BMEG-E 510 Artificial Intelligence in Biomedical Engineering
3 credits
- Prerequisite(s): None
- Delivery: On-Campus
Description
This course covers AI principles in biomedical engineering, emphasizing machine learning, deep learning, and advanced models in healthcare applications. Students examine foundational models, biomedical data types (tabular, text, imaging, genomics), data curation, feature extraction, and statistical analysis, with discussions on foundation models, large language models, and ethical implications.
Topics
Introduction to AI in Healthcare
- Overview of AI principles
- Applications and impact on biomedical engineering
Machine Learning Foundations
- Supervised learning
- Unsupervised learning
- Model selection and evaluation
Deep Learning in Biomedical Engineering
- Neural networks
- Convolutional neural networks (CNNs)
- Generative adversarial networks (GANs) for medical imaging
Biomedical Data Types and Data Management
- Data types: Tabular, text, imaging, and genomics
- Data normalization and cleaning processes
Feature Extraction and Data Integration
- Feature extraction techniques
- Integration of multimodal biomedical data
Statistical Analysis for AI in Healthcare
- Model robustness
- Cross-validation techniques
- Performance metrics and error analysis
Foundation Models in Biomedical Applications
- Definition and overview of foundation models
- Examples of biomedical applications
Large Language Models (LLMs) in Biomedical Data Processing
- LLM architectures and functionalities
- Use of LLMs for biomedical text and data interpretation
Medical Imaging Applications of AI
- Segmentation
- Classification
- Detection in medical imaging
AI Applications in Genomics and Proteomics
- Predictive analytics in genomics
- Proteomics and disease progression analysis
Bioinformatics and AI
- Sequence alignment techniques
- Protein structure prediction
Drug Discovery and Personalized Medicine
- AI in drug discovery processes
- AI-driven solutions for personalized medicine
Ethical Considerations in AI for Healthcare
- Bias and fairness in AI models
- Techniques for bias mitigation
Regulatory Aspects of AI in Clinical Deployment
- Overview of regulatory considerations
- Compliance and safety standards for AI-based medical devices
Future Trends in AI for Healthcare
- Emerging technologies and methodologies
- Potential advancements in biomedical engineering
Learning Outcomes
- Analyze the impact of AI in healthcare to identify transformative applications in biomedical engineering.
- Evaluate machine learning algorithms to select appropriate models for specific biomedical data types.
- Design deep learning models, including CNNs and GANs, for medical imaging applications.
- Integrate multimodal biomedical data sources to improve predictive accuracy in AI models.
- Assess statistical methods for model robustness and cross-validation in AI-based healthcare solutions.
- Develop foundation models and large language models tailored for biomedical data processing.
- Critique ethical concerns and propose bias mitigation strategies for AI in biomedical contexts.
- Formulate regulatory considerations to guide the deployment of AI-based medical devices.
- Create AI-driven solutions for personalized medicine and drug discovery, emphasizing clinical applications.
Policies and Procedures
Please be aware of the following linked policies and procedures. Note that in individual courses instructors will have stipulations specific to their course.