Search Results

Sleepiz One+ is a contactless medical device intended to measure heart rate and respiration rate in adult patients, at rest or during sleep (in non-motion condition) and to detect patient presence and body movements.

The Sleepiz One+ hardware unit is intended to be used by a healthcare professional when the recordings are performed in a clinical setting, or by patients or their caregivers when the recordings are performed in a home environment. The Sleepiz One+ cloud software is intended for use by healthcare professionals.

This device is not indicated for active patient monitoring, as it does not provide alarms for timely response in life-threatening situations. It is not indicated for use on pregnant women or patients with active implantable devices.

Sleepiz One+ is a contactless medical device that uses radar technology to measure respiration rate and heart rate from a resting or sleeping patient.

The Sleepiz One+ consists of a hardware unit and cloud-based software The hardware unit can be positioned on a bedside table, mounted on a stand, or attached to the wall behind the patient's bed. It is designed to monitor physiological signals by detecting small body movements, such as those caused by breathing and heartbeat, using Doppler radar. The recorded signals are then transmitted via Wi-Fi to cloud-based software, where they are analyzed to obtain respiration rate, heart rate, and body movement. These outputs can be exposed via the Application Programming Interfaces (APIs) to allow healthcare professionals the review and annotation of the data and compilation of results into reports.

Outputs

• Breathing pattern
• Instantaneous breathing rate [breaths per minute]
• Breathing rate statistics (10th, 50th, and 90th quantiles) [breaths per minute]
• Body movement
• Time in bed [hours]
• Presence detection
• Heart rate [beats per minute]
• Heart rate statistics (10th, 50th, and 90th quantiles) [beats per minute]

The overall system can be grouped into 4 major components, which are classified on the basis of the logical component interfaces where data exchange is occurring.

• Sleepiz Hardware - This is a hardware component serving as primary data acquisition device.
• Embedded Software - This encompasses the firmware running of the Sleepiz Hardware. This, together with Sleepiz hardware, is responsible for data acquisition. The embedded software forms the crux of the Sleepiz hardware such that it defines and controls the data acquisition process. The security aspects related to the operation of the device are incorporated in the design and implementation of embedded software.
• Sleep Analytics Software - The sleep analytics software is responsible for processing data from the Sleepiz Hardware and returning its analytics (e.g., breathing rate, heart rate), as well as its statistics (e.g., mean breathing rate, total recording time, etc.). This refers to the ML model deployed within the cloud software. By itself, the Sleep Analytics Software does not have an external interface. It is wholly encapsulated by the cloud software component Data Processing Layer.
• Cloud Software - The cloud software can be divided into the backend service and the analytics service. The backend service includes modules for data ingestion, a public API, a private API, and a module for sending analysis process requests. The analytics service is responsible for receiving analysis requests and interacting with the sleep analytics software.

The FDA 510(k) clearance letter for Sleepiz One+ (2.5) indicates that the device's substantial equivalence to a predicate device (Sleepiz One+) was established primarily through non-clinical performance testing, focusing on software verification and validation, electrical safety, and electromagnetic compatibility. The document states that the subject device and the predicate device have the same intended use, principle of operation, and similar technological characteristics. The minor modifications (API-based data access instead of web interface and plug-in power instead of battery) were assessed for safety and effectiveness without requiring extensive new clinical studies.

The provided document does not detail specific acceptance criteria for the accuracy of heart rate and respiration rate measurements, nor does it provide a study proving the device meets these specific performance criteria. The clearance is based on the conclusion that "The verification and validation tests performed on the subject device confirm that the device performs as intended in the specified use conditions and comparably to the predicate device. The performance testing conducted shows comparable results between the two models, thereby, demonstrating the safety and performance of the Sleepiz One+ (V.2.5)."

Therefore, based solely on the provided text, a comprehensive table of acceptance criteria and the detailed study proving the device's accuracy against those criteria cannot be constructed. The document infers that the device performs as intended and comparably to the predicate, but it does not present the raw performance data or the specific acceptance thresholds for heart rate and respiration rate accuracy.

Here's a breakdown of the requested information based on the provided text, with clear indications where the information is NOT available.

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

Information NOT available in the provided text. The 510(k) summary states that "performance testing conducted shows comparable results between the two models," but it does not quantify these results or list specific acceptance criteria for heart rate and respiration rate accuracy. The testing primarily focused on software validation, electrical safety, and EMC.

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

Information NOT available in the provided text. The document mentions "non-clinical performance tests" and "verification and validation tests," but it doesn't specify any sample sizes for a test set related to the accuracy of vital sign measurements, nor the provenance of any data used for such testing.

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)

Information NOT available in the provided text. There is no mention of external experts or ground truth establishment in the context of vital sign accuracy, as the clearance seems to rely on comparability to a predicate device and engineering verification/validation. For devices measuring physiological parameters, ground truth is typically established via reference medical devices (e.g., ECG, capnography) rather than expert consensus on subjective data.

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

Information NOT available in the provided text. Since no details on a clinical or performance study involving human subjects and expert review are provided, there is no mention of an adjudication method.

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

Information NOT available in the provided text. The Sleepiz One+ is a vital signs monitor, not typically an AI-assisted diagnostic imaging device that would undergo MRMC studies. The device primarily measures heart rate and respiration rate via radar and processes this data in cloud software (Sleep Analytics Software contains the ML model). The interaction is between the device and the patient, not a "human reader" interpreting AI outputs in a MRMC context. The cleared device provides raw data and statistics (like quantiles), which healthcare professionals would then interpret.

