Search Results

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 Falcon HST is an EEG and respiratory signal recorder. The device is intended for use by adult patients in the home or clinical environment, under the direction of a qualified healthcare practitioner, to aid in the diagnosis of sleep disorders.

The Falcon HST comprises hardware and software which provide separate parameters for recording, review, and analysis of collected and stored physiological parameters, including EEG, EOG, ECG and respiratory signals, which are then used as an aid in the diagnosis of respiratory and/or cardiac related sleep disorders by qualified physicians.

The Falcon system consists of the main unit and the charging cradle. The main unit is a small device that is worn on the patient's chest over clothing. It is equipped with a touch-screen LCD and contains various channel inputs such as for the inductive plethysmography bands, and electrodes. The Falcon charging cradle is used to charge the device, as well as provide a USB interface for transferring study data to the PC.

The manufacturer, Compumedics Limited, demonstrates the substantial equivalence of the Falcon HST to its predicate devices for aid in the diagnosis of sleep disorders. The acceptance criteria and the study that proves the device meets the acceptance criteria are described below.

Acceptance Criteria and Reported Device Performance

The acceptance criteria for the Falcon HST are based on establishing substantial equivalence to its predicate devices, the Zmachine Synergy (K172986) and Zmachine DT-100 (K101830). The performance of the Falcon HST was deemed acceptable if its capabilities for recording EEG, respiratory effort, respiratory airflow, body position, and pulse oximetry, as well as its software's ability to produce AHI and sleep staging results, were found to be substantially equivalent to the predicate devices and gold standard polysomnography (PSG) data.

Study Details:

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

   • Bench Testing (Side-by-Side Comparison): The text does not specify the exact number of devices or data points used for the side-by-side bench comparison tests between the Falcon HST and Zmachine Synergy for EEG input, respiratory effort, respiratory airflow, body position, and pulse oximetry. The description implies at least one of each device was used, subject to repeated measurements or simulated inputs.
   • Clinical Performance Testing (Profusion PSG Software): The text does not provide a specific sample size for the clinical performance testing used to validate the software's ability to calculate AHI and sleep staging.
   • Data Provenance: The document does not explicitly state the country of origin or whether the data for the mentioned tests was retrospective or prospective. For bench testing, it involved simulated inputs or direct comparison against predicate devices. For clinical performance testing of the software, it's compared against "gold standard polysomnography data," implying real patient data.

2. 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):

   • For the clinical performance testing of the Profusion PSG software, the ground truth for AHI and sleep staging was established through "expert review of gold standard polysomnography data." The number of experts and their specific qualifications (e.g., years of experience, specific certifications) are not specified in the provided text.

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

   • The document does not specify an adjudication method for establishing ground truth, particularly for the clinical performance testing where expert review was used.

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:

   • The provided text does not mention an MRMC comparative effectiveness study involving human readers or any AI assistance. The study focuses on the device's equivalence to existing technology and the accuracy of its software against expert-reviewed data, not on human reader performance with or without AI assistance. The Falcon HST is an EEG and respiratory signal recorder, and its software is used to aid in the diagnosis by processing these signals, not primarily as an AI assistance tool for human interpretation in the context of what would typically be considered an MRMC study for AI.

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

   • For the hardware components (EEG, respiratory effort, airflow, body position, pulse oximetry), standalone performance testing was conducted by comparing the Falcon HST's output directly against that of the predicate devices or against angular references/simulated inputs.
   • For the Profusion PSG software 5.1, its ability to calculate AHI and sleep staging was validated by comparing its outputs directly against "expert review of gold standard polysomnography data." This indicates a standalone performance evaluation of the algorithm's output against established ground truth, effectively without human-in-the-loop for the algorithm's calculation step itself. The device is intended "to aid in the diagnosis," implying that its output will be reviewed by a human practitioner.

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

   • For testing the accuracy of AHI and sleep staging calculations by the Profusion PSG software, the ground truth used was expert review of gold standard polysomnography data.
   • For the bench testing of individual physiological parameters (EEG, respiratory effort, airflow, body position, pulse oximetry), the ground truth was established by comparison to the predicate device (Zmachine Synergy) or by using controlled simulated inputs and angular references.

