This proposal requests K07 support for Dr. Elizabeth Burnside to become an independent investigator and leader in the use of computer models to improve the early detection of breast cancer. This award will allow Dr. Burnside to optimize and validate a computer model called a Bayesian network designed to provide decision-support for radiologists interpreting mammography. This project is a multidisciplinary effort integrating computer science, applied medical informatics, population health science and breast imaging. The University of Wisconsin is an ideal environment for this work because it provides access to renowned researchers in these areas and individuals experienced with the inclusion of diverse populations in women's health research. To achieve these research and career goals, the candidate will follow a career development plan that consists of 1) acquisition of advanced research competencies in artificial intelligence, machine learning algorithms, probability theory, Bayesian reasoning, research ethics, and clinical trial design; 2) mentorship from nationally and internationally recognized experts; and 3) innovative research in computer-aided decision support in breast cancer diagnosis. The current state of breast cancer screening reveals a wide variability of practice and a shortage of expert mammographers. Dr. Burnside's model envisions using expert knowledge to improve non- expert performance in mammography. The model complements current computer-assisted detection algorithms by contributing information to crucial post-discovery aspects of mammography: interpretation and decision-making. Using probability theory, the model defines relationships between a patient's demographic risk factors, her mammographic findings, and diseases of the breast to generate a breast cancer risk assessment uniquely tailored to her. If successful, the model will improve the accuracy of decision-making, decrease the human costs of underperformance and variability, and deliver personalized medicine to patients who undergo mammography.
| Ayvaci, Mehmet U S; Alagoz, Oguzhan; Chhatwal, Jagpreet et al. (2014) Predicting invasive breast cancer versus DCIS in different age groups. BMC Cancer 14:584 |
| Wu, Yirong; Rubin, Daniel L; Woods, Ryan W et al. (2014) Developing a comprehensive database management system for organization and evaluation of mammography datasets. Cancer Inform 13:53-62 |
| Wu, Yirong; Alagoz, Oguzhan; Ayvaci, Mehmet U S et al. (2013) A comprehensive methodology for determining the most informative mammographic features. J Digit Imaging 26:941-7 |
| Alagoz, Oguzhan; Chhatwal, Jagpreet; Burnside, Elizabeth S (2013) Optimal Policies for Reducing Unnecessary Follow-up Mammography Exams in Breast Cancer Diagnosis. Decis Anal 10:200-224 |
| Ayvaci, Mehmet U S; Alagoz, Oguzhan; Burnside, Elizabeth S (2012) The Effect of Budgetary Restrictions on Breast Cancer Diagnostic Decisions. Manuf Serv Oper Manag 14:600-617 |
| Burnside, Elizabeth S; Chhatwal, Jagpreet; Alagoz, Oguzhan (2012) What is the optimal threshold at which to recommend breast biopsy? PLoS One 7:e48820 |
| Percha, Bethany; Nassif, Houssam; Lipson, Jafi et al. (2012) Automatic classification of mammography reports by BI-RADS breast tissue composition class. J Am Med Inform Assoc 19:913-6 |
| Woods, Ryan W; Sisney, Gale S; Salkowski, Lonie R et al. (2011) The mammographic density of a mass is a significant predictor of breast cancer. Radiology 258:417-25 |
| Ferreira, Pedro; Fonseca, Nuno A; Dutra, Inês et al. (2011) Predicting Malignancy from Mammography Findings and Surgical Biopsies. Proceedings (IEEE Int Conf Bioinformatics Biomed) 2011: |
| Ayer, Turgay; Chhatwal, Jagpreet; Alagoz, Oguzhan et al. (2010) Informatics in radiology: comparison of logistic regression and artificial neural network models in breast cancer risk estimation. Radiographics 30:13-22 |
Showing the most recent 10 out of 18 publications
