A Deep Language Model for Symptom Extraction From Clinical Text and its Application to Extract COVID-19 Symptoms From Social Media

Abstract

Patients experience various symptoms when they haveeither acute or chronic diseases or undergo some treatments for diseases. Symptoms are often indicators of the severity of the disease and the need for hospitalization. Symptoms are often described in free text written as clinical notes in the Electronic Health Records (EHR) and are not integrated with other clinical factors for disease prediction and healthcare outcome management. In this research, we propose a novel deep language model to extract patient-reported symptoms from clinical text. The deep language model integrates syntactic and semantic analysis for symptom extraction and identifies the actual symptoms reported by patients and conditional or negation symptoms. The deep language model can extract both complex and straightforward symptom expressions. We used a real-world clinical notes dataset to evaluate our model and demonstrated that our model achieves superior performance compared to three other state-of-the-art symptom extraction models. We extensively analyzed our model to illustrate its effectiveness by examining each component's contribution to the model. Finally, we applied our model on a COVID-19 tweets data set to extract COVID-19 symptoms. The results show that our model can identify all the symptoms suggested by the Center for Disease Control (CDC) ahead of their timeline and many rare symptoms.

Fig. 1:

Model Architecture

Fig. 2:

Dependency Tree

Fig. 3:

Symptom Distribution by N-grams

Fig. 4:

Number of Tweets by Date

Fig. 5:

Sample Tweets with Symptom Mentions

Fig. 6:

Trends of the Symptoms listed by CDC

Fig. 7:

Trends of the Other Frequent Symptoms