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

The device's core function, measuring heart rate and respiration rate from radar signals using its Sleep Analytics Software (which contains the ML model), operates in a standalone manner to generate these outputs. The outputs themselves (instantaneous rates, statistics) are generated by the algorithm without human intervention in the loop of the measurement process itself. Healthcare professionals then access and interpret these results via API. The non-clinical performance testing would have validated the output of this standalone algorithm against internal specifications or a reference.

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

Information NOT explicitly stated in the provided text regarding vital sign accuracy. For devices measuring heart rate and respiration rate, ground truth is typically established using established reference medical devices (e.g., synchronously recorded ECG for heart rate, capnography or impedance pneumography for respiration rate). While not stated, it can be inferred that if accuracy was evaluated, it would be against such objective physiological measurements rather than subjective expert consensus or pathology.

8. The sample size for the training set

The device uses an "ML model deployed within the cloud software" for "Sleep Analytics Software." However, the provided 510(k) summary does NOT provide any details about the training set size or methodology for this ML model. The focus of the substantial equivalence claim is on the overall system's safety and performance comparability to the predicate, with modifications primarily linked to data access and power source.

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

Information NOT available in the provided text. As with the training set size, the 510(k) summary does not provide details on how the ground truth for the training set (if any specific to the ML model) was established.

Ask a specific question about this device

The Circadia C200 System is intended for the measurement of respiratory rate and heart rate, including spot measurement.
The system is indicated for adult patients in clinical settings, such as skilled nursing and long-term care facilities.
The system is not indicated for active patient monitoring, and does not provide alarms for timely response in acute lifethreatening situations. The system is not intended to monitor heart rate in patients with arrhythmias.
The system is intended to be used by healthcare professionals (HCPs) and data are intended by HCPs to inform patient care.
The system also monitors patient motion, and patient presence or absence near the device (exits).

The Circadia C200 System is a contactless system that uses radar to monitor respiratory rate (RR), heart rate (HR), motion, and presence of a patient in its detection range. The System is designed to monitor a patient automatically, without the need for the patient to wear or do anything, or for a healthcare professional (HCP) to interact with the device. The System is thus suitable for long-term and unsupervised monitoring.
The System may also be used to obtain on-demand spot measurements of heart rate and respiratory rate. This allows HCPs to control the frequency and timing of these measurements using the C200 System.
The System consists of the Circadia Contactless Cardiorespiratory Monitor (the "Monitor"), the Circadia Cloud Service (the "Cloud Service"), and the Circadia Pro App (the "App").
The Monitor may be installed next to a patient's bedside. It uses a radar-based motion sensor to detect micromotions caused by ventilation and heartbeat, to measure a patient's RR and HR while the patient is in its detection range at rest. Data is processed continuously on the Monitor, and streamed to the Cloud Service over a Wi-Fi network.
The Cloud Service offers a set of Application Programming Interfaces (APIs) that allows the Monitor to connect to the server and send data over a secure channel. In addition, it allows for patient data to be retrieved from the App.
The App allows a healthcare professional to retrospectively review RR and HR data from multiple connected Monitors. Motion and presence/exit data are available in real time. The App operates from an Android tablet (not supplied, not included in the System). The App includes a functionality to notify a user if no HR has been obtained within the most recent 8 hours.

Here's an analysis of the acceptance criteria and the studies that demonstrate the Circadia C200 System meets them, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance:

The document primarily focuses on Heart Rate (HR) and Respiratory Rate (RR) monitoring performance. The specific acceptance criteria are stated for HR. For RR, it states equivalence to a reference device.

Note: For Respiratory Rate (RR), the document states that clinical testing demonstrated "RR monitoring performance of the subject device was equivalent to the reference device (Circadia C100 System, K200445)". The specific numerical acceptance criteria for RR are not explicitly detailed in this summary for the subject device, but rather implied by equivalence to the C100.

2. Sample Sizes and Data Provenance for Test Set:

• Heart Rate (HR) Studies:

  • Study 1: N = 49 patients
  • Study 2: N = 41 patients
  • Total: N = 90 patients across both studies.
  • Data Provenance: The document does not explicitly state the country of origin. It describes the subjects as being from "clinical populations" and use cases "representative of the subject device indications for use," which are "clinical settings, such as skilled nursing and long-term care facilities." This suggests prospective clinical data collection.

• Respiratory Rate (RR) Study:

  • The sample size for the RR study is not explicitly stated in the summary, but it refers to "clinical testing" using the Circadia C100 System (reference device).

3. Number of Experts and Qualifications for Ground Truth:

The document does not explicitly state the "number of experts used to establish the ground truth" for the test set or their qualifications.

4. Adjudication Method for the Test Set:

The adjudication method is not explicitly stated in the provided text.

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

A multi-reader multi-case (MRMC) comparative effectiveness study was not done or at least not reported in this summary. The studies described are focused on the standalone performance of the device against a gold standard, not on how human readers' performance improves with or without AI assistance from this device.

6. Standalone (Algorithm Only) Performance:

Yes, a standalone performance study was done. The clinical testing described for both Heart Rate and Respiratory Rate directly evaluates the performance of the Circadia C200 System's algorithm against a "gold standard reference HR" and a "reference device" for RR measurement.