7. The sample size for the training set:

   • The document does not provide any information regarding a training set size. This might be because the device's algorithms or software features (like sleep staging) may have been developed and validated previously, or the submission focuses on demonstrating equivalence to established technologies rather than novel algorithm training. The software, Profusion PSG software 5.1, is mentioned to be identical to versions previously cleared (K072201 and K093223), suggesting its core functionality and training (if any) happened prior to this submission.

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

   • As no information about a training set is provided, how its ground truth was established is not detailed in the document.

Ask a specific question about this device

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

The Somfit is a home-based sleep monitoring device which records signals from the patient's forehead and surrounding environment. Somfit 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, Peripheral Arterial Tonometry (PAT), PPG, motion, and snore. Somfit uses a mobile phone application to acquire data wirelessly via Bluetooth LE technology, then transfer into a secure cloud, for management, storage and postprocessing. The software reports measured parameters in a format compatible with AASM guidelines, including sleep time, pAHI and conventional graphical displays such as a hypnogram.

The Somfit device underwent rigorous testing to establish its performance against predefined acceptance criteria, particularly for its ability to detect sleep stages and related parameters.

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

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a formal "acceptance criteria" table with specific thresholds for each metric. However, the clinical performance section implicitly defines acceptance by demonstrating non-inferiority to the predicate device (Watch-PAT300) and superior or comparable performance against the gold standard (PSG) for key metrics.

Based on the provided text, here's a table summarizing the performance metrics that act as implicit acceptance criteria:

Implicit Acceptance Criteria & Reported Device Performance for Somfit

2. Sample Size and Data Provenance

• Test Set Sample Size: 92 subjects for the comparative clinical study involving Somfit, Watch-PAT300, and PSG.
• Data Provenance: The subjects were recruited from 3 site locations in Australia. The study was a prospective clinical study conducted to compare the devices' performance.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: Three scoring sleep technologists.
• Qualifications of Experts: The document states they were "scoring sleep technologists." Specific educational background or years of experience are not provided, but their role implies expertise in polysomnography scoring.

4. Adjudication Method for the Test Set

The adjudication method for sleep staging ground truth was expert consensus. The PSG epochs were classified based on the "consensus of three scoring sleep technologists." This implies a form of 3-way consensus. Further details on how discrepancies were resolved (e.g., majority rule, discussion to reach agreement) are not provided.

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

No, a traditional MRMC comparative effectiveness study was not explicitly described in the provided text in the context of human readers improving with AI vs. without AI assistance. The study evaluated the device's performance (Somfit and Watch-PAT300) against a human-scored gold standard (PSG), rather than measuring the improvement of human readers assisted by AI. The Somfit system is described as a diagnostic aid that calculates and reports parameters to clinicians, implying that clinicians review the output, but the study design was not focused on measuring changes in human reader performance.

6. Standalone (Algorithm Only) Performance

Yes, the study primarily evaluated the standalone performance of the Somfit algorithm (and Watch-PAT300) in deriving parameters like pAHI and sleep stages, comparing its output directly to the gold standard PSG and the predicate device. There was no human-in-the-loop component as part of the evaluated performance for regulatory submission.

7. Type of Ground Truth Used

The primary ground truth used for the clinical study was Polysomnography (PSG), which is considered the gold standard technology for diagnosing sleep disorders. Specifically, for sleep staging, it was expert consensus-scored PSG data. For SpO2, it was gold standard SaO2 data obtained from an invasively controlled desaturation study.

8. Sample Size for the Training Set

The document does not provide information on the sample size for the training set for the Somfit algorithms. It focuses solely on the clinical validation/test set.

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

As the training set details are not provided, the method for establishing its ground truth is also not mentioned in the document.

Ask a specific question about this device

The Okti System is intended for use in the recording, displaying, analysis, printing and storage of human biological parameters such as heart and muscle activity, eye movement, breathing and body movements to assist in the diagnosis of various neurological disorders. The Okti is designed for use in a hospital or other clinical environment. The Okti is only to be used under the direction of a physician.

