Umeå University's logo

umu.sePublications
910111213141512 of 18
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Navigating epidemics: by leveraging data science and data-driven modelling
Umeå University, Faculty of Medicine, Department of Public Health and Clinical Medicine, Section of Sustainable Health. (Henrik Sjödin)
2024 (English)Doctoral thesis, comprehensive summary (Other academic)Alternative title
Navigera i epidemier : genom att utnyttja datavetenskap och datadriven modellering (Swedish)
Abstract [en]

Ours is an era of global change—including climate change, land-use change, urbanization, increased mobility of humans, species and goods, and environmental shifts. Concurrently, we are witnessing a tangible increase in the rate of (re)emerging infectious diseases, mostly driven by global change factors. This complex landscape of infectious diseases necessitates strategies underpinned by computational tools such as data-driven models to enhance our understanding, response, and predictions of potential epidemics.

In this thesis, I leveraged data science algorithms and developed data-driven models that extend beyond specific pathogens, providing insights to prepare for future epidemics, with a focus on Europe. I delved into three temporal contexts: 1) retrospective analyses to understand the contribution of global change factors—specifically climate change and human mobility—fuelling the disease outbreaks and expansion (papers I & IV), 2) develop model to improve disease severity estimation during an outbreak for immediate response (paper III), and 3) future disease transmission risk trajectories under various projected scenarios of global change (paper II)—each playing a crucial role in proactive public health planning and response.

In paper I, we assessed the predictive ability and the influence of eco-climatic factors on West Nile virus (WNV)—a pathogen with multiple hosts and mosqutio-vectors, and of public health concern in Europe. Utilizing an advanced machine learning classifier XGBoost, trained on a diverse dataset encompassing eco-climatic, sociodemographic predictors to the WNV presence/absence data, the model accurately predicted the WNV risk a season ahead. Furthermore, by employing an explainable AI algorithm, we uncovered both local and European-level drivers of WNV transmission. Higher temperatures in summer and spring, along with drier winters, were pivotal in the escalated frequency of WNV outbreaks in Europe from 2010 to 2019.

In paper II, we projected the WNV risk under climate change and socioeconomics scenarios by integrating augmenting the outputs of climate ensemble into machine learning algorithms. We projected transmission risk trends and maps at local, national, regional and European scale. We predicted a three to five fold increase in WNV transmission risk during the next few decades (2040-60) compared 2000-2020 under extreme climate change scenarios. The proportion of diseasereported European land areas could increase from 15% to 23-30%, putting 161 to 244 million people at risk. Western Europe remains at largest relative risk of WNV increase under all scenarios, and Northern Europe under extreme scenarios. With the current rate of spread and in the absence of intervention or vaccines the virus will have sustained suitability even under low carbon emission scenarios in currently endemic European regions.

In paper III, we developed a method to quantify an important epidemiological parameter-case fatality ratio (CFR)— commonly used measure to assess the disease severity during novel outbreaks. In our model, we accounted for the time lags between the reporting of a cases and that of the case fatalities and the probability distribution of time lags and derived the CFR and distribution parameters using an optimization algorithm. The method provided more accurate CFR estimations earlier than the widely used estimators under various simulation scenarios. The method also performed well on empirical COVID-19 data from 34 countries.  

In paper IV, we modelled annual dengue importations in Europe and the United States driven by human mobility and climate. Travel rates were modelled using a radiation model based on population density, geographic distance, and travel volumes. Dengue viraemic travellers were computed considering local mosquito bite risk, travel-associated bite probability, and visit duration. A dynamic vector life-stage model quantified the climatic suitability of transmissionpermissive local areas. Dengue importations linearly increased in Europe and the U.S. from 2015-2019, rising by 588% and 390%, respectively, compared to 1996-2000 estimates, driven by increased travel volumes (373%) and dengue incidence rates (30%) from endemic countries. Transmission seasons lengthened by 53% and 15% in Europe and the U.S., respectively, indicating increasingly permissive climates for local outbreaks. These findings apply to other diseases such as chikungunya, Zika, and yellow fever, sharing common intermediate host vectors, namely Aedes mosquitoes.

This thesis highlights Europe's increasing vulnerability to infectious diseases due to global change factors, putting millions at risk. It emphasizes the significance of advanced modelling and innovative data streams in anticipating epidemic risks. Developing digital early warning systems to track disease drivers and taking urgent climate change mitigation and adaptation measures are crucial to anticipate and reduce future epidemic risks. The outcomes of this research can be used to develop technology-driven