“2022 Monkeypox Outbreak: Situational Awareness” with Syra Madad [Zoom]

[from Harvard Kennedy School’s Belfer Center, part of Harvard University]

Thursday, July 21, 2:30-4:00 PM EDT

RSVP (Required)

The 2022 Monkeypox outbreak continues to expand with case counts mounting in many countries. This seminar will cover where we are in the global fight against monkeypox, where we may be headed as a nation, and what we need to do right now to mitigate the growing threat of monkeypox. Join Belfer Fellow Dr. Syra Madad in conversation with Kai Kupferschmidt, Dr. Krutika Kuppalli, Dr. Anne Rimoin, Dr. Boghuma Kabisen Titanji, and Dr. Jay K. Varma.

About the Speakers

Dr. Anne Rimoin is a Professor of Epidemiology at the UCLA Fielding School of Public Health. She is the Gordon-Levin Endowed Chair in Infectious Diseases and Public Health. Dr. Rimoin is the director of the Center for Global and Immigrant Health and is an internationally recognized expert on emerging infections, global health, surveillance systems, and vaccination.

Rimoin has been working in the DRC since 2002, where she founded the UCLA-DRC Health Research and Training Program to train U.S. and Congolese epidemiologists to conduct high-impact infectious disease research in low-resource, logistically-complex settings.

Dr. Rimoin’s research focuses on emerging and vaccine-preventable diseases. It has led to fundamental understandings of the epidemiology of human monkeypox in post-eradication of smallpox, long-term immunity to Ebola virus in survivors and durability of immune response to Ebola virus vaccine in health workers in DRC. Her current research portfolio includes studies of COVID-19, Ebola, Marburg, Monkeypox and vaccine-preventable diseases of childhood.

Boghuma Kabisen Titanji (MD, MSc., DTM&H, PhD) is a Cameroonian born physician-scientist and Assistant Professor of Medicine at Emory University in Atlanta. She obtained her MD from the University of Yaoundé I in Cameroon and worked for two years after graduation as a medical officer, before pursuing post-graduate research training in London, United Kingdom. As an awardee of the prestigious Commonwealth Scholarship program, she obtained a Masters Degree in Tropical Medicine and International Health from the London School of Hygiene and Tropical Medicine, a diploma in Tropical Medicine and Hygiene from the Royal College of Physicians and a Ph.D. in Virology from University College London. Dr. Titanji joined Emory University School of Medicine in 2016 where she completed a residency in Internal Medicine, on the ABIM research pathway and a fellowship Infectious Diseases. She has three parallel career interests: translational and clinical research in HIV and emerging virus infections, science communication, and global health. Her clinical focus is general infectious diseases and people with HIV. Her current research focuses on chronic inflammation as a mediator of cardiovascular disease in people with HIV. She is passionate about leveraging translational research to improve the care of people with HIV, global health equity and using science to influence health policy through science communication and advocacy.

Jay K. Varma, MD is a Professor of Population Health Sciences and Director of the Cornell Center for Pandemic Prevention and Response at Weill Cornell Medicine. Dr. Varma is an expert on the prevention and control of diseases, having led epidemic responses, developed global and national policies, and led large-scale programs that have saved hundreds of thousands of lives in China, Southeast Asia, Africa, and the United States. After graduating magna cum laude with highest honors from Harvard, Dr. Varma completed medical school, internal medicine residency, and chief residency at the University of California, San Diego School of Medicine. From 2001-2021, he worked for the U.S. Centers for Disease Control and Prevention with postings in Atlanta, Thailand, China, Ethiopia, and New York City. From April 2020 – May 2021, he served as the principal scientific spokesperson and lead for New York City’s COVID-19 response. Dr. Varma has authored 143 scientific manuscripts, 13 essays, and one book.

