Hello, and welcome to this final course in our health care data literacy specialization offered by UC Davis. My name is Brian Paciotti, and I have over 15 years of experience working as a data scientist within the healthcare industry. For those that join me in the first course, my story hasn't really changed much, but for those that just joined me, let me catch you up on my career story. I started my career with an interdisciplinary PhD, in Human Ecology, from the University of California, Davis. In my dissertation, I used ethnography and games from the field of behavioral economics to understand co-operative ethnic groups in Tanzania, East Africa. After being accused of being a CIA spy by the Tanzanian government, I left the country and analyzed homicide data. After graduate school, I was interested in applied aspects of research. Thus, I earned a healthcare, informatics masters degree from UC Davis, in 2010. In my thesis, I used data mining techniques to understand the quality of administrative hospital data. With an informatics degree and a strong research background related to organizational behavior, I've enjoyed a variety of employment adventures. First, I worked for the State of California to use administrative data and vital statistics to create hospital level outcomes reports. Second in 2010, I joined the bioinformatics group at UC Davis to provide informatics and statistical services to autism researchers. Third, I joined the UC Davis institute for population health improvement, where I created analytical reports to understand health disparities, and high cost patients among California's Medicaid population. Fourth, continuing with Medicaid research and data science, I worked for a health analytics company called Optum, where I worked to continue analytical work consulting with California's medical program. Throughout these interesting positions, I was vice president of analytics for healthcare analytics start-up company. In this course, we're going to go over analytical solutions to common health care problems. I will remind you of these business problems, and you'll build out various data structures to organize your data. We'll then explore ways to group data, and to categorize medical codes into actionable categories. You will then be able to extract, transform, and load data into data structures required for solving medical problems, and then be able to also harmonize data from multiple sources. Finally, you will create a data dictionary to communicate the source and value of data. Creating these artifacts of data processes is a key skill, when working with health care data. The format of the course is primarily video lecture-based, but a lot of in-video and end of module quizzes to make sure you're able to understand and apply these concepts that we've been discussing. There is also a four-part project that I spread out into various modules to help you build your skills throughout the course. In part one, you will review output from real-world provider profiles, and risk stratification projects. Next in part two, you will access opensource grouper software, and evaluate how granular medical codes and concepts are grouped into more meaningful categories. In part three, I will ask you to create an analytical project plan that has a predictive modeling component, and a strategy to extract and transform data from a de-identified clinical database. Finally, in part four, I will ask you to build off the previous three projects and perform risk stratification analyses, at least conceptually, using the de-identified Medicare claims database. This last part may require some documentation such as creating data dictionaries and a report summary, where you interpret what the information means, based on the context of the data. Healthcare analytics is about solving real-world problems, helping both the patient and their care team provide the best care possible, all the while, helping the health system improve their bottom line. It's very interesting and exciting work, and we have a lot to cover. So, let's dive in.