(95 days)
The Venue Go is a general purpose diagnostic ultuse by qualified and trained healthcare professionals for ultrasound imaging, measurement, display and analysis of the human body and fluid. Venue Go is intended to be used in a hospital or medical clinic. Venue Go clinical applications include: abdominal (GYN and Urology), thoracic/pleural, ophthalmic, Fetal/OB, Small Organ (including breast, thyroid), Vascular/Peripheral vascular, neonatal and adult cephalic, pediatric, musculoskeletal (conventional and superficial), cardiac (adults and pediatic), Transrectal, Transvaginal, Transesophageal, Intraoperative (vascular) and interventional guidance (includes tissue biopsy, fluid drainage, vascular and non-vascular access). Modes of operation include: B, M, PW Doppler, CW Doppler, Color Doppler, Color M Doppler, Power Doppler, Harmonic Imaging, Coded Pulse and Combined modes: B/M, B/Color M, B/ PWD, B/Color/PWD, B/Power/PWD, B/CWD, B/Color/CWD.
Venue Go is a general-purpose diagnostic ultrasound system intended for use by qualified healthcare professionals to evaluate the body by ultrasound imaging and fluid flow analysis. The Venue Go is a compact, portable system with a small footprint. The system can be hand carried using an integrated handle, placed on a horizontal surface, attached to a mobile cart or wall mounted. It has a high resolution color LCD monitor, with a simple, multi-touch user interface that makes the system intuitive. The system can be powered through an electrical wall outlet for long term use or from an internal battery for a short time. The Venue Go utilizes a varietv of linear, convex, and phased array transducers which provide high imaging performance and support standard acquisition modes. Compatible biopsy kits can be used for needle-guidance procedures. The system is capable of displaying the patient's ECG trace synchronized to the scanned image. This allows the user to view an image from a specific time of the ECG signal which is used as an input for gating during scanning. The ECG signal can be input directly from the patient or as an output from an ECG monitoring device. ECG information is not intended for monitoring or diagnosis. A barcode reader and RFID scanner are available as additional input devices. A roller bag will also be available for the customer to use when transporting the system. Venue Go is capable of wireless communication through a builtin Wireless LAN device. The system meets DICOM requirements to support image storage and archiving (local PACS or products such as Q-Path) and allows for output to printing devices. The user documentation is available electronically.
The provided document is a 510(k) Premarket Notification Submission for the GE Venue Go ultrasound system. It includes a specific section detailing the AI feature cNerve. Based on this information, here's a description of the acceptance criteria and the study that proves the device meets them:
1. Table of Acceptance Criteria and Reported Device Performance (cNerve AI Feature)
| Acceptance Criterion (cNerve) | Reported Device Performance (cNerve) |
|---|---|
| Overall cNerve Performance (Sequence Accuracy) | |
| At least 70% of the sequences are meaningfully detected. | Performance not explicitly stated as a percentage for "meaningfully detected sequences" in the provided document, but implied by the "successfully detected" metric. |
| At least 80% of the meaningfully detected sequences are successfully detected (meeting frame accuracy criteria). | The document states performance requirements, but the actual achieved performance data (e.g., "cNerve achieved X% of meaningfully detected sequences" or "cNerve successfully detected Y% of these") against these specific criteria are not numerically reported in the "AI Summary of Testing" section. It only states what the performance requirements are, not what was measured against those requirements. |
| Pixel Accuracy in Frames (Specific thresholds for appropriate intended use derived from preliminary survey) | Specific numerical thresholds for pixel accuracy are not provided in the document. |
| Frame Accuracy in Sequences (Specific thresholds for appropriate intended use derived from preliminary survey) | Specific numerical thresholds for frame accuracy are not provided in the document. |
Important Note: The document outlines the acceptance criteria for cNerve but does not explicitly provide the measured numerical performance results of the device against these criteria. It states that the "cNerve performance requirements" are listed but does not follow up with a section detailing the actual tested performance numbers.
2. Sample Size and Data Provenance for the Test Set
- Sample Size (Individuals): A total of 44 individuals contributed to the verification dataset.
- Sample Size (Sequences/Frames): The test dataset included 124 sequences and 3776 frames.
- Relationship between Samples: Each individual contributed up to 2 sequences per view location (often both left and right laterals were scanned).
- Demographic Distribution:
- Gender: Male and Female
- Age: 18-82 years
- Ethnicity/Country: USA, Japan, Israel
- Subgroups Tested: The algorithm performance was verified via frame accuracy on all demographic subgroups: Gender (M/F), Age (=60), BMI (25). It was also tested for all supported nerve block locations and supported probe types.
- Data Provenance: The document implies the data was collected from a mix of clinical settings (implied by "USA, Japan, Israel" for ethnicity/country) and clinical scenarios ("all supported nerve block locations and all supported probe types"). The study type (retrospective or prospective) is not explicitly stated, but the process of collecting and annotating an existing dataset suggests a retrospective approach for the dataset creation for validation.
3. Number of Experts and Qualifications for Ground Truth
- Number of Experts: A single clinical expert annotated the frames from scouting sequences.
- Qualifications of Experts: The specific qualifications (e.g., years of experience, specific specialty like "radiologist") of the "single clinical expert" are not detailed in the provided text.
4. Adjudication Method for the Test Set
- The ground truth was established by a single clinical expert. Therefore, there was no adjudication method described (e.g., 2+1, 3+1 concensus), as only one expert was involved in marking the ground truth.
5. Multi Reader Multi Case (MRMC) Comparative Effectiveness Study
- The document does not indicate that an MRMC comparative effectiveness study was done to evaluate how much human readers improve with AI vs without AI assistance. The study focuses solely on the standalone performance measurement of the cNerve algorithm against defined ground truth.
6. Standalone (Algorithm Only) Performance Study
- Yes, a standalone performance study was done. The "AI Summary of Testing" section describes the evaluation of the cNerve algorithm's accuracy, focusing on its ability to detect and track nerve bundles independently. The acceptance criteria ("Sequence accuracy requirement - for testing overall cNerve performance") explicitly relate to the algorithm's performance.
7. Type of Ground Truth Used
- The ground truth used was expert annotation/consensus (from a single expert). The frames were "annotated by a single clinical expert, where the anatomical area of the nerves was marked in each frame."
8. Sample Size for the Training Set
- The sample size for the training set is not provided in the document. The document explicitly states: "The data used for verification is completely distinct from that used during training process and there is no overlap between the two." However, it does not disclose details about the training data itself.
9. How the Ground Truth for the Training Set was Established
- The document does not describe how the ground truth for the training set was established. It only mentions that the test data was distinct from the training data.
§ 892.1550 Ultrasonic pulsed doppler imaging system.
(a)
Identification. An ultrasonic pulsed doppler imaging system is a device that combines the features of continuous wave doppler-effect technology with pulsed-echo effect technology and is intended to determine stationary body tissue characteristics, such as depth or location of tissue interfaces or dynamic tissue characteristics such as velocity of blood or tissue motion. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.