A Temporal Visualization of Chronic Obstructive Pulmonary Disease Progression using Deep Learning and Unstructured Clinical Notes

Researchers utilized a two-step approach for the visualization of chronic obstructive pulmonary disease (COPD) progression using a deep-learning model and unstructured clinical notes analyzing irregular time lapse segments. This was then used to create a temporal visualization. The study tracked 15,500 COPD patients that both received care within the Partners Healthcare network as well as died between 2011 and 2017. The experiments demonstrated the deep-learning approach is a feasible model and could be used to generate graphical information pulled from clinical notes.

Citation for the Full-text Article

Tang C, Plasek JM, Zhang H, Kang MJ, Sheng H, Xiong Y, Bates DW, Zhou L. A temporal visualization of chronic obstructive pulmonary disease progression using deep learning and unstructured clinical notes. BMC Medical Informatics and Decision Making. 2019;19(8);258. DOI: 10.1186/s12911-019-0984-8