM and accessories are indicated for continuous monitoring of skin temperature of adults.

The Radius VSM and accessories are indicated for monitoring of the orientation and activity of patients including those susceptible to pressure ulcers.

The Radius VSM and accessories are indicated for the continuous non-invasive monitoring of PVi as a measure of relative variability of the photoplethysmograph (pleth) of adults during no motion conditions. PVi may be used as a noninvasive dynamic indicator of fluid responsiveness in select populations of mechanically ventilated adult patients. Accuracy of PVi in predicting fluid responsiveness is variable and influenced by numerous patient, procedure and device related factors. PVi measures the variation in the plethysmography amplitude but does not provide measurements of stroke volume or cardiac output. Fluid management decisions should be based on a complete assessment of the patient's condition and should not be based solely on PVi.

Devices with Masimo technology are only indicated for use with Masimo accessories.

Radius VSM Accessories:

Radius VSM ECG Electrodes are disposable, single-patient use ECG electrodes intended to acquire ECG signals from the surface of the body. They are indicated for use on adults for up to 3 days of skin surface contact.

Radius VSM Blood Pressure Cuffs are accessories intended to be used with a noninvasive blood pressure measurement system to measure blood pressure. They are indicated for use on adults during no motion conditions.

The Radius VSM and accessories are an FDA cleared (K223498), wearable, battery-operated, multi-modular patient monitoring platform that allows for the ability to scale and tailor the use of different monitoring technologies based upon the hospital and clinician's assessment of what technologies are appropriate.

As part of this submission, a MAP feature is being added to the Radius VSM. The feature is a software feature that uses the previously cleared systolic and diastolic measurement capabilities to automate the calculation of MAP using the following formula: MAP = 1/3* Systolic + 2/3*Diastolic.

The MAP is calculated by the Radius VSM NIBP Module and displayed on the Radius VSM Wearable Monitor. There were no other features added as part of this submission.

The provided 510(k) clearance letter and summary discuss the addition of a Mean Arterial Pressure (MAP) feature to the previously cleared Radius VSM and Accessories device. The primary focus of the performance data section is on validating this new MAP feature.

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

Acceptance Criteria and Reported Device Performance

The document states that the acceptance criterion for Blood Pressure (including MAP) is:

"Meets ISO 81060-2 (Mean difference of ≤5 mmHg with a standard deviation of ≤8 mmHg)"

The document directly states that the results of the clinical testing supported the clinical performance of the MAP in accordance with ISO 81060-2. While specific numerical results (e.g., the exact mean difference and standard deviation achieved) are not explicitly provided in the summary table, the clearance implies that these metrics fell within the specified ISO 81060-2 limits for the MAP feature.

Table 1: Acceptance Criteria and Reported Device Performance for MAP Feature (as inferred from the document)

Study Details for MAP Feature Validation

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

   • Sample Size: The document does not explicitly state the numerical sample size (number of subjects/patients) used for the clinical test set. It only mentions "clinical study data."
   • Data Provenance: The document does not specify the country of origin. It indicates it was a "clinical study" and implies it was prospective ("clinical testing is provided to support its performance" for the added feature).

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

   • Not applicable as the ground truth was established by an objective reference device, not human experts.

3. Adjudication Method for the Test Set:

   • Not applicable, as the method for ground truth establishment was comparison to a reference device.

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

   • No, an MRMC study was not done. The study was a comparison of the device's calculated MAP to invasively measured MAP from a reference device. This is a technical performance validation, not a study assessing human reader improvement with AI assistance.

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

   • Yes, this was a standalone performance study. The Radius VSM automatically calculates the MAP based on the NIBP measurements (Systolic and Diastolic Pressure). The clinical testing validated the accuracy of this calculation against a reference standard, without human intervention in the MAP calculation or interpretation for the test itself.

6. The Type of Ground Truth Used:

   • Reference Ground Truth: Invasively measured MAP values from a 510(k) cleared reference device (K171801). This reference device is identified as "IntelliVue Multi-Measurement Module X3." This constitutes a device-based reference standard or instrument-based ground truth.

