Xiao-Hua Andrew Zhou' Home Page!

Xiao-Hua (Andrew) Zhou,Ph.D
Professor
Department of Biostatistics
School of Public Health and Community Medicine
University of Washington
Director and Research Career Scientist
Biostatistics Unit, HSR&D Center of Excellence
Veterans Affairs Puget Sound Health Care System

email: azhou@u.washington.edu
office: Met Park West #1400, Puget Care System Care and H-655E, HSB, University of Washington
phone: 206 - 277- 3588

This page has had <#exec cgi="/cgi-bin/counter.pl"-->

Academic History:

I received my B.Sc. in mathematics from Sichuan University in 1984, my M.Sc. in statistics from University of Calgary in 1987, and my Ph.D in biostatistics from Ohio State University in 1991. I finished a two-year post-doc fellowship in biostatistics at Medical School of Harvard University in 1993. I joined Division of Biostatistics in Indiana University School of Medicine as an Assistant Professor in 1993, and was promoted to an Associate Professor in 1997. I took the Director of Biostatistics Unit position in the U.S. Department of Veterans Affairs Puget Sound Health Care System . I was promoted to a Full Research Professor in 2003 and became a Full Professor in 2005 in the Department of Biostatistics at University of Washington . I was elected to International Statistical Institute in 1998 and Fellow of the American Statistical Association in 2004. I was the Chair of the Section on Statistics in Epidemiology of the American Statistical Association in 2004. I am curently Chair-Elect of the Section on Health Policy Statistics of the ASA. I served as a member on a Study Section of National Institute of Health and on an Advisory Committee in Center for Devices and Radiological Health in U.S. Food and Drug Administration (FDA) . I am currently a member on Oncologic Drugs Advisory Committee in Center for Drug Evaluation and Research, U.S. Food and Drug Administration (FDA). I received a Research Career Scientist Award (RCS) from the U.S. Federal Government Department of Veterans Affairs in 2007. Along with my two colleasgues I have written the first textbook on statistical methods in diagnostic medicine, published by Wiley & Sons. See Statistical Methods in Diagnostic Medicine for the detailed information.

Statistical methods in diagnostic medicine.
One of my major research areas is the development of new methods for evaluating the accuracy of diagnostic tests using receiving operating characteristic (ROC) curve methodology. Since 1993, I have been working on the development of new statistical methods for studies of diagnostic tests. My efforts in this area had been supported by one R29 grant (FIRST award) from the National Institute of Health (NIH) (1994-1999) and are currently being supported by a R01 grant from the National Institute of Health (2005-2008) and a research grant from the National Sciences Foundation (2006-2009). I have published more than 25 statistical papers in this area, and in 2002 along with two co-authors I have published the first comprehensive statistical textbook in diagnostic medicine, which was published by Wiley & Sons and can be ordere at Amazon.com .
The analysis of skewed data.
Another area of my major statistical research is the development of new methods for health services research, particularly for studies of health care costs and the factors affecting such costs. Since 1995, I have been working on the development of new statistical methods for the analysis of health care costs that can adjust for special characteristics of health care costs. My work had been supported by one R03 grant from the Agency for Health Care Policy and Research (AHCPR) (1997-1998) and two R01 grants from National Institute of Health (NIH) (1998-2001 and 2002-2006) and is currently being supported by a research grant from U.S. Federal Government Department of Veterans Affairs (2007-2009). I have published more than 20 statistical papers in this area.
Causal inferences in observational studies.
The third area of my active research is on the development of new statistical methods for an observational study, which is an important tool for obtaining accurate information about the effects of drugs or treatments in the usual practice of patient care. A major problem with the causal inferences in an observational study is confounding by indication, which means that the background characteristics of drug treatments often differ. Working with my colleagues, I have published a paper on the propensity-score methodology and another paper on a bootstrap confidence interval for the treatment effect using the propensity-score methodology.
Causal inferences in randomized encouragement design studies.
The fourth area of my active research is on the development of new statistical methods for for the analysis of encouragement design studies (EDS). In a randomized EDS, clinicians are randomly assigned to receive or not to receive an encouragement for the use of the treatment on their patients. Rigorous evaluation about the causal effects of the treatment on patient outcomes in a randomized EDS is often difficult because of the issue of clinician compliance with the intervention in a randomized EDS. The clinicians can decide to comply or not to comply with the encouragement or to perform the suggested treatment regardless of whether they have been encouraged to do so. Ignoring the issues of clinician non-compliance in these studies can lead to unreliable inferences and predictions. Working with colleagues at UCLA, Harvard, and John Hopkins University, I have published two papers in this area. My effort in this area is currently being supported by one R01 grant from the National Institute of Health (NIH) (2002-2006).
Personalized Medicine Using Genomic Information
My fifth research area is on the development of new statistical methods for assessing prognostic and predictive values of biomarkers. A prognostic biomarker indicates likelihood of outcome independent of treatments. A predictive biomarker predicts the clinical benefits from a specific therapy based on the biomarker status. The rapid advance of molecular genetic technology and the boom of molecular diagnostics companies have set the stage for a new era in personalized treatments. Patient responses to treatments are often heterogeneous. By identifying patients using biomarkers who are more or less likely to benefit from a treatment, we are able to provide the most effective treatment to those who are most in need. This research is being funded by the U.S. Federal Government Department of Veterans Affairs.

My Collaborative Research Interests:

Since 1993, I have been engaged in medical and health services research in collaboration with other researchers. These studies have resulted in more thn 40 publications in refereed medical journals.

Health Services Research: health service research is a "multidisciplinary field that examines the use, costs, quality, accessibility, delivery, organization, financing, and outcomes of health services to increase knowledge and understanding of the structure, process, and effects of health services for individuals and populations"
National Alzheimer's Coordinating Center (NACC): The NACC facilitates collaborative research among the approximately 30 Alzheimer's Disease Centers funded by the National Institute on Aging and maintains a Uniform Data Set (UDS) database of information collected by the Alzheimer's Disease Centers regarding patients with Alzheimer's Disease and controls.
Profling Quality of Hospitals
Assisted Living Research.
Mental Health.