The Okti is a physiological data acquisition device intended for conducting EEG studies. It is used in conjunction with a PC running Compumedics Profusion EEG software. Power is provided by either an internal Lithium-Ion battery or a POE 100BASE-TX network connection. Physically, the Okti comprises a base unit housing the battery and digital electronic circuits. A changeable module connects to the base unit and houses the analogue circuity and electrode connectors providing options for 32, 64 or 128 referential, or single ended, channels primarily intended for EEG. Each module includes several differential inputs for electrode-based signals such as ECG, EMG or EOG. All these inputs are class CF for patient safety. Patient physiological data is digitised using multiple 24-bit ADCs and filtered using fixed point FIR filters implemented internally to an FPGA located in the analogue module. The data is transferred to a generalpurpose processor in the base unit over a synchronous serial link. From there the patient data may be saved to a device internal SD card or sent to a remote PC over an Ethernet or Wi-Fi LAN connection. A Bluetooth interface is also included for connection to external devices such as an oximeter. The Okti system is available in Okti32, Okti64, or Okti128. These differ only in channel number.

The provided text describes a medical device, Okti, which is an Electroencephalograph (EEG) system. The document is a 510(k) premarket notification to the FDA, asserting the substantial equivalence of Okti to a previously cleared predicate device, the Grael EEG system.

While the document extensively covers the electrical, mechanical, and performance specifications of the Okti device and compares it to its predicate, it does not describe a study involving AI assistance, human readers, or the establishment of ground truth by multiple experts for diagnostic performance evaluation, as would be expected for a typical AI/ML-driven device. The device described here is an EEG recording device, not an AI or diagnostic algorithm. Therefore, many of the requested criteria related to AI/ML device performance evaluation (e.g., sample size for test/training sets, data provenance, number of experts, adjudication, MRMC study, standalone performance, type of ground truth for diagnostic accuracy) are not applicable or not provided in this specific document.

The "performance data" summary relates to the technical validation of the device's ability to accurately record and process physiological signals, ensuring electrical safety, electromagnetic compatibility, and adherence to established EEG standards. It's about the quality of the signal acquisition, not the diagnostic accuracy of an AI interpreting the signals or a human interpreting with AI assistance.

Based on the provided text, here's what can be extracted regarding acceptance criteria and device performance, focusing on the device's technical performance rather than diagnostic AI performance:

Acceptance Criteria and Reported Device Performance (Technical Validation)

The document focuses on demonstrating substantial equivalence to a predicate device (Grael EEG) by comparing technical, electrical, and physical specifications, and by conducting standard performance and safety tests for EEG acquisition devices.

Table of Acceptance Criteria and Reported Device Performance (Technical Parameters):

Ask a specific question about this device

The Orion LifeSpan™ MEG non-invasively measures the magnetoencephalographic (MEG) (and, optionally, electroencephalographic (EEG) signals) produced by electrically active tissue of the brain. These signals are recorded by a computerized data acquisition system, displayed, and may then be interpreted by trained physicians to help localize these active areas. The locations may then be correlated with anatomical information of the brain. MEG is routinely used to identify the locations of visual, auditory, and somatosensory in the brain when used in conjunction with evoked response averaging devices. MEG is also used to non-invasively locate regions of epileptic activity within the brain. The localization information provided by the device may be used, in conjunction with other diagnostic data, as an aid in neurosurgical planning.

It is assumed that the users of the Orion LifeSpan™ MEG are physicians or neurology laboratory technicians who have received training in the following areas:

• Hospital procedures
• Physiological monitoring of patients
• Training relevant to the specific discipline or disorder under investigation

Note: This indication for use specifically excludes use of the Orion LifeSpan™ MEG as life support equipment, for example vital signs monitoring in intensive care units.

The Orion LifeSpan™ MEG is a magnetoencephalograph (MEG) which records magnetic signals from the human brain. The Orion LifeSpan™ MEG uses the CURRY software platform (K001781) to acquire, process and display these signals. Optionally EEG can be recorded simultaneously with the MEG using an integrated SynAmps2 (K023771) hardware system.

