Introduction to Biostatistics (BST 206/207) provides a detailed introduction to the theory and application of statistical techniques that commonly are used in clinical research. Topics include probability distributions, significance testing, confidence intervals, sample size calculation and power, measures of association, chi-square tests, stratified and matched analyses, t-tests, non-parametric analyses, analysis of variance and the basics of linear regression. By the end of the course, students should be able to conduct all of the basic statistical tests, recognize the assumptions behind their analyses, and interpret the results. Lectures are supplemented by homework and computing labs to acquaint the participants with different methods for conducting analyses. The SAS, Stata, and R statistical programs will be taught during classes and used to carry out analyses.

Introduction to Clinical Epidemiology (EPI 208) covers core epidemiologic concepts and study designs from the perspective of clinical research. Topics include the design and analysis of cohort and case-control studies, randomized controlled trials, time series and quasi-experimental designs and quality improvement studies; minimization of bias; identification and control of confounding; and assessment of effect modification. Other related topics that are covered include diagnostic test evaluation, screening for disease, measuring quality of life, assessing the reliability and validity of questionnaires, propensity scores, and clinical prediction rules. One session is devoted to the writing of proposals and scientific papers.

Students use this methodologic training to prepare a clinical research study proposal and receive feedback from senior investigators during office hours and small-group workshops, make a formal presentation of their research plan during class, and submit a final written proposal in the form of a grant application. Ideally, these proposals will provide the foundation for future research projects. We strongly recommend that students have a few possible ideas for their project in mind before the beginning of the course.

Linear and Longitudinal Regression (BST 215) is intended for students who are already very comfortable with fundamental techniques in statistics. The course will cover methods for building and interpreting linear regression models, including statistical assumptions and diagnostics, estimation and testing, and model building techniques. These models will be extended to handle data arising from longitudinal studies employing repeated measurement of subjects over time. Lectures will be accompanied by computing exercises using the Stata statistical package.

Large longitudinal healthcare databases (e.g., claims, electronic health records) have become important tools for studying the utilization patterns and clinical effectiveness of medical products and interventions in a wide variety of care settings and for evaluating the impact of clinical programs or policy changes. This course will prepare students to identify and use longitudinal databases in their own research.

Strengths and limitations of large longitudinal healthcare databases that are commonly used for research will be considered. Special attention will be devoted to nationally representative databases that are critical for comparative effectiveness research and local electronic medical record data sources that are readily available to new investigators.

Practical issues in obtaining, linking, and analyzing large databases will be emphasized throughout the course, and key analytic issues will be addressed, including design considerations and multivariate risk-adjustment. Students will work in teams with faculty advisors to conduct research projects using a nationally representative claims database of 23 million lives. They will work with an easy-to-use software platform that helps them implement complex studies without requiring programming skills. The course focuses on analytic principles and their application to database research. It requires an understanding of epidemiologic study designs (cohort, case-control) and typical analysis strategies (logistic regression, Cox regression, propensity score analysis).

Improvement in Quality in Health Care (HPM 253) is designed for practicing clinicians and those with an interest in health care management. This interactive and challenging course will provide students with a fresh perspective on improvement in health care systems and provide them with the necessary tools to effect the kind of real change in their own organizations and practices that can improve outcomes for patients. Topics of the sessions will include: systems thinking; the leadership of improvement; statistical thinking and the management of variation; process knowledge and design; change methods, improvement, and design and creativity; collaborative work; matching service design to needs; personal and professional learning and change; the diffusion of innovations; spreading new models of care across organizational silos and boundaries; and integrating cost and quality, and managing resistance to improvement.

Implementation Research in Health and Healthcare (HPM 284) introduces students to the study of interventions to facilitate the translation evidence-based interventions into practice. There is a growing awareness that studies on comparative and cost effectiveness, which identify practices that will maximize quality and value, require companion work on implementation research to assure that current evidence is ultimately implemented into real-world clinical settings and health policy. This course is intended to provide an introduction to the theory and methods that address the facilitators and barriers to the translation of evidence into practice, i.e., the field of implementation research. The course uses real-life case studies and with a special emphasis on the under- and overuse of health care interventions in higher-income health systems. Individual sessions will cover the historical developments that have led to the current emphasis on implementation research, theories of individual and organizational behavior and behavior change, qualitative and mixed methods study designs, observational and experimental methods for implementation research and associated analytic techniques. Along with several of their classmates, students will design and develop a brief proposal to evaluate an evidence-based intervention addressing a significant gap in health or healthcare.

