Search Results

The Huxley Home Sleep Apnea Test (SANSA) is a wearable device intended for use in the recording, 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 Al/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 (reference channel only). 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. The ECG channel is intended to be used as a reference channel and is not intended to be used for diagnostic purposes and is not intended by any automated ECG analysis system or algorithm.

Here's a breakdown of the acceptance criteria and study details for the Huxley SANSA Home Sleep Apnea Test (SANSA HSAT), based solely on the provided text:

1. Table of acceptance criteria and the reported device performance:

Note: The table combines the "Performance" section for the predicate and subject devices from the Device Comparison table (page 7) and the "Clinical Performance Data" section for additional reported performance values (page 12). For Sleep/Wake classification, no direct "acceptance criteria" based on the predicate were provided in the document.

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

• SpO2 Accuracy Test Set: The number of subjects is not explicitly stated, but the test was conducted on "healthy subjects" (page 12).
• Comparison to PSG (Moderate to Severe SDB Diagnosis Test Set):
  • Sample Size: n = 533
  • Data Provenance: Prospective multi-center clinical study in the United States (page 12).
• Sleep/Wake Classification Validation Test Set:
  • Sample Size: n = 340 (ITD - likely "Intention To Diagnose")
  • Data Provenance: Not explicitly stated beyond being "gold standard scored PSG data" (page 12).

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

This information is not explicitly provided in the text. The ground truth for the comparison to PSG study is stated as "gold standard polysomnography (PSG)" (page 12), and for SpO2, it's "arterial blood gas samples" (page 12). While PSG scoring generally involves experts (e.g., sleep specialists, polysomnographic technologists), the number and specific qualifications of these experts are not detailed in this document.

4. Adjudication method for the test set:

This information is not explicitly provided in the text.

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

• No, an MRMC comparative effectiveness study was not explicitly described. The study focused on the standalone diagnostic performance of the SANSA device compared to PSG. The predicate device's diagnostic performance is noted as being based on "manual scoring of data by HCP" (Healthcare Professional), while the subject device "utilizes an autoscored algorithm with no overread and correction." This suggests a comparison of the AI-driven auto-scoring performance to a human-scored gold standard, but not a study of human readers improving with AI assistance.

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

• Yes, a standalone performance study was done. The "Comparison to PSG" study (n=533) directly evaluates the diagnostic performance of the SANSA device's algorithm for moderate to severe SDB, stating it "utilizes an autoscored algorithm with no overread and correction" (page 7) and yielded specific sensitivity and specificity values. The Sleep/Wake classification also reports algorithm-only performance.

7. The type of ground truth used:

• For SpO2 Accuracy: Arterial blood gas samples (page 12).
• For comparison to PSG (SDB diagnosis) and Sleep/Wake classification: Gold standard polysomnography (PSG) data (page 12).

8. The sample size for the training set:

• For the Sansa device AI-based Sleep/Wake classification algorithm: 101 subjects (page 12).
• For other algorithms (e.g., AHI calculation): This information is not explicitly provided.

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

• For the Sansa device AI-based Sleep/Wake classification algorithm: The algorithm was "trained on 101 subjects and validated against the validation dataset (n=340 ITD) taken from gold standard scored PSG data" (page 12). This implies the ground truth for the training set was also established using "gold standard scored PSG data."
• For other algorithms: This information is not explicitly provided.

Ask a specific question about this device

ANNE One is a wireless monitoring platform indicated for the measurement of electrocardiography (ECG) waveforms. heart rate, respiratory rate, function of arterial hemoglobin (SpO2), pulse rate, activity, body position, fall detection, skin temperature by qualified healthcare professionals in home and healthcare settings. ANNE One is compatible with third-party, FDA-cleared devices for noninvasive blood pressure, SpO2, pulse rate, and body temperature measurements. The device is indicated for monitoring ECG waveforms and heart rate on ambulatory patients. The device is not intended to monitor or measure respiratory rate. SpO2, pulse rate, or noninvasive blood pressure while the patient undergoes significant motion or is active.

ANNE One continuously monitors the orients to aid in the prevention of pressure ulcers for at-risk patients. The system provides visual notification when the pation has not changed from a preset threshold of time.

The device is intended for use on general care patients who are 12 years of age or older as a general patient monitor to provide continuous physiological information as an aid to diagnosis and treatment. The data from ANNE One are transmitted wirelessly for display, storage, and analysis. The device is not intended for use on critical care patients.

