HERC: BD-STEP Fellows at VA Palo Alto Health Care System
Attention A T users. To access the menus on this page please perform the following steps. 1. Please switch auto forms mode to off. 2. Hit enter to expand a main menu option (Health, Benefits, etc). 3. To enter and activate the submenu links, hit the down arrow. You will now be able to tab or arrow up or down through the submenu options to access/activate the submenu links.

BD-STEP Fellows at VA Palo Alto Health Care System


Below are the 2017 VA Palo Alto BD-STEP Fellows, including a brief description of their project. 

Andrew Chang, PhD. Dr. Chang has a PhD in Biochemistry and Cell Biology from Rice University and a MS in Biomedical Informatics from the University of Texas Health Science Center at Houston. 

Using machine learning and big-data for better disease prediction and prevention: By combining the machine learning technology and the tremendous HER database of the VA system, we can search for possible patterns and factors of these fast-developing cancers that were previously ignored or neglected by humans.

Steven Cogill, PhD. Dr. Cogill has a PhD in Genetics/Bioinformatics from Clemson University and a MS in Biochemistry/Biotech from IU School of Medicine.

Data mining techniques for the identification of post chemotherapy sepsis risk: Given that sepsis accounts for ~10% of cancer deaths in the US, particularly for post chemotherapy patients with neutropenic fever, better sepsis diagnostic/prognostic tool would enable improved sepsis management in cancer patients. We will mine available VA data on cancer patients with ED visits to identify predictors for various clinical or operational outcomes using novel machine-learning approaches. 

Kent Heberer, PhD. Dr. Heberer has a PhD in Biomedical Engineering from UCLA and a MS in Biomedical Engineering from UCLA. 

Clinical predictors of outcomes to cancer treatments: Predictive analytics and existing natural language processing tools will be used to identify clinical predictors for treatment outcomes. These outcomes include treatment response, side effects and complications, remission/NED, quality of life and frailty measures, and survival. Eventually, the intent is to construct a core pipeline framework that can be customized and scalable for any cancer type, and be updated with teh entry of new patients. Importantly, this pipeline can be used for future research and clinical operations in real-time to inform actionable strategies for the local, regional, and national levels of the VA healthcare system. 

Joanna Sylman, PhD. Dr. Sylman is a second year BD-STEP Fellow and has a PhD in Chemical and Biomedical Engineering from Oregon Health and Science University. 

Utilization of longitudinal complete blood count informatoin to improve cancer patient detection and prognosis: This project focuses on leveraging longitudinal complete blood count informatoin, particularly platelets, neutrophils, lymphocytes, and albumin in an effort to detect cancer in early stages and improve patient prognosis predictions. Machine learning approaches and traditional epidemiological methods will be compared to determine the potential added value of these readily available measurements in Veteran patient medical health records.

Wen-Wai Yim, PhD. Dr. Yim is a second year BD-STEP Fellow and has a PhD in Biomedical Informatics from the University of Washington. 

Development and validation of surgery and pain-related quality metrics: Using structured and unstructured VA data to study outcomes and develop/evaluate quality metrics for quality improvement.