The Orion LifeSpan™ MEG can optionally be provided with adult, child or both sized helmets.

The Orion LifeSpan™ MEG is used by skilled operators or physicians trained in the acquisition and interpretation of such signals. It is used as an adjunct as part of a range of measurements performed, such as imaging and other studies, to form a more complete picture of the patient's pathology alongside a standard clinical workup.

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

Device Name: Orion LifeSpan™ MEG
Predicate Device: Elekta Neuromag

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not explicitly state a "sample size" in terms of number of patients or cases for the non-clinical performance studies. Instead, it describes:

• Empty-room noise performance & Device compatibility tests: Performed using the Orion LifeSpan™ MEG and the predicate Elekta Neuromag devices themselves in an empty, magnetically shielded room. The data provenance includes a specific measurement of the Elekta Neuromag TRIUX MEG at Swinburne University of Technology, dated November 6th, 2019. This indicates retrospective use of the predicate device's data for comparison.
• Phantom Comparison Test: An "identical phantom signal" was recorded with both systems. This implies one or more phantom measurements. Data provenance again includes the Elekta Neuromag TRIUX MEG measured at Swinburne University of Technology.
• Limited Channel Operation Test: Phantom localization testing was performed. The number of phantom trials or repetitions for this test is not specified, but it was performed at three different degrees of channel operation (95%, 90%, and 80% of full channel capacity).

There is no mention of human subject data (clinical data) in these performance studies.

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

Not applicable. The ground truth for the non-clinical tests (empty-room noise, phantom localization, device compatibility, software verification) was established by physical measurements and engineering specifications, not by human expert interpretation of medical images or signals.

4. Adjudication Method for the Test Set

Not applicable, as no human expert review or adjudication process was described for establishing ground truth in these non-clinical tests.

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

No, an MRMC comparative effectiveness study was not done. The document explicitly states: "Clinical testing was not performed." The studies presented are non-clinical, comparing device performance metrics directly to a predicate device or pre-defined engineering criteria, not evaluating human reader performance with or without AI assistance.

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

The device, the Orion LifeSpan™ MEG, is a medical instrument (magnetoencephalograph/electroencephalograph with associated software) for measuring brain signals, not an AI algorithm. Therefore, the concept of a "standalone algorithm performance" study as typically understood for AI/ML devices is not directly applicable. The non-clinical studies evaluate the standalone performance of the device itself (noise levels, localization accuracy) against established benchmarks. The CURRY software, while a component, is verified for its functionalities like processing, display, and localization, which are intrinsic to the device's operation.

7. The Type of Ground Truth Used

The ground truth for the non-clinical studies was based on:

• Physical measurements and established engineering benchmarks: For noise levels (fTrms/√Hz).
• Known phantom signal locations: For localization accuracy, where the true source location in the phantom is precisely known.
• Compliance with international standards: IEC 60601-1, IEC 60601-1-2, IEC 80601-2-26, IEC 62304, ISO 14971.

8. The Sample Size for the Training Set

Not applicable. This device is a measurement instrument, not an AI/ML algorithm that requires a "training set" in the context of machine learning. The software component, CURRY, undergoes verification and validation but not "training" in the AI sense.

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

Not applicable, as there is no training set for an AI/ML algorithm described for this device.

Ask a specific question about this device

The GRAEL SYSTEM is intended for use in the recording, displaying, analysis, printing and storage of human biological parameters such as heart and muscle activity, eye movement, breathing and body movements to assist in the diagnosis of various sleep disorders or neurological disorders. The Grael is designed for use in a hospital or other clinical environment. The Grael is only to be used under the direction of a physician.

Grael and Grael EEG are standalone units, which together with sensors and a PC running Compumedics PSG Online and Profusion PSG software for sleep studies and/or Profusion EEG for EEG studies, can record, review and analyze a number of physiological parameters, including EEG, EOG, EOG and respiratory signals. These are then used as an aid in the diagnosis of respiratory and/or neurological related sleep disorders or other neurological conditions by qualified physicians. The system is comprised of hardware and software which, depending on the model type, provides up to 60 separate parameters for recording, review and analysis.

