Suresh K. Bhavnani

Center for Computational Medicine and Bioinformatics, Medical School
University of Michigan

3D Network Analysis in Immersive CAVE

Used an immersive CAVE environment to analyze a 3D network of renal diseases and genes. The analysis revealed a new regularity of domain importance that was missed in the 2D network analysis of the same data. The results led to hypotheses for the role played by different CAVE functionalities in enabling new discoveries (Bhavnani et al., in review).

Network Visualization and Analysis of Cancer Patients and Symptoms

Used networks to visualize and analyze the co-occurrence of 18 symptoms across 665 cancer patients undergoing chemotherapy. The results led to the design of algorithms to help clinicians rapidly identify co-occurring symptoms (Bhavnani et al., in press).

Network Visualization and Analysis of Renal Diseases and Genes

Used networks to visualize and analyze the relationship between renal diseases and genes that are up or down regulated. The results led to implications for a molecular basis of classifying renal diseases (Bhavnani et al., 2009).

Network Visualization and Analysis of Toxic Chemicals and Symptoms

Used networks to visualize and analyze toxic chemicals and acute symptoms. The results led to the design of algorithms and interfaces to help first-responders rapidly identify toxic chemicals in emergencies (Bhavnani et al., 2007).

Scatter of Healthcare Information on the Web

Analyzed patterns in the scatter of healthcare information on the Web. The results led to search strategies for finding comprehensive healthcare information, and to the Information Scatter model which proposes how information scatter occurs over time (Bhavnani, 2005, Bhavnani & Peck, in press).

Semi-Structured Interviews of Translational and Clincal Science (CTSA) Researchers

Analyzed the needs of 30 junior and senior researchers to conduct effective translational and clinical science. The results led to the design of a prototype for a research portal, which should enable translational researchers discover, find, and make more effective use of human and computational resources (Bhavnani et al., in preparation).

Cognitive Analysis of Expert-Novice Search Strategies

Analyzed the domain-specific search strategies used by experts and by novices to find online healthcare and shopping information. The results led to strategies needed by novice searchers to find accurate healthcare information (Bhavnani, 2001).

Contextual Study of Patent Searchers

Analyzed the collaborative search and sensmaking activities between patent searchers (in a tech transfer office), and inventors. The results led to design requirements for a system to support collaborative search and sensemaking (Bhavnani et al., 2008).

Contextual Study of Rural Indians

Analyzed how rural Indians perceived computers and their uses. The results led to insights about the role of literacy in the perception of computer use, and methods to quickly elicit responses from farmers who have little or no exposure to computer devices (in preparation).

Ethnographic Study of Architectural CAD Users

Analyzed how professional architects performed real-world tasks using a CAD system. The results led to an understanding of why CAD systems are often used ineffectively, and to a small set of general and effective strategies to address that problem (Bhavnani et al., 1996).

Computational Cognitive Model of Computer Interactions

Used computational GOMS models to identify the knowledge required to use complex CAD systems. The results led to the design of Strategy-Based Instruction, which has been used to teach effective strategies to use computer applications in 3 universities to 400 students (Bhavnani & John, 2000).

MAIDN: Mining And Interpretation of Diagnostic Networks

Developed a decision-support system for the rapid identification of toxic chemicals during emergencies. The system, developed in collaboration with first responders, ranks symptoms based on their ability to elminate close to half of the remaining chemicals. The system significantly reduces the symptoms required to uniquely identify a chemical (Bhavnani et al., 2008).

Strategy Hub: Design and Evaluation of Website for Cancer Patients

Developed and evaluated the StrategyHub for Healthcare which provides expert search strategies to help novice searches find comprehensive healthcare information. The results led to design guidelines for providing online search procedures. (Bhavnani et al., 2006).

GoogleBuddy: Development of a Social Computing System for Learning and Sharing Search Strategies

Developed and evaluated GoogleBuddy to help users share and learn effective search strategies. The results are leading to insights for providing online search knowledge (in progress).