7. Type of Ground Truth Used:

• Heart Rate (HR): The ground truth was established using a "gold standard reference HR (obtained using reference device K182030)." This implies a validated medical device known for accurate HR measurement.
• Respiratory Rate (RR): The ground truth was established by comparing the subject device's performance to the "Circadia C100 System (reference device, K200445)," which has identical hardware and RR monitoring functionality. This suggests the C100 itself served as the ground truth reference for RR measurement in its own clinical validation.

8. Sample Size for the Training Set:

The document does not provide any information about the sample size used for the training set of the device's algorithms. The summary focuses solely on pre-market clinical validation studies.

9. How Ground Truth for Training Set Was Established:

The document does not provide any information on how the ground truth for the training set was established. This information is typically not included in the 510(k) summary unless the device relies heavily on historical data for training in a way that directly impacts the clinical validation strategy.

Ask a specific question about this device

The Vios Monitoring System (VMS) is intended for use by medically qualified personnel for physiological vital signs monitoring of adult (18+) patients in healthcare facilities. It is indicated for use in monitoring of 7-lead ECG, heart rate, functional oxygen saturation of arterial hemoglobin, non-invasive blood pressure and activity. VMS allows for the input of body temperature, and can display data from peripheral devices. VMS can generate alerts when the physiological vital signs fall outside of selected parameters.

VMS can also generate alerts when cardias arrhythmias (Tachycardia, Asystole, Ventricular Fibrillation and Atrial Fibrillation/ Atrial Flutter) are detected.

The ECG rhythm analysis is intended for use by medified professionals in the identification of arrhythmia events and to aid in clinical review of arrhythmias and medical interventions.

The Vos CSM/CS Software is indicated for use by healthcare professionals for the purpose of centralized monitoring of patient data within a healthcare facility. The Vios CSMCS SW receives, stores, and displays patient physiological and waveform data and alams generated by Vios proprietary patient vitals monitoring software.

The Vios Monitoring System (VMS) Model 2050 is a wireless mobile medical device platform that allows caregivers in healthcare settings to monitor patient vitals. The VMS includes a proprietary monitoring software, Chest Sensor, Finger Adapter and Central Server and Central Monitoring Station. The VMS BSM SW Model B2050 is stand-alone software that can receive, analyze, and display physiological vitals data from one or more patient-worn sensors via standard communication protocols (Bluetooth™). It runs on a commercial IT platform and is intended to be used in conjunction with the Vios Chest Sensor and Vios Lead Adapters and can support peripheral, medical grade, Bluetooth™-enabled devices. The VMS Chest Sensor Model CS2050 is a small, patient-worn, non-sterile multiple use,

The Vios Monitoring System (VMS) Model 2050 was evaluated for its arrhythmia detection features, specifically assessing its performance against the ANSI/AAMI EC57:2012 standard and additional database records.

Here's a breakdown of the acceptance criteria and study details:

1. Table of Acceptance Criteria and Reported Device Performance:

The document primarily references compliance with the ANSI/AAMI EC57:2012 standard for cardiac rhythm and ST-segment measurement algorithms. While specific numerical acceptance criteria (e.g., minimum sensitivity, positive predictivity) for each arrhythmia are not explicitly listed in the provided summary, the study's conclusion of meeting "performance requirements as outlined in the consensus standard ANSI/AAMI EC57:2012" implies that the device achieved the performance thresholds defined within that standard for the tested arrhythmias.

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

The document states that the device's performance was evaluated using:

• Records from the ANSI/AAMI EC57 standard. This standard often utilizes a combination of standard ECG databases (e.g., MIT-BIH Arrhythmia Database).
• Additional records from LTAF, AAEL, and VFDB databases.

The specific sample sizes (number of patients or ECG recordings) for each arrhythmia or for the combined test set are not provided in the summary. The provenance of LTAF, AAEL, and VFDB databases is not detailed; however, these are generally recognized public databases of ECG recordings used for algorithm testing, often comprising retrospective data.

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

The document does not state the number of experts used or their specific qualifications for establishing the ground truth of the test set. For publicly available and widely used databases like those mentioned (MIT-BIH, LTAF, AAEL, VFDB), the ground truth labels are typically established by multiple expert cardiologists or electrophysiologists using established criteria, often after multiple review rounds. However, this specific information is not in the provided text.

4. Adjudication Method for the Test Set:

The document does not specify the adjudication method used (e.g., 2+1, 3+1). For standard ECG databases, ground truth is usually established via expert consensus, which inherently involves an adjudication process, but the specific mechanics are not described here.

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

The document does not indicate that a multi-reader multi-case (MRMC) comparative effectiveness study was done to assess how much human readers improve with AI vs. without AI assistance. The testing described is focused on the standalone performance of the device's arrhythmia detection algorithm.

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

Yes, a standalone performance evaluation was done. The summary explicitly states: "The non-clinical tests for evaluation of performance of Vios system with the addition of arrhythmia alarms is based on ANSI/AAMI EC57, showing substantial equivalence to the predicate (K180472). The subject device's performance was also evaluated using additional records from LTAF, AAEL, and VFDB database..." This describes the algorithm's performance without direct human intervention as part of the detection process.

7. Type of Ground Truth Used:

The ground truth for the test was established through expert consensus/annotations from well-known ECG databases (ANSI/AAMI EC57, LTAF, AAEL, and VFDB). These databases contain ECG recordings that have been meticulously reviewed and annotated by medical experts (typically cardiologists or electrophysiologists) to identify and label different cardiac events and arrhythmias,
Pathology and outcomes data are not mentioned as sources for ground truth in this context.

