Back to search

Boston University

Adapting AI models for healthcare applications

Abstract

dc:description.abstract

General-purpose AI models often struggle to maintain performance when applied to the healthcare domain due to distributional mismatch between training data and the deployment setting, available resources, and task requirements. Domain adaptation bridges this gap by adapting AI models to specific clinical contexts. However, there is no universal approach that fits all constraints and application domains. This dissertation investigates how constraints drive strategy selection and how to adapt traditional machine learning, convolutional neural networks, and large language models accordingly to specific medical domain problems. The first study starts by exploring domain adaptation for structured clinical data. Models developed using high-resource features often become inapplicable when deployed in low-resource environments due to mismatched feature availability. This work develops models tailored to the specific feature sets available at different levels of care. Shifting from structured data to visual modalities, this study examines adaptation strategies for vision models in neuropsychological assessments. Models pre-trained on natural images show minimal visual similarity to clinical Trail Making Test drawings. This work demonstrates that lightweight transfer learning (fine-tuning only a classification head) effectively adapts general-purpose vision models to this specialized clinical task. For biomedical literature screening, where labeled data and computational resources are limited, this dissertation demonstrates that prompt engineering provides a data-efficient alternative to full training for adapting general language models to domain-specific screening tasks. As the most intensive adaptation approach, this dissertation introduces PandemIQ Llama for epidemiological applications. This model undergoes continuous pre-training on a large domain-specific corpus before task-specific fine-tuning. This continuous pre-training approach outperforms both prompt engineering and standard fine-tuning methods. In conclusion, aligning adaptation strategies with available data, resources, and clinical context is essential for developing broadly applicable AI tools in healthcare. This dissertation demonstrates how systematically tailoring methods to specific constraints enables effective healthcare AI solutions.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy
Level thesis:degree_level
doctoral
Discipline thesis:degree_discipline
Systems Engineering
Grantor
Boston University
Year dc:date.issued
2026

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Yang, Jingmei
Advisor dc:contributor.advisor
  • Paschalidis, Ioannis Ch.
ORCID dc:identifier.orcid

Subjects

dc:subject × 1

Rights

dc:rights
Statement dc:rights
  • Attribution-NonCommercial-NoDerivatives 4.0 International
Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/2144/52999

Chain of custody

source
Harvested from
Boston University
Base URL
open.bu.edu/oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
related terms
citation

Yang, Jingmei. Adapting AI models for healthcare applications. doctoral thesis, Boston University, 2026. https://hdl.handle.net/2144/52999