Validation of a Natural Language Processing Algorithm for Detecting Infectious Disease Symptoms in Primary Care Electronic Medical Records in Singapore.

Antony Hardjojo Arunan Gunachandran Long Pang Mohammed Ridzwan Bin Abdullah Win Wah Joash Wen Chen Chong Ee Hui Goh Sok Huang Teo Gilbert Lim Mong Li Lee Wynne Hsu Vernon Lee Mark I-Cheng Chen Franco Pey Gein Wong Jonathan Siung King Phang

Published in: JMIR medical informatics (2018)

We have developed an natural language processing algorithm dubbed CHESS that achieves good performance in extracting signs and symptoms from primary care free-text clinical records. In addition to the presence of symptoms, our algorithm can also accurately distinguish affirmed, negated, and suspected assertion statuses and extract symptom durations.

Keyphrases

primary care
machine learning
deep learning
infectious diseases
autism spectrum disorder
sleep quality
neural network
general practice
oxidative stress
depressive symptoms
smoking cessation
patient reported