Authors:
Navya Martin Kollapally
1
and
James Geller
2
Affiliations:
1
Department of Computer Science, New Jersey Institute of Technology, Newark, U.S.A.
;
2
Department of Data Science, New Jersey Institute of Technology, Newark, U.S.A.
Keyword(s):
Hyperparameter Optimization, Clinical BioBERT, Social Determinants of Health (SDoH), Ontology, Electronic Health Record (EHR), Genetic Algorithm, Simulated Annealing.
Abstract:
Clinical factors account only for a small portion, about 10-30%, of the controllable factors that affect an individual’s health outcomes. The remaining factors include where a person was born and raised, where he/she pursued their education, what their work and family environment is like, etc. These factors are collectively referred to as Social Determinants of Health (SDoH). Our research focuses on extracting sentences from clinical notes, using an SDoH ontology (called SOHO) to provide appropriate concepts. We utilize recent advancements in Deep Learning to optimize the hyperparameters of a Clinical BioBERT model for SDoH text. A genetic algorithm-based hyperparameter tuning regimen improved with principles of simulated annealing was implemented to identify optimal hyperparameter settings. To implement a complete classifier, we pipelined Clinical BioBERT with two subsequent linear layers and two dropout layers. The output predicts whether a text fragment describes an SDoH issue of
the patient. The proposed model is compared with an existing optimization framework for both accuracy of identifying optimal parameters and execution time.
(More)