7. The Sample Size for the Training Set:

   • The document does not provide information about a training set since the MAP feature appears to be a direct calculation using a standard formula (MAP = 1/3* Systolic + 2/3*Diastolic) rather than a machine learning model that requires a training phase. While the device as a whole (Radius VSM) likely had training and validation phases for its other parameters, the specific "addition of a Mean Arterial Pressure (MAP) feature" is described as a software feature that "automates the calculation" using a known formula. Therefore, a separate training set for this specific MAP feature is unlikely to have been required or used in the conventional machine learning sense.

8. How the Ground Truth for the Training Set was Established:

   • As inferred above, a specific training set and ground truth establishment for this isolated MAP calculation feature are not described, given its nature as a direct formulaic calculation.

Summary of Key Information:

The core of this submission revolves around adding a simple, formula-based calculation for MAP. The primary study presented is a clinical validation confirming that the device's computed MAP aligns with a known industry standard (ISO 81060-2) when compared against an invasive reference device. This is a technical performance validation rather than a complex AI-driven diagnostic study.

Ask a specific question about this device

DeepRhythmAI is a cloud-based software that utilizes AI algorithms to assess cardiac arrhythmias using a single- or two-lead ECG data from adult patients. It is intended for use by a healthcare solution integrator to build web, mobile or another types of applications to let qualified healthcare professionals review and confirm the analytic result. The product supports downloading and analyzing data recorded in the compatible formats from ECG devices such as Holter, Event recorder, Outpatient Cardiac Telemetry devices or other similar recorders when the assessment of the rhythm is necessary. The product can be electronically interfaced and perform analysis with data transferred from other computer-based ECG systems, such as an ECG management system. DeepRhythmAI can be integrated into medical devices. In this case, the medical device manufacturer will identify the indication for use depending on the application of their device. DeepRhythmAI is not for use in life-supporting or sustaining systems or ECG Alarm devices. 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 DeepRhythmAI is a cloud-based software utilizing CNN and transformer models for automated analysis of ECG data. It uses a scalable Application Programming Interface (API) to enable easy integration with other medical products. The main component of DeepRhythmAI is an automated proprietary deep-learning algorithm, which measures and analyzes ECG data to provide qualified healthcare professional with supportive information for review. DeepRhythmAI can be integrated into medical devices. The product supports downloading and analyzing data recorded in compatible formats from ECG devices such as Holter, Event recorder, Outpatient Cardiac Telemetry devices or other similar recorders used when assessment of the rhythm is necessary. The DRAI can also be electronically interfaced and perform analysis with data transferred from other computer-based ECG systems, such as an ECG management system. DeepRhythmAI doesn't have User Interface therefore it should be integrated with the external visualization software used by the ECG technicians for the ECG visualization and analysis reporting.

The provided FDA 510(k) clearance letter and summary for DeepRhythmAI offer general statements about performance testing but lack the specific details required to fully address all aspects of the request, especially quantifiable acceptance criteria and the results that prove them. The document primarily focuses on the substantial equivalence argument against a predicate device (which is itself DeepRhythmAI).

Based on the provided text, here's an attempt to extract and infer the information:

Acceptance Criteria and Device Performance:

The document mentions that the device was tested "according to the recognized consensus standards, ANSI/AAMI/IEC 60601-2-47:2012/(R)2016 and AAMI/ANSI/EC57:2012." These standards define performance requirements for ECG analysis devices, including aspects like beat detection accuracy, heart rate accuracy, and arrhythmia detection. However, the exact quantifiable acceptance criteria (e.g., "accuracy must be >X%") and the observed numeric device performance (e.g., "accuracy was Y%") are not reported in the provided text.

The closest we get to "reported performance" is the statement: "Overall, the software verification & validation testing was completed successfully and met all requirements. Testing demonstrated that the subject device performance was deemed to be acceptable." This is a qualitative statement, not quantitative performance data.

Table of Acceptance Criteria and Reported Device Performance:

Study Details:

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

   • Test Set Sample Size: The document states the algorithm was "tested against the proprietary database (MDG validation db) that includes a large number of recordings captured among the intended patient population." The exact number of recordings is not specified, only "a large number."
   • Data Provenance: The data comes from a "proprietary database (MDG validation db)." The country of origin is not explicitly stated. The document indicates it includes data for both two-lead and single-lead patch recorders, implying diverse ECG device sources. It is implied to be retrospective data collected for validation purposes.

