Identification of patients with immune-related adverse events from clinical notes using machine learning Conference Paper
| Authors: | Gupta, S.; Belouali, A.; Shah, N.; Atkins, M.; Madhavan, S. |
| Title: | Identification of patients with immune-related adverse events from clinical notes using machine learning |
| Conference Title: | 8th IEEE International Conference on Healthcare Informatics (ICHI) |
| Abstract: | Although Immune Checkpoint Inhibitors (ICIs) have substantially improved survival in patients with advanced malignancies, they are associated with a unique spectrum of side effects termed Immune-Related Adverse Events (irAEs). To ensure treatment safety, research efforts are needed to comprehensively detect and understand irAEs. The goal of this work is to evaluate a Machine Learning-based phenotyping approach that can identify patients with irAEs from a large volume of retrospective clinical notes. We applied different shallow and deep Machine Learning (ML) models using different feature representations (frequency-based, distributed word embeddings) on the reduced text to classify the presence or absence of any irAE. Evaluation shows promising results with an average F1-score=0.75 and AUC-ROC=0.78. © 2020 IEEE. |
| Keywords: | side effect; health care; adverse events; machine learning; natural language processing; learning systems; research efforts; cancer; clinical notes; deep learning; large volumes; turing machines; feature representation; phenotyping; unique spectra |
| Journal Title | 2020 IEEE International Conference on Healthcare Informatics |
| Conference Dates: | 2020 Nov 30-Dec 3 |
| Conference Location: | Virtual |
| ISBN: | 9781728153827 |
| Publisher: | Institute of Electrical and Electronics Engineers Inc. |
| Date Published: | 2020-01-01 |
| Language: | English |
| DOI: | 10.1109/ichi48887.2020.9374360 |
| PROVIDER: | scopus |
| DOI/URL: | |
| Notes: | Conference Paper -- Export Date: 3 May 2021 -- Source: Scopus |
