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