2. 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 document. The document states a "proprietary database" was used for validation, but it does not detail how the ground truth within this database was established (e.g., by how many cardiologists or expert technicians, or their qualifications).

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

   • This information is not provided in the document.

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:

   • A MRMC comparative effectiveness study involving human readers and AI assistance is not mentioned in the provided text. The study described focuses on the standalone performance of the device against a ground truth. The device "is offered to physicians and clinicians on an advisory basis only" and results are "not intended to be the sole means of diagnosis," indicating a human-in-the-loop context, but no study is presented to quantify this human-AI interaction's effect on reader performance.

5. 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 the algorithm was "tested against the proprietary database (MDG validation db)." The entire summary of performance data refers to evaluation of the "DeepRhythmAI software for arrhythmia detection and automated analysis of ECG data." There is no mention of human interaction during this performance evaluation.

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

   • The document implies the use of an "MDG validation db" but does not specify the type of ground truth used to annotate this database. It's common for such ECG databases to rely on expert adjudicated annotations, but this is not explicitly stated.

7. The sample size for the training set:

   • The sample size for the training set is not provided. The document only discusses the "MDG validation db" which is used for testing/validation.

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

   • As the training set sample size is not provided, neither is information on how its ground truth was established.

Summary of Missing Information:

The provided document, being a 510(k) clearance letter and summary, serves to establish substantial equivalence. It confirms that specific performance testing was conducted according to recognized standards and deemed acceptable, but it does not provide the detailed scientific study results that would include:

• Quantifiable acceptance criteria and the exact numeric performance results for each criterion.
• The raw sample size of the test set.
• Details on the experts involved in ground truth creation for the test set (number, qualifications, adjudication method).
• Information on any MRMC studies or effect sizes of AI assistance on human readers.
• Explicit details about the ground truth methodology for the validation database.
• Any information regarding the training dataset (size, ground truth methodology).

To fully answer the request, one would typically need access to the full 510(k) submission, which contains the detailed V&V (Verification and Validation) reports.

Ask a specific question about this device

VitalRhythm is a cloud-based software application for continuous and automatic analysis of cardiac arrhythmias. VitalRhythm is compatible with the "Vista Solution" platform, which includes the VitalPatch biosensor and VistaCenter web application. VitalRhythm is intended to be used for outpatient cardiac telemetry and patient monitoring in non-critical healthcare settings for non-urgent clinical decision-making. VitalRhythm provides analysis of cardiac arrhythmias using ECG data and RR-interval from the VitalPatch in patients who are 18 years of age or older. Results of the VitalRhythm are displayed within the VistaCenter web application to be reviewed and confirmed by qualified healthcare professionals and/or cardiac technicians. VitalRhythm is not intended for use in life-supporting or sustaining systems or for critical care monitoring. The arrhythmia analysis results are not intended to be the sole means of diagnosis and are offered on an advisory basis only, in conjunction with the physician's knowledge of ECG patterns, patient background, clinical history, symptoms, and other diagnostic information.

VitalRhythm is a cloud-based, arrhythmia detection software application that is compatible and intended to be used with the VitalConnect "Vista Solution" platform. The Vista Solution Platform consists of the VitalPatch biosensor, a phone (VistaPhone) or tablet (VistaTablet) relay device preloaded with the VistaPoint software application, VC Cloud and the cloud-based VistaCenter user interface.

VitalRhythm is intended to be used for outpatient cardiac telemetry and patient monitoring in non-critical healthcare settings for non-urgent clinical decision-making.

VitalRhythm analyzes ECG data and RR-interval from the VitalPatch biosensor for reporting of cardiac arrhythmias to be reviewed and adjudicated by qualified healthcare professionals and/or cardiac technicians.

The cloud-based VitalRhythm software application supports the analysis of ECG data and RR-interval using a proprietary algorithm developed using deep learning techniques. The application works in the following way:

1. VitalRhythm accepts ECG and RR-interval data transmitted from the VitalPatch via a secure, cloud-based API (Application Programming Interface).

