Search Results

The Perin Health Platform is a wireless remote monitoring system intended for use by healthcare professionals for spot check collection of physiological data in healthcare and home settings for long-term monitoring. The Perin Health Patch can monitor auscultation data of heart and lung sounds, photoplethysmography waveforms (PPG), oxygen saturation (%SpO2), heart rate, electrocardiography (ECG), heart rate variability, R-R interval, respiratory rate, skin temperature, activity detection (including step count), and posture (body position relative to gravity including fall).

The Perin Health System is intended for spot-checking and tracking changes of adult patients in hospitals, clinics, long-term care, and at home. In home-use environments, the Perin Health Platform is able to integrate with optional third-party devices for blood pressure, and weight data collection via the mobile application. The mobile application transmits data from the Health Patch and third party devices to the cloud and web-based portal for storage, analysis, and review by healthcare professionals. The Perin Health Platform can include the ability to notify healthcare professionals when physiological data falls outside set limits or manual trigger by the patient.

The device is intended to provide physiological information for non-critical, adult population.

The Perin Health System is a wireless remote patient monitoring platform that enables healthcare professionals to perform spot-checking and retrospective monitoring of physiological data from adult patients. The Perin Health System is designed for use in hospitals, clinics, long-term care facilities, physician offices, and home environments.

The Perin Health System comprises the following components:

1. Perin Health Patch wearable device
2. Perin Health Patient Mobile Application
3. Perin Health Cloud
4. Perin Health Provider Portal
5. Perin Health Inpatient Application

1. The Perin Health Patch
The Perin Health Patch is a chest-worn wearable device that performs scheduled spot-check measurements of multiple physiological parameters. Unlike continuous monitoring systems, the Perin Health Patch captures measurements at predetermined intervals configured by healthcare providers based on clinical need.

The device integrates six primary sensing modalities:

• Auscultation (heart and lung sounds)
• Electrocardiography (1-channel ECG)
• Pulse oximetry via photoplethysmography (PPG)
• Bioimpedance (BioZ) for respiratory monitoring
• Temperature sensing (skin)
• Motion and orientation detection via accelerometer

The combination of these modalities in a small, low-power wearable form allows for the spot-checking of primary vital signs:

• Heart rate and R-R intervals
• Heart rate variability (HRV) parameters
• ECG waveform data
• Auscultation sound data (heart and lung sounds)
• Respiratory rate
• Pulse (PPG) waveform
• Oxygen saturation (SpO2%)
• Skin temperature
• Fall detection events
• Body posture
• Activity level and step count

The device adheres to the patient's upper left chest at the second intercostal space with a medical-grade long-term wear adhesive. The adhesive is placed on the patient-facing side of the wearable, with cutouts for the sensors to make direct contact with the skin. The wearable device is lightweight and semi-flexible, allowing for the device to conform to the natural curvature of the chest. It is water resistant, allowing for bathing and normal activities while the patient is wearing the system.

The wearable communicates to the receiving unit (mobile phone) via an encrypted Bluetooth Low Energy connection. Measurements, all notifications and control commands, and software updates are transmitted over the BLE connection. The wearable uses Near Field Communication (NFC) to facilitate the Bluetooth pairing process with the mobile phone by simply having to tap their phone to the device to initiate a Bluetooth connection. The wearable device also contains on-board memory that can store over two weeks of spot-check data. When measurements are taken and no receiving unit is present, the wearable can store recordings in the onboard memory. Recordings are stored in a stack, such that at the next connection possibility between the wearable and the receiving unit, the most recent data will be transmitted first followed by other measurements in reverse chronological order.

Other key features of the wearable include:

• Customizable recording schedule set by the healthcare provider in their care program
• Replaceable battery
• Patient-triggered recordings via double-tap
• Signal quality indicators for measurement validation and identification of noisy measurements

2. The Patient Mobile Application
The Patient Mobile Application, available on iOS or Android platforms, is intended exclusively for use in home environments by patients under healthcare provider supervision. The application serves as a data relay and display interface, allowing the patient to complete key tasks, including onboarding, device setup, device communication, and patient-reported data.

The application serves as the primary interface between the Perin Health Patch and the cloud infrastructure, receiving spot-check measurements from the device and uploading them for provider review. The application establishes and manages secured BLE communication with the Health Patch. Given that the Health Patch operates on provider-configured recording schedules, the application manages data transfer in the background with minimal patient interaction required. When internet connectivity is unavailable, the application stores measurements locally until transmission becomes possible. The system also manages firmware updates for the Perin Health Patch.

The application integrates with FDA-cleared third-party blood pressure cuff and scale using BLE and transfers the data to the Cloud System. Healthcare providers determine which patients require the additional third-party device monitoring as part of their individualized care programs. The system also allows users to optionally enter manual data for blood pressure and weight if no third-party device is connected.

Patients are able to review their historical measurement data taken throughout their monitoring program and their goals and thresholds set by their providers. The patient can view metrics assigned within their care program:

• Heart Rate and Heart Rate Variability
• Respiratory Rate
• Oxygen Saturation
• Step Count
• Temperature
• Blood Pressure
• Weight

Patients can also select audio segments captured by the device for playback (no visualization).

The application provides comprehensive patient engagement features. Patients can complete customized questionnaires with up to 20 questions in various formats, review educational content delivered through their care programs, and submit non-critical medical reports to their care team. The reporting feature includes anatomical body mapping for location-specific symptoms, severity scaling, and photo attachment capabilities. The application supports secure messaging with care providers, virtual appointment attendance with waiting room functionality, and comprehensive offline operation with automatic synchronization upon connectivity restoration.

3. The Perin Health Cloud
The Perin Health Cloud infrastructure serves as the central hub for data management and processing. The cloud system receives encrypted spot-check data from relay systems and manages raw data processing (for Health Patch data only), storage, and retrieval of physiological measurements for retrospective clinical review. Algorithms are run in the cloud to process measurements from the Health Patch and generate Signal Quality Index, Heart Rate, Heart Rate Variability, Respiratory Rate, Oxygen Saturation, and Posture.

The alert and notification system enables healthcare professionals to configure multi-level alerts based on clinical parameters, technical issues, or manual patient triggers. Clinical alerts are based on provider-configured thresholds that are set in during the enrollment of a patient in a care program. The system supports complex notification rules including threshold exceedances, percentage changes, trending patterns, and consecutive violations. Alerts are displayed to providers for the purpose of highlighting data during their retrospective review and are not intended to support real-time patient monitoring or urgent care provider action.

