Search Results

The Vitls Platform is a wireless remote monitoring system intended for use by healthcare professionals for continuous collection of physiological data in in healthcare and home settings. This includes heart rate (HR) and body tomperature.

The data from the Tego VSS Sensor is intended for use by healthcare professionals as an aid to diagnosis and treatment. It is not intended for use on critical care patients nor replace standard monitoring and/or rouance care,

The device is intended for use as a general patient monitor, to provide physiological information, on patients who are 2 years of age or older.

The Vitls Platform is a wireless multi-parameter vital signs monitoring system. The Vitls Platform was developed to include an Application Programming Interface (API) which is intended to allow development of user interface applications, enabling clinicians and medically qualified personnel to access recorded vital signs information for respective analysis only, not for active patient monitoring. The Vitls Platform consists of: Wearable device with multiple sensors (the Tego VSS Sensor – An Adhesive Patch with integrated Sensors) The Secure Server Library (Cloud-based, including an API) The Vitls App (accessible on a smartphone, tablet, PC or monitor that displays the data and configures the Tego VSS Sensor)

The Tego VSS Sensor is a battery-operated adhesive patch with integrated sensors and wireless transceiver which is worn on the upper body and records heart rate and body temperature. There are two different sizes, one for adult and one for pediatric patients, they are 140 cm and 80 cm in length of the flexible portion of the sensor, respectively. The Tego VSS Sensor continuously gathers multiparameter vital signs data from the person being monitored and then transmits the encrypted data via bi-directional communication to the third-party connectivity relay, when in range. When not in range, the collected data is stored on the Tego VSS Sensor (for a maximum of 3 hours) and transmitted when a connection with the third-party connectivity relay has been restored. The encrypted wireless data recorded by the Sensor is sent, by the third-party connectivity relay, to the Secure Server. The data may be downloaded from the Secure Server Library or integrated into a Third-Party Application via the APIs of the Secure Server Library. In addition, the wireless data may be transferred to an optional Secure Server Library where they may be stored for future analysis.

The provided text describes the Vitls Platform, a wireless remote monitoring system that continuously collects physiological data, specifically heart rate and body temperature. The document is an FDA 510(k) summary, which focuses on demonstrating substantial equivalence to predicate devices rather than proving novel clinical effectiveness through extensive clinical trials for new AI/ML devices. Therefore, the information regarding acceptance criteria and performance studies is primarily focused on engineering and functional validation against established standards and predicate device performance for the cleared device.

Based on the provided text, here's a breakdown of the requested information:

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

The document does not present a formal table of quantitative acceptance criteria for clinical performance (e.g., sensitivity, specificity, or accuracy metrics typical for AI/ML diagnostic devices) for the entire Vitls Platform beyond the temperature accuracy specification. Instead, it focuses on demonstrating compliance with recognized consensus standards and performance in comparison to predicate devices, particularly for heart rate and temperature measurements.

• "Electrical safety testing per ISO 60601-1-11 shows the device meets the relevant requirements for devices used in home healthcare environment." |
  | Software V&V | - Demonstrated performance as intended. | - "Software V&V demonstrates that the device performs as intended." |
  | EMC | - Compliance with IEC 60601-1-2, FCC Part 15, Subpart B, Class B, RF Exposure Evaluation per 47 CFR 2.1091 and 2.1093, wireless coexistence per ASNI C63.27.2017, and RF Testing per FCC Part 15, Subpart C, 15.247. | - "Electromagnetic compatibility testing showed the device met the requirements of IEC 60601-1-2, FCC Part 15, Subpart B, Class B, RF Exposure Evaluation per 47 CFR 2.1091 and 2.1093, wireless coexistence per ASNI C63.27.2017 and RF Testing per FCC Part 15, Subpart C, 15.247." |
  | Clinical Thermometer Performance | - Compliance with ISO 80601-2-56. | - "Compliance with ISO 80601-2-56 regarding performance of clinical thermometers for body temperature measurement." |

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

The document does not explicitly state the sample size (number of subjects/patients) for the heart rate and temperature comparison studies, nor does it specify the country of origin of the data or whether the studies were retrospective or prospective. It only mentions a comparison against an FDA cleared patient monitor for heart rate and compliance with a standard for temperature. This level of detail is typically not required for 510(k) substantial equivalence claims for monitoring devices unless there are novel clinical claims or significant technological differences.

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 in the context of this device and study. The ground truth for physiological measurements like heart rate and temperature is typically established directly by reference devices (e.g., FDA-cleared patient monitors or calibrated thermometers) or established clinical methods, not by expert human readers/reviewers in the same way it would be for image-based diagnostic AI.

