Biomedical Informatics Commons^™

A Specification-Driven Framework For Self-Supervised Learning In Specialized Vision Domains, Mahmut S. Gokmen

Theses and Dissertations--Computer Science

Self-supervised learning (SSL) has emerged as a principled approach to visual representation learning that derives supervisory signal directly from unlabeled data, enabling foundation models to be trained at scale without manual annotation. Deployments in medical imaging and biometric recognition have demonstrated the potential of this paradigm, yet the assumptions that make SSL effective on natural image benchmarks fail systematically in specialized domains. Generic SSL pipelines encode a tacit assumption that the most informative correspondence is spatial proximity within a single acquisition. In specialized domains this assumption breaks at the level of the data-generating process: the signal that carries domain-specific information …

Biomedical Relation Extraction In The Era Of (Large) Language Models, Yuhang Jiang

Theses and Dissertations--Computer Science

Biomedical relation extraction is a key task in information extraction supporting downstream applications such as knowledge discovery, information retrieval, and question answering. As such, improvements in relation extraction (RE) are expected to have major implications for other information needs in biomedicine. In this dis- sertation, we pursue biomedical relation extraction in several advanced settings with recent advances in large language models (LLMs) and retrieval augmented generation (RAG). First, we address an important slot filling task on social media that arose during the Covid-19 pandemic, using the idea of continuous prompts with encoder models. Next, we handle a tricky dynamic n-ary …

Machine Learning Framework For Real-World Electronic Health Records Regarding Missingness, Interpretability, And Fairness, Jing Lucas Liu

Theses and Dissertations--Computer Science

Machine learning (ML) and deep learning (DL) techniques have shown promising results in healthcare applications using Electronic Health Records (EHRs) data. However, their adoption in real-world healthcare settings is hindered by three major challenges. Firstly, real-world EHR data typically contains numerous missing values. Secondly, traditional ML/DL models are typically considered black-boxes, whereas interpretability is required for real-world healthcare applications. Finally, differences in data distributions may lead to unfairness and performance disparities, particularly in subpopulations.

This dissertation proposes methods to address missing data, interpretability, and fairness issues. The first work proposes an ensemble prediction framework for EHR data with large missing …