The cloud infrastructure includes comprehensive audit logging of all user actions, data access, and system events. The system provides API access for integration with electronic health records with HL7 v2.x, HL7 FHIR R4, and other standard protocols, enabling bidirectional data exchange with major EHR systems.

4. The web-based Provider Portal
The web-based Provider Portal enables healthcare professionals to access and manage patient data and alert statuses remotely through any compatible web browser. Through the portal, providers can review spot-check measurements and historical trends, playback audio recordings of auscultation sounds captured by the Patch, configure individualized care programs, set measurement schedules and alert thresholds, and communicate with patients through various modalities.

Through the portal, providers can review spot-check measurements with customizable vital sign charts displaying trends over days, weeks, or months. Advanced visualization includes waveform analysis for ECG and PPG signals, audio playback for auscultation recordings, and comprehensive annotation tools. The portal displays signal quality indicators and out-of-range values with appropriate visual highlighting based on configured thresholds. The portal also displays patient severity levels (Low/Medium/High) based on the NEWS2 scoring methodology. Additional clinical measures, such blood pressure and weight, that are manually input into the EHR can be read into the Perin Health System and viewed in the Provider Portal using the EHR interface.

The system employs a structured care program architecture that ensures appropriate clinical oversight throughout the monitoring process. Healthcare organizations create standardized care program templates for common conditions. Individual providers can then select from these approved templates and customize them for specific patient needs, prescribing the specific devices needed, measurement frequencies appropriate to the condition, and recording schedules tailored to clinical requirements.

The portal includes comprehensive communication capabilities supporting both patient and care team interactions. Providers can conduct virtual appointments with integrated video calling, AI-powered real-time transcription using AWS HealthScribe, and automated clinical note generation structured into standard sections. The messaging system supports secure text communication with file attachments, while the task management system enables care coordination across team members. Providers can create and deploy customized questionnaires with various response types and scoring algorithms, manage educational content delivery, and review patient-submitted reports with collaborative response capabilities.

Additional portal features include appointment scheduling with EHR integration, comprehensive alert management with acknowledgment workflows, administrative functions for user and device management, and organization hierarchy configuration. The portal provides detailed audit trails, performance analytics, and compliance reporting to support quality improvement initiatives.

5. The Perin Health Inpatient Module
The Perin Health Inpatient Module provides a monitoring dashboard for monitoring capabilities in healthcare facility environments. The modules leverage the existing architectures for the Mobile Application and Provider Portal but offer unique interfaces for inpatient spot-check measurements.

The web-based monitoring dashboard, a page accessible through the Provider Portal, displays vital signs for up to 50 concurrent patients in a grid layout. Each patient card shows the latest values for heart rate, respiratory rate, oxygen saturation, temperature, and device status, with automatic sorting by alert priority and visual indicators for threshold violations. The dashboard refreshes every second, updating as new spot-check recordings are captured from patients across the unit.

The bedside Inpatient Application is built on top of the Android architecture of the Patient Mobile app and operates in kiosk mode. The Beside app only interfaces with the Perin Health Patch and relays information to the Cloud to provide clinicians with access to recent measurements in the Provider Portal Inpatient view. The application also maintains local data storage for backup operation and automatically synchronizes with the cloud upon connectivity restoration. Providers are unable to manually input clinical data (e.g., blood pressure measurements) directly into the bedside Inpatient Application but manual data input into the EHR can be read into and visualized in the Provider Portal over the EHR interface.

The Perin Health System supports monitoring in hospitals and out-of-hospital patient care settings where care is administered by healthcare professionals. Visual alarm indicators highlight parameter exceedances according to configured thresholds. High-priority alerts display prominently with appropriate color coding, though all clinical responses and acknowledgments must be performed through the Provider Portal to maintain proper documentation and workflow management.

The Perin Health System facilitates comprehensive spot-checking and retrospective monitoring across the continuum of care. Data flows from the wearable patch and third-party devices through the patient mobile application to the central cloud infrastructure, where processing algorithms derive clinical insights. Healthcare providers access this information through the web portal or inpatient displays for clinical review and analysis, enabling healthcare providers to track patient progress, adjust treatment plans based on measurements, and identify patients requiring intervention based on retrospective data trends.

Here's a breakdown of the acceptance criteria and the study details for the Perin Health System (PHD80060-2), based on the provided FDA 510(k) clearance documentation:

Acceptance Criteria and Device Performance Study (Perin Health System PHD80060-2)

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria and reported device performance for key physiological parameters are summarized below:

Note: For several parameters (Skin Temperature, Posture, Body Motion, Fall Detection, Step Count, Auscultation data), the document states they were "verified by using bench testing as per the acceptance criteria" or "in accordance with acceptance criteria," implying they met the specified thresholds without explicitly re-stating the achieved performance metrics.

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

• SpO2% (Induced Hypoxia Study):

  • Sample Size: 12 healthy adults (5 female, 7 male)
  • Data Provenance: Not explicitly stated (e.g., country of origin), but implied to be prospective clinical validation conducted for this submission.

• Respiratory Rate (Clinical Validation):

  • Sample Size: 35 participants (17 males, 18 females)
  • Data Provenance: Not explicitly stated (e.g., country of origin), but implied to be prospective clinical validation conducted for this submission.

• ECG, Heart Rate, R-R Interval, and Heart Rate Variability (Clinical Validation):

  • Sample Size: 243 participants
  • Data Provenance: Not explicitly stated (e.g., country of origin), but implied to be prospective clinical validation conducted for this submission.

• Wear-life Performance (Internal Clinical Wear Life Evaluation):

  • Sample Size: 26 participants
  • Data Provenance: Across 3 clinical sites. Implied to be prospective clinical evaluation.

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

The document does not explicitly state the number or specific qualifications of experts used to establish ground truth for the clinical test sets. However, it references:

• SpO2%: "arterial blood samples analyzed by a laboratory co-oximeter" as the gold standard. This implies specialized laboratory personnel for analysis, but their number and specific qualifications are not detailed.
• Respiratory Rate: "manually counted end-tidal CO2" as the gold standard. This would typically be performed by trained clinical staff, but their number and qualifications are not specified.
• ECG, HR, HRV: "standard Holter monitor" as the reference for comparison. Interpretation of Holter data would involve cardiologists or trained technicians, but the document doesn't specify if this was used as "ground truth" to establish the Holter reference itself or if it refers to the Holter output as the reference measurement.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method (e.g., 2+1, 3+1, none) for the test sets. The studies compare the device's measurements directly to a "gold standard" or "reference monitor" without mentioning a multi-reader adjudication process for discrepancies.

