New paper: Predicting COVID-19 exposure risk perception using machine learning

masv on 19. July 2023

Nan Zou Bakkeli (Consumption Research Norway, SIFO, and affiliated with PANSOC) has just published a new research paper Predicting COVID-19 exposure risk perception using machine learning | SpringerLink in BMC Public Health, funded by PANSOC.

Abstract
Background: Self-perceived exposure risk determines the likelihood of COVID-19 preventive measure compliance to a large extent and is among the most important predictors of mental health problems. Therefore, there is a need to systematically identify important predictors of such risks. This study aims to provide insight into forecasting and understanding risk perceptions and help to adjust interventions that target various social groups in different pandemic phases.


Methods: This study was based on survey data collected from 5001 Norwegians in 2020 and 2021. Interpretable machine learning algorithms were used to predict perceived exposure risks. To detect the most important predictors, the models with best performance were chosen based on predictive errors and explained variances. Shapley
additive values were used to examine individual heterogeneities, interpret feature impact and check interactions between the key predictors.

Results: Gradient boosting machine exhibited the best model performance in this study (2020: RMSE=.93, MAE=.74,
RSQ=.22; 2021: RMSE=.99, MAE=.77, RSQ=.12). The most influential predictors of perceived exposure risk were compliance with interventions, work-life conflict, age and gender. In 2020, work and occupation played a dominant role in predicting perceived risks whereas, in 2021, living and behavioural factors were among the most important predictors. Findings show large individual heterogeneities in feature importance based on people’s sociodemographic backgrounds, work and living situations.

Conclusion: The findings provide insight into forecasting risk groups and contribute to the early detection of vulnerable
people during the pandemic. This is useful for policymakers and stakeholders in developing timely interventions
targeting different social groups. Future policies and interventions should be adapted to the needs of people
with various life situations

Nei er utsatt ja

masv on 7. July 2023

Kan presset om å publisere bli mer håndterbart om vi feirer alle prosessene, er åpne om avslag og innfører holdningen «nei er utsatt ja»? Det hevder senterleder i denne nye kronikken i Khrono. Han bruker egen avslagshistorie for å underbygge sine argumenter. Les mer her: Nei er utsatt ja (khrono.no)

The stay at CAS 2022-23 is ending this month

masv on 1. June 2023

Over the past year, we at PANSOC have had the pleasure of hosting a large international team of researchers behind the Social Science Meets Biology: Indigenous People and Severe Influenza Outcomes project at Centre for Advanced Study (CAS) at the Norwegian Academy of Science & Letters in Oslo, Norway. This interdisciplinary research project has sought to explore the complex factors that contribute to the severe influenza outcomes often experienced by Indigenous communities in Northern Europe, North America and Oceania.

As the project comes to an end, Centre leader of PANSOC and head of the CAS-project, Professor Mamelund, has given his reflections on the project, its findings, and the future of pandemic research in an interview at CAS. Read more here: End Interview: Social Science Meets Biology | CAS (cas-nor.no)

Portrait picture: Svenn-Erik Mamelund

Natalie Bennett is visiting us 22-26 May, 2023.

masv on 23. May 2023

Dr. Bennett is our second PANSOC visiting scholar this semester. Bennett is at the Population Health Sciences Institute, Faculty of Medical Sciences, Newcastle University.

Dr. Bennett is presenting two times this week at the Centre for Advanced study at the Norwegian Academy of Science and Letters. The first presentation is titled “Geographical inequalities in COVID-19 vaccination and mortality” and the second is a workshop on Structural Equation Modelling.

PANSOC centre leader, Svenn-Erik Mamelund, and Dr. Natalie Bennett

 

Please meet our new researcher: Maria Bekker-Nielsen Dunbar

masv on 9. May 2023

Maria is an incoming researcher at the OsloMet Center for Research on Pandemics & Society (PANSOC). Maria graduated with an MSc in Statistics from the University of Copenhagen in 2016 and will defend her PhD thesis on 11th of July 2023 in Epidemiology and Biostatistics at the University of Zurich which she started in 2020. The topic of her PhD is time-varying transmission weights in endemic-epidemic models which she has applied to COVID-19 surveillance and leveraged to examine policy questions such as what is the impact of social distancing measures and would a different vaccine distribution scheme have led to greater societal protection.

She has a keen interest in environmental epidemiology and infectious disease modelling. She has previously worked at the European Centre for Disease Prevention and Control (ECDC), Public Health England, and the World Health Organization (WHO) and has enjoyed learning how interdisciplinary research is used in policy making at various governmental levels. At ECDC her focus was on vaccine-preventable diseases, particularly modelling herpes zoster and understanding how national immunisation task action groups operated in European Union member states.

At Public Health England she did a project on the black death modelling the risk of death in periods of known outbreaks compared with periods without and this interest in historical epidemiology was further honed during her time at the University of Zurich where she did a project on syphilis in the sixteenth century constructed around stigma.

Maria will be working with Svenn-Erik Mamelund and Jessica Dimka at PANSOC and will be developing a grant application during her time at OsloMet. Her current research interests are environment, infectious diseases and vaccines, public health emergencies, and disasters (both natural and human-caused) as well as open science and good scientific practices.