Date of Award
Master of Science (MS)
Survey data collected from human subjects can contain a high number of features while having a comparatively low quantity of examples. Machine learning models that attempt to predict outcomes from survey data under these conditions can overfit and result in poor generalizability. One remedy to this issue is feature selection, which attempts to select an optimal subset of features to learn upon. A relatively unexplored source of information in the feature selection process is the usage of textual names of features, which may be semantically indicative of which features are relevant to a target outcome. The relationships between feature names and target names can be evaluated using large language models (LLMs) such as ClinicalBERT to produce semantic textual similarity (STS) scores, which can then be used to select features. This thesis introduces two new variations upon the minimal-redundancy-maximal-relevance (mRMR) algorithm that integrate semantic textual similarity (STS) into selection. The performance of STS as a feature selection metric is evaluated against preliminary survey data collected as a part of a clinical study on persistent post-surgical pain (PPSP). The results suggest that features selected with STS can result in higher performance models compared to those with the baseline mRMR algorithm.
Simon Haroutounian Thomas Kannampallil Cynthia Ma
Anesthesiology Commons, Artificial Intelligence and Robotics Commons, Biomedical Informatics Commons, Databases and Information Systems Commons, Health Information Technology Commons, Quality Improvement Commons, Theory and Algorithms Commons