Speakers: Emily Leary, PhD
Emily Leary, PhD
Director of Orthopaedic Biostatistics
Department of Orthopaedic Surgery
University of Missouri
Dr. Emily Leary is the Director of Orthopaedic Biostatistics in the Department of Orthopaedic Surgery and a member of the Thompson Laboratory for Regenerative Orthopaedics in the Missouri Orthopaedic Institute, at the University of Missouri. She previously worked in the health care industry and Dr. Leary received her PhD in statistical ecology from the University of Florida and her master’s degree in Biostatistics from the University of Oklahoma Health Sciences Center. Her current research program is centered upon using data and analytical methods to improve patient outcomes and treatment regimens. Specifically, she focuses on better leveraging data to develop tools to improve clinical treatment plans and to better understand economic considerations in treatments and treatment adherence, such as economic cost, health cost, and quality of life cost. Her current research includes using machine learning methods to characterize disease progression and risk of disease progression, developing pre‐surgical profiles related to muscle and bone health to predict post-surgical outcomes, planning surgical clinical trials, and the development of statistical methodologies to better analyze gait.
Clinical Decision Making Tools to Individualize Treatment Regimens to the Patient
Clinical decision-making tools are needed to individualize treatment regimens. Although many clinicians and health systems claim to improve patient outcomes, a key missing component lies in much-needed clinical decision-making tools to individualize treatment regimens to the patient. To improve adherence to chosen treatment regimens, better understanding of patient expectations, preferences, satisfaction, and economic concerns that factor into treatment planning are important considerations that lead to ultimately better patient outcomes. Understanding how treatments affect patients short-term and over the long-term, in terms of function, pain, cost-utility and quality of life, can be used for reporting and to develop important decision-making algorithms. These decision-making tools are targeted towards patients and clinicians and are health-effectiveness tools not cost-effectiveness tools. During my presentation, I will discuss my experience designing and conducting analyses which utilize large, mis-aligned data and integrate machine learning techniques, towards individualized prediction – or better stated, optimized – models for patients that allow clinicians to adjust treatment regimens based on patient expectations, preferences, satisfaction, and economic factors.