Developing Novel NLP-Enabled Timely and Accurate Decision Making for Precision Medicine
Author(s)
Zhu, Yuanda
Advisor(s)
Editor(s)
Collections
Supplementary to:
Permanent Link
Abstract
Precision medicine uses big data capturing “individual differences in patients’ genes, environments, and lifestyles focuses” to make prevention strategies, screening, diagnosis of diseases and treatment therapies. In recent years, the rapid development of Natural Language Processing (NLP) uses Artificial Intelligence and Machine Learning to make sense of large volumes of language or time-series data. In this dissertation, I have not only investigated how NLP can extract precise information from electronic health records (EHRs) and free-text clinical notes, but also examined how NLP models such as transformers can be used for analyzing human physiological Electroencephalography (EEG) data for accurate clinical decision making. Specifically, on EHRs, I have shown how NLP is able to decipher and sequentially report death events for individual patients; on free-text clinical notes, I have demonstrated how the pretrained transformer-based NLP model BERT can precisely discern long COVID-19 patients from the rest; and on time-series EEG data, I have illustrated how Long Short-Term Memory (LSTM) and transformer architectures, when combing with convolutional neural networks (CNNs), can extract both spatial and temporal features for accurate seizure detection. My PhD research aims to provide a foundation for advancing NLP for personalized patient care in modern Precision Medicine.
Sponsor
Date
2023-12-05
Extent
Resource Type
Text
Resource Subtype
Dissertation