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

There is no indication of a Multi-Reader Multi-Case (MRMC) comparative effectiveness study being done to evaluate how much human readers improve with AI vs. without AI assistance. The document focuses on the standalone performance of the device's measurements against established standards.

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

Yes, standalone performance was done for several key parameters. The clinical validation studies directly assess the Perin Health System's ability to measure physiological data (SpO2%, Respiratory Rate, ECG/HR/HRV) against a specified gold standard or reference device. These studies inherently evaluate the algorithm's performance without direct human interpretation influencing the measurement output. For example:

• SpO2% accuracy is measured against arterial blood samples.
• Respiratory rate accuracy is measured against manually counted end-tidal CO2.
• ECG, HR, HRV performance is validated against a standard Holter monitor.

7. Type of Ground Truth Used

The types of ground truth used for the clinical validation studies include:

• Laboratory Standard / Direct Measurement: For SpO2%, the ground truth was "arterial blood samples analyzed by a laboratory co-oximeter."
• Clinical Gold Standard: For Respiratory Rate, the ground truth was "manually counted end-tidal CO2."
• Reference Clinical Device: For ECG, Heart Rate, R-R Interval, and Heart Rate Variability, the ground truth/reference was a "standard Holter monitor."

8. Sample Size for the Training Set

The document does not provide any information regarding the sample size for the training set. This information is typically proprietary to the manufacturer and not usually disclosed in 510(k) summaries unless specifically relevant to a novel AI/ML algorithm requiring such details for FDA review.

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

Since no information about the training set or its sample size is provided, there is no information available on how the ground truth for the training set was established.

Ask a specific question about this device

The Huxley Home Sleep Apnea Test (SANSA) is a wearable device intended for use in the recording, analysis and storage of biophysical parameters to aid in the evaluation of sleep-related breathing disorders of adults suspected of sleep apnea. The device is intended for the clinical and home use setting under the direction of a Healthcare Professional (HCP)

The Huxley Home Sleep Apnea Test (SANSA™) is a wearable device intended for use in the recording, analysis, and storage of biophysical parameters to aid in the evaluation of sleep-related breathing disorders of adults suspected of sleep apnea. The device is intended for clinical and home use setting under the direction of a Healthcare Professional (HCP). The system is prescription use only.

The SANSA HSAT collects multiple physiological signals using a single wearable patch worn on the chest. The SANSA device contains a reflective PPG sensor, a single-lead ECG sensor, and a 3-axis accelerometer. The signals from these sensors are passed into a cloud-based algorithm which utilizes a combination of signal processing and AI/ML components to compute time-series data for clinician review and summary metrics for report output. The device outputs the following time-series channels: Oximetry, Heart Rate, Chest Movement, Snoring, Body Position, Respiratory Effort, Actigraphy, Sleep staging (Wake, REM, Non-REM), ECG (reference only). The following summary metrics are calculated: SANSA-Apnea Hypopnea Index (sAHI), SANSA Apnea Hypopnea Index – Central (sAHIc), Sleep Times (Total Sleep Time, Total REM Time, Non-REM sleep time) and AHI during REM.

Recorded data is uploaded to a software portal where physiological tracings are made available for review and event editing by a qualified healthcare professional. The device is intended to be worn for 10 hours per study.

The subject SANSA HSAT device consists of the same physical device components, intended use case, and operation, as the predicate SANSA HSAT device cleared under K244027. This submission updates the algorithm to update performance and add the ability to classify between Obstructive and Central Sleep Apnea events using an AI/ML classifier and present a summary metric, SANSA Apnea Hypopnea Index – Central (sAHIc). REM/NREM Classification and REM related sleep metrics were also added.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) clearance letter for SANSA HSAT:

Acceptance Criteria and Reported Device Performance

Study Details

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

• Sample Size: 325 subjects
• Data Provenance: The study was a "multisite in-lab comparison study." While specific countries are not mentioned, "multisite" implies data collected from multiple clinical locations. The study population details (racial and ethnic demographics) suggest data from diverse populations within a likely Western healthcare system (e.g., North America). The study is prospective in nature, as it involved patients undergoing in-lab comparison.

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

The document does not explicitly state the number of experts used or their specific qualifications for establishing the ground truth. It mentions a "PSG reference standard" and implicitly implies expert scoring for the Polysomnography (PSG) data. For a sleep study, this would typically involve Registered Polysomnographic Technologists (RPSGTs) and/or Board-Certified Sleep Physicians.

3. Adjudication Method for the Test Set

The document does not explicitly state the adjudication method. The common practice for establishing ground truth in comparison to a gold standard like PSG is that the PSG is scored according to established guidelines (e.g., AASM manual), and this score serves as the ground truth. It doesn't mention multiple scorers for the PSG data or a specific adjudication process beyond the "PSG reference standard."

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

The document does not indicate that an MRMC comparative effectiveness study was done. The study focuses on the standalone performance of the device against a PSG reference standard rather than comparing human reader performance with and without AI assistance.

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

Yes, a standalone performance study was done. The reported performance for sAHIc and REM/NREM classification directly reflects the performance of the SANSA HSAT device's algorithm in classifying events and sleep stages without human intervention other than the initial setup and data collection. The performance metrics are reported for the device itself (e.g., "The sensitivity of the Sansa device to detect AHIc ≥ 10...").

6. Type of Ground Truth Used

The type of ground truth used is expert consensus/Polysomnography (PSG) reference standard. PSG is widely considered the gold standard for diagnosing sleep-related breathing disorders and for sleep staging. The document explicitly states, "The performance of AHIc and NREM/REM sleep classification were compared to the PSG reference standard."

7. Sample Size for the Training Set

The document does not explicitly state the sample size for the training set. It only describes the clinical performance data derived from the test set of 325 subjects.

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

The document does not explicitly state how the ground truth for the training set was established. Given the nature of the device (AI/ML components), it is highly probable that the training data's ground truth was also established using scored PSG data, similar to the test set, but this is not directly specified in the provided text.

