Projects

Supporting Coordination in Complex Healthcare

Children with complex health conditions require care from a large, diverse team of caregivers that includes multiple types of medical professionals, parents and community support organizations. Coordination of their outpatient care, essential for good outcomes, presents major challenges. We are building on a computational theory of teamwork to create entirely new tools to support complex, loosely-coupled teamwork.

Amir, Ofra, Barbara Grosz, Krzysztof Gajos, Sonja Swenson, and Lee Sanders. 2015. “From Care Plans to Care Coordination: Opportunities For Computer Support of Teamwork in Complex Healthcare.” Proceedings of CHI'15 [honorable mention].
Amir, Ofra, Barbara J Grosz, Krzysztof Z Gajos, Sonja M Swenson, and Lee M Sanders. 2014. “AI Support of Teamwork for Coordinated Care of Children with Complex Conditions.” AAAI Fall Symposium on Expanding the Boundaries of Health Informatics Using AI: Making Personalized and Participatory Medicine A Reality.
Amir, Ofra, Barbara J Grosz, Edith Law, and Roni Stern. 2013. “Collaborative health care plan support.” Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems.

Personalized Change Awareness

Complex tasks such as treating patients with chronic conditions and developing software products are typically accomplished by teams that collaborate over an extended time duration. To remain coordinated, team members need to be aware of others’ activities if those activities are likely to affect their own actions. We are developing Personalized Change Awareness mechanisms, which support team coordination by automatically identifying and sharing the subset of information about others’ activities that is most relevant to each of the team members.

Amir, Ofra, Barbara Grosz, and Krzysztof Gajos. 2016. “Mutual Influence Potential Networks: Enabling Information Sharing in Loosely-Coupled Extended-Duration Teamwork.” IJCAI'16.
Gehrmann, Sebastian, Lauren Urke, Ofra Amir, and Barbara J Grosz. 2015. “Deploying AI Methods to Support Collaborative Writing: a Preliminary Investigation.” CHI'15 Extended Abstracts on Human Factors in Computing Systems. ACM.

Agent Strategy Summarization

People increasingly interact with autonomous agents. We are developing methods summarizing and visualizing the behavior of agents with the goal of increasing people’s familiarity with the agent’s capabilities and limitations.

Amir, Ofra, Finale Doshi-Velez, and David Sarne. 2018. “Agent Strategy Summarization.” the 17th International Conference on Autonomous Agents and Multiagent Systems (AAMAS'18)
Amir, Dan, and Ofra Amir. 2018. “HIGHLIGHTS: Summarizing Agent Behaviors to People.” the 17th International Conference on Autonomous Agents and Multiagent Systems (AAMAS'18)

4 in a row board, human problem solving illustration

Human problem solving and computational complexity

On a daily basis, people make decisions in uncertain environments with combinatorially bifurcating paths of possible outcomes. We study both individual problem solving strategies as well as group performance on combinatorial problems. How do people search an enormous space of possibilities and is their search strategy optimal? When will groups be able to converge to a correct solution to a complex problem?

Amir, Ofra, Dor Amir, Yuval Shahar, Yuval Hart, and Kobi Gal. 2018. “The More the Merrier? Increasing Group Size may be Detrimental to Decision-Making Performance in Nominal Groups.” PLOS ONE.
Amir, Ofra, Yuval Shahar, Ya'akov Gal, and Litan Ilani. 2013. “On the Verification Complexity of Group Decision-Making Tasks.” First AAAI Conference on Human Computation and Crowdsourcing.

Supporting journalists in identifying visual misinformation

Journalistic work increasingly depends on information from web sources and social media. Visual misinformation, for example images that have been manipulated or taken out of context, pose a significant issue for journalists using these sources. We are developing DejaVu, a system for supporting journalists in identifying visual misinformation.

Matatov, Hana, Adina Bechhofer, Lora Aroyo, Ofra Amir, and Mor Naaman. 2018. “DejaVu: A System for Journalists to Collaboratively Address Visual Misinformation.” Computation + Journalism Symposium. Miami, FL.

Predicting abnormal growth curves in preterm infants

Preterm infants remain under close monitoring in the NICU to ensure they reach normal weight. In this project (collaboration with Shearey Tzedek hospital), we aim to characterize growth curves and identify early potential divergence from the desired growth curve.

Google Sites

Report abuse