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

Not applicable. Physiological measurements are directly compared to reference devices, not subject to human 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 comparative effectiveness study was done. This type of study is more common for diagnostic AI/ML algorithms that assist human interpretation of complex data (e.g., medical images). The Vitls Platform is a physiological monitoring device, not a diagnostic AI intended to assist human readers in interpreting readings.

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

Yes, a form of "standalone" performance was effectively assessed for the core physiological measurements. The device's heart rate and temperature measurements were compared directly against established reference methods/devices (GE Dash 5000 for HR, and compliance with ISO 80601-2-56 for temperature), without an explicit human-in-the-loop component being evaluated. The device itself is intended for continuous collection of physiological data for healthcare professionals to use as an aid, meaning the algorithm is providing the base measurements that healthcare professionals use.

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

The ground truth for heart rate and temperature measurements was established by comparison to established, FDA-cleared reference devices/methods (e.g., GE Medical Systems Information Technologies Dash 5000 Patient Monitor for heart rate, and compliance with ISO 80601-2-56 for body temperature measurements, which would imply a validated reference thermometer).

8. The sample size for the training set

The document pertains to a 510(k) submission for a physiological monitoring device, not a machine learning or AI-driven diagnostic device in the modern sense that typically involves extensive training datasets. While the "Vitls Platform" might have some algorithmic processing for its physiological signal acquisition (e.g., PPG signal processing for heart rate), the document does not discuss a discernible "training set" in the context of machine learning. The validation described is more akin to traditional medical device testing for accuracy, reliability, and safety against known standards and predicate devices.

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

Not applicable, as a distinct "training set" and associated ground truth establishment process for machine learning are not detailed or implied by the provided 510(k) summary for this device.

Ask a specific question about this device

Where the clinician decides to monitor cardiac arrhythmia of adult, pediatric, and neonatal patients and/or ST segment of adult patients to gain information for treatment, to monitor adequacy of treatment, or to exclude causes of symptoms.

The intended use of the ST/AR cardiotach is to monitor a neonatal, pediatric, or adult patient's ECG for heart rate and produce events/alarms for one or two ECG leads. The cardiotach function is capable of monitoring both paced and non-paced patients.

The intended use of the ST/AR arrhythmia analysis algorithm is to monitor a neonatal, pediatric, or adult patient ECG's for heart rate and ventricular arrhythmias, and produce events/s] prms for one or two ECG leads. The arrhythmia analysis algorithm is capable of monitoring both paced and non-paced patients.

The intended use of the ST/AR ST analysis algorithm is to monitor an adult patient's ECG for ST segment elevation or depression and produce events/alarms for all possible ECG leads. The ST analysis algorithm is capable of monitoring paced and non-paced adult patients.

The intended use of the ST/AR QT/QTc analysis is for use by the physician in the risk assessment process indicated for neonatal, pediatric and adult patients with and without symptoms of arrhythmia. QT measurement is intended to be used by qualified health professionals in hospital or clinical environments. Composite QT (single or multi-lead derived) measures the interval only and is not intended to produce any interpretation or diagrosis of those measurements.

The modification is a software-based change that adds the following features: - Atrial Fibrillation alarm - Heart Rate configuration to short or yellow long alarm - Addition of messages indicating causes of invalid OT measurement

The provided document is a 510(k) premarket notification for the Philips ST/AR ST and Arrhythmia Software, Release J.0. It states that the device is substantially equivalent to previously cleared devices and outlines the new features, such as Atrial Fibrillation alarm. However, the document does not contain specific acceptance criteria or detailed study results with the requested information (sample sizes, ground truth experts, adjudication methods, MRMC studies, standalone performance, training set details). It broadly states that "Verification, validation, and testing activities establish the performance, functionality, and reliability characteristics of the new device with respect to the predicate," and that "Pass/Fail criteria were based on the specifications cleared for the predicate device and test results showed substantial equivalence."

Therefore, I cannot provide a detailed answer to your request based solely on the provided text. The document is a regulatory submission summary, not the full study report.

To address your request, I will explain what would be expected in such a study for a device like this and how the information would typically be presented, acknowledging that the specifics are missing from the provided text.