Ask a specific question about this device

The Hexoskin Medical System (HMS) is intended for use at home, or at a healthcare facility, on the order of a licensed medical professional, to record, display and store the following physiological data: a) 3 leads of electrocardiogram; b) heart rate; c) respiratory rate; and d) activity. The device is intended for use when the clinician decides to evaluate the physiologic signals of adult patients as an aid to diagnosis and treatment. The HMS ECG recordings are indicated for the manual assessment of cardiac rhythm disturbances. The device does not produce alarms and is not intended for active patient monitoring (real-time). The device is not intended for use as life supporting equipment on high-risk patients such as critical care patients. The device is not intended for use in the presence of a pacemaker.

The HMS consists of four main components - three physical components and one software user interface (UI) component. The physical components are the HMS Recorder, the HMS Shirt, and the Cable. The Recorder is a rechargeable data acquisition module that connects to the Shirt. The Shirt is available in a wide range of configurations, catering to diverse patient body types and builds. The Cable is a USB to micro-USB cable that connects to the Recorder for data transfer and charging. The UI component is a PC-based, stand-alone software that displays the recordings stored on the Recorder.

This device is not an apnea monitor. Users should not rely on its respiration monitoring for detecting cessation of breathing. The Hexoskin Medical System does not provide any automatic analysis or diagnosis.

N/A

Ask a specific question about this device

The Huxley Home Sleep Apnea Test (SANSA) is a wearable device intended for use in the recording, analysis, and storage of biophysical parameters to aid in the evaluation of sleep-related breathing and cardiac disorders of adults suspected of sleep apnea. The device is intended for the clinical and home use setting under the direction of a Healthcare Professional (HCP). The system is prescription use only.

The SANSA device records and stores ECG recording for up to 10 hours of wear time which can be displayed in the software portal for manual annotation and analysis. The SANSA does not provide automated analysis of the ECG and is not intended to be used with a 3rd party automated algorithm and is not intended for pacemaker analysis.

The Huxley Home Sleep Apnea Test (SANSA™) is a wearable device intended for use in the recording, analysis, and storage of biophysical parameters to aid in the evaluation of sleep-related breathing disorders of adults suspected of sleep apnea. The device is intended for clinical and home use setting under the direction of a Healthcare Professional (HCP). The system is prescription use only. The SANSA™ device records and stores ECG recording for up to 10 hours of wear time which can be displayed in the software portal for manual annotation and analysis. The SANSA™ does not provide automated analysis of the ECG and is not intended to be used with a 3rd party automated algorithm and is not intended for pacemaker analysis.

The SANSA HSAT collects multiple physiological signals using a single wearable patch worn on the chest. The SANSA device contains a reflective PPG sensor, a single-lead ECG sensor, and a 3-axis accelerometer. The signals from these sensors are passed into a cloud-based algorithm which utilizes a combination of signal processing and AI/ML components to compute time-series data for clinician review and summary metrics for report output. The device outputs the following time-series channels: Oximetry, Heart Rate, Chest Movement, Snoring, Body Position, Respiratory Effort, Actigraphy, Sleep staging (Sleep/Wake), and ECG. The following summary metrics are calculated: sansa-Apnea Hypopnea Index (sAHI) and Total Sleep Time (TST).

Recorded data are uploaded to a software portal where physiological tracings are made available for review and event editing by a qualified healthcare professional. The device is intended to be worn for 10 hours per study.

Here's a breakdown of the acceptance criteria and the study information for the SANSA HSAT device, based on the provided FDA 510(k) clearance letter:

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria and performance data are primarily found on Page 9 of the document, under the "Performance" section within "Table 1: Device Comparison."

Note: For Heart Rate, SpO2, and OSA diagnosis metrics, the predicate device (iRhythm Zio Monitor) does not provide these analyses or collect SpO2. Therefore, the "acceptance criteria" for these aspects are implicitly met by the absence of safety/effectiveness concerns with the SANSA HSAT's reported performance, which aligns with its intended use in sleep apnea evaluation. The ECG recording accuracy metrics are directly comparable and are identical between the subject device and the predicate.

2. Sample Size and Data Provenance for the Test Set

The document does not explicitly state the sample size used for the clinical performance validation of the SANSA HSAT's ECG, nor does it specify the country of origin or whether the data was retrospective or prospective. It only mentions:

• Sample Size: Not specified.
• Data Provenance: Not specified (country/retrospective/prospective).

For the Aid to Diagnosis of OSA, a sensitivity of 88.2% and specificity of 87.3% are reported. The document does not provide the sample size or provenance for this particular study, but it was leveraged from a previous clearance (K244027).

3. Number of Experts and Qualifications for Ground Truth - Test Set

The document does not provide details on the number or qualifications of experts used to establish ground truth for the test set specifically for the ECG clinical performance validation.

For the "Aid to Diagnosis of Moderate to Severe OSA", the percentages suggest a comparison against a diagnostic standard, which would typically involve expert interpretation, but the details are not provided in this document.

4. Adjudication Method for the Test Set

The document does not specify any adjudication method (e.g., 2+1, 3+1) used for establishing the ground truth for the test set.

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

No information is provided about a multi-reader multi-case (MRMC) comparative effectiveness study, or any effect size related to human reader improvement with or without AI assistance. The SANSA device explicitly states it "does not provide automated analysis of the ECG and is not intended to be used with a 3rd party automated algorithm." (Pages 4 and 5).

6. Standalone Performance Study

Yes, a standalone performance study was done for the SANSA HSAT's ECG:

• Study Type: "Sansa ECG clinical performance was validated through comparison to a simultaneously collected reference standard Holter monitor." (Page 11)
• Performance: "Clinically acceptable performance was demonstrated through qualitative and quantitative analysis of the ECG signal." (Page 11)

The reported sensitivity and specificity for OSA diagnosis (Page 9) also represent standalone algorithm performance.

7. Type of Ground Truth Used

• For ECG Clinical Performance: "simultaneously collected reference standard Holter monitor." (Page 11)
• For Aid to Diagnosis of OSA (reported sensitivity/specificity): While not explicitly stated, the context of "Aid to Diagnosis" for Sleep Apnea typically implies comparison to a polysomnography (PSG) study, which is the gold standard, interpreted by sleep specialists. This data was "leveraged from previous clearance."

