epiDAMIK

Workshop will be held on August 15, 2022, 9 am - 5 pm EDT. All times below are in EDT.

Time	Event
9:00am-9:10am	epiDAMIK opening Remarks
9:10am-9:20am	Contributed Talk 1 (Oral) Paper: Impact of Seeding and Spatial Heterogeneity on Metapopulation Disease Dynamics. [PDF] Authors: Rohit Srinivas Rajuladevi, Madhav Marathe, Przemyslaw Porebski, Srinivasan Venkataramanan.
9:20am-9:30am	Contributed Talk 2 (Oral) Paper: EVADE: Exploring Vaccine Dissenting Discourse on Twitter. [PDF] Authors: Shreya Ghosh, Prasenjit Mitra, Bernice L Hausman.
9:30am-10:00am	Stretch, Networking Break
10:00am-10:50am	Invited Keynote 1. Rachel Slayton [expand] Dr. Rachel Slayton is a Ph-D trained epidemiologist and infectious disease modeler. She leads a mathematical modeling unit focused on healthcare-associated infections and multi-drug resistant organisms in the U.S. Centers for Disease Control and Prevention (CDC)’s Division of Healthcare Quality Promotion, Epidemiology Research and Innovations Branch. She also serves as the Scientific Director for the Modeling Infectious Diseases in Healthcare (MInD-Healthcare) network and co-led CDC’s COVID-19 mathematical modeling unit. Title: Improving Pandemic Response: Employing Mathematical Modeling to Confront COVID-19 [expand] Abstract: Modeling complements surveillance data to inform coronavirus disease 2019 (COVID-19) public health decision making and policy development. When urgent public health decisions are needed and data are limited, mathematical modeling offers opportunities to combine data from multiple sources, assess critical uncertainties and needs, and inform decisions. The Centers for Disease Control and Prevention (CDC) has used mathematical modeling to inform public health practice for emerging infectious diseases for many years, working in collaboration with partners in other government agencies, academia, and the private sector. This includes the use of modeling to improve situational awareness, assess epidemiological characteristics, and inform the evidence base for prevention strategies.
10:50am-11:10am	Lightning Talks - Part 1 [expand] 3 min per each paper in the following order: EVADE: Exploring Vaccine Dissenting Discourse on Twitter. Impact of Seeding and Spatial Heterogeneity on Metapopulation Disease Dynamics. Optimal Intervention on Weighted Networks via Edge Centrality. Optimal Epidemic Control as a Contextual Combinatorial Bandit with Budget. Modelling Healthcare Associated Infections with Hypergraphs. Real-time Anomaly Detection in Epidemic Data Streams.
11:10am-12:00am	Invited Keynote 2. Bryan Wilder [expand] Bryan Wilder is an incoming Assistant Professor in the Machine Learning Department at Carnegie Mellon University. His research focuses on the intersection of optimization, machine learning, and social networks, motivated by applications to public health. Areas of focus include HIV prevention, maternal and child health, and COVID-19. He is supported by the Schmidt Science Fellows program and was previously supported by the NSF and Siebel Fellowships. His dissertation was recognized with the 2021 IFAAMAS Victor Lesser Distinguished Dissertation Award, and his work has been a finalist for best paper awards at ICML, AAMAS, and the INFORMS Doing Good with Good OR competition. Title: AI for infectious disease prevention and response [expand] Abstract: As exemplified by the COVID-19 pandemic, our health and wellbeing depend on a difficult-to-measure web of societal factors and individual behaviors. This effort requires new algorithmic and data-driven paradigms which span the full process of gathering costly data, learning models to understand and predict the interactions of many agents, and optimizing the use of limited resources in interventions. In response to these needs, I will present methodological developments at the intersection of machine learning, optimization, and social networks which are motivated by on-the-ground work related to HIV prevention and the COVID-19 response.
12:00pm-1:00pm	Lunch Break
1:00pm-1:20am	Lightning Talks - Part 2 [expand] 3 min per each paper in the following order: Using Survey Data to Estimate the Impact of the Omicron Variant on Vaccine Efficacy against COVID-19 Infection. Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data. Detecting COVID-Risky Behavior from Smartphones. Impact of the composition of feature extraction and class sampling in medicare fraud detection. Automated Infectious Disease Forecasting: Use-cases and Practical Considerations for Pipeline Implementation.
1:20pm-2:10pm	Invited Keynote 3. Cecile Viboud [expand] Cecile Viboud is a senior research scientist in the Division of International Epidemiology and Population Studies of the Fogarty International Center, National Institutes of Health, USA. Her research focuses on the epidemiology and transmission dynamics of acute viral infections, at the interface of public health and computational modeling. Her work has concentrated on modeling the epidemiology, excess mortality, and transmission dynamics of respiratory viruses, including seasonal and pandemic influenza, and COVID-19. She has recently become interested in the potential of Big Data to strengthen infectious disease surveillance, disease forecasts, and the population-level impact of vaccination programs. Title: The power of collaborative hubs for disease modeling [expand] Abstract: Drawing from past experience with the COVID19 Scenario Modeling Hub and the RAPIDD Ebola Forecast Challenge, I will illustrate how collaborative and coordinated modeling hubs can help guide the response to infectious disease crises. I will also discuss areas where more research is needed to improve the utility of these hubs.
2:10pm-3:00pm	Poster session. All contributed papers
3:00pm-3:30pm	Stretch, Networking Break
3:30pm-4:15pm	Discussion Panel. Bridging the gap between CS/ML work and public health practice.
4:15pm-4:25pm	Contributed Talk 3 (Oral) Paper: Optimal Intervention on Weighted Networks via Edge Centrality. [PDF] Authors: Dongyue Li, Tina Eliassi-Rad, Hongyang R Zhang.
4:25pm-4:35pm	Contributed Talk 4 (Oral) Paper: Using Survey Data to Estimate the Impact of the Omicron Variant on Vaccine Efficacy against COVID-19 Infection. [PDF] Authors: Jesús Rufino, Carlos Baquero, Davide Frey, Christin A. Glorioso, Antonio Ortega, Nina Reščič, Julian Charles Roberts, Rosa E. Lillo, Raquel Menezes, Jaya Prakash Champati, Antonio Fernandez Anta.
4:35pm-4:45pm	Contributed Talk 5 (Oral) Paper: Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data. [PDF] Authors: Hari Prasanna Das, Ryan Tran, Japjot Singh, Xiangyu Yue, Geoffrey H. Tison, Alberto Sangiovanni-Vincentelli, Costas Spanos.
4:45pm-4:50pm	Contributed Talk 6 (Oral) Paper: On Detecting COVID-Risky Behavior from Smartphones. [PDF] Authors: Thomas Hartvigsen, Walter Gerych, Marzyeh Ghassemi.
4:50pm-5:00pm	Closing Remaks

Time

Event

9:00am-9:10am

epiDAMIK opening Remarks

9:10am-9:20am

Contributed Talk 1 (Oral)
Paper: Impact of Seeding and Spatial Heterogeneity on Metapopulation Disease Dynamics. [PDF]
Authors: Rohit Srinivas Rajuladevi, Madhav Marathe, Przemyslaw Porebski, Srinivasan Venkataramanan.

9:20am-9:30am

Contributed Talk 2 (Oral)
Paper: EVADE: Exploring Vaccine Dissenting Discourse on Twitter. [PDF]
Authors: Shreya Ghosh, Prasenjit Mitra, Bernice L Hausman.

9:30am-10:00am

Stretch, Networking Break

10:00am-10:50am

Invited Keynote 1. Rachel Slayton [expand]

Dr. Rachel Slayton is a Ph-D trained epidemiologist and infectious disease modeler. She leads a mathematical modeling unit focused on healthcare-associated infections and multi-drug resistant organisms in the U.S. Centers for Disease Control and Prevention (CDC)’s Division of Healthcare Quality Promotion, Epidemiology Research and Innovations Branch. She also serves as the Scientific Director for the Modeling Infectious Diseases in Healthcare (MInD-Healthcare) network and co-led CDC’s COVID-19 mathematical modeling unit.

Title: Improving Pandemic Response: Employing Mathematical Modeling to Confront COVID-19 [expand]

Abstract: Modeling complements surveillance data to inform coronavirus disease 2019 (COVID-19) public health decision making and policy development. When urgent public health decisions are needed and data are limited, mathematical modeling offers opportunities to combine data from multiple sources, assess critical uncertainties and needs, and inform decisions. The Centers for Disease Control and Prevention (CDC) has used mathematical modeling to inform public health practice for emerging infectious diseases for many years, working in collaboration with partners in other government agencies, academia, and the private sector. This includes the use of modeling to improve situational awareness, assess epidemiological characteristics, and inform the evidence base for prevention strategies.

10:50am-11:10am

Lightning Talks - Part 1 [expand]

3 min per each paper in the following order:

EVADE: Exploring Vaccine Dissenting Discourse on Twitter.
Impact of Seeding and Spatial Heterogeneity on Metapopulation Disease Dynamics.
Optimal Intervention on Weighted Networks via Edge Centrality.
Optimal Epidemic Control as a Contextual Combinatorial Bandit with Budget.
Modelling Healthcare Associated Infections with Hypergraphs.
Real-time Anomaly Detection in Epidemic Data Streams.

11:10am-12:00am

Invited Keynote 2. Bryan Wilder [expand]

Bryan Wilder is an incoming Assistant Professor in the Machine Learning Department at Carnegie Mellon University. His research focuses on the intersection of optimization, machine learning, and social networks, motivated by applications to public health. Areas of focus include HIV prevention, maternal and child health, and COVID-19. He is supported by the Schmidt Science Fellows program and was previously supported by the NSF and Siebel Fellowships. His dissertation was recognized with the 2021 IFAAMAS Victor Lesser Distinguished Dissertation Award, and his work has been a finalist for best paper awards at ICML, AAMAS, and the INFORMS Doing Good with Good OR competition.

Title: AI for infectious disease prevention and response [expand]

Abstract: As exemplified by the COVID-19 pandemic, our health and wellbeing depend on a difficult-to-measure web of societal factors and individual behaviors. This effort requires new algorithmic and data-driven paradigms which span the full process of gathering costly data, learning models to understand and predict the interactions of many agents, and optimizing the use of limited resources in interventions. In response to these needs, I will present methodological developments at the intersection of machine learning, optimization, and social networks which are motivated by on-the-ground work related to HIV prevention and the COVID-19 response.

12:00pm-1:00pm

Lunch Break

1:00pm-1:20am

Lightning Talks - Part 2 [expand]

3 min per each paper in the following order:

Using Survey Data to Estimate the Impact of the Omicron Variant on Vaccine Efficacy against COVID-19 Infection.
Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data.
Detecting COVID-Risky Behavior from Smartphones.
Impact of the composition of feature extraction and class sampling in medicare fraud detection.
Automated Infectious Disease Forecasting: Use-cases and Practical Considerations for Pipeline Implementation.

1:20pm-2:10pm

Invited Keynote 3. Cecile Viboud [expand]

Cecile Viboud is a senior research scientist in the Division of International Epidemiology and Population Studies of the Fogarty International Center, National Institutes of Health, USA. Her research focuses on the epidemiology and transmission dynamics of acute viral infections, at the interface of public health and computational modeling. Her work has concentrated on modeling the epidemiology, excess mortality, and transmission dynamics of respiratory viruses, including seasonal and pandemic influenza, and COVID-19. She has recently become interested in the potential of Big Data to strengthen infectious disease surveillance, disease forecasts, and the population-level impact of vaccination programs.

Title: The power of collaborative hubs for disease modeling [expand]

Abstract: Drawing from past experience with the COVID19 Scenario Modeling Hub and the RAPIDD Ebola Forecast Challenge, I will illustrate how collaborative and coordinated modeling hubs can help guide the response to infectious disease crises. I will also discuss areas where more research is needed to improve the utility of these hubs.

2:10pm-3:00pm

Poster session. All contributed papers

3:00pm-3:30pm

Stretch, Networking Break

3:30pm-4:15pm

Discussion Panel.
Bridging the gap between CS/ML work and public health practice.

4:15pm-4:25pm

Contributed Talk 3 (Oral)
Paper: Optimal Intervention on Weighted Networks via Edge Centrality. [PDF]
Authors: Dongyue Li, Tina Eliassi-Rad, Hongyang R Zhang.

4:25pm-4:35pm

Contributed Talk 4 (Oral)
Paper: Using Survey Data to Estimate the Impact of the Omicron Variant on Vaccine Efficacy against COVID-19 Infection. [PDF]
Authors: Jesús Rufino, Carlos Baquero, Davide Frey, Christin A. Glorioso, Antonio Ortega, Nina Reščič, Julian Charles Roberts, Rosa E. Lillo, Raquel Menezes, Jaya Prakash Champati, Antonio Fernandez Anta.

4:35pm-4:45pm

Contributed Talk 5 (Oral)
Paper: Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data. [PDF]
Authors: Hari Prasanna Das, Ryan Tran, Japjot Singh, Xiangyu Yue, Geoffrey H. Tison, Alberto Sangiovanni-Vincentelli, Costas Spanos.

4:45pm-4:50pm

Contributed Talk 6 (Oral)
Paper: On Detecting COVID-Risky Behavior from Smartphones. [PDF]
Authors: Thomas Hartvigsen, Walter Gerych, Marzyeh Ghassemi.

4:50pm-5:00pm

Closing Remaks

Schedule

Invited Keynote Speakers

List of Accepted Papers

Oral Papers

Poster Papers