Publications associées à Unite du Prof. Salathe (IC/SV)

COVID-19 represents the most severe global crisis to date whose public conversation can be studied in real time. To do so, we use a data set of over 350 million tweets and retweets posted by over 26 million English speaking Twitter users from January 13 to June 7, 2020. We characterize the retweet network to identify spontaneous clustering of users and the evolution of their interaction over time in relation to the pandemic's emergence. We identify several stable clusters (super-communities), and are able to link them to international groups mainly involved in science and health topics, national elites, and political actors. The science- and health-related super-community received disproportionate attention early on during the pandemic, and was leading the discussion at the time. However, as the pandemic unfolded, the attention shifted towards both national elites and political actors, paralleled by the introduction of country-specific containment measures and the growing politicization of the debate. Scientific super-community remained present in the discussion, but experienced less reach and became more isolated within the network. Overall, the emerging network communities are characterized by an increased self-amplification and polarization. This makes it generally harder for information from international health organizations or scientific authorities to directly reach a broad audience through Twitter for prolonged time. These results may have implications for information dissemination along the unfolding of long-term events like epidemic diseases on a world-wide scale.

NATURE PORTFOLIO2021

A digital reconstruction of the 1630–1631 large plague outbreak in Venice

Giovanni Colavizza, Frédéric Kaplan, Gianrocco Lazzari, Marcel Salathé

The plague, an infectious disease caused by the bacterium Yersinia pestis, is widely considered to be responsible for the most devastating and deadly pandemics in human history. Starting with the infamous Black Death, plague outbreaks are estimated to have killed around 100 million people over multiple centuries, with local mortality rates as high as 60%. However, detailed pictures of the disease dynamics of these outbreaks centuries ago remain scarce, mainly due to the lack of high-quality historical data in digital form. Here, we present an analysis of the 1630–1631 plague outbreak in the city of Venice, using newly collected daily death records. We identify the presence of a two-peak pattern, for which we present two possible explanations based on computational models of disease dynamics. Systematically digitized historical records like the ones presented here promise to enrich our understanding of historical phenomena of enduring importance. This work contributes to the recently renewed interdisciplinary foray into the epidemiological and societal impact of pre-modern epidemics.

2020

Assessing Public Opinion on CRISPR-Cas9: Combining Crowdsourcing and Deep Learning

Marcel Salathé

Background: The discovery of the CRISPR-Cas9-based gene editing method has opened unprecedented new potential for biological and medical engineering, sparking a growing public debate on both the potential and dangers of CRISPR applications. Given the speed of technology development and the almost instantaneous global spread of news, it is important to follow evolving debates without much delay and in sufficient detail, as certain events may have a major long-term impact on public opinion and later influence policy decisions. Objective: Social media networks such as Twitter have shown to be major drivers of news dissemination and public discourse. They provide a vast amount of semistructured data in almost real-time and give direct access to the content of the conversations. We can now mine and analyze such data quickly because of recent developments in machine learning and natural language processing. Methods: Here, we used Bidirectional Encoder Representations from Transformers (BERT), an attention-based transformer model, in combination with statistical methods to analyze the entirety of all tweets ever published on CRISPR since the publication of the first gene editing application in 2013. Results: We show that the mean sentiment of tweets was initially very positive, but began to decrease over time, and that this decline was driven by rare peaks of strong negative sentiments. Due to the high temporal resolution of the data, we were able to associate these peaks with specific events and to observe how trending topics changed over time. Conclusions: Overall, this type of analysis can provide valuable and complementary insights into ongoing public debates, extending the traditional empirical bioethics toolset.

JMIR PUBLICATIONS, INC2020

Keep calm and carry on vaccinating: Is anti-vaccination sentiment contributing to declining vaccine coverage in England?

Marcel Salathé

Background: In England, coverage for childhood vaccines have decreased since 2012/13 in the context of an increasingly visible anti-vaccination discourse. We determined whether anti-vaccination sentiment is the likely cause of this decline in coverage. Methods: Descriptive study triangulating a range of data sources (vaccine coverage, cross-sectional survey of attitudes towards vaccination, UK-specific Twitter social media) and assessing them against the following Bradford Hill criteria: strength of association, consistency, specificity, temporality, biological gradient and coherence. Results: Strength of association: compared with well-documented vaccine scares, the decline in childhood vaccination seen since 2012/13 is 4-20 times smaller;consistency: while coverage for completed courses of the hexavalent and meningococcal vaccines decreased by 0.5-1.2 percentage points (pp) between 2017 and 2019, coverage for the first dose of these vaccines increased 0.5-0.7 pp; specificity: Since 2012-13, coverage decreased for some vaccines (hexavalent, MMR, HPV, shingles) and increased for others (MenACWY, Td/IPV, antenatal pertussis, influenza in 2 years of children), with no agespecific patterns. Temporality and biological gradient: the decline in vaccine coverage was preceded by an increase in vaccine confidence and a decrease in the proportion of parents encountering antivaccination materials. Coherence: attitudes towards vaccination expressed on Twitter in the UK became increasingly positive between 2017 and 2019 as vaccine coverage for childhood vaccines decreased. Conclusions: In England, trends in vaccine coverage between 2012/13 and 2018/19 were not homogenous and varied in magnitude and direction according to vaccine, dose and region. In addition, confidence in vaccines increased during the same period. These findings are not compatible with anti-vaccination sentiment causing a decline in vaccine coverage In England. (C) 2020 The Authors. Published by Elsevier Ltd.

