Search Results

The Clover 50/Clover60/Clover70 Diagnostic Ultrasound System is applicable for adults, pregnant women, pediative patients and neonates. It is intended for use in gynecology, obstetric, abdominal, pediatric, small parts (breast, testes, thyroid, etc.), neonatal cephalic, transcranial, cardiac, transvaginal, peripheral vascular, urology, orthopedic, and musculoskeletal (conventional and superficial) exams.

Device Description

The Clover 50/Clover60/Clover70 Diagnostic Ultrasound System is a mobile software controlled ultrasonic system. Its function is to acquire and display ultrasound data in B-Mode, M-Mode, Color-Mode, Power (Dirpower)-Mode, PW-Mode, CW-mode, and the combined mode. The system can also measure anatomical structures and offer software analysis packages performance to provide information based on which the competent health care professionals can make the diagnosis.

The Clover 50/Clover60/Clover70 Diagnostic Ultrasound System consists of the main unit named clover series, ultrasound probes, power adapter, connecting cable, probe extender, needle-guided bracket, batteries, mobile trolley and travelling case.

Three models for the main units are included in this submission that is Clover 50, Clover 60 and Clover 70. Seven different models of probes are available for the Clover series.

AI/ML Overview

The provided text describes the Clover 50/Clover60/Clover70 Diagnostic Ultrasound System and its substantial equivalence to predicate devices, focusing on non-clinical performance testing. It does not contain information about acceptance criteria and a study proving the device meets acceptance criteria in a clinical setting with human subjects, nor does it detail a standalone algorithm performance, MRMC study, or ground truth establishment relevant to AI.

However, it does describe the performance testing criteria and results for various measurement accuracies and modes of operation. It considers these performance tests as evidence for substantial equivalence, implying they serve as acceptance criteria for the device's technical functionality relative to the predicate devices.

Here's a breakdown of the information that can be extracted, addressing your points where possible:

1. Table of Acceptance Criteria and Reported Device Performance

The device's performance was compared against the listed predicate device (Mindray M7/M7T, K131690). The "acceptance criteria" are implied by the performance of the predicate device, which the new device aims to be "substantially equivalent" to or better. The table shows the performance of the Clover 70 model and compares it to the predicate device.

Note: The predicate device's performance appears to set the acceptance criteria for the new device. Both devices are marked 'S' (Same) indicating substantial equivalence in these performance metrics.

Items	Acceptance Criteria (from predicate M7/M7T)	Clover 70 Reported Performance	Substantial Equivalence
Precision of 2D Images
Distance	Within ±3%; or when the measured value is less than 40mm, the error is less than 1.5mm	Max Error: 1.4% (Full screen)	S
Area (Trace)	Within ±7%; or when the measured value is less than 16 cm², the error is less than 1.2 cm²	-5.11% (Full screen)	S
Area (ellipse, circle)	Within ±7%; or when the measured value is less than 16 cm², the error is less than 1.2 cm²	0.8% (Full screen)	S
Circumference	Within ±7%; or when the measured value is less than 16 cm², the error is less than 1.2 cm²	-0.47% (Full screen)	S
Angle	Within ±3%	-1.89% (Full screen)	S
Volume	Within ±10%; or when the measured value is less than 64 cm³, the error is less than 6.4 cm³	0.51% (Full screen)	S
Basic Time/Motion measurements
Distance	Within ±3%; or when the measured value is less than 40mm, the error is less than 1.5mm	-2% (Full screen)	S
Time	Within ±2%	0 (Timeline Display)	S
Heart rate	Within ±4%	0 (15-999 beats per minute)	S
Velocity (PW mode)	When angle ≤ 60°, ≤5%	C5-1: 4.3% max; L15-4: 3.3% max; LH15-6: 3.1% max; P4-1: 4.8% max; EV10-4: 3.3% max; P7-3: 5.0% max	S
Velocity (CW mode)	When angle ≤ 60°, ≤5%	P4-1: 4.8% max; P7-3: 4.3% max	S

2. Sample size used for the test set and the data provenance

The document refers to "Performance testing was conducted on the Clover 50/Clover60/Clover70 Diagnostic Ultrasound System, to evaluate the clinic measurement accuracy and system sensitivity, and all of the tested parameters met the predefined acceptance criteria." However, it does not specify the sample size used for this performance testing. It also does not mention data provenance (e.g., country of origin, retrospective or prospective) as this was non-clinical performance data, likely gathered in a lab or testing environment rather than a clinical dataset from patients.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

This information is not provided. The ground truth for this type of performance testing would typically be based on highly accurate physical measurements using calibrated equipment rather than expert human interpretation.

4. Adjudication method for the test set

This information is not provided. Given it's non-clinical performance metrics, an adjudication method (like 2+1, 3+1) would not be applicable in the same way as for clinical studies involving human interpretation.

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

There is no mention of an MRMC comparative effectiveness study or any AI component. The device described appears to be a traditional diagnostic ultrasound system and not an AI-powered device.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

There is no mention of a standalone algorithm or AI performance.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

For the performance testing metrics (distance, area, velocity, etc.), the ground truth would likely be established using precise physical phantoms and calibrated measurement tools, rather than clinical expert consensus, pathology, or outcomes data. The document does not explicitly state the method, but this is standard for ultrasound system calibration and performance verification.

8. The sample size for the training set

There is no mention of a training set, as this is not an AI/ML device.

9. How the ground truth for the training set was established

There is no mention of a training set or its ground truth, as this is not an AI/ML device.

Ask a Question

Ask a specific question about this device

Page 1 of 1