Based on the provided text (K080461 - Philips ST/AR ST and Arrhythmia Software, Release J.0), the following information is available or can be inferred:

• Device Name: Philips ST/AR ST and Arrhythmia Software, Release J.0
• New Features: Atrial Fibrillation alarm, Heart Rate configuration, messages for invalid QT measurement causes.
• Predicate Devices: K964122, K991773, K001348, K003621, K014261, K021251, K033513, K040357, K070260 (Philips ST/AR ST and Arrhythmia Software), K073462 (GE Dash monitor), K031320 (GE EK-Pro Arrhythmia Detection Algorithm).
• General Statement on Testing: "Verification, validation, and testing activities establish the performance, functionality, and reliability characteristics of the new device with respect to the predicate. Testing involved system level tests, performance tests, and safety testing from hazard analysis. Pass/Fail criteria were based on the specifications cleared for the predicate device and test results showed substantial equivalence."

Missing Information (Not present in the provided document):

• Specific numerical acceptance criteria for each performance metric.
• Reported device performance values against these criteria.
• Sample sizes for test sets.
• Data provenance (country of origin, retrospective/prospective).
• Number and qualifications of experts for ground truth.
• Adjudication method for the test set.
• Details of a Multi-Reader Multi-Case (MRMC) comparative effectiveness study (effect size, improvement with AI assistance).
• Details of standalone algorithm performance.
• Type of ground truth used (e.g., pathology, outcomes data).
• Sample size for the training set.
• Method for establishing ground truth for the training set.

Hypothetical Example of Acceptance Criteria and Study Design (What would typically be found in a more detailed submission for an arrhythmia detection algorithm, not based on the provided text directly):

Given the device includes an "Atrial Fibrillation alarm" as a new feature, a study validating this specific feature would typically involve comparing the algorithm's detection of Atrial Fibrillation (AFib) against a ground truth established by expert cardiologists.

Hypothetical Table of Acceptance Criteria and Reported Device Performance (Illustrative, not from the provided text):

Detailed Study Information (Illustrative, not from the provided text):

1. Sample Size for Test Set and Data Provenance:

   • Sample Size: 2,500 hours of continuous ECG recordings.
   • Data Provenance: Retrospective, collected from five major hospitals across the United States, Europe (Germany, UK), and Japan. The dataset included a diverse patient population (age, gender, comorbidities) representing the intended use population (adults).

2. Number of Experts Used to Establish Ground Truth and Qualifications:

   • Number of Experts: 3 independent electrophysiologists.
   • Qualifications: All experts were board-certified cardiologists with sub-specialty certification in electrophysiology, each with a minimum of 10 years of experience in ECG interpretation and arrhythmia diagnosis.

3. Adjudication Method for the Test Set:

   • Method: 2+1 Adjudication.
     • Each ECG recording segment was independently reviewed by two electrophysiologists.
     • If the two initial reviewers agreed on the presence or absence of AFib, that consensus became the ground truth.
     • If the two initial reviewers disagreed, a third, senior electrophysiologist (the "tie-breaker") reviewed the segment, and their decision established the ground truth.

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

   • Was it done?: No, an MRMC study was not performed for this 510(k) submission, as the focus was on the performance of the algorithm itself in detecting new features like AFib in a standalone manner, with comparison to predicate algorithms, rather than comparing human reader performance with and without AI assistance for this specific feature. (However, for image-based AI or diagnostic AI, MRMC studies are common).

5. Standalone (Algorithm Only) Performance:

   • Was it done?: Yes. The performance metrics presented in the hypothetical table above represent the standalone performance of the Philips ST/AR ST and Arrhythmia Software, Release J.0 algorithm in detecting AFib based on the ECG input, without human intervention in the detection process.

6. Type of Ground Truth Used:

   • Type: Expert Consensus. The ground truth for the presence or absence of Atrial Fibrillation was established by the independent review and adjudication of the electrophysiologists as described in section 3.

7. Sample Size for the Training Set:

   • Sample Size: 15,000 hours of continuous ECG recordings. This dataset was distinct from the test set to ensure independent evaluation.

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

   • Method: The ground truth for the training set was established through a combination of automated pre-annotation followed by expert review and correction. An initial algorithmic pass provided preliminary annotations for various arrhythmias, including AFib. These annotations were then meticulously reviewed and corrected by a team of experienced ECG technicians under the supervision of a lead electrophysiologist. For ambiguous cases, adjudication by two independent electrophysiologists ensured accuracy, similar to the test set ground truth establishment process, but with a higher throughput focus.

Conclusion from the provided K080461 document:

The provided 510(k) summary (K080461) indicates that the device underwent "Verification, validation, and testing activities" and that "Pass/Fail criteria were based on the specifications cleared for the predicate device and test results showed substantial equivalence." This is a general statement required for a 510(k) summary and does not include the detailed performance data, acceptance criteria, sample sizes, ground truth methodology, or expert qualifications that you requested. Such detailed information would typically be found in the full submission, which is not publicly available under the 510(k) summary.

Ask a specific question about this device