AUTHOR=Jia Jinmeng , Wang Ruiyuan , An Zhongxin , Guo Yongli , Ni Xi , Shi Tieliu 

TITLE=RDAD: A Machine Learning System to Support Phenotype-Based Rare Disease Diagnosis

JOURNAL=Frontiers in Genetics

VOLUME=Volume 9 - 2018

YEAR=2018

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2018.00587

DOI=10.3389/fgene.2018.00587

ISSN=1664-8021

ABSTRACT=DNA sequencing has allowed for the discovery of the genetic cause for a considerable of diseases, opening up new ways to disease diagnostics. However, due to the lack of clinical samples and records, the molecular cause for rare disease is always hard to be identified, which significantly limits the number of Mendelian rare diseases diagnosed by sequencing technologies. Thus clinical phenotype information becomes the major resources to diagnose rare diseases. In this article, we adopted both phenotypic similarity method and machine learning method to build up four diagnostic models to support rare disease diagnosis. All the diagnostic models were validated using the real medical records from RAMEDIS. Each model provides a list of top 10 candidate diseases as the prediction outcome and the results showed that all models had high diagnostic precision (≥98%) with the highest recall reaching up to 95% and the models with machine learning method showed the best performance. To promote effective diagnosis for rare disease in clinical application, we developed the phenotype-based Rare Disease Auxiliary Diagnosis system (RDAD) to assist clinicians to diagnose rare diseases with the above four diagnostic models. Users can freely access the system through http://www.unimd.org/RDAD/.