2. ECG and RR-interval data are analyzed by VitalRhythm using a proprietary algorithm, which detects the following cardiac rhythms:

   • Atrial fibrillation/atrial flutter
   • AV Block (2nd degree, Type I and II)
   • Pause
   • Paroxysmal supraventricular tachycardia (PSVT)
   • Ventricular tachycardia/run
   • Sinus bradycardia
   • Sinus tachycardia
   • Normal sinus rhythm
   • Others (inconclusive)

3. For use with Mobile Cardiac Telemetry (MCT), i.e., outpatient cardiac telemetry: any of the above listed arrhythmias that are detected by the software algorithm are displayed in VistaCenter to be reviewed and analyzed by a qualified cardiac technician in the 24/7 attended Cardiac Monitoring Center, prior to transmitting a notifiable event consistent with the prescribed notification criteria to the prescribing physician during the monitoring period. An event report is generated by VistaCenter as a result of the analysis.

For use with patient monitoring in non-critical healthcare settings: any of the above listed arrhythmias that are detected by the software algorithm are displayed and notified in VistaCenter, in accordance with the notification criteria, during the monitoring period to be reviewed by the prescribing healthcare professional for non-urgent clinical decision-making.

The features, operating procedures, and mitigations in place for the compatible devices ensure continuous data collection and transmission to support the VitalRhythm application for the intended use. Further information is provided in the VitalRhythm Instructions for Use document.

Here's a detailed breakdown of the VitalRhythm device's acceptance criteria and the study that proves it meets those criteria, based on the provided FDA 510(k) clearance letter:

Acceptance Criteria and Device Performance

Study Details

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

   • Patient count: 3,309 patients (18 years of age or older).
   • Dataset count: 7,553 datasets.
   • Annotated arrhythmia episodes: 22,034.
   • Data Provenance: Retrospective, de-identified ECG and RR-interval data obtained from patients prescribed the VitalPatch biosensor across 7 clinical sites in the United States (US).

2. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications:
   The document does not explicitly state the number of experts or their specific qualifications (e.g., "radiologist with 10 years of experience") used to establish the ground truth for the test set. However, it indicates that the results are "to be reviewed and confirmed by qualified healthcare professionals and/or cardiac technicians" in the context of device usage and implies that annotation for ground truth would follow a similar expert-driven process.

3. Adjudication Method for the Test Set:
   The document does not explicitly state the adjudication method (e.g., 2+1, 3+1, none) used for establishing the ground truth of the test set. It only states that the generated "event report is generated by VistaCenter as a result of the analysis" and is "to be reviewed and analyzed by a qualified cardiac technician in the 24/7 attended Cardiac Monitoring Center, prior to transmitting a notifiable event consistent with the prescribed notification criteria to the prescribing physician during the monitoring period." This describes post-processing of algorithm results by human readers, not the method for establishing the ground truth used for algorithm validation.

4. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
   The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study, nor does it provide an effect size of how much human readers improve with AI vs without AI assistance. The study described focuses on the standalone performance of the algorithm.

5. Standalone Performance (Algorithm Only Without Human-in-the-Loop Performance):
   Yes, a standalone performance study was conducted. The performance metrics (Sensitivity, Specificity, PPV, NPV, Accuracy) presented in the table are explicitly for the VitalRhythm algorithm "when assessed using the independent test database," indicating standalone algorithm performance against a pre-established ground truth.

6. Type of Ground Truth Used:
   The ground truth was established through annotated arrhythmia episodes. While the specific process is not detailed, it implies expert review and labeling of ECG and RR-interval data to define the 'true' presence or absence of arrhythmias. The "results are displayed within the VistaCenter web application to be reviewed and confirmed by qualified healthcare professionals and/or cardiac technicians," suggesting human consensus or expert interpretation forms the basis of the ground truth.

7. Sample Size for the Training Set:

   • Patient count: 23,587 patients.
   • Dataset count: 81,391 datasets.

8. How the Ground Truth for the Training Set Was Established:
   The document states the training database was from 354 US clinical sites, but it does not explicitly detail how the ground truth for the training set was established. It implies a process of data collection from clinical sites and subsequent processing for training the deep learning algorithm.

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