The provided text (K093222 submission for the GRAEL SYSTEM) is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device. It does not contain the detailed information typically found in a clinical study report that would describe acceptance criteria and the methods used to prove the device meets them in the way modern AI/medical device submissions do.

Specifically, the document:

• Identifies predicate devices and states that the GRAEL SYSTEM is substantially equivalent to them.
• Describes the system's hardware and software components and their functions.
• Lists shared technologies with other approved devices, implying that their prior approval supports the safety and effectiveness of these components in the GRAEL SYSTEM.
• States the intended use of the device.

However, it does not include:

• A table of acceptance criteria and reported device performance metrics in the format requested.
• Details about a specific study designed to prove the device meets performance criteria, especially in the context of an AI/ML algorithm's analytical or clinical performance.
• Information on sample sizes, data provenance, expert qualifications, ground truth establishment, or any form of comparative effectiveness study (MRMC or standalone algorithm performance).

Therefore, I cannot fulfill your request for detailed information regarding acceptance criteria and a study proving their fulfillment based on the provided text.

This K093222 submission is from 2010. The regulatory framework and expectations for demonstrating device performance, particularly for AI/ML-driven devices, have evolved significantly since then. For devices like the GRAEL SYSTEM, the "acceptance criteria" at the time would primarily revolve around demonstrating that the device functions as intended, is safe, and is substantially equivalent to existing predicate devices, likely through electrical safety testing, EMC testing, and functional verification. The "study" would often refer to the documentation of these engineering tests and a comparison table establishing substantial equivalence.

Without additional documentation (e.g., a specific verification and validation report or clinical study report), the requested information cannot be extracted from this 510(k) summary.

Ask a specific question about this device

The Somté PSG is intended for use in the recording, displaying, analysis, printing and storage of human biological parameters such as heart and muscle activity, eye movement, breathing and body movements to assist in the diagnosis of various sleep disorders or sleep related respiratory or cardiac disorders. The Somté PSG is designed for ambulatory and mobile operation and can be used in either the patient's home, the hospital or other environments, thus enabling patients to be investigated under as realistic conditions as possible. The Somté PSG is only to be used under the direction of a physician.

The Somté PSG System comprises hardware and software which provides up to 27 separate parameters for recording, review and analysis of collected and stored physiological parameters, including EEG, EOG, ECG and respiratory signals, which are then used as an aid in the diagnosis of respiratory and/or cardiac related sleep disorders by qualified physicians. The Somté PSG device consists of two components permanently connected by a cable: the Patient Input Box (PIB) and the Recorder. The Somté PSG device is powered by 2 AA Batteries - Alkaline or NiMh.

Acceptance Criteria and Device Performance for SOMTÉ PSG SYSTEM (K072201)

The provided 510(k) summary for the Compumedics SOMTÉ PSG SYSTEM primarily focuses on demonstrating substantial equivalence to predicate devices through a detailed comparison of technological characteristics and successful completion of various tests. It does not explicitly state specific quantifiable acceptance criteria for diagnostic performance metrics (e.g., sensitivity, specificity for a particular sleep disorder). Instead, the performance validation relies on demonstrating the device's ability to accurately record and process physiological signals comparable to the predicate devices and conform to relevant safety and electromagnetic compatibility standards.

Therefore, the "acceptance criteria" can be inferred from the nature of the tests conducted and the general objective of demonstrating substantial equivalence for a medical device that aids in diagnosis.

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not explicitly state the sample size for the test set used in the performance validation. It refers to a "Performance Validation Report" which would contain this information.

The data provenance is implicitly from "an internal and external Sleep authority" who generated the validation report. There is no mention of country of origin or whether the study was retrospective or prospective.

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

The document states, "an internal and external Sleep authority generated a Somté PSG Performance Validation Report."

