Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Apr 5, 2019
Open Peer Review Period: Apr 8, 2019 - May 8, 2019
Date Accepted: Jun 11, 2019
(closed for review but you can still tweet)
A novel intelligent scan assistant system for early pregnancy ultrasound diagnosis; a CDSS evaluation study
ABSTRACT
Background:
Early pregnancy ultrasound scans are usually performed by non-expert examiners in OB/GYN emergency departments. Establishing the precise location diagnosis is key for appropriate management of early pregnancies, and experts are usually able to locate pregnancy at the first scan. A decision support system based on semantic expert-validated knowledge base may improve diagnosis performance of non-expert examiners, for early pregnancy transvaginal ultrasound.
Objective:
This study aims to evaluate a novel Intelligent Scan Assistant System for early pregnancy ultrasound on pregnancy location diagnosis and on image quality.
Methods:
Two trainees performed virtual transvaginal ultrasound examinations of early pregnancy cases without and with the system. The ultrasound images and reports were blindly reviewed by two experts using scoring methods. Pregnancy location diagnosis and ultrasound image quality was compared in scan performed without and with the system.
Results:
Each trainee performed a virtual vaginal examination for all 32 cases without and with the system. The analysis of the 128 resulting scans showed higher quality for the images (quality score +23%, p<0.001), less images per scan (4.6 vs. 6.3, p <0.001) and higher confidence in report conclusions (trust score +20%, p<.0001), when using the system. The use of the system cost an additional 8 minutes per scan. We observed a correct location diagnosis in 39/64 (61%) and 52/64 (81%) scans, in non-assisted mode and in assisted mode, respectively. Additionally, the exact diagnosis (with precise ectopic location) was achieved in 30/64 and 49/64 scans, without and with the system, respectively. These differences in diagnosis performance, +20% of correct location diagnosis and +30% in exact diagnosis were both statistically significant (p=0.002 and p<0.001, respectively).
Conclusions:
The Intelligent Scan Assistant System based on an expert-validated knowledge base demonstrates significant improvement in early pregnancy scan both in diagnosis performance (pregnancy location and precise diagnosis) and in scan quality (selection of images, confidence and image quality). Clinical Trial: N/A
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.