Master of Science in Artificial Intelligence for Biomedical and Healthcare Applications

This course provides a comprehensive introduction to computer programming using the Python language, tailored for graduate students entering the field of Artificial Intelligence for Biomedical and Healthcare Applications. The course covers fundamental concepts (variables, control structures, functions) and advances to intermediate topics (object-oriented programming, data structures, file handling, and error management).

Computational biology is based on genomics data obtained that describe the biology of the cell. The word Genomics encompasses genomics (DNA), transcriptomics (RNA), and proteomics, which have been active fields of research for the last 30 years and have generated an explosion of BIG data from different organisms. After the completion of the human genome project in 2005, the entire DNA sequences of several organisms, including humans, are now available. These are long strings of base pairs (A, C, G, T) containing all the information necessary for an organism's development and life. Computer science plays a central role in genomics: from sequencing and assembling DNA sequences to analyzing genomes in order to localize genes, repeat sequence families, similarities between sequences of different organisms, and several other applications. In addition, computational biology focuses on developing novel algorithms for the analysis of genomic sequences and integrating transcriptomic and proteomic data. This course presents essential algorithms for sequence analysis, transcriptomic count calling, and proteomics analysis. Topics include alignment, transcript count normalization algorithms such as STAR and DESeq, differential protein abundance analysis, and integration of computational biology data from multiple modalities.

This course provides a broad introduction to machine learning. Main topics include regression, classification, and clustering. Detailed subjects include simple and multiple regression, Ridge regression, kernel features, feature selection and Lasso, linear classifiers and logistic regression, decision trees and ensemble learning, support vector machines, and artificial neural networks. Best practices in machine learning, such as overfitting, regularization, and bias-variance theory, are also covered. Students will learn how to identify and implement appropriate machine learning algorithms for a variety of problems.

This course introduces graduate students to the practice of research. The preliminary topic list includes: What is research? Research in Computer Science, research methodologies and resources, basic methods for reading technical papers, selecting research topics, devising research questions, planning research, writing thesis proposals, technical writing and publication, presentation skills, and reviewing technical papers.

This course examines the integration and application of artificial intelligence into biomedical and healthcare research, including genomics, digital health, personalized medicine, and clinical decision support. Students explore both classical machine learning and advanced deep learning techniques, evaluating their potential to solve healthcare challenges while acknowledging their practical limitations. Beyond technical skills, the curriculum covers the essential regulatory, ethical, and clinical frameworks required for the responsible deployment of AI in professional healthcare settings.

Prerequisite: 24 Cr. Hr.

A comprehensive individual research project conducted under the supervision of one or more faculty members, focused on advancing Artificial Intelligence for biomedical and healthcare applications. The work may involve (i) proposing and developing an innovative AI algorithm, framework, or theory motivated by healthcare needs, and/or (ii) designing, implementing, and evaluating AI solutions using biomedical or clinical data. The outcomes should be of publishable quality in the form of a research paper. The thesis must be written in an academic format and defended successfully before an examination committee to achieve a pass grade.

Prerequisite: 24 Cr. Hr.

This course covers advanced computational methods used to acquire, represent, process, analyze, and deploy biomedical and healthcare data. It emphasizes practical, reproducible pipelines for multimodal data (medical imaging, biosignals, electronic health records, and omics) and modern AI methods (deep learning, self-supervised learning, transformers, graph learning, and generative models) under real clinical constraints (privacy, fairness, interpretability, safety, and deployment). Students will complete a project using real or realistic healthcare datasets and deliver a reproducible implementation and technical report.

This course provides advanced knowledge and hands-on experience in deep learning techniques applied to biomedical and healthcare domains. Students explore CNNs, RNNs, Transformers, Graph Neural Networks, and multimodal architectures for medical imaging, genomics, EHR analytics, disease prediction, drug discovery, and personalized medicine. Ethical considerations, interpretability, bias mitigation, and regulatory aspects of AI in healthcare are addressed.

This advanced graduate course explores the application of Artificial Intelligence (AI) techniques to medical image processing and analysis. It covers fundamental concepts in medical imaging modalities (MRI, CT, X-ray, and Ultrasound) and advances toward deep learning-based methods for image enhancement, segmentation, registration, classification, and disease detection. Students study deep learning architectures such as convolutional neural networks, recurrent neural networks, autoencoders, transformer-based models, multimodal learning, and explainable AI in clinical contexts. The course emphasizes practical implementation using modern AI frameworks, performance evaluation using appropriate metrics (e.g., Dice score, sensitivity, and specificity), and ethical considerations including data privacy and bias. The course integrates critical paper discussions with lectures and includes a substantial research project to explore contemporary research challenges.

This course focuses on the design, implementation, management, and governance of database systems in healthcare environments. Students will learn how to model clinical data, implement relational and NoSQL databases for healthcare applications, manage health data standards, ensure interoperability, and address privacy, security, and regulatory requirements in digital health systems.

Data science is an interdisciplinary field that provides tools to extract insights from data in various forms, including structured and unstructured data. This course provides theories, strategies, and tools to understand and apply data preparation, data cleaning and integration, data analysis, classification, clustering, text analysis, and visualization.

Prerequisite: 1501531 Machine Learning

This course presents advanced research topics in Data Science. It explores research topics in the analysis and management of large-scale data. The course discusses and analyzes papers covering applications, algorithms, systems, and theory, with a focus on recent developments. The instructor will introduce topics based on their area of specialization.

Prerequisite: 1501531 Machine Learning

This advanced graduate course explores several important topics in machine learning in depth. The course emphasizes both practical and theoretical aspects. Topics may include artificial neural networks, graph neural networks, relational learning, Bayesian machine learning, embedding models, and generative models. Lectures will be supplemented with paper discussions, and students will complete a significant research project to explore current research issues.

This course provides a general introduction to consumer health informatics (CHI). The course covers theories of health behavior and information behavior, key concepts and terminology, and major application domains. It explores the application of artificial intelligence, machine learning, and natural language processing to personal health management, wearable consumer health devices, health literacy, and patient-centered digital tools. The course also introduces key issues such as health literacy, patient-centered communication, patient empowerment, patient-generated data, epidemiological analysis, and privacy. Finally, the course covers CHI applications in major domains, including personal health records, e-Health, telehealth, and telemedicine.

This course focuses on the convergence of Artificial Intelligence (AI) and precision medicine to transform healthcare. It introduces fundamental knowledge and skills in applying Artificial Intelligence and Machine Learning (AI/ML) techniques in precision medicine. Students develop skills to preprocess and analyze data using AI/ML methods, generate insights, and build and explain predictive models for precision medicine applications. The course bridges high-level computational techniques with clinical biology and covers genomic data analysis, predictive risk modeling, and ethical integration of AI into healthcare workflows.

This course emphasizes the theory and AI/ML applications in virtual screening, molecular modeling simulations and docking, molecular dynamics, mechanics, thermodynamics of biomolecular interactions, biological activity, equilibrium binding, formation of biomolecular and conformational complexes, and the design of small molecule inhibitors for drug discovery.