• Number of Experts: Not explicitly stated, but it implies at least two ("internal and external Sleep authority").
• Qualifications of Experts: The term "Sleep authority" suggests expertise in sleep medicine, likely physicians qualified in sleep disorder diagnosis. No specific details like years of experience or board certifications are provided in this summary.

4. Adjudication Method for the Test Set

The document does not specify an adjudication method (e.g., 2+1, 3+1, none) for establishing ground truth in the performance validation. It simply mentions that a "Sleep authority" generated the validation report, implying their expert opinion served as the reference.

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly mentioned or performed in the context of comparing human readers with and without AI assistance. The device in question is a physiological signal recording system, not an AI-powered diagnostic algorithm designed to assist human readers. Its purpose is to collect data for human interpretation.

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

The Somté PSG System is a data acquisition system, not a standalone diagnostic algorithm. While it collects data for analysis (which can be computer-assisted or manual), its primary function is accurate signal recording. Therefore, the concept of "standalone performance" for an algorithm without human-in-the-loop directly assisting diagnosis does not apply in the typical sense for this device. Its performance validation is focused on the accuracy of data acquisition and signal processing.

7. The Type of Ground Truth Used

The ground truth for the performance validation was established by "an internal and external Sleep authority" as part of a "Clinical Validation Report." This indicates that the ground truth was based on expert consensus/clinical judgment from sleep experts, likely comparing the device's recorded signals and derived parameters against established clinical standards or other validated PSG systems. The "Vampire Heart Rate Verification Report" suggests physiological signal accuracy verification, which would use known physiological measurements as a reference.

8. The Sample Size for the Training Set

The document does not mention a training set or any machine learning components for which a training set would be required. The Somté PSG System is a medical device for acquiring physiological signals, not an AI/ML diagnostic algorithm.

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

As there is no mention of a training set for an AI/ML algorithm, this question is not applicable to the information provided.

Ask a specific question about this device

The Somté System is a multi-functional ambulatory recording device intended to be used to collect and store signals related to sleep disorders, including respiratory signals, ECG signals and limb movement signals, to aid in the diagnosis of respiratory and/or cardiac related sleep disorders.

The Somté System is not intended for use as life support equipment such as vital signs monitoring in intensive care units.

The Somté System is only to be used under the direction and supervision of a physician, technologist or clinician. It will not prevent or restore the interruption or loss of any physiological system.

The Compumedics Somté Patient Recording System is a multi-functional, ambulatory recording device. The Somté is used to collect and store a patient's ECG and respiratory signals, which are then used as an aid in the diagnosis of cardiac and/or respiratory related sleep disorders by qualified physicians.

The system is comprised of hardware and software, which provides up to 13 separate parameters for recording, review and analysis.

The data are acquired from a combination of electrodes, sensors and transducers. Signal types can include electrocardiogram (ECG), pressure, airflow, snore, respiratory effort, body position, limb movement, oxygen saturation, pulse rate and pulse waveform.

The electrodes and sensors used to acquire patient data are connected between the patient and the Somté System Recorder. Patient Studies are recorded using the Compumedics Somté Software which allows the user to view, print, summarise, analyse and create Patient Study reports.

The Somté Patient Recording Unit has a built in Compact Flash Disk interface for storage and convenient transfer to review workstations. There is no proprietary hardware required to transfer the study data.

This 510(k) summary for the Compumedics Somté Patient Recording Unit does not include acceptance criteria or detailed results from a study proving the device meets acceptance criteria.

The document primarily focuses on establishing substantial equivalence to previously cleared devices. It describes the device, its intended use, and lists predicate devices (Compumedics Limited E-Series System (K000068) and Oxford Instruments Medilog® Excel 3 Holter Management System (K002544)).

Therefore, I cannot provide the requested table or information about specific studies, sample sizes, ground truth establishment, or expert involvement based on the provided text.

What is present is a general description of the device's function: "The Somté is used to collect and store a patient's ECG and respiratory signals, which are then used as an aid in the diagnosis of cardiac and/or respiratory related sleep disorders by qualified physicians." This implies that the device is intended to accurately record these physiological signals, but specific performance metrics are not given.

Ask a specific question about this device

Ask a specific question about this device