Utilizing and Evaluating Different BERT Models to Predict Patients’ Length of Stay (LOS) and Mortality by Leveraging Only the Initial Nursing Note Assessments
Bioinformatics Data Science PhD Student
University of Delaware
Abstract:This study aims to explore and compare various BERT models for predicting two critical healthcare outcomes: patients’ Length of Stay (LOS) and mortality. The project focuses on leveraging only the initial nursing note assessments, which are crucial early-stage evaluations the nursing staff write upon a patient’s admission. Furthermore, BERT, a state-of-the-art natural language processing (NLP) model, has proven to be highly effective in understanding and representing the context of textual data. In this project, different variations of BERT models will be employed to process and interpret the nursing notes. The potential benefits of this project include enhancing patient care by providing healthcare professionals with early predictions of the length of stay and mortality risk, enabling them to allocate resources more efficiently, optimize treatment plans, and improve patient outcomes. Additionally, by focusing solely on initial nursing notes, the approach may save time and resources compared to using a broader range of medical data, making it a practical and valuable tool for healthcare providers.
Bio: Saad Althabiti is a Ph.D. student in Bioinformatics Data Science. His academic journey includes the attainment of a bachelor’s degree in Health Informatics from Saudi Arabia and a master’s degree in Health Informatics, with a specialization in Data Science Track, from the University of Pittsburgh in 2020. His current research concentrated on text mining within electronic health records, intending to discover diverse clinical outcomes. He is currently co-advised by Dr. Shanker and Dr. Wu.