NSU HPD Catalog 2024-2025

Dr. Kiran C. Patel College of Osteopathic Medicine—Health Informatics Program 93 needed to support the various system designs, such as Hadoop ecosystems and Hadoop-based tools. Students will be exposed to the application of predictive analytics specific to health care, so they will understand the use of data to help deliver quality and safe patient care, as well as data-driven methods of improving care. The course will expose students to realtime data analytics where data is collected and reported on around the clock. It will also expose student to mobile data acquisition and analysis coming from various local and remote devices and will introduce students to data visualization methods that will teach them how to communicate analytical insights to both technical and nontechnical audiences. (3 credit hours) MI 6428—Artificial Intelligence for Health Care This advanced cognitive engineering systems course will expand upon introductory topics presented as part of the clinical decision support, database management, and analytics courses to take a deeper dive into data science and artificial intelligence algorithms, with specific application to such medical specialties as oncology, cardiology, pulmonology, radiology, neurology, and psychology. It will provide students with skills necessary to undertake programmatic statistical analysis of complex patient information data sets; to apply unsupervised learning techniques that will enhance outcomes of the predictive and prescriptive analytics methods; to use supervised learning methods that represent evidence-based guidelines and detect medical fraud; to process and exchange structured and unstructured clinical data; to compare and analyze graphs (i.e., ECHO) and images (i.e., MRI/X-Ray); and to apply natural language processing techniques to ingest and analyze clinical data. Students will learn how to choose among various AI methods; integrate clinical data and algorithms; translate research applications into clinical practice; and perform longitudinal data analysis using primary sources of clinical data, such as electronic medical records, lab information systems, and imaging databases. Participants will combine research methods with real-world evidence to discover new ways of approaching drug performance and pharmacological surveillance through real-time aggregation and monitoring of health care provider databases. (3 credit hours) MI 6430—Methods of Health Care Analytics This course will introduce students to a variety of mathematical techniques that are commonly used in health care analytics and health informatics. The emphasis will be on developing an understanding of the methods, their uses, and their limitations. Mathematical rigor would not be emphasized, but instead, an understanding of the meaning and uses of the techniques. The instruction would also include teaching a mathematical mindset to the students that will allow them to extend their knowledge and understanding to further areas as needed in their future endeavors. (3 credit hours) MI 6432—Big Data Analysis in Health Care This course provides a comprehensive and rigorous introduction to big data analytics in health care. It will describe the hardware/software infrastructures that are used today for big data (e.g., Hadoop, Hive) and the implications of these infrastructures for the accurate and efficient analysis of big data for health care applications. Students will learn the mathematical, statistical, artificial intelligence, and modeling techniques that have been developed for analysis of big data, especially for health care applications. Also, it will describe the visualization techniques that are useful for displaying big data analysis results for meaningful interpretation of the results by humans. It will use current, real-world problems involving big data analytics in health care, including the Big Data to Knowledge (BD2K) initiative of the National Institutes of Health. Students will gain experience in applying the techniques of big data analytics to health care problems. (3 credit hours) MI 6700—Computational Informatics This course will provide an introductory, hands-on experience for life science researchers in bioinformatics using R and Bioconductor. Emphasis will be placed on accessing, formatting, and visualizing genomics data. Most analyses will deal with “little” data (no mapping or assembly of short reads), but some techniques to work with “big” data (e.g., BAM files) will be covered. Lecture and lab will both be held in a computer lab, so lecture will be hands-on. Working in small groups is encouraged. (3 credit hours) MI 6900—Bioinformatics This course introduces the concepts and practice of bioinformatics. Topics of discussion include biological databases, sequence alignment, gene and protein structure prediction, molecular phylogenetics, genomics, and proteomics. This is a hands-on, skill-based class. Students will develop basic skills in the collection and presentation of bioinformatics data, as well as the rudiments of programming in a scripting language. (3 credit hours) MI 7000—Health Informatics Project/Practicum This is a required course for all M.S. students. The practicum allows the student to select an area of interest in which to apply the theories, concepts, knowledge, and skills gained during the didactic courses in a real-world setting. The student will work under the supervision of a site-based preceptor and an NSU-based faculty adviser. The student is expected to acquire skills and experiences in the application of basic health informatics concepts and specialty knowledge to the solution of health information technology (HIT) problems. Students will be actively involved in the development, implementation, or evaluation of an informaticsbased application or project.

RkJQdWJsaXNoZXIy NDE4MDg=