Curriculum: Certificate in Health Data Science and Artificial Intelligence

This course introduces the student to a variety of statistical methods, study design, and programming as essential skills in data science. Students practice techniques such as data cleaning, data wrangling, data exploration, analysis, visualization, and interpretation. Students use a variety of healthcare datasets in this course and are also prepared to discuss healthcare data standards and measures, best practices in data management, and trends in healthcare data science and management.

This course will introduce students to a variety of cutting edge analytics and business intelligence tools applicable to health or healthcare data. Both structured and unstructured data will be introduced in this course. The coursewill also address topics related to data governance and data quality and various other topics relevant to health data management. This course is predominately hands-on and students willcomplete a project to demonstrate skills acquired.Students will learn how other industries have applied similar or the same tools.

This course is a survey of Machine Learning (ML) and Artificial Intelligence (AI) from the Data Scientist’s perspective. It explores ML and AI topics, current and emerging technologies, and applications for students to gain understanding of the successful implementation of ML and AI to address key business and industry problems.

This is a course in statistical data mining with emphasis on hands-on case study experiences using various data mining/machine learning methods and major software packages to analyze complex real world data. Topics include data preprocessing, k-nearest neighbors, generalized linear regression, subset and LASSO variable selection, model evaluation, cross validation, classification and regression trees.

This is a course in statistical data mining with emphasis on hands-on case study experiences using various data mining/machine learning methods and major software packages to analyze complex real world data. Topics include advanced trees: bagging, random forests, boosting; nonparametric smoothing methods; generalized additive models; data preprocessing/scaling; neural networks; deep learning; cluster analysis; association rules.

This course teaches the use of healthcare data to make decisions and transform healthcare delivery and the health of individuals and populations. The course concentrates on big and small data, and structured and unstructured data. Tools, applications and approaches for health data analytics are taught. This course covers topics such as statistical approaches; data, web and textmining; data visualization, simulation, modeling and forecasting. Key regulatory health and healthcare reporting requirements are taught.

This course introduces machine learning and data mining techniques. The course focuses on using applied methods and software tools to discover hidden patterns or identify anomalies in the data generated in modern IT networks.

Students will be introduced to various electronic health information standards such as vocabulary, terminology and messaging standards. Students will apply knowledge and information discovery and extraction techniques for health and healthcare scenario. This course introduces standards for health and healthcare data communication, storage and representation, emphasizing new paradigms.

This course introduces legislation relevant to electronic health information privacy and information security. Topics such as electronic health information privacy and security safeguards, risk assessment methodology and contingency planning are taught. Students learn how to mitigate risk to business continuity and plan for disaster recovery.

This course teaches students principles of data modeling and database design. Students gain hands-on experience data modeling, designing and developing a database for a health scenario. Students gain experience with a querying language such as structured query language (SQL).

This course applies project and program managementknowledge and frameworks to health and healthcare scenarios specifically focusing on health information technology projects and programs. The course focuses mostly on project management but introduces key knowledge and frameworks utilized by program managers. Topics such as professional communication, team building, project integration management, project risk management, project time management, and project quality management are covered. Students learn the characteristics of a successful project and program. Advanced principles of project scheduling and control are taught. This course is aligned to Project Management Institute's standards.

This course teaches students how to develop, scale-up, and sustainably manage high-performing Artificial Intelligence/Machine Learning systems in business organizations. It introduces concepts and techniques that enable the development of surrogate approaches to explain AI/ML models, build redundancy in AI/ML systems, and calculate and minimize risk of failures while using such approaches.

This independent study course is available to graduate students in the Health Informatics discipline, and allows the student to work under the direction of a faculty member to delve deeply into a health informatics topic as identified and specified by the faculty sponsor and student. Each independent study will be designed specifically for the student, and thus each will be a unique offering and experience. Each experience will culminate in a meaningful final academic product.