8. Sample Size for the Training Set

The document does not provide any information about the sample size used for a training set. This is consistent with the statement that the device does not provide automated analysis of the ECG and explicitly states that it is not intended for use with a 3rd party automated algorithm. While the device uses "AI/ML components" for other signals (Snoring, Body Position, Respiratory Effort, Actigraphy, Sleep staging), the training set size for these components is not detailed in this document.

9. How Ground Truth for the Training Set Was Established

The document does not provide information on how the ground truth for any potential training set was established. Given the focus on manual annotation and analysis for ECG, and the lack of detail on the AI/ML components for other signals, this information is not present in the clearance letter.

Ask a specific question about this device

Linshom Continuous Predictive Respiratory Monitoring System (CPRMS) is indicated for use by healthcare professionals in healthcare facilities, such as procedural areas and recovery rooms, to monitor breathing in adult, (at least 22 years of age) patients.

The CPRMS is a non-invasive system that graphically displays temperature changes against time and reports values of respiratory rate and seconds since last breath, along with a trend of tidal volume.

CPRMS measurements are used as an adjunct to other clinical information sources.

The Linshom CPRMS (Continuous Predictive Respiratory Monitoring System) is a portable and reliable system for detection of spontaneous respiration. It's non-invasive and is not corrupted by motion artifacts. The system autonomously adapts to the local thermal environment to deliver a usable signal without complicated hardware and firmware processing.

N/A

Ask a specific question about this device

The WatchPAT400 (WP400) is a non-invasive home care device for use with patients suspected to have sleep related breathing disorders. The device is a diagnostic aid for the detection of sleep related breathing disorders, sleep staging (REM Sleep, Light Sleep, Deep Sleep and Wake), snoring level and body position. The WP400 generates a peripheral arterial tonometry ("PAT"), Respiratory Disturbance Index ("pRDI"), Apnea-Hypopnea index ("pAHI"), Central Apnea-Hypopnea index ("pAHIc"), sleep staging identification (pSTAGES) and optional snoring level and body position discrete states from an external integrated snoring and body position sensor. The device's pSTAGES and snoring level and body position provide supplemental information to its pRDI/pAHI/pAHIc. The device's pSTAGES and snoring level and body position are not intended to be used as the sole or primary basis for diagnosing any sleep related breathing disorder, prescribing treatment, or determining whether additional diagnostic assessment is warranted.

pAHIc is indicated for use in patients 17 years and older. All other parameters are indicated for 12 years and older.

The WP400 is a ventilatory effort recorder that utilizes PAT technology. The controller part of the device is worn on the wrist and records the PAT signal and arterial blood oxygen saturation levels by a finger-mounted probe based on an optical plethysmographic method. An actigraph, embedded in the wrist worn controller unit, records wrist motion that is used to determine periods of sleep vs wake. A chest sensor is attached to the patient's chest right under the sternal notch for measuring snoring level, body position states and chest movements. The device is battery powered and connects via Bluetooth to a mobile application.

The WP400 is a re-usable device, with sensors common with the WP300 and wireless connectivity identical to the WP1. With the same core technology, signal acquisition, and signal processing identical across all three WatchPAT devices, the WP400 is a combination of its predecessors: device housing leveraged from the WP300 for its re-usable nature, combined with the ability for wireless communication leveraged from the WP1. Signals recording, processing, and analysis has not changed from the predicate devices.

N/A

Ask a specific question about this device

The PVDF Effort Sensor is intended to measure and output respiratory effort signals from a patient for archival in a sleep study. The sensor is an accessory to a polysomnography system which records and conditions the physiological signals for analysis and display, such that the data may be analyzed by a qualified sleep clinician to aid in the diagnosis of sleep disorders.

The PVDF Effort Sensor is intended for use on both adults and children by healthcare professionals within a hospital, laboratory, clinic, or nursing home, or outside of a medical facility under the direction of a medical professional.

The PVDF Effort Sensor does not include or trigger alarms, and is not intended to be used alone as, or a critical component of,

• an alarm or alarm system;
• an apnea monitor or apnea monitoring system; or
• life monitor or life monitoring system.

The PV01 PVDF Effort Sensor is a respiratory effort monitoring accessory designed for use during sleep studies to assess breathing patterns by measuring chest and abdominal wall movement. The device functions as an accessory to polysomnography (PSG) systems, enabling qualified sleep clinicians to analyze respiratory data for the diagnosis of sleep disorders.

The sensor consists of two main components: a PVDF (polyvinylidene fluoride) sensor module and an elastic belt. The sensor module contains two plastic enclosures connected by a piezoelectric PVDF sensing element encased in a silicone laminate. The PVDF material generates a tiny voltage that is output through the lead wire to the sleep amplifier. The change in voltage as the tension on the PVDF film fluctuates corresponds to the breathing of the patient. Since the PVDF material generates voltage, the sensor does not require a battery or power from the amplifier. The output signal is processed by the sleep recording system for monitoring and post-study analysis.

The PV01 PVDF Effort Sensor is intended for prescription use only by healthcare professionals in hospitals, sleep laboratories, clinics, nursing homes, or in home environments under medical professional direction. The device is designed for use on both adult and children participating in sleep disorder studies. The sensor is intended to be worn over clothes and not directly on the patient's skin.

The 510(k) clearance letter for the PV01 PVDF Effort Sensor does not contain the specific details required to fully address all aspects of your request regarding acceptance criteria and the study proving the device meets them. This document is a regulatory approval letter, summarizing the basis for clearance, not a detailed study report.

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

Overview of Device Performance Study

The PV01 PVDF Effort Sensor underwent "comprehensive verification and validation testing" including "functional and performance evaluations" and "validation studies" to confirm it meets design specifications and is safe and effective. Additionally, "comparative testing against the Reference Device" was performed.

This suggests that the performance evaluation primarily focused on:

1. Safety Tests: Compliance with UL 60601-1 standards to ensure electrical and liquid ingress safety.
2. Usability and Validation Test: Assessment of user experience and comfort during a simulated sleep study.
3. Performance Comparison Test: Electrical signal output comparison to a legally marketed predicate device under simulated breathing conditions.
4. Temperature Range Test: Verification of signal output performance at extreme operating temperatures.

