This presentation will discuss why some traditional research studies, such as those aimed at identifying risk factors, should really be reframed as clinical prediction studies. Building and validating prediction models would more directly benefit individual patients during clinical care. This presentation will also provide guidance for understanding, evaluating, and critiquing studies aimed and improving our ability to predict individual outcomes and discuss common mistakes researchers make in presenting these types of studies the FPMRS literature.

1. To understand important characteristics of clinical prediction models and how they are useful for clinical decision-making
2. To understand when to evaluate models through a predictive approach compared to an explanatory approach
3. To understand the how to evaluate and critique studies that claim to predict outcomes to improve the quality of research and peer review

J. Eric Jelovsek, MD, MMEd, MSDS is an Associate Professor of Obstetrics and Gynecology at Duke University School of Medicine in Durham, North Carolina where he currently serves as Vice Chair for Education and Director of the Women’s Health Data Science Program. Dr. Jelovsek received his MD degree from East Tennessee State University, completed his residency in Obstetrics and Gynecology at Duke University and fellowship in Female Pelvic Medicine and Reconstructive Surgery at Cleveland Clinic. He holds a Master’s degree in Medical Education with Distinction from the University of Dundee and a Master’s degree in Data Science from Northwestern University.

Dr. Jelovsek’s expertise lies in the development and validation of “individualized,” patient-centered prediction tools to improve patient and clinician decision-making around  a variety of women’s health conditions including: the risk of pelvic floor disorders after childbirth, predicting prolapse recurrence and utility change after undergoing pelvic organ prolapse surgery, complications and health status after pelvic organ prolapse surgery, risk of recurrent urinary incontinence and adverse events after mid-urethral sling placement, risk of de novo stress urinary incontinence after surgery for pelvic organ prolapse, and transfusion during gynecologic surgery. Dr. Jelovsek currently leads the clinical deployment of these tools into the electronic medical record in the Department of ObGyn at Duke. Dr. Jelovsek currently serves as co-principal investigator in the NIDDK Symptoms of Lower Urinary Tract Dysfunction Research Network (LURN) and is involved in the study of unsupervised learning approaches such as clustering of lower urinary tract phenotypes. He also serves as an investigator in the NICHD Pelvic Floor Disorders Network and as a mentor in the NIDDK-Duke KURe Program and NICHD AUGS/DUKE UrogynCREST program.