(193 days)
ScanNav Anatomy Peripheral Nerve Block is indicated to assist qualified healthcare professionals to identify and label the below mentioned anatomy in live ultrasound images in preparation for ultrasound guided regional anesthesia prior to needle insertion for patients 18 years of age or older.
The highlighting of structures in the following anatomical regions is supported:
- Axillary level brachial plexus ●
- Erector spinae plane .
- Interscalene level brachial plexus ●
- Popliteal level sciatic nerve .
- Rectus sheath plane
- Sub-sartorial femoral triangle / Adductor canal .
- Superior trunk of brachial plexus
- Supraclavicular level brachial plexus ●
- . Longitudinal suprainguinal fascia iliaca plane
ScanNav Anatomy Peripheral Nerve Block is an accessory to compatible general-purpose diagnostic ultrasound systems.
ScanNav Anatomy Peripheral Nerve Block is a software medical device which assists anesthetists and other qualified healthcare professionals in the identification of anatomical structures within ultrasound images during ultrasound-guided regional anesthesia (UGRA) procedures by highlighting the relevant anatomical structures in realtime.
The device performs the highlighting by using deep learning artificial intelligence technology based on convolutional networks (CNNs). These deep-learning models generate a colored overlay that allows the user to identify the specific anatomical structures of interest for the procedure. A separate monitor displays the highlighted images as an overlay on top of the ultrasound image, so the original view from the ultrasound machine is not affected. The deep learning models are locked, and they do not continue to learn in the field.
The device interfaces with ultrasound machine with an external monitor output that meets the compatibility requirements. The ScanNav Anatomy Peripheral Nerve Block is run on a mobile computing platform (a commercial off the shelf panel PC) performing the processing with an integrated touchscreen monitor to display the user interface and anatomy highlighting
The Software as a Medical Device is packaged with a tablet PC, power cable, compatible plug, and mounting bracket and instructions for mounting the tablet to the ultrasound host. This acts as a separate monitor to display the highlighted images as an overlay on top of the ultrasound image, so the original view from the ultrasound machine is not affected. The ScanNav Anatomy Peripheral Nerve Block system is composed of a software medical device and other non-medical devices such as a panel PC, power supply, an HDMI interface cable and a VESA mount.
Acceptance Criteria and Device Performance Study for ScanNav Anatomy Peripheral Nerve Block
This document outlines the acceptance criteria for the ScanNav Anatomy Peripheral Nerve Block device and details the studies conducted to demonstrate its compliance.
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria Category | Specific Metric | Acceptance Criterion | Reported Device Performance |
|---|---|---|---|
| Clinical Performance (Primary Endpoint) | Assistance in obtaining correct ultrasound view prior to needle insertion | Majority view (at least 8/15 participants) agree the device assists. | 63% (19/30) of participants were assisted, meeting the criterion. |
| Clinical Performance (Secondary Endpoint 1) | Assistance in identification of anatomical structures (up to BMI 35 kg/m2) | Majority view (at least 8/15 participants) agree the device assists. | 70% (21/30) of participants were assisted, meeting the criterion. |
| Clinical Performance (Secondary Endpoint 2) | Assistance in supervision and training for anatomical structure identification | Majority view (at least 8/15 supervising experts) agree the device assists. | 87% (13/15) of experts were assisted, meeting the criterion. |
| Clinical Performance (Secondary Endpoint 3) | Improvement in operator confidence | Majority view (at least 8/15 participants) agree the device improves confidence. | 63% (19/30) of participants had improved confidence, meeting the criterion. |
| Safety (Misidentification) | Frequency of misidentification (FP Rate) of anatomical structures | Not explicitly stated as a numerical criterion for all blocks, but assessed as a primary endpoint in one study. | Varies by block, ranging from 0% (ESP, Adductor) to 21.9% (SFIC). Details in section 2 below. |
| Safety (Adverse Events Risk) | Frequency of highlighting risking an adverse event | = 80% of total for each block. | Varies by block, ranging from 76.2% (SFIC) to 98.3% (SC). Details in section 2 below. |
| Human Factors | Successful completion of essential and critical tasks by users | All participants complete essential and critical tasks without patterns of use failures, confusion, or difficulties. | All 30 participants completed tasks. No UI design issues, use errors, or task failures were found. |
| Software | Compliance with design and safety standards | Software documentation acceptable, with Major Level of Concern addressed. | Documentation reviewed and accepted. Supports cybersecurity and hazard analysis. |
| Electromagnetic Compatibility & Electrical Safety | Compliance with IEC 60601-1-12 and IEC 60601-1-2 | Test results support electrical safety and electromagnetic compatibility. | Test results support compliance. |
2. Study Details for Device Performance
The provided documentation describes two main studies relevant to device performance: a Clinical Validation Study to assess Performance and predict Adverse Events (IU2021 AG 07) and a Human Factors (HF) Study Design.
Clinical Validation Study (IU2021 AG 07)
- Sample Size: 40 volunteers.
- Data Provenance: Single-center, prospective validation study conducted in the USA (Oregon Health & Science University, Portland).
- Number of Experts for Ground Truth: Three (3) expert anesthesiologists in UGRA.
- Qualifications of Experts: Anesthesiologists competent to perform independent UGRA.
- Adjudication Method: Majority opinion (2/3) determined TP, TN, FP, FN, and AE rates.
- Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study: No, this study was primarily a standalone validation of the device's highlighting performance against expert consensus. It did not directly compare human readers with and without AI assistance to quantify an effect size in human improvement. However, the Human Factors study (described below) did involve performance "with and without the aid of the device," providing some insight into assisted performance.
- Standalone Performance (Algorithm-only): Yes, the study assessed the "device output" and its highlighting performance, with experts evaluating the device's interpretations in isolation. Experts answered questions on the device's highlighting performance (TP, TN, FP, FN).
- Type of Ground Truth: Expert consensus. Three expert anesthesiologists viewed recorded ultrasound clips side-by-side with the ScanNav Anatomy PNB output and determined the correctness of the highlighting.
- Sample Size for Training Set: Not explicitly stated in the provided text. The device uses "deep learning artificial intelligence technology based on convolutional networks (CNNs)."
- How Ground Truth for Training Set was Established: Not explicitly stated, but typically involves expert annotation of ultrasound images for relevant anatomical structures.
Key Performance Metrics (from IU2021 AG 07):
- Primary Endpoint (Misidentification - FP Rate):
- Axillary: 0.3%
- ESP: 0.0%
- IS: 1.3%
- Pop: 0.6%
- RS: 3.2%
- Adductor: 0.0%
- ST: 5.2%
- SC: 0.8%
- SFIC: 21.9%
- Secondary Endpoint (Accuracy - Correct Identification - TP+TN Rate):
- Axillary: 97.7%
- ESP: 88.8%
- IS: 94.1%
- Pop: 98.1%
- RS: 96.8%
- Adductor: 90.4%
- ST: 90.9%
- SC: 98.3%
- SFIC: 76.2%
- Adverse Event Rates: Redacted sections (b)(4) indicate specific risks (PONS, LAST, Pneumothorax, Peritoneum risk) were assessed per block, aiming for
N/A