8. Sample Size for the Training Set:

The document does not specify the sample size used for the training set of the Vios Monitoring System's arrhythmia detection algorithm.

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. However, it is common practice for such algorithms to be trained on large, expertly annotated ECG datasets, similar to those used for testing (expert consensus/annotations).

Ask a specific question about this device

The Neteera 130H-Plus device is intended for spot and continuous measurement of heart rate and respiration rate in adult patients (in healthcare facilities and home monitoring) and inform on bed exit.

The indications provided are to be used by health care professionals and are intended to be reviewed by clinicians to inform patient care.

The Neteera device is not intended to be used as an alarm system for potentially acute life-threatening situations in which medical intervention is necessary (e.g., ICU).

Neteera 130H-Plus device is a modification of the predicate device Neteera 130H (K212143). It is a contact-free vital-signs monitor based on a high frequency (122.25-123 GHz) micro-radar on-chip and algorithm, capable of detecting Respiration Rate (RR) and Heart Rate (HR) during rest or subject's mild body movement, with the additional capability of identifying and notifying on bed exit.
Neteera's micro- radar-based solution enables remote measurement, in real-time, in a non-invasive and contact-free manner. The system works by measuring only the ballistocardiograph micro-movements of of the skin (BCG) through nonmetallic materials such as furniture and clothing at a high resolution, and it has several different mounting options and measuring ranges.

This FDA 510(k) summary provides information on the Neteera 130H-Plus Vital Sign Monitoring Sensor, which is a modification of a previously cleared device. The summary primarily focuses on demonstrating substantial equivalence to the predicate device rather than detailing comprehensive acceptance criteria and a standalone study for the current device. However, it does provide some clinical validation details.

Here's an attempt to extract and interpret the information based on your requested format:

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

The document does not explicitly present a table of acceptance criteria with corresponding performance metrics for HR, RR, or bed exit detection. It states that "all outcomes met the same pre-specified performance criteria" from the predicate device's clearance, but these criteria are not detailed in this submission. To fully answer this, one would need to refer to the K212143 submission for the predicate device.

However, based on general expectations for vital sign monitors, the reported measurement ranges can be inferred as indirectly related to performance.

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

• Sample Size (Clinical Validation): 46 subjects.
• Data Provenance: The study was a "GCP-compliant confirmatory clinical validation study under Independent Ethical Committee approval." This implies a prospective study. The country of origin is not explicitly stated, but the sponsor, Neteera Technologies Ltd., is based in Jerusalem, Israel, which might suggest the study was conducted there.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

This information is not provided in the document. The ground truth was established by "FDA-cleared devices ECG and Capnograph," which are considered reference standards, not human experts for interpretation.

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

This information is not applicable as the ground truth was established by FDA-cleared reference devices (ECG and Capnograph), not through human expert 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

• MRMC Study: No, an MRMC comparative effectiveness study was not done. This device is a standalone vital signs monitor, not an AI-assisted diagnostic tool for human readers.

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

• Standalone Performance: Yes, the clinical validation study was for the standalone performance of the Neteera 130H-Plus device, comparing its measurements directly against FDA-cleared reference devices (ECG and Capnograph). The device is described as "contact-free vital-signs monitor based on a high frequency (122.25-123 GHz) micro-radar on-chip and algorithm."

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

• Type of Ground Truth: Measurements from FDA-cleared reference devices: ECG (for Heart Rate) and Capnograph (for Respiration Rate).

8. The sample size for the training set

This information is not provided in the 510(k) summary. The summary focuses on the clinical validation of the modified device, not its initial algorithm development or training data.

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

This information is not provided in the 510(k) summary.

Ask a specific question about this device

Sleepiz One+ is a contactless medical device intended to measure heart rate and respiration rate in adult patients, at rest or during sleep (in non-motion condition).

The Sleepiz One+ hardware unit is intended to be used by a healthcare professional when the recordings are performed in a clinical setting, or by patients or their caregivers when the recordings are performed in a home environment. The Sleepiz One+ web application is Intended for use by healthcare professionals.

Sleepiz One+ device can also detect the presence of patients and their body movements at rest or during sleep. This device is not indicated for active patient monitoring, as it does not provide alarms for timely response in life-threatening situations. It is not indicated for use on pregnant women or patients with active implantable devices.

Sleepiz One+ is a contactless medical device that uses radar technology to measure respiration rate and heart rate. The device is placed on a bedside table or a stand, mounted slightly higher than the mattress level, from where it detects the presence of a patient and their physiological signals. From that position, distance changes between the device and the patient's body are captured by Doppler radar. The recorded signals are then transmitted to the cloud software where these are analyzed by the signal processing software ("Sleep Analytics Software") to obtain respiration rate, heart rate and facilitate the monitoring of the presence of the patient and their body movement. These outputs are then displayed on the web application to allow the annotation of the data, compilation of results into reports, and the management of the hardware units.