2020

2019

Assessment of menstrual health status and evolution through mobile apps for fertility awareness

Marcel Salathé, Laura Symul

For most women of reproductive age, assessing menstrual health and fertility typically involves regular visits to a gynecologist or another clinician. While these evaluations provide critical information on an individual's reproductive health status, they typically rely on memory-based self-reports, and the results are rarely, if ever, assessed at the population level. In recent years, mobile apps for menstrual tracking have become very popular, allowing us to evaluate the reliability and tracking frequency of millions of self-observations, thereby providing an unparalleled view, both in detail and scale, on menstrual health and its evolution for large populations. In particular, the primary aim of this study was to describe the tracking behavior of the app users and their overall observation patterns in an effort to understand if they were consistent with previous small-scale medical studies. The secondary aim was to investigate whether their precision allowed the detection and estimation of ovulation timing, which is critical for reproductive and menstrual health. Retrospective self-observation data were acquired from two mobile apps dedicated to the application of the sympto-thermal fertility awareness method, resulting in a dataset of more than 30 million days of observations from over 2.7 million cycles for two hundred thousand users. The analysis of the data showed that up to 40% of the cycles in which users were seeking pregnancy had recordings every single day. With a modeling approach using Hidden Markov Models to describe the collected data and estimate ovulation timing, it was found that follicular phases average duration and range were larger than previously reported, with only 24% of ovulations occurring at cycle days 14 to 15, while the luteal phase duration and range were in line with previous reports, although short luteal phases (10 days or less) were more frequently observed (in up to 20% of cycles). The digital epidemiology approach presented here can help to lead to a better understanding of menstrual health and its connection to women's health overall, which has historically been severely understudied.

Springer2019

WHO and ITU establish benchmarking process for artificial intelligence in health

Ramesh Krishnamurthy, Marcel Salathé, Shan Xu

ELSEVIER SCIENCE INC2019

Digital epidemiology: what is it, and where is it going?

Marcel Salathé

Digital Epidemiology is a new field that has been growing rapidly in the past few years, fueled by the increasing availability of data and computing power, as well as by breakthroughs in data analytics methods. In this short piece, I provide an outlook of where I see the field heading, and offer a broad and a narrow definition of the term.

BMC2018

Crowdbreaks: Tracking Health Trends Using Public Social Media Data and Crowdsourcing

Marcel Salathé

In the past decade, tracking health trends using social media data has shown great promise, due to a powerful combination of massive adoption of social media around the world, and increasingly potent hardware and software that enables us to work with these new big data streams. At the same time, many challenging problems have been identified. First, there is often a mismatch between how rapidly online data can change, and how rapidly algorithms are updated, which means that there is limited reusability for algorithms trained on past data as their performance decreases over time. Second, much of the work is focusing on specific issues during a specific past period in time, even though public health institutions would need flexible tools to assess multiple evolving situations in real time. Third, most tools providing such capabilities are proprietary systems with little algorithmic or data transparency, and thus little buy-in from the global public health and research community. Here, we introduce Crowdbreaks, an open platform which allows tracking of health trends by making use of continuous crowdsourced labeling of public social media content. The system is built in a way which automatizes the typical workflow from data collection, filtering, labeling and training of machine learning classifiers and therefore can greatly accelerate the research process in the public health domain. This work describes the technical aspects of the platform, thereby covering the functionalities at its current state and exploring its future use cases and extensions.

2019

Assessing the Dynamics and Control of Droplet- and Aerosol-Transmitted Influenza Using an Indoor Positioning System

Gianrocco Lazzari, Marcel Salathé

There is increasing evidence that aerosol transmission is a major contributor to the spread of influenza. Despite this, virtually all studies assessing the dynamics and control of influenza assume that it is transmitted solely through direct contact and large droplets, requiring close physical proximity. Here, we use wireless sensors to measure simultaneously both the location and close proximity contacts in the population of a US high school. This dataset, highly resolved in space and time, allows us to model both droplet and aerosol transmission either in isolation or in combination. In particular, it allows us to computationally quantify the potential effectiveness of overlooked mitigation strategies such as improved ventilation that are available in the case of aerosol transmission. Our model suggests that recommendation-abiding ventilation could be as effective in mitigating outbreaks as vaccinating approximately half of the population. In simulations using empirical transmission levels observed in households, we find that bringing ventilation to recommended levels had the same mitigating effect as a vaccination coverage of 50% to 60%. Ventilation is an easy-to-implement strategy that has the potential to support vaccination efforts for effective control of influenza spread.

2019