Acceptance Criteria and Reported Device Performance

Based on the "Summary of Tests Performed" section, the following can be inferred:

Missing Information and Limitations:

The provided FDA 510(k) clearance letter is a high-level summary and does not contain the granular details typically found in a full study report. Therefore, most of the following requested information cannot be extracted directly from this document.

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

   • Test Set Size: Not specified for any of the performance tests. For the usability test, it mentions "Participants" (plural), but no number. For the performance comparison test, it states "Both devices were placed on a rig," implying a comparison, but no human subject or case count.
   • Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). The usability test mentions "participants," potentially implying prospective data collection, but this is a broad inference.

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

   • Not Applicable/Not Specified: The device is a "PVDF Effort Sensor" that measures and outputs respiratory effort signals. Its purpose is to provide raw physiological data for a "qualified sleep clinician to aid in the diagnosis of sleep disorders." The device itself does not provide a diagnosis or interpretation that would require expert ground truth labeling in the traditional sense of an AI diagnostic device (e.g., image-based AI). The performance assessment appears to be against expected signal characteristics and comparison to a known device, not against clinical ground truth established by experts.

3. Adjudication method for the test set:

   • Not Applicable/Not Specified: Given the nature of the device (a sensor outputting physiological signals) and the described tests, a formal adjudication process (like for interpreting medical images) is not mentioned or implied.

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

   • No: This type of study (MRMC for AI assistance) is not mentioned. The device is a sensor, not an AI interpretative tool designed to assist human readers directly. It provides raw data for clinicians to analyze.

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

   • Partially Yes (for the sensor itself): The "Performance Comparison Test" and "Temperature Range Test" assess the device's signal output performance independently without a human in the loop for interpretation. The "Safety Tests" are also standalone tests on the device's physical and electrical properties.

6. The type of ground truth used:

   • Physiological Simulation / Device Output Comparison: For the "Performance Comparison Test," the ground truth was essentially the simulated breathing patterns produced by a "rig" and the expected output signals of a known predicate/reference device.
   • User Feedback / Self-Reported Metrics: For the "Usability and Validation Test," the ground truth was the participants' subjective feedback on comfort and ease-of-use, and the absence of reported use errors or adverse events.
   • Compliance with Standards: For "Safety Tests," the ground truth was compliance with the specified clauses of the UL 60601-1 standard.

7. The sample size for the training set:

   • Not Applicable/Not Specified: The PV01 PVDF Effort Sensor is described as a passive hardware sensor ("generates a tiny voltage," "does not require a battery or power from the amplifier") that measures physical movement. It is not an AI/ML algorithm that requires a "training set" in the computational sense.

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

   • Not Applicable: As stated above, there is no mention or implication of a training set as this is a hardware sensor, not an AI/ML algorithm.

In summary, the provided document gives a high-level overview of the acceptance criteria met for regulatory clearance, primarily focusing on safety, basic functional performance relative to another device, and usability. It does not delve into the detailed statistical methodology and independent ground truth establishment typical of AI/ML device studies.

Ask a specific question about this device

The Somfit D is a single-use, non-invasive prescription device for home use with patients suspected to have sleep-related breathing disorders. The Somfit D is a diagnostic aid for the detection of sleep-related breathing disorders, sleep staging (REM, N1, N2, N3, Wake), and snoring level. The Somfit D system acquires electrical data from three frontal electrodes, tri-axial accelerometer data, acoustical and plethysmographic data. The Somfit D calculates and reports to clinicians EEG/EOG channels, Sleep Stages, SpO2, Peripheral Arterial Tonometry signal, pulse rate, and snoring level. The Somfit D calculates and reports to clinicians derived parameters such as Peripheral Arterial Tonometry-derived Apnea Hypopnea Index, Obstructive Desaturation Index; and hypnogram-derived indices such as time in each sleep stage. Somfit D data is not intended to be used as the sole or primary basis for diagnosing any sleep-related breathing disorder, prescribing treatment, or determining whether additional diagnostic assessment is warranted. The Somfit D is not intended for use as life support equipment, for example vital signs monitoring in intensive care unit. The Somfit D is a prescription device indicated for adult patients aged 21 years and over.

The Somfit D is a home-based sleep monitoring device which records signals from the patient's forehead. Somfit D is a wearable, low voltage, battery operated device which is attached to subject forehead via a self-adhesive and disposable skin electrode patch. The electrodes are placed on the anterior Prefrontal cortex (PFC) at the Fp1 and Fp2 positions according to the 10/20 EEG system. The device allows for recording of two frontal EEG signals, pulse rate, SPO2, PAT, PPG, motion, and snore. Somfit D uses a mobile phone application to acquire data wirelessly via Bluetooth BLE technology, then transfer into a secure cloud, for management, storage and post-processing. The software reports measured parameters in a format compatible with the American Academy of Sleep Medicine guidelines, including sleep time, ODI, pAHI and conventional graphical displays such as a hypnogram.

The provided FDA 510(k) clearance letter and Somfit D 510(k) Summary describe the acceptance criteria and the study that proves the device meets those criteria. However, it explicitly states that the Somfit D is substantially equivalent to the predicate device, Somfit (K231546), and therefore, the performance data for the Somfit D is derived from the studies conducted on the Somfit. The summary then refers to already submitted and approved studies for the Somfit device.

Here's a breakdown of the requested information based on the provided document:

Acceptance Criteria and Device Performance (Derived from Predicate Device, Somfit)

Table 1: Acceptance Criteria and Reported Device Performance

Study Details (Pertaining to the Predicate Device, Somfit, as explicitly stated for Somfit D equivalence)

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

   • Oximeter Validation: Controlled desaturation study in accordance with ISO 80601-2-61. Specific sample size not specified in this document, but implied to be sufficient for standard compliance. Data provenance is implied to be from a "Hypoxia Lab." The document doesn't specify if it was retrospective or prospective, or country of origin, but clinical studies for FDA clearance are typically prospective to ensure controlled conditions.
   • Home Sleep Apnea Test Validation (pAHI, ODI, Sleep Staging): A "Multi-Site Clinical Study" was conducted. Specific sample sizes for each of these validations are not provided in this summary. The document states "clinical data for the purpose of the predicate device Somfit (K231546), already submitted and approved," indicating these details would be found in the original Somfit 510(k) submission. The provenance is from "Multi-Site Clinical Study," implying multiple locations, likely within the regulatory jurisdiction where the clearance was sought (e.g., US, Australia). It's implied to be prospective 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 explicitly stated in the provided 510(k) summary for any of the clinical validations (Oximeter, pAHI, ODI, Sleep Staging). It only mentions that the studies were "meaningful validations" and "concordance," implying comparison to a gold standard. For sleep staging, ground truth is typically established by certified polysomnography technologists and/or sleep physicians.