Here's a breakdown of the acceptance criteria and study information for the Sleepiz One+ device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

• Accuracy: +/- 3 breaths per minute (99% accuracy rate)
• 95% Limits of Agreement: -1.42 to 0.97 breaths/min (for neurorehabilitation ward patients)
• 95% Limits of Agreement: -1.3 to 0.8 breaths/minute (for patients suspected of sleep apnea)

Compared to end-tidal CO2 (etCO2) via capnography:

• Accuracy: +/- 2 breaths/minute (93.7% accuracy)
• 95% Limits of Agreement (instantaneous breathing rate): -2.51 to 2.04 breaths/minute
• Mean Absolute Error (average breathing rate): 0.79 breaths/minute
• 95% Limits of Agreement (average breathing rate): -2.63 to 2.01 breaths/minute |
  | Heart Rate Accuracy | The subject device performs comparably to established methods for heart rate measurement. | Compared to Electrocardiography (ECG):
• Accuracy: +/- 5 beats per minute (94% accuracy rate)
• 95% Limits of Agreement: -2.64 to 5.82 beats/min (for neurorehabilitation ward patients)
• 96% heart rate accuracy (for patients suspected of sleep apnea) |
  | Safety | Complies with relevant electrical, mechanical, and emission safety standards. | Passed all electrical and mechanical safety tests per ANSI AAMI ES60601-1 and IEC 60601-1-11. Passed all emission tests per IEC 62304 and Federal Register CFR 47 Part 15 subpart B. Passed Coexistence Immunity and Wireless Crosstalk tests per 27701:2019 and ANSI IEEE C63.27-2017. |
  | Software Performance | Software components function as intended and meet user needs. | All software components verified against System Requirements Specifications and system-level validated against user needs. All tests passed. |
  | Risk Management | Identified hazards are mitigated through risk controls. | Risk analysis performed per ISO 14971; risk controls implemented. Cybersecurity risks identified and addressed through penetration testing. |
  | Usability | Device is usable for intended users in intended environments. | Extensive Human Factor Engineering/Usability Engineering performed per IEC 62366-1 and FDA guidance; found substantially equivalent for intended users, uses, and environments. |

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

The clinical studies involved a total of 199 subjects.
The data provenance is from clinical studies conducted with patients in a neurorehabilitation ward and patients suspected of suffering from sleep apnea. The studies were prospective as patients were continuously monitored overnight.

Specific sample sizes for each comparison are:

• Neurorehabilitation ward patients: 59 patients for respiration rate (compared to respiratory effort belt), 32 patients for heart rate (compared to ECG).
• Patients suspected of sleep apnea: 105 patients for respiration rate, 73 patients for heart rate.
• etCO2 comparison: 35 participants.

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 Qualifications

The text indicates that some measurements were "manually scored by a healthcare professional" for the comparison with end-tidal CO2 (etCO2). However, it does not specify the number of experts involved or their specific qualifications (e.g., years of experience, specialty). For other comparisons (respiratory effort belt, ECG), the ground truth devices are referenced, but expert involvement in scoring those particular signals is not detailed beyond the etCO2 mention.

4. Adjudication Method for the Test Set

The text does not explicitly state an adjudication method (e.g., 2+1, 3+1). It implies that the comparator device measurements (e.g., respiratory effort belt, ECG, etCO2) served as the direct reference or "ground truth." For the "manually scored" etCO2 data, it's not clear if multiple healthcare professionals scored the data and an adjudication process was used.

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

An MRMC comparative effectiveness study was not explicitly mentioned or performed to assess improvement of human readers with AI assistance. The studies described are focused on the device's accuracy against established medical reference standards.

6. Standalone (Algorithm Only) Performance

Yes, the studies described are primarily standalone (algorithm only) performance evaluations. The Sleepiz One+ outputs (heart rate, respiration rate) were compared directly against reference devices (ECG, pulse oximetry, respiratory effort belt, nasal cannula, etCO2 measurements). While the device records and transmits data for healthcare professionals to view, the reported accuracy metrics are for the device's automated estimation of these vital signs.

7. Type of Ground Truth Used

The ground truth for the test set was established using:

• Established Medical Devices: Electrocardiography (ECG), pulse oximetry, respiratory effort belt, nasal cannula, and an FDA-cleared device for end-tidal CO2 (etCO2) measurements.
• Expert Scoring: For the etCO2 comparison, the ground truth was "manually scored by a healthcare professional."

Polysomnography devices (Somnotouch RESP (K140861), Nox A1 (K192469)) were used as comparator devices in the clinical studies, specifically using subsets of their channels for the performance assessment.

8. Sample Size for the Training Set

The document does not specify the sample size used for the training set for the Sleepiz One+ device's algorithms.

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 only describes the methodology for the performance evaluation (test set).

Ask a specific question about this device

The Neteera 130H/131H device is intended for spot and continuous measurement of heart rate and respiration rate in adult patients (in healthcare facilities and home monitoring).

The indications provided are to be used by health care professionals and are intended to be reviewed by clinicians to inform patient care.

The Neteera device is not intended to be used as an alarm system for potentially acute life-threatening situations in which medical intervention is necessary (e.g., ICU).

Neteera 130H/131H device is a contact-free vital-signs monitor based on a high frequency (122.25-123 GHz) micro-radar on-chip and algorithm, capable of detecting a variety of parameters: Respiration Rate (RR), Heart Rate (HR), during rest or subject's mild body movement.
Neteera's micro radar-based solution enables measuring the micro-motions of the skin (BCG-Ballistocardiograph) remotely, in a real-time, non-invasive, and non-contact manner, through non-metallic materials such as furniture and clothing at a high resolution.

