(122 days)
Vivid E80 / Vivid E90 / Vivid E95 is a general-purpose ultrasound system, specialized for use in cardiac imaging. It is intended for use by, or under the direction of a qualified and trained physician for ultrasound imaging, measurement, display and analysis of the human body and fluid. The device is intended for use in a hospital environment including echo lab, other hospital settings, operating room, Cath lab and EP lab or in private medical offices. The systems support the following clinical applications: Fetal/Obstetrics, Abdominal (including renal, GYN), Pediatric, Small Organ (breast, testes, thyroid), Neonatal Cephalic, Adult Cephalic, Cardiac (adult and pediatric), Peripheral Vasculo-sketal Conventional, Musculo-skeletal Superficial, Urology (including prostate), Transvaginal, Transvaginal, Transrectal, Interventional Guidance (including Biopsy, Vascular Access), and Intraoperative (vascular). Modes of operation include: 3D, Real time (RT) 3D Mode (4D), B, M, PW Doppler, CW Doppler, Color M Doppler, Power Doppler, Harmonic Imaging, Coded Pulse and Combined modes: B/M, B/Color M, B/PWD or CWD, B/Color/PWD or CWD, B/ Power/PWD.
Vivid E80 / Vivid E90 / Vivid E95 is a Track 3, diagnostic ultrasound system, which is primarily intended for cardiac imaging and analysis but also includes vascular and general radiology applications. It is a full featured diagnostic ultrasound system that provides digital acquisition, processing, analysis and display capability. The Vivid E80 / Vivid E90 / Vivid E95 consists of a mobile console with a height-adjustable control panel, color LCD touch panel, OLED or LCD display monitor (alternatives) and optional image storage and printing devices. It includes a variety of electronic array transducers operating in linear, curved, sector/phased array, matrix array or dual array format, including dedicated CW transducers and real time 3D transducer. The system includes electronics for transmit and receive of ultrasound data, ultrasound signal processing, software computing, hardware for Image storage, hard copy printing, and network access to the facility through both LAN and wireless (supported by use of a wireless LAN adapter) connection.
This document is a 510(k) premarket notification for the GE Medical Systems Ultrasound and Primary Care Diagnostics Vivid E80/Vivid E90/Vivid E95 ultrasound systems. It does not contain detailed information about a study proving the device meets specific acceptance criteria for AI-related features.
The document states:
- "The subject of this premarket submission, Vivid E80 / Vivid E90 / Vivid E95, did not require clinical studies to support substantial equivalence."
- "Summary of Non-Clinical Tests: Vivid E80 / Vivid E90 / Vivid E95 were evaluated for acoustic output, biocompatibility, cleaning and disinfection effectiveness as well as thermal, electrical, electromagnetic, and mechanical safety, and have been found to comply with applicable medical device safety standards."
While new AI features are mentioned (AI Auto Measure - 2D, AI Auto Measure Spectrum Recognition, AFI 3.0, Auto EF 3.0, AFI RV, AFI LA, 4D Auto TVQ), the document primarily focuses on demonstrating substantial equivalence to predicate devices based on safety, technological characteristics, and intended use, rather than presenting a clinical study with detailed acceptance criteria and performance metrics for these AI features.
Therefore, most of the information requested in your prompt regarding acceptance criteria, study design, sample sizes, expert ground truth, and adjudication methods for a study proving AI device performance is not available in the provided text.
The only performance metric mentioned related to an AI feature is for "AI Auto Measure - 2D": "This saves time compared to manual measurements, due to elimination of user interactions (clicks) by 79% (4 vs. 19)." However, this is a statement of performance, not an acceptance criterion, and the methodology of that specific evaluation is not detailed.
Without a detailed clinical or performance study presented in the document, it is not possible to fill out the table and answer most of the questions.
However, based on the limited information provided, I can infer the following about what kind of information would be relevant if such a study were present:
Hypothetical Example of Desired Information (Not Found in Document):
If a study were present for the AI Auto Measure - 2D feature, here's what the requested information might look like:
1. Table of Acceptance Criteria and Reported Device Performance (Hypothetical)
| Acceptance Criteria Category | Acceptance Criteria (Threshold) | Reported Device Performance (Example) |
|---|---|---|
| Accuracy (e.g., PLAX measurements) | Mean absolute difference (MAD) for LV end-diastolic dimension (LVEDD) 50%. | 79% reduction in user interactions (4 clicks vs. 19 clicks). (This is the only actual metric given) |
| Clinical Equivalence | No statistically significant difference in diagnostic classification (e.g., normal/abnormal) vs. predicate. | Equivalence demonstrated, 95% agreement with predicate device's manual measurements. |
2. Sample size used for the test set and the data provenance:
- Hypothetical: Test Set: 500 cardiac ultrasound studies (images/clips).
- Hypothetical: Data Provenance: Multi-center retrospective study from hospitals in the US, Europe, and Asia.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Hypothetical: 3 board-certified cardiologists with 10+ years of experience in echocardiography.
4. Adjudication method for the test set:
- Hypothetical: 2+1 (two experts independently reviewed cases, and a third expert adjudicated disagreements).
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done:
- Hypothetical: Yes, an MRMC study was performed comparing human performance with and without AI assistance for tasks involving cardiac structure measurements (e.g., LVEDD, LVESV, EF).
- Hypothetical Effect Size: Human readers demonstrated a 15% improvement in efficiency (time to read) and a 10% reduction in inter-reader variability when assisted by the AI Auto Measure - 2D feature, primarily due to automated initialization of measurements and reduced manual interactions. The diagnostic accuracy (e.g., agreement with consensus ground truth on disease severity) remained equivalent or showed a slight (e.g., 2%) non-significant improvement with AI assistance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Hypothetical: Yes, standalone algorithm performance was evaluated against the consensus expert ground truth for relevant measurements, achieving a mean absolute error of X for LVEDD and Y for EF.
7. The type of ground truth used:
- Hypothetical: Expert consensus measurements by highly experienced cardiologists on the ultrasound images/clips.
8. The sample size for the training set:
- Hypothetical: 10,000 cardiac ultrasound studies (images/clips) for AI Auto Measure - 2D.
9. How the ground truth for the training set was established:
- Hypothetical: Initial ground truth was established by automated scripts based on existing clinical reports and validated by a team of trained sonographers under the supervision of cardiologists. A subset of the training data (e.g., 10%) was manually annotated and verified by a smaller group of expert cardiologists for quality control and refinement.
§ 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.