Research with Large Databases (HPM 299) provides an overview of existing large administrative, clinical, and national survey databases and addresses the potential uses of these data to study important questions regarding clinical risk factors, treatment, outcomes and health policy. Strengths and limitations of large databases that are commonly used for research will be considered. Special attention will be devoted to large federal databases that are publicly available and readily usable by new0 investigators. Students will have hands-on experience using SAS statistical software to obtain, create, manipulate, and analyze large databases. Key statistical issues, including risk-adjustment and sampling weights, will be emphasized in the course. Students will evaluate published studies based on large databases and develop a proposal for analyzing a specific research question with a large database. Note that this course uses SAS software (not STATA). Prior experience with SAS is not assumed or required.

Medical Informatics (HPM 512) and health information technology are increasingly critical for delivery of safe, effective health care, and also for research, and management. Health information technology is transforming health care, and electronic health records represent a treasure trove of data for anyone interested in clinical effectiveness research, and a vehicle for improving healthcare delivery. In this course we describe the core issues in the field of medical informatics, survey the methods used to perform clinical effectiveness research using clinical systems, give examples of healthcare improvement using health information technology, and describe how to evaluate clinical systems interventions. Major topics include: the impact of clinical systems with a focus on clinical decision support, evaluation methods, obtaining information from clinical systems, and the role of informatics standards. Issues such as confidentiality and privacy, organizational factors, interoperability, and return on investment will also be covered. So will the topics of social media, mobile health, big data, artificial intelligence and the cloud. The relevance of informatics in disease management, genomics, patient computing, bio surveillance, and health care policy will also be highlighted. You do not need to be a programmer or to have medical informatics as a primary interest to take this course.

Improvement by Design: Using the Science of Design, Test, and Spread to Innovate and Improve Healthcare (HPM 576) focuses on the practical application of human-centered design and implementation science methodologies to improve healthcare systems by defining and closing know-do gaps, which represent the difference between what we know should be done based on evidence and what takes place in practice. Over the four-module course, participants will select a know-do gap to address and design, prototype, and test a proposed solution (tool or evidence-based practice change) and a plan for scale and spread. This will culminate in a final project, which can be brought back to your home organization and put into action.

Decision Analysis in Clinical Research (RDS 286) introduces students to systematic methods of decision analysis relevant to clinical decision making, clinical research and comparative effectiveness research. Topics of the sessions include: the use of causal estimands to express efficacy and real-world clinical effectiveness; the use of probability and sensitivity analysis to express and assess uncertainty; Bayes theorem and evaluation of diagnostic test strategies; utility theory and its use to express patient preferences for health outcomes; benefit-harm analysis and cost-effectiveness analysis in clinical research, clinical guideline development, health technology assessment and health policy decision making. Lectures are accompanied by case problems, review sessions and computer exercises. After this course, students will understand the uses, strengths, limitations and ethical issues of decision analysis and cost effectiveness in clinical decision making and research design. We will discuss case examples from different disease areas including cancer, cardiovascular disease, infectious disease and others.

The first two weeks of this course focus on methods for learning from data in order to gain useful predictions and insights. Through real-world examples of wide interest, we introduce methods for five key facets of an investigation: 1. data wrangling/cleaning in order to construct an informative, manageable data set; 2. software engineering skills for accessing data as well as organizing data analyses and making these analyses sharable and reproducible; 3. exploratory data analysis to generate hypotheses and intuition about the data; 4. inference and prediction based on statistical tools with a focus on machine learning; 5. communication of results through visualization, stories, and interpretable summaries.

During the last week of the course, with the help of the instructors and TAs, student teams will choose a clinically relevant question and complete a group project that includes parsing the question into a study design and methodology for data analysis and interpretation, with an emphasis on the data curation that is required before any analysis can be performed. The Medical Information Mart for Intensive Care (MIMIC) database and the eICU Collaborative Research Database will be used for each project. Students are expected to be familiar with R and RStudio before enrolling in this course.

Survival Methods in Clinical Research (BST 224) will cover statistical methods of survival analysis used in clinical research, including study design and power analysis, Kaplan-Meier product-limit estimation, Cox proportional hazards models, models with time-dependent covariates and repeated events, and models with competing risks. We will use SAS software in the course; however, students can use Stata, R, SPSS or other software. Students are encouraged to bring in their own project data for consultation. Course evaluation will be based on 13 daily quizzes.

Analytic Issues of Clinical Epidemiology (EPI 236) examines some features of study design but is primarily focused on analytic issues encountered in clinical research. These include techniques for stratified analysis, regression modeling, propensity scores, and matching. Emphasis is placed on the use of these techniques for the control of confounding and for the development of clinical prediction rules. The focus of this course is on applications and interpretations of results with limited introduction to theory that underlies these techniques. Course Activities include computer lab workshops that are scheduled during regular class time. Students must develop written summaries of the analyses of an assigned clinical data set from the results of daily computer workshops.