The Neteera 130H/131H Vital Signs Monitoring Sensor is intended for "spot and continuous measurement of heart rate and respiration rate in adult patients (in healthcare facilities and home monitoring)." The following details describe the acceptance criteria and the study that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implied by the performance metrics reported, specifically the percentage of measurements falling "under 10% error" or meeting "5% or 5bpm Criteria" for HR, and "under 10% error or 2brpm" for RR. These thresholds represent the satisfactory performance levels.

2. Sample Size for the Test Set and Data Provenance

The clinical validation study involved 170 subjects in total across two parts.

• Part 1: 100 subjects from Israel.
• Part 2: 70 subjects from the US population, specifically recruiting subjects with cardiopulmonary and metabolic medical disorders.

The study was prospective as it was a "GCP-compliant clinical study."

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

No information is provided about the number of experts or their qualifications used to establish ground truth.

4. Adjudication Method for the Test Set

No information is provided about an adjudication method for the test set. Given that the ground truth for vital signs is typically established through direct measurement with reference devices, complex adjudication methods like 2+1 or 3+1 are typically not applicable.

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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not conducted. The Neteera 130H/131H is a direct measurement device for vital signs, rather than an AI-assisted diagnostic tool that would typically involve human readers.

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

Yes, a standalone performance study was done. The performance results presented in the table are for the Neteera device's measurements compared to a reference device, indicating its standalone accuracy in measuring HR and RR. The device is described as "a high frequency (122.25-123 GHz) micro-radar on-chip and algorithm," implying autonomous measurement.

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

The ground truth for the performance testing was established using a reference medical device. Specifically, the "MindRay Patient Monitor, model ePM 10M (K200015)," which is an FDA-cleared device.

8. The sample size for the training set

The document does not specify the sample size for the training set. The provided clinical study data (170 subjects) appears to be for validation/testing, not training.

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, was established. It only mentions the reference device used for validation.

Ask a specific question about this device

The Ivy Biomedical Model 7600EP/7800EP is a basic cardiac monitor used to provide cardiac trigger pulse outputs used by third-party diagnostic imaging systems that require ECG synchronization, such as nuclear medicine, computed axial (CAT), or positron emission (PET) tomography and other imaging systems requiring similar cardiac cycle specific timing. The Ivy Biomedical Model 7600EP/7800EP monitors can also be used to provide cardiac trigger pulse output used by a third-party ablation and lithotripsy systems.

Not Found

I understand you're asking for details about the acceptance criteria and study data for a medical device. However, the provided text is an FDA 510(k) clearance letter for the Ivy Biomedical Model 7600EP/7800EP Cardiac Synchronization Monitor.

This document explicitly states that the device is a "Cardiac Monitor (Including Cardiotachometer And Rate Alarm)" and is intended to "provide cardiac trigger pulse outputs used by third-party diagnostic imaging systems that require ECG synchronization."

This is not an AI/ML medical device, and the provided text does not contain any information about acceptance criteria, study data, ground truth establishment, or any of the other AI/ML-specific details you are asking for.

Therefore, I cannot extract the information requested for a study proving an AI/ML device meets acceptance criteria, as the document concerns a traditional medical device.

Ask a specific question about this device

The Vital Sign Monitoring Sensor (Model XK300) is intended to measure heart rate and respiration rate in adult patients in a general care hospital environment including nursing homes. The Vital Sign Monitoring Sensor can be used for home healthcare for data collection to inform patient care but not to acutely treat a patient. XK300 monitors presence or absence of a patient in detection area of within 7 meters. The XK30 also monitors the length of continuous patient motion or absence of patient motion.

The Vital Sign Monitoring Sensor (Model XK300) measures heart rate, respiratory rate (breathing rate), and movement of people with very little or no movement (rest mode) using Impulse Radio Ultra-Wideband (IR UWB) radar technology. The heart rate and respiratory rate are measured by detecting minute displacements of the chest and converting the movement into the number of breaths and heart beats per minute.

The provided document is a 510(k) summary for the Xandar Kardian Vital Sign Monitoring Sensor (Model XK300). It focuses on establishing substantial equivalence to a predicate device rather than presenting a detailed study proving the device meets specific acceptance criteria with quantifiable metrics. Therefore, some information requested in the prompt, such as specific acceptance criteria for performance, detailed study designs, sample sizes for test sets, expert qualifications, and ground truth establishment methods, are not explicitly provided in the text.

However, based on the available information, here's what can be extracted and inferred:

1. Table of Acceptance Criteria and Reported Device Performance:

The document states that "performance testing has confirmed that this difference does not affect the performance of the Vital Signs Monitoring Sensor." This implies that the device's performance, despite having different measurement ranges than the predicate, was deemed acceptable. However, specific, quantifiable acceptance criteria (e.g., accuracy, precision, bias) for heart rate and respiration rate, and the corresponding reported performance values from a dedicated study, are not provided. The comparison table (Table 5-1) mainly focuses on technical specifications and intended use comparison with the predicate, not performance metrics against acceptance criteria.

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

The document mentions "performance testing" was conducted, but it does not specify the sample size used for this testing. It also does not mention the data provenance (e.g., country of origin, retrospective or prospective nature).

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

The document does not provide information regarding the number of experts used or their qualifications for establishing ground truth in performance testing.

4. Adjudication Method for the Test Set:

The document does not specify an adjudication method for the test set.

