Suresh K. Bhavnani, Ph.D., Network Analysis of Toxic Chemicals and Symptoms: Implications for Designing Effective First-Responder Systems
The rapid and accurate identification of toxic chemicals is critical for saving lives in emergency situations. However, first-responder systems such as WISER typically require a large number of inputs before a chemical can be identified. Dr. Bhavnani will discuss how his team addressed this problem by using network visualizations and associated quantitative methods to analyze the complex relationship between toxic chemicals and their symptoms. These results helped to identify regularities related to symptom co-occurrence and explain why current approaches require a large number of inputs. Based on this understanding, Dr. Bhavnani and his colleagues designed and developed a first-responder system to help rapidly identify toxic chemicals in emergency situations. He concludes by showing how they have used the above methodology to analyze other biomedical datasets (e.g., cancer patients and symptoms, renal diseases and genes) leading to general approaches for analyzing co-occurrence in biomedical datasets, and for symptom management.
Suresh K. Bhavnani holds a PhD in Computational Design and Human-Computer Interaction from Carnegie Mellon University and is currently a Research Assistant Professor in the Center of Computational Medicine and Bioinformatics at the University of Michigan Medical School. His current research focuses on developing effective biomedical applications based on the network analysis and visualization of biomedical datasets, and the analysis of user needs. His research has been selected as a distinguished paper, and an outstanding paper by the American Medical Informatics Association, and his student advising has received an outstanding research mentorship award from the Undergraduate Research Opportunity Program at the University of Michigan. His current research is funded by NIH/CTSA, and his prior work has been funded by NSF and Microsoft.