ANNE One is a wireless monitoring platform that streams and stores real-time biosignals including electrocardiography (ECG), photoplethysmography (PPG), 3-axis accelerometry, and temperature to measure vital signs such as heart rate, respiratory rate, SpO2, pulse rate, skin temperature, and body temperature. The ECG signal is not intended for automated arrhythmia detection or classification; rather it is intended for manual interpretation, and the automated computation of heart rate through QRS identification using the well-known Pan-Tompkins beat detection algorithm. The displayed waveform is only intended for display as a check for normal ECG rhythm. The waveform is not intended for manual discrimination of any arrhythmias or cardiac conditions. The system features two skin-mounted, bio-integrated sensors that pair with the ANNE View software application for the continuous display, storage, and analysis of vital sign measurements and physiological waveforms. The system is also compatible with optional FDA-cleared third-party devices for SpO2, non-invasive blood pressure, and body temperature measurements.

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

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document primarily focuses on demonstrating substantial equivalence to predicate and reference devices, with specific performance values provided for SpO2 and Respiratory Rate from clinical studies. The other parameters are stated to meet relevant standards or are equivalent to predicate/reference device performance.

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

• SpO2 Accuracy Study:

  • Sample Size: n=12 healthy subjects.
  • Data Provenance: Not explicitly stated (e.g., country of origin), but implies a controlled clinical setting. The study is described as "Sibel validated the accuracy...".
  • Retrospective/Prospective: Implied prospective as it's a validation study conducted by Sibel.

• Respiratory Rate Accuracy Study:

  • Sample Size: n=40 healthy adult subjects.
  • Data Provenance: Not explicitly stated (e.g., country of origin), but implies a controlled clinical setting. The study is described as "Sibel validated the accuracy...".
  • Retrospective/Prospective: Implied prospective as it's a validation study conducted by Sibel.

• Other Parameters: For other parameters like Heart Rate, ECG waveform display, Activity, etc., "performance testing" and adherence to "consensus standards" are mentioned, but specific sample sizes for these test sets are not provided in this summary. The comparison table also mentions "ambulatory databases" for ECG during motion, but no sample size is given.

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

• SpO2 Accuracy Study: Ground truth was established by "blood gas analysis." This typically involves laboratory analysis, not expert consensus on visual assessment.
• Respiratory Rate Accuracy Study: Ground truth was established by "etCO2" (end-tidal CO2). This is a physiological measurement, not an expert consensus.
• Other Parameters: No information is provided regarding experts or their qualifications for establishing ground truth for other parameters. Ground truth for these values would likely derive from established measurement techniques compliant with the referenced standards.

4. Adjudication Method for the Test Set

• Given that the ground truth for SpO2 and Respiratory Rate relied on objective physiological measurements (blood gas analysis and etCO2, respectively), there was likely no "adjudication method" in the sense of reconciling disagreements between multiple graders or clinicians. The measurements themselves serve as the ground truth.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• No MRMC comparative effectiveness study involving human readers and AI assistance is mentioned in the provided text. The device is a "wireless monitoring platform" for physiological measurements. Its primary function is to collect and display vital sign data, not to interpret complex medical images or data that typically require a human reader for adjudication or enhancement by AI.

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

• Yes, the performance data provided for SpO2 and Respiratory Rate are standalone algorithm capabilities. The device measures these parameters and the reported accuracy is the algorithm's performance against a reference standard, without human intervention in the measurement or calculation process. The description of "automated computation of heart rate through QRS identification using the well-known Pan-Tompkins beat detection algorithm" also indicates a standalone algorithmic function.

7. The Type of Ground Truth Used

• SpO2: Blood gas analysis (objective physiological measurement).
• Respiratory Rate: EtCO2 (objective physiological measurement).
• Heart Rate: Implied to be derived from ECG signals, with validation against established standards (e.g., IEC 60601-2-27, IEC 60601-2-47), which would use a recognized reference for HR. The Pan-Tompkins algorithm is for beat detection, which is then used to compute HR.
• Other Parameters (Skin Temperature, Body Position, Activity, ECG Waveform Display, Pulse Rate): Ground truth is likely established through a combination of physical reference measurements and adherence to recognized consensus standards (e.g., ISO, IEC). Bench testing is mentioned for several parameters.

8. The Sample Size for the Training Set

• The document does not explicitly state the sample size for any training set for machine learning models. The device description mentions the use of "the well-known Pan-Tompkins beat detection algorithm" for heart rate, which is a classical signal processing algorithm and may not require a 'training set' in the modern machine learning sense. While algorithms are likely involved in respiratory rate and SpO2 calculations, the summary focuses on validation, not the development or training phase.

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

• As training set information is not provided, the method for establishing its ground truth is also not detailed.

Ask a specific question about this device