N. Orangi-Fard
Georgia Gwinnett College,
United States
Keywords: machine learning, COPD, diagnosis, exacerbation, prediction, natural language processing, medical
Summary:
Chronic obstructive pulmonary disease (COPD) is a major public health problem with over 16.4 million adults suffer from COPD and the 4th leading cause of death in US. Over 2.2 million patients are admitted to hospitals annually due to COPD exacerbations. Monitoring and predicting patient’s exacerbations on-time could save their life. In this work presents three different predictive models to predict COPD exacerbation using AI and Natural Language processing (NLP) approaches. These models use respiration summary notes, symptoms and vital signs. To train and test these models, we used over 8000 data records containing physiologic signals and vital signs time series captured from patient monitors, and comprehensive clinical data obtained from hospital medical information systems, for tens of thousands of Intensive Care Unit (ICU) patients. We achieved an Area under the ROC curve of 0.84 and accuracy of 97.0% in detection and prediction of COPD exacerbation. Our work suggests that clinically available patient’s data and vital signs can predict risk of COPD exacerbations.