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

The document does not mention an MRMC comparative effectiveness study involving human readers.

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

The document implies standalone performance testing was done, as it discusses "performance testing" of the device itself and its ability to measure heart rate and respiration rate. The description of the device as a "sensor" that detects minute displacements and converts them into rates suggests it operates autonomously. However, it does not explicitly label a study as a "standalone" study with detailed methodology.

7. The Type of Ground Truth Used:

The document implying heart rate and respiration rate measurement suggests the ground truth for performance testing would likely be established using reference medical devices (e.g., ECG for heart rate, capnography or spirometry for respiration rate) that are considered gold standards for these physiological measurements. However, the document does not explicitly state the type of ground truth used.

8. The Sample Size for the Training Set:

The document does not mention a training set or its sample size. This is common in a 510(k) submission where the focus is on substantial equivalence to a predicate rather than a de novo approval requiring extensive AI model validation. The device description suggests a sensor-based measurement system rather than a deep learning algorithm that typically requires a large training set.

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

Since a training set is not mentioned, the method for establishing its ground truth is also not provided.

Ask a specific question about this device

The Philips wearable biosensor-G5 is indicated for single patient use whenever heart rate measurement is needed in noncritical hospital settings. The Philips wearable biosensor-G5 solution is used as a higher resolution heart rate log by nurses or physicians retrospectively as an aid in making non-ife threatening therapeutic decisions. The biosensor is intended for patients who are 18 years of age or older.

The G5 Biosensor is intended only for patients with a baseline narrow QRS complex (less than 100 ms).

Philips wearable biosensor-G5 Solution is a physiological sensing solution that gathers and stores a patient's heart rate. Philips wearable biosensor-G5 Solution is comprised of the:

• Philips wearable biosensor-G5
• and data visualization application "G5 application" ●

The Philips wearable biosensor-G5 is a battery operated, single-use device, measuring heart rate by continuously acquiring surface electrical waveforms related to cardiac excitations and measuring beat-to-beat intervals when a patient is stationary or ambulatory. The sensor functions by capturing and then sending physiological data wirelessly to the software application. The sensor's frequency of data collection and transmission is configurable. The G5 application receives and displays data from the Philips wearable biosensor-G5 providing a user interface and exportable file for retrospective review and analysis.The G5 Biosensor is intended only for patients with a baseline narrow QRS complex (less than 100 ms).

The Philips wearable biosensor-G5 Solution is a physiological sensing solution that measures heart rate by continuously acquiring surface electrical waveforms and beat-to-beat intervals.

Here's an analysis of the acceptance criteria and supporting studies based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

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

• Wear Duration Study: 28 normal healthy volunteers.
• Data Provenance: The text does not explicitly state the country of origin. The study appears to be prospective due to its nature of testing volunteers for wear duration.
• Other Performance Testing: The text does not specify sample sizes for biocompatibility, electrical safety, EMC, or general performance bench testing. These typically involve laboratory tests on devices rather than human subjects.

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

• Wear Duration Study: The text does not specify the number or qualifications of experts for establishing ground truth regarding adhesive performance or wear duration. The assessment for adhesive performance was "calculated per the ANSI/AAMI EC12:2000/(R) 2010 Disposable ECG Electrodes," suggesting adherence to a recognized standard rather than expert consensus on individual cases.
• Heart Rate Accuracy: For heart rate accuracy, the text refers to compliance with IEC standards (IEC 60601-2-27, IEC 60601-2-47), which imply a standardized testing methodology for accuracy rather than expert adjudication of ground truth for each measurement.

4. Adjudication Method for the Test Set:

• The text does not mention an explicit adjudication method (like 2+1 or 3+1) for any of the studies. This suggests that the performance metrics were determined through standardized testing protocols (e.g., against reference measurements for heart rate) or direct measurement against a defined standard (e.g., ANSI/AAMI EC12 for adhesive performance).

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

• No, a "multi-reader multi-case (MRMC) comparative effectiveness study" comparing human readers with and without AI assistance was not done. The device is a biosensor that measures heart rate, not an AI-assisted diagnostic imaging or interpretation tool that would typically involve human readers.

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

• Yes, the performance data presented primarily reflects the standalone performance of the device.
  • The "Performance Testing bench testing" using voluntary standards like IEC 60601-2-27 and IEC 60601-2-47 directly assesses the algorithm's ability to accurately measure heart rate in a controlled setting.
  • The "Wear Duration Study" also assesses the physical performance of the biosensor itself.
  • The "Software Verification and Validation Testing" is also a standalone assessment of the software's functionality.

7. Type of Ground Truth Used:

• Heart Rate Accuracy: The ground truth for heart rate accuracy would likely be established by a highly accurate reference standard heart rate monitor or ECG system as specified by the IEC 60601-2-27 and IEC 60601-2-47 standards.
• Adhesive Performance: The ground truth for adhesive performance was established through calculation "per the ANSI/AAMI EC12:2000/(R) 2010 Disposable ECG Electrodes," which is a recognized standard for evaluating such performance.
• Biocompatibility: Ground truth is established by the outcomes of standardized biological tests (cytotoxicity, sensitization, irritation) against defined acceptable limits.

8. Sample Size for the Training Set:

• The document does not provide any information regarding a training set sample size. This suggests that the device's algorithms for heart rate detection might be based on established physiological principles and signal processing techniques rather than a machine learning model that requires explicit training on a large dataset mentioned in this summary.

