(152 days)
The Diagnostic Ultrasound Systems Aplio i900 Model TUS-AI900, Aplio i800 Model TUS-AI800 and Aplio i700 Model TUS-AI700 are indicated for the visualization of structures, and dynamic processes with the human body usinq ultrasound and to provide image information for diaqnosis in the following clinical applications: fetal, abdominal, intra-operative (abdominal), pediatric, small orqans, trans-vaqinal, trans-rectal, neonatal cephalic, adult cephalic, cardiac (both adult and pediatric), peripheral vascular, transesophageal, musculo-skeletal (both conventional and superficial) and laparoscopic.
The Aplio i900 Model TUS-Al900, Aplio i800 Model TUS-Al800 and Aplio i700 Model TUS-Al700, V2.1 are mobile diagnostic ultrasound systems. These systems are Track 3 devices that employ a wide array of probes including flat linear array, convex linear array, and sector array with frequency ranges between approximately 2 MHz to 20 MHz.
Here's a breakdown of the acceptance criteria and the study details for the Aplio i900/i800/i700 Diagnostic Ultrasound System, V2.1, based on the provided text:
Acceptance Criteria and Device Performance
The provided document primarily focuses on demonstrating substantial equivalence to a predicate device, rather than explicit numerical acceptance criteria for a novel AI feature. However, it does highlight the performance of the 2D WMT function.
Table of Acceptance Criteria and Reported Device Performance
| Criterion Description | Device Performance (2D WMT function) Reported |
|---|---|
| Substantial equivalence to predicate device for display and calculation of GLS, GCS, GRS, EDV/ESV/EF, and global/segment strain in Polar Map display. | The study concluded that the 2D WMT function is substantially equivalent to the predicate device with regard to the display of GLS, GCS, GRS and EDV/ESV/EF and the calculation/provision of global and segment strain in a Polar Map display. |
| Workflow Improvement (reduced operation time with 2D WMT full-assist). | Using the 2D WMT full-assist function on the subject device resulted in reduced operation time over that of the predicate device. (Specific quantitative improvement not provided). |
| Intentional performance for cardiac wall trace, local wall motion tracking, wall motion information analysis/display, cardiac volume measurement, and cardiac function analysis. | Representative clinical images were obtained, and it was concluded that the 2D WMT implemented on the subject device performs as intended. More specifically, it enables the cardiac wall trace (initial contour setting), the local wall motion tracking and provides wall motion information analysis and display, cardiac volume measurement, and cardiac function analysis. |
| Measurement accuracy/precision for key cardiac parameters (EDV, ESV, Long. Strain Inner, Radial Strain, Total and Circumferential Strain Inner). | In a 10-patient study, the measurement of major parameters (EDV, ESV, Long. Strain Inner, Radial Strain, Total and Circumferential Strain Inner) had a less than 11% coefficient of variation. The initial contour trace lines created by clinicians showed little differences, attributed to ultrasound image border recognition, read-out conditions, and image frame selection differences. |
Study Details
This document describes a performance study conducted to support the substantial equivalence claim, specifically focusing on the new "2D WMT" feature.
-
Sample size used for the test set and the data provenance:
- Sample Size: 10 patients.
- Data Provenance: Not specified (e.g., country of origin). It is also not specified whether the data was retrospective or prospective, though the description "representative clinical images were obtained" suggests prospective data collection or selection for the purpose of this validation.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Three (3) clinicians.
- Qualifications of Experts: Not specified beyond "clinicians."
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Not explicitly stated. The text mentions "initial contour trace lines created by the clinicians showed little differences," implying that the 3 clinicians each performed measurements and their results were compared, rather than a formal adjudication process to establish a single "ground truth" per case. The low coefficient of variation suggests a high degree of agreement among them.
-
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:
- A comparative effectiveness study was conducted regarding workflow improvement. It was concluded that using the 2D WMT full-assist function resulted in reduced operation time over that of the predicate device.
- Effect Size: The document states that the new feature "resulted in reduced operation time" but does not provide a quantitative effect size (e.g., percentage reduction in time, average time saved).
-
If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
- The term "2D WMT full-assist function" suggests that this feature is intended to assist a human operator. The evaluation of reduced operation time implies a human-in-the-loop scenario. There is no explicit mention of a standalone algorithm performance study without human interaction in this document. The "initial contour setting" is described as being "created by the clinicians," further supporting that it's not a fully autonomous AI system.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The ground truth appears to be based on expert consensus/measurement by three clinicians. The measurements of "major parameters EDV, ESV, Long. Strain Inner, Radial Strain, Total and Circumferential Strain Inner" by these clinicians were used for comparison and to assess variability.
-
The sample size for the training set:
- Not specified. The document primarily details the performance study for the modified device, not the development or training of any AI components. The 2D WMT is mentioned as a "previously cleared feature implemented on subject device" with a "newly implemented" auto initial contour setting. This suggests the "AI" (if any, related to auto contour) was likely trained prior to this submission, and its training data is not discussed here.
-
How the ground truth for the training set was established:
- Not specified, as the training set details are not provided in this regulatory submission.
§ 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.