%0 Journal Article
%@ 1438-8871
%I JMIR Publications
%V 21
%N 7
%P e14286
%T A Novel Intelligent Scan Assistant System for Early Pregnancy Diagnosis by Ultrasound: Clinical Decision Support System Evaluation Study
%A Dhombres,Ferdinand
%A Maurice,Paul
%A Guilbaud,Lucie
%A Franchinard,Loriane
%A Dias,Barbara
%A Charlet,Jean
%A Blondiaux,Eléonore
%A Khoshnood,Babak
%A Jurkovic,Davor
%A Jauniaux,Eric
%A Jouannic,Jean-Marie
%+ Service de Médecine Fœtale, Sorbonne Université, Assistance Publique - Hôpitaux de Paris / Hôpitaux Universitaires Est Parisiens, Hôpital Armand Trousseau, 26 avenue du Dr Arnold Netter, Paris, 75012, France, 33 622286740, ferdinand.dhombres@inserm.fr
%K decision support system
%K ontology
%K knowledge base
%K medical ultrasound
%K ectopic pregnancy
%D 2019
%7 03.07.2019
%9 Original Paper
%J J Med Internet Res
%G English
%X Background: Early pregnancy ultrasound scans are usually performed by nonexpert examiners in obstetrics/gynecology (OB/GYN) emergency departments. Establishing the precise diagnosis of pregnancy location is key for appropriate management of early pregnancies, and experts are usually able to locate a pregnancy in the first scan. A decision-support system based on a semantic, expert-validated knowledge base may improve the diagnostic performance of nonexpert examiners for early pregnancy transvaginal ultrasound. Objective: This study aims to evaluate a novel Intelligent Scan Assistant System for early pregnancy ultrasound to diagnose the pregnancy location and determine the image quality. Methods: Two trainees performed virtual transvaginal ultrasound examinations of early pregnancy cases with and without the system. The ultrasound images and reports were blindly reviewed by two experts using scoring methods. A diagnosis of pregnancy location and ultrasound image quality were compared between scans performed with and without the system. Results: Each trainee performed a virtual vaginal examination for all 32 cases with and without use of the system. The analysis of the 128 resulting scans showed higher quality of the images (quality score: +23%; P<.001), less images per scan (4.6 vs 6.3 [without the CDSS]; P<.001), and higher confidence in reporting conclusions (trust score: +20%; P<.001) with use of the system. Further, use of the system cost an additional 8 minutes per scan. We observed a correct diagnosis of pregnancy location in 39 (61%) and 52 (81%) of 64 scans in the nonassisted mode and assisted mode, respectively. Additionally, an exact diagnosis (with precise ectopic location) was made in 30 (47%) and 49 (73%) of the 64 scans without and with use of the system, respectively. These differences in diagnostic performance (+20% for correct location diagnosis and +30% for exact diagnosis) were both statistically significant (P=.002 and P<.001, respectively). Conclusions: The Intelligent Scan Assistant System is based on an expert-validated knowledge base and demonstrates significant improvement in early pregnancy scanning, both in diagnostic performance (pregnancy location and precise diagnosis) and scan quality (selection of images, confidence, and image quality). 
%M 31271152
%R 10.2196/14286
%U http://www.jmir.org/2019/7/e14286/
%U https://doi.org/10.2196/14286
%U http://www.ncbi.nlm.nih.gov/pubmed/31271152