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

   • This information is not explicitly stated in the provided 510(k) summary for any of the clinical validations.

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 study is mentioned. The Somfit D (and its predicate Somfit) is described as a diagnostic aid that calculates and reports parameters to clinicians. It's not presented as an AI-assissted reading tool for human interpretation, but rather a device that quantifies specific physiological signals and derives standard indices. The human role is in interpretation of the reported data, not in an AI-assisted reading workflow.

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

   • Yes, the device (Somfit D, through its predicate Somfit) performs standalone algorithmic analysis to calculate:
     • Sleep Stages (REM, N1, N2, N3, Wake)
     • SpO2
     • Peripheral Arterial Tonometry (PAT) signal
     • Pulse rate
     • Snoring level
     • PAT-derived Apnea Hypopnea Index (pAHI)
     • Obstructive Desaturation Index (ODI)
     • Hypnogram-derived indices (e.g., time in each sleep stage)
   • The "meaningful validation" studies for these parameters (pAHI, ODI, Sleep Staging) suggest a comparison of the device's algorithmic outputs against established ground truth.

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

   • Oximeter Validation: Performed in a "Hypoxia Lab," implying comparison to a highly accurate laboratory reference oximeter or blood gas analysis (gold standard for SpO2 measurements).
   • Home Sleep Apnea Test Validation (pAHI, ODI, Sleep Staging): While not explicitly stated, for HSAT devices, "ground truth" for pAHI and ODI is typically derived from comparison to full in-lab Polysomnography (PSG) data scored by a certified sleep technologist and/or interpreted by a board-certified sleep physician, which is considered the clinical gold standard. For sleep staging, the ground truth would be expert-scored PSG recordings.

7. The sample size for the training set:

   • This information is not provided in the summary. The summary focuses on the validation studies, which imply the device's algorithms were already developed and trained.

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

   • This information is not provided in the summary, as it pertains to the development phase rather than the validation phase described.

Ask a specific question about this device

The LuMon™ System is a noninvasive, non-radiation device that provides information on regional impedance variation within a cross-section of a patient's thorax. Graphical and numerical information is presented to the user as an adjunctive tool to other clinical information to support the user to assess a patient's respiratory condition.

The LuMon™ System is indicated for neonatal and infant patients with chest circumferences between 16.5 - 50 cm and adolescent through adult patients with chest circumferences between 76 - 128 cm who are breathing spontaneously or require mechanical ventilation in professional healthcare facilities.

Impedance-based respiratory rate monitoring is indicated for adults 22 years and older whose chest circumference is above 76 cm only.

The LuMon™ System also displays selected physiological and respiratory parameters from supported bedside devices.

The LuMon™ System does not measure regional ventilation of the lungs.

The LuMon™ System is a compact and lightweight Electrical Impedance Tomography (EIT) system that provides noninvasive monitoring of variations of regional air content/volume within a cross-section of the patient's thorax and patient respiration. It displays the results as real-time EIT images, waveforms, and derived parameters.

The system consists of a controller display unit, signal acquisition connector cable, and patient-applied conductive textile electrode belts. The system can connect to external bedside devices such as ventilators and monitoring devices to display contextual information for interpretation of EIT measurements.

The provided FDA 510(k) clearance letter and summary for the LuMon™ System contains information regarding its acceptance criteria and the studies conducted to demonstrate its performance. However, some specific details commonly found in a comprehensive study report (e.g., exact sample size for each clinical study, number of experts for ground truth, adjudication methods beyond "clinician-scored") are not explicitly stated in this high-level summary.

Based on the provided text, here's a structured response addressing your request:

Acceptance Criteria and Device Performance for LuMon™ System

The LuMon™ System underwent extensive non-clinical (bench and pre-clinical) and clinical testing to demonstrate its safety and effectiveness. The acceptance criteria are implicitly defined by the performance characteristics presented in the comparison tables and the successful attainment of stated accuracies and correlations.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are generally established as equivalent to or better than the predicate/reference devices, or as meeting pre-defined tolerances for specific parameters.

2. Sample Size and Data Provenance

• Test Set Sample Size:
  • Pre-clinical: "Rabbit and piglet models" (specific number not given).
  • Clinical (Global Volume Changes): "Healthy Adult Volunteers" and "Adult ICU patients on mechanical ventilation" (specific numbers not given).
  • Clinical (Regional Impedance Distribution): "Healthy Adult Volunteers" (specific numbers not given).
  • Clinical (Respiration Rate): "Healthy Adult Volunteers" and "Adult spontaneously breathing and mechanically ventilated ICU patients" (specific numbers not given).
  • Chest Circumference for EIT Measurements: Validated across 19 cm to 47 cm (pre-clinical) and 16.5 - 50 cm (neonatal/infant) and 76 - 128 cm (adolescent/adult) (indications for use).
  • Chest Circumference for RR Monitoring: Adults 22 years and older with chest circumference > 76 cm.
• Data Provenance: Not explicitly stated regarding country of origin for clinical data. The studies are described as "pre-clinical" and "clinical," with no indication of being retrospective. "Clinical testing was performed to support safety and effectiveness" generally implies prospective data collection for regulatory purposes.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: Not specified.
• Qualifications of Experts: For the Respiration Rate study, the reference standard was "Clinician-scored EtCO2 capnogram." This implies medical professionals were involved in establishing the ground truth, but their specific qualifications (e.g., types of physicians, years of experience) are not detailed.

4. Adjudication Method for the Test Set

• For Respiration Rate Ground Truth: "Clinician-scored EtCO2 capnogram" implies expert review. However, the exact adjudication method (e.g., 2+1, 3+1, majority vote, independent reads with reconciliation) is not specified.

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

• It is not explicitly stated that a specific MRMC study was conducted to compare human readers with and without AI assistance.
• The device is presented as an "adjunctive tool to other clinical information to support the user," meaning it assists clinicians rather than replacing them. Its effectiveness is shown through its ability to provide accurate EIT data and respiratory rate, which clinicians would then integrate into their assessment. The summary focuses on the device's accuracy relative to reference standards or predicate devices, not on direct human-AI performance comparison studies.

