Susan Shortreed's research brings together statistics and machine learning methods to address health science problems, with a special emphasis on analyzing complex longitudinal data and overcoming missing-data challenges. Much of her methodological work is focused on developing and evaluating statistical inference approaches for observational data, such as data from electronic health care records or from randomized clinical trials with missing information. Dr. Shortreed is also interested in developing new machine learning methods and extending current best-practice methods, specifically for personalized dynamic treatment strategies, clustering, and model selection methods.
Dr. Shortreed earned her PhD in statistics from the University of Washington in 2006. After completing her degree, she spent two years in the Department of Epidemiology and Preventive Medicine at Monash University in Melbourne, Australia, and two years in the School of Computer Science at McGill University. Dr. Shortreed has collaborated with scientists in a broad range of areas including cancer screening, cardiovascular disease, and medication and vaccine safety. Currently, she works most often with researchers in mental and behavioral health, evaluating and comparing treatments for chronic pain, depression, and bipolar disorder, and interventions to prevent alcohol misuse, smoking, and suicide. Dr. Shortreed is an investigator with the Mental Health Research Network, designing studies to address important public health concerns, such as determining which antidepressant medications work best for which patients.
In addition to her work at Kaiser Permanente Washington Health Research Institute, Dr. Shortreed is an affiliate associate professor at the University of Washington Biostatistics Department. She serves on the Executive Board for the American Statistical Association’s Section on Statistics in Epidemiology.
Analysis of complex longitudinal data and data collected from electronic health records; methods for overcoming missing data; computational statistics and algorithms; variable selection methods
Biostatistics; data mining
Biostatistics; treatment for chronic depression and bipolar disorder; suicide prevention; developing personalized dynamic treatment strategies
Von Korff M, Shortreed SM, LeResche L, Saunders K, Thielke S, Thakral M, Rosenberg D, Turner JA. A longitudinal study of depression among middle-aged and senior patients initiating chronic opioid therapy. J Affect Disord. 2017;211:136-143. doi: 10.1016/j.jad.2016.12.052. Epub 2017 Jan 6. PubMed
Shortreed SM, Ertefaie A. Outcome-adaptive lasso: variable selection for causal inference. Biometrics. 2017 Mar 8. doi: 10.1111/biom.12679. [Epub ahead of print]. PubMed
Williams EC, Lapham GT, Shortreed SM, Rubinsky AD, Bobb JF, Bensley KM, Catz SL, Richards JE, Bradley KA. Among patients with unhealthy alcohol use, those with HIV are less likely than those without to receive evidence-based alcohol-related care: a national VA study. Drug Alcohol Depend. 2017 Mar 6;174:113-120. doi: 10.1016/j.drugalcdep.2017.01.018. [Epub ahead of print]. PubMed
Hansen RN, Walker RL, Shortreed SM, Dublin S, Saunders K, Ludman EJ, Von Korff M. Impact of an opioid risk reduction initiative on motor vehicle crash risk among chronic opioid therapy patients. Pharmacoepidemiol Drug Saf. 2016 Nov 14. doi: 10.1002/pds.4130. [Epub ahead of print]. PubMed
With support from the Garfield Memorial Fund, Kaiser Permanente researchers are using big data to help customize and improve care for depression.
Read it in News and Events.
Mental health research excels at linking bad experiences to poor outcomes, writes Dr. Greg Simon. Here’s how to focus on recovery and resilience instead.
Read about it in Healthy Findings.