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

• As no training set is mentioned, this information is not provided. If the device uses algorithms that were developed and validated internally, the "ground truth" for their development would involve a similar process of comparing algorithm outputs against known, accurate physiological signals under controlled conditions, but the document does not elaborate on this developmental phase.

Ask a specific question about this device

The Vios Monitoring System (VMS) is intended for use by medically qualified personnel for physiological vital signs monitoring of adult (18+) patients in healthcare facilities. It is indicated for use in monitoring of 7-lead ECG, heart rate, respiratory rate, pulse rate, functional oxygen saturation of arterial hemoglobin, non-invasive blood pressure, and patient posture and activity. VMS allows for the input of body temperature, and can display data from peripheral devices. VMS can generate alerts when rate-based carthythmias are detected and when physiological vital signs fall outside of selected parameters.

The Vios Monitoring System (VMS) Model 2050 is a wireless mobile medical device platform that allows caregivers in healthcare settings to monitor patient vitals. VMS includes Vios-proprietary monitoring software and a Vios-proprietary vitals sensor with two Vios-proprietary adapters. It is compatible with a medical grade, Bluetooth™-enabled NIBP cuff. The VMS BSM SW Model B2050 is stand-alone software that can receive, analyze, and display physiological vitals data from one or more patient-worn sensors via standard communication protocols (Bluetooth™). It runs on a commercial IT platform and is intended to be used in conjunction with the Vios Chest Sensor and Vios Lead Adapters and can support peripheral, medical grade, Bluetooth™-enabled devices. The VMS Chest Sensor Model CS2050 is a small, patient-worn, non-sterile, multiple use, and rechargeable sensor that acquires 3-channel ECG, bioimpedance, 2-channel pulse oximetry, and tri-axial accelerometer data. The sensor contains signal acquisition firmware (embedded software) and wirelessly communicates acquired data via standard communication protocols (Bluetooth™) to the BSM SW for analysis and display. The Chest Sensor has a button that, when pressed, sends a patient call alert to the BSM SW. VMS Chest Sensor Adapter Models L2050E (Pulse Ox Ear Adapter) and L2050F (Pulse Ox Finger Adapter) are plastic, non-sterile, patient-worn, multiple use pulse oxygenation sensors that connect to the Vios Chest Sensor and are secured to the patient via medical grade ECG electrodes.

The provided text is a 510(k) Summary for the Vios Monitoring System™ Model 2050. This document outlines the device's intended use, regulatory information, and a summary of the testing performed to demonstrate substantial equivalence to predicate devices.

However, the document does not contain specific details about acceptance criteria, reported device performance metrics (e.g., sensitivity, specificity, accuracy for arrhythmia detection), the sample size of a test set, the number and qualifications of experts for ground truth establishment, adjudication methods, or effects of AI assistance on human readers.

The text focuses on hardware and software description, regulatory compliance, and general types of testing conducted (electrical safety, biocompatibility, usability, software development lifecycle, specific clinical testing for pulse oximetry and respiratory rate). It mentions that "VMS can generate alerts when rate-based cardiac arrhythmias are detected," but does not provide performance metrics for this specific function in the context of acceptance criteria.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets them based solely on the provided text. The information required for your questions (especially points 1-7, and 9) is not present in this 510(k) Summary.

Here's an overview of what is mentioned in relation to testing, which is very high-level:

Summary of Non-Clinical, Clinical, and Conformance Testing:
The document states that "The safety, effectiveness, and substantial equivalency of the VMS Model 2050 have been confirmed through the following non-clinical, clinical, and conformance testing:"

• Non-clinical:

  • Electrical safety, EMC, and vitals sign monitoring standards (IEC 60601-1, IEC 60601-1-2, IEC 60601-1-8, IEC 60601-2-27, IEC 60601-2-49, EC53)
  • Biocompatibility standards (ISO 10993)
  • Usability and human factors standards (EN 62366)
  • Transportation Simulation testing (ASTM D4169-16)
  • Software development life cycle (EN 62304)
  • Risk Management (ISO 14971)

• Clinical:

  • Pulse oximetry clinical testing (IEC 80601-2-61)
  • Respiratory Rate clinical testing

Missing Information:

• Acceptance Criteria Table & Reported Performance: Not provided for any specific vital sign or arrhythmia detection.
• Sample size (test set) & Data Provenance: Not detailed. It only mentions "clinical testing."
• Number & Qualifications of Experts, Adjudication Method: Not specified for any ground truth establishment.
• MRMC Study / AI Assistance: Not mentioned. The device generates alerts for rate-based arrhythmias, but there's no comparative study with human readers described or any 'AI' effect size.
• Standalone Performance: While the device has an algorithm for arrhythmia detection, the specific performance metrics (sensitivity, specificity) are not reported here.
• Type of Ground Truth: For pulse oximetry and respiratory rate clinical testing, it's implied that a reference standard was used as per relevant IEC standards, but the exact method (e.g., expert consensus on ECG, pathology) for arrhythmia detection is not disclosed.
• Training Set Sample Size: Not mentioned, as this document focuses on substantial equivalence testing rather than algorithm development.
• Ground Truth for Training Set: Not mentioned.

In summary, while the document indicates that various tests were performed to support substantial equivalence, it does not provide the granular detail needed to answer your questions regarding acceptance criteria and performance metrics for the device's diagnostic or alerting capabilities.

Ask a specific question about this device