6. Standalone (Algorithm Only) Performance

• Yes, the performance characteristics listed in the tables (e.g., R-squared correlations for EIT-CT, accuracy for RRi against reference standards, SNR, voltage accuracy) represent the standalone performance of the algorithm and the device. The clinical studies compare the device's output itself to established medical standards or other modalities, distinct from how a human user might interpret or use that output.

7. Type of Ground Truth Used

• Pre-clinical (Regional Impedance Distribution): Differential CT changes in aeration (healthy and injured lungs, one- and two-sided intubation) and "established physiological changes" were used as ground truth.
• Clinical (Global Volume Changes): Body plethysmograph traces and Ventilator flow-sensed volumes were used as ground truth.
• Clinical (Regional Impedance Distribution): The Timpel Enlight 2100 predicate comparison was used for ground truth.
• Clinical (Respiration Rate): Clinician-scored EtCO2 capnogram was used as ground truth.

8. Sample Size for the Training Set

• The information provided is a 510(k) summary, which typically focuses on validation. The sample size for the training set is not provided in this document. Training data details are usually proprietary and not disclosed in 510(k) summaries unless directly relevant to the regulatory pathway or substantial equivalence claim.

9. How Ground Truth for the Training Set Was Established

• The document does not specify how ground truth was established for the training set. Similar to the training set size, details about the training data and its ground truth establishment are generally considered proprietary and are not typically included in a public 510(k) summary. The summary focuses on the independent test data performance.

Ask a specific question about this device

The Respiree Cardio-Respiratory Monitor is a respiratory monitor intended for hospitals and hospital-type facilities in non-ICU settings and home settings.

The Respiree Cardio-Respiratory Monitor is indicated for the non-invasive spot checking of respiration rate (RR) for adult patients.

The Respiree Cardio-Respiratory Monitor System comprised of the following devices:

• Respiree Cardio-Respiratory Monitor
• Respiree Gateway and accessories (Antenna, charging cable)
• Respiree Dashboard

The Respiree Cardio-Respiratory Monitor is a wearable respiratory monitor. For measurement of respiration rate (RR), the device is affixed to the chest using a disposable adhesive patch with a hook-and-loop fastener to attach to the monitor. The device uses a vertical-cavity surface-emitting diode to emit optical light directed toward the skin. An integrated photodetector in a nearby position senses the diffused collected light. An adaptive signal processing method is used to enhance the device respiratory rate measurements by splitting the signal processing optimizations across different respiratory rate bands.

The monitor is powered by a 3.7V rechargeable, lithium-ion battery and is charged using the gateway provided. The Respiree Cardio-Respiratory Monitor transmits respiration rate raw data to the gateway via AES 256 encrypted Bluetooth wireless technology, and the latter uploads the data to the fixed secured cloud server either via Wi-Fi or LTE.

The Respiree Dashboard is a web application user interface that enable healthcare professional to access recorded respiration rate information for spot patient monitoring. The data from the Respiree Cardio- respiratory Monitor are intended for use by healthcare professionals as an aid to diagnosis and treatment. The device is not intended for use on critical care patients.

The provided FDA 510(k) clearance letter and summary for the Respiree Cardio-Respiratory Monitor System (K250934) indicate that clinical studies were not required for this specific submission, as there was "no change in the respiration rate software algorithm cleared in the previous version of the device (K223681)." This implies that the performance data for the respiration rate measurement itself was established in a prior submission (K223681).

Therefore, I cannot extract specific details about new clinical studies for K250934 that would directly prove the device meets acceptance criteria for respiration rate measurement within this document. The document primarily focuses on demonstrating substantial equivalence based on the updated hardware, expanded use environment (home setting), and data presentation methods, leveraging the previous clearance for the core measurement accuracy.

However, I can infer information about the acceptance criteria for the respiration rate measurement and the reported device performance based on the comparison table with the predicate devices. The other requested information (sample size, experts, adjudication, MRMC, standalone, ground truth, training set details) is typically found in the clinical study report itself, which is not part of this 510(k) summary for K250934.

Inference from K250934 Document (based on predicate comparison):

1. Table of Acceptance Criteria and Reported Device Performance (Inferred from Predicate Comparison)

Explanation of Inferences:

• The document explicitly states that the subject device "uses the identical technology (i.e., same sensor units and algorithms) for measuring respiratory rate compared to the primary predicate."
• The "Performance Accuracy (Arms)" and "Performance Range" are listed as identical for the subject device and the primary predicate, implying that these are the established performance characteristics for the core respiration rate measurement, and these values serve as the reported device performance and implicitly, the acceptance criteria derived from the predicate.

Information NOT available in the provided document for the core respiration rate measurement (as no new clinical study was conducted for K250934 to re-evaluate RR accuracy):

2. Sample size used for the test set and the data provenance: Not present for a new RR accuracy study. This information would have been part of the K223681 submission.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience): Not present for a new RR accuracy study.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not present for a new RR accuracy study.
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 applicable for a spot-checking respiration rate monitor. This device measures a physiological parameter, not for interpreting medical images.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The "Performance Accuracy (Arms) < 3rpm" implies a standalone performance measure of the algorithm against a reference standard. However, the details of how this was established (e.g., specific study design, reference standard) are not in this document.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not specified in this document for the RR measurement. For respiration rate, this typically involves a highly accurate reference method like capnography, impedance pneumography, or manually adjudicated observation.
8. The sample size for the training set: Not present.
9. How the ground truth for the training set was established: Not present.

Additional Study Information Available in the Document for K250934:

The document highlights the studies conducted to support the changes in the device (home use, hardware modifications, data presentation), rather than re-validating the core RR measurement where the algorithm remained unchanged:

• Software verification and validation: Confirmed acceptability for intended use.
• Biocompatibility testing: According to ISO 10993-5 and -10 for patient-contacting components.
• Human factors and usability testing: Conducted by intended users to support acceptability of risks associated with clinical use.
• Electrical, EMC, and Wireless Coexistence requirements: Meeting IEC 60601-1, IEC 60601-1-11, IEC 60601-1-2, and C63.27:2021.

In summary, the provided document leverages the prior clearance (K223681) for the respiration rate measurement accuracy, focusing the current submission (K250934) on demonstrating substantial equivalence for design changes and the expanded use environment.

Ask a specific question about this device