PREREQUISITES AND PLACEMENT IN THE CURRICULUM: Must be an M4

PURPOSE:
Recent years have seen an explosive growth in use of artificial intelligence in medicine arising from big data, e-commerce, and automation. Developments in information technologies, analytical and quantitative techniques have enabled the processing and analyses of vast troves of data to provide better patient care. This trend has fueled a demand for people with requisite technology and analytical knowledge and skills for utilizing the data obtain to perform quality improvement activities and improve patient safety. This elective will prepare healthcare students to have adequate foundational knowledge to participate on a technical team implementing an Al project.
This is an online course with a virtual face to face meeting twice a week. Students will be expected to commit to four to five hours of work time per day to cover the following topics. There will be weekly quizzes and students are expected to complete a capstone project to present on research day.

OBJECTIVES:
Prepare healthcare students to have adequate foundational knowledge to participate on a technical team implementing an Al project.

1. Define and describe the linkages between evidence-based medicine, high-value care, precision medicine, mobile computing and artificial intelligence.
2. Explain various forms of artificial intelligence and how they are applied today in healthcare to improve outcomes. Review use cases of applied Al in value-based care being used by health systems today.
3. Identify the drivers, decision factors and collaboration required across clinical, operational and technology teams to realize return on investment from Al. (lnterprofessional Collaborative Practice)

INSTRUCTIONAL METHODS:
This is an online course with a virtual face to face meeting twice a week. Students will be expected to commit to four to five hours of work time per day to cover the following topics. There will be weekly quizzes and students are expected to complete a capstone project to present on research day.

Week 1. Biomedical informatics foundations

1. EMR essentials.
2. Information systems design principles.
3. Healthcare project management principles: systems development lifecycle (SDLC), waterfall technology development, agile software development.
4. Infrastructure and networking essentials: the basics of computer networking, telemedicine, cloud computing, Big Data infrastructure, computer databases.
5. Ethical considerations in informatics and clinical analytics.
6. Economics of clinical analytics and healthcare informatics.

Week 2. Essentials of Healthcare Data Science

1. Population health, small data, big data.
2. Health outcomes research and support from Big Data.
3. Introduction to business and clinical intelligence: dashboards, reports, clinical measures.
4. Data analytics and evidence-based medicine.
5. Detailed review of medical data ontologies (ICD, CPT, LOINC, RxNORM, UMLS, DRG, SNOMED, and more).
6. Healthcare systems interoperability standards: intro to HL7, JSON, XML, and jq.
7. Biomedical informatics and healthcare data interoperability across all healthcare domains: provider care, life sciences, genetics and personalized medicine, payers, retail pharmacies, biomedical device engineering, mobile health.
8. The basics of data visualization.
9. Practical skills with workflows, data flows, business data diagrams, and use case diagrams.
10. Soft skills for data scientists: ability to present complex concepts to general audiences in simple terms.

Week 3. Predictive Analytics and Artificial Intelligence

1. Introduction to algorithms.
2. Hypothesis development.
3. Essentials of predictive analytics.
4. Introduction to statistical methods in clinical analytics.
5. Supervised learning, rule based programming, and expert systems.
6. Fundamentals of clinical decision support systems: supervised and unsupervised learning.
7. Introduction to fuzzy logic.
8. Unsupervised learning, machine learning, deep learning.
9. Imaging analysis and frequent subgraph mapping. Integration of image analysis into clinical analytics, machine learning algorithms, and workflows.
10. Real world evidence (RWE) and clinical data integration across all healthcare domains.
11. Artificial intelligence for precision medicine and drug discovery.

Week 4. Integrating and Applying Al

1. Bringing it all together: medicine at the crossroads of tradition and innovation, what Al means to new and already practicing physicians, what Al is and is not in medicine.
2. Challenges and opportunities of traditional and machine learning analytics in medicine: the Al value problem.
3. Hot topic discussion: as a clinician, how to embrace rather than fight and fear Al.
4. Telling a story with data: how to bring data wrangling, analysis, visualizations, and testing together into a cohesive business and clinical story that resonates with those not familiar with Al.
5. Presentation to virtual (or physical) audience and a comprehensive project building blueprints for a new Al application from the ground up, utilizing all knowledge gained in the course.

ASSESSMENT: Quiz each week, Team Project and Presentation

Required Reading: Benson, Tim. Principles of Health Interoperability HL7 and SNOMED (3rd Ed). Springer, 2016. ISBN: 978-3-319-30368-0. Reddy, Chandan K., Aggarwal, Charu C. (Ed.) (2015). Healthcare Data Analytics. United States: Boca Raton, Florida, CRC Press, Taylor and Francis Group.
ISBN: 978-1-482- 23211-0. Shotts, William E. (2019). The Linux Command Line: A Complete Introduction (2nd Ed.). United States: San Francisco, California, No Starch Press. ISBN: 978-1593279523.

Additional Resources: Required Software will be provided free of charge by the university

ADMINISTRATIVE INFORMATION:

Program Number: ELEC 440
Program Directors: Dr. Linda Chang, Dr. Radhika Sreedhar
Email: [email protected]
Duration: 4 Weeks

Updated:  6/5/20