Kai Kupferschmidt is a science journalist based in Berlin, Germany. He is a contributing correspondent for Science where he often covers infectious diseases. Kai received a diploma in molecular biomedicine from the University of Bonn, Germany and later visited the Berlin Journalism School. He has won several awards for his work, including the Journalism Prize of the German AIDS Foundation. Together with two colleagues he runs a podcast on global health called Pandemia [German]. He has also written two books, one about infectious diseases and one about the science of the color blue.

Krutika Kuppalli, MD, FIDSA is a Medical Officer for Emerging Zoonotic Diseases and Clinical Management in the Health Emergencies Program at the World Health Organization where she currently supports activities for the Monkeypox outbreak and COVID-19 pandemic. She completed her Internal Medicine residency and Infectious Diseases fellowship at Emory University, a Post-Doctoral Fellowship in Global Public Health at the University of California, San Diego and the Emerging Leader in Biosecurity Fellowship at the Johns Hopkins Center for Health Security. Dr. Kuppalli currently serves on the American Society of Tropical Medicine and Hygiene (ASTMH) Trainee Committee and is the Chair of the Infectious Diseases Society of America (IDSA) Global Health Committee.

Dr. Kuppalli was previously awarded the NIH Fogarty International Clinical Research Fellowship and conducted research in Southern India to understand barriers to care and how emerging infections impacted persons living with HIV/AIDS. She was the medical director of a large Ebola Treatment Unit in Sierra Leone during the 2014 West Africa Ebola outbreak, helped lead the development and implementation of pandemic response preparedness activities in resource limited settings, and has consulted on the development of therapeutics for emerging pathogens. Her clinical and research interests focus on health systems strengthening in resource limited settings, research and clinical care for emerging infections, outbreak preparedness and response, and policy. She has worked in numerous countries including Ethiopia, India, Sierra Leone, Uganda, and Haiti.

During the COVID-19 pandemic Dr. Kuppalli served as a consultant for the San Francisco Department of Health and helped develop and operationalize a field hospital. She served as an expert witness to the U.S. Congress, Financial Services Committee Task Force on Artificial Intelligence (AI) about how digital technologies may be leveraged for exposure notification and contact tracing to improve the pandemic response. She also collaborated with the Brennan Center for Justice to develop guidelines to inform “Healthy in-person Voting” in advance of the 2020 U.S. election and testified before the U.S. House Select Subcommittee regarding these recommendations. Prior to her position at WHO, she was the medical lead for COVID-19 vaccine rollout at the Medical University of South Carolina (MUSC) and helped coordinate vaccine education events for the staff and community and oversaw the reporting of adverse vaccine events.

Since joining WHO in August 2021, Dr. Kuppalli has been part of the WHO headquarters incident management team (IMST) for COVID-19, the clinical characterization and management working group for COVID-19, the COVID-19 therapeutics steering committee, and is the technical focal point for the post COVID-19 condition (Long COVID) steering committee. She is a member of the secretariat on the scientific advisory group on the origins of emerging and re-emerging infectious diseases (SAGO) which was convened by the Director General to understand and investigate the origins of SARS-CoV-2 and other novel pathogens. More recently since the development of the multi-country monkeypox outbreak she has been part of the IMST at WHO as one of the clinical management focal points. In this capacity she was part of the WHO core group that helped write the recently published Clinical Management and Infection Prevention and Control guidelines for Monkeypox and advising on the clinical endpoints for the global CORE therapeutics protocol.

Dr. Kuppalli is recognized as a scientific expert in global health, biosecurity and outbreak response. She was recognized by NPR Source of The Week early in the pandemic as an expert to follow and named to Elemental’s 50 Experts to Trust in a Pandemic. She has been a frequent contributor to numerous domestic and international media outlets including The New York Times, NPR, Reuters, The Washington Post, Vox, Stat News, San Francisco Chronicle, Forbes, NBC Bay Area, BBC News.

Science-Watching: Forecasting New Diseases in Low-Data Settings Using Transfer Learning

[from London Mathematical Laboratory]

by Kirstin Roster, Colm Connaughton & Francisco A. Rodrigues


Recent infectious disease outbreaks, such as the COVID-19 pandemic and the Zika epidemic in Brazil, have demonstrated both the importance and difficulty of accurately forecasting novel infectious diseases. When new diseases first emerge, we have little knowledge of the transmission process, the level and duration of immunity to reinfection, or other parameters required to build realistic epidemiological models. Time series forecasts and machine learning, while less reliant on assumptions about the disease, require large amounts of data that are also not available in early stages of an outbreak. In this study, we examine how knowledge of related diseases can help make predictions of new diseases in data-scarce environments using transfer learning. We implement both an empirical and a synthetic approach. Using data from Brazil, we compare how well different machine learning models transfer knowledge between two different dataset pairs: case counts of (i) dengue and Zika, and (ii) influenza and COVID-19. In the synthetic analysis, we generate data with an SIR model using different transmission and recovery rates, and then compare the effectiveness of different transfer learning methods. We find that transfer learning offers the potential to improve predictions, even beyond a model based on data from the target disease, though the appropriate source disease must be chosen carefully. While imperfect, these models offer an additional input for decision makers for pandemic response.


Epidemic models can be divided into two broad categories: data-driven models aim to fit an epidemic curve to past data in order to make predictions about the future; mechanistic models simulate scenarios based on different underlying assumptions, such as varying contact rates or vaccine effectiveness. Both model types aid in the public health response: forecasts serve as an early warning system of an outbreak in the near future, while mechanistic models help us better understand the causes of spread and potential remedial interventions to prevent further infections. Many different data-driven and mechanistic models were proposed during the early stages of the COVID-19 pandemic and informed decision-making with varying levels of success. This range of predictive performance underscores both the difficulty and importance of epidemic forecasting, especially early in an outbreak. Yet the COVID-19 pandemic also led to unprecedented levels of data-sharing and collaboration across disciplines, so that several novel approaches to epidemic forecasting continue to be explored, including models that incorporate machine learning and real-time big data data streams. In addition to the COVID-19 pandemic, recent infectious disease outbreaks include Zika virus in Brazil in 2015, Ebola virus in West Africa in 2014–16, Middle East respiratory syndrome (MERS) in 2012, and coronavirus associated with severe acute respiratory syndrome (SARS-CoV) in 2003. This trajectory suggests that further improvements to epidemic forecasting will be important for global public health. Exploring the value of new methodologies can help broaden the modeler’s toolkit to prepare for the next outbreak. In this study, we consider the role of transfer learning for pandemic response.

Transfer learning refers to a collection of techniques that apply knowledge from one prediction problem to solve another, often using machine learning and with many recent applications in domains such as computer vision and natural language processing. Transfer learning leverages a model trained to execute a particular task in a particular domain, in order to perform a different task or extrapolate to a different domain. This allows the model to learn the new task with less data than would normally be required, and is therefore well-suited to data-scarce prediction problems. The underlying idea is that skills developed in one task, for example the features that are relevant to recognize human faces in images, may be useful in other situations, such as classification of emotions from facial expressions. Similarly, there may be shared features in the patterns of observed cases among similar diseases.

The value of transfer learning for the study of infectious diseases is relatively under-explored. The majority of existing studies on diseases remain in the domain of computer vision and leverage pre-trained neural networks to make diagnoses from medical images, such as retinal diseases, dental diseases, or COVID-19. Coelho and colleagues (2020) explore the potential of transfer learning for disease forecasts. They train a Long Short-Term Memory (LSTM) neural network on dengue fever time series and make forecasts directly for two other mosquito-borne diseases, Zika and Chikungunya, in two Brazilian cities. Even without any data on the two target diseases, their model achieves high prediction accuracy four weeks ahead. Gautam (2021) uses COVID-19 data from Italy and the USA to build an LSTM transfer model that predicts COVID-19 cases in countries that experienced a later pandemic onset.

These studies provide empirical evidence that transfer learning may be a valuable tool for epidemic forecasting in low-data situations, though research is still limited. In this study, we aim to contribute to this empirical literature not only by comparing different types of knowledge transfer and forecasting algorithms, but also by considering two different pairs of endemic and novel diseases observed in Brazilian cities, specifically (i) dengue and Zika, and (ii) influenza and COVID-19. With an additional analysis on simulated time series, we hope to provide theoretical guidance on the selection of appropriate disease pairs, by better understanding how different characteristics of the source and target diseases affect the viability of transfer learning.

Zika and COVID-19 are two recent examples of novel emerging diseases. Brazil experienced a Zika epidemic in 2015–16 and the WHO declared a public health emergency of global concern in February 2016. Zika is caused by an arbovirus spread primarily by mosquitoes, though other transmission methods, including congenital and sexual have also been observed. Zika belongs to the family of viral hemorrhagic fevers and symptoms of infection share some commonalities with other mosquito-borne arboviruses, such as yellow fever, dengue fever, or chikungunya. Illness tends to be asymptomatic or mild but can lead to complications, including microcephaly and other brain defects in the case of congenital transmission.

Given the similarity of the pathogen and primary transmission route, dengue fever is an appropriate choice of source disease for Zika forecasting. Not only does the shared mosquito vector result in similar seasonal patterns of annual outbreaks, but consistent, geographically and temporally granular data on dengue cases is available publicly via the open data initiative of the Brazilian government.

COVID-19 is an acute respiratory infection caused by the novel coronavirus SARS-CoV-2, which was first detected in Wuhan, China, in 2019. It is transmitted directly between humans via airborne respiratory droplets and particles. Symptoms range from mild to severe and may affect the respiratory tract and central nervous system. Several variants of the virus have emerged, which differ in their severity, transmissibility, and level of immune evasion.

Influenza is also a contagious respiratory disease that is spread primarily via respiratory droplets. Infection with the influenza virus also follows patterns of human contact and seasonality. There are two types of influenza (A and B) and new strains of each type emerge regularly. Given the similarity in transmission routes and to a lesser extent in clinical manifestations, influenza is chosen as the source disease for knowledge transfer to model COVID-19.

For each of these disease pairs, we collect time series data from Brazilian cities. Data on the target disease from half the cities is retained for testing. To ensure comparability, the test set is the same for all models. Using this empirical data, as well as the simulated time series, we implement the following transfer models to make predictions.

  • Random forest: First, we implement a random forest model which was recently found to capture well the time series characteristics of dengue in Brazil. We use this model to make predictions for Zika without re-training. We also train a random forest model on influenza data to make predictions for COVID-19. This is a direct transfer method, where models are trained only on data from the source disease.
  • Random forest with TrAdaBoost: We then incorporate data from the target disease (i.e., Zika and COVID-19) using the TrAdaBoost algorithm together with the random forest model. This is an instance-based transfer learning method, which selects relevant examples from the source disease to improve predictions on the target disease.
  • Neural network: The second machine learning algorithm we deploy is a feed-forward neural network, which is first trained on data of the endemic disease (dengue/influenza) and applied directly to forecast the new disease.
  • Neural network with re-training and fine-tuning: We then retrain only the last layer of the neural network using data from the new disease and make predictions on the test set. Finally, we fine-tune all the layers’ parameters using a small learning rate and low number of epochs. These models are examples of parameter-based transfer methods, since they leverage the weights generated by the source disease model to accelerate and improve learning in the target disease model.
  • Aspirational baseline: We compare these transfer methods to a model trained only on the target disease (Zika/COVID-19) without any data on the source disease. Specifically, we use half the cities in the target dataset for training and the other half for testing. This gives a benchmark of the performance in a large-data scenario, which would occur after a longer period of disease surveillance.

The remainder of this paper is organized as follows. The models are described in more technical detail in Section 2. Section 3 shows the results of the synthetic and empirical predictions. Finally, Section 4 discusses practical implications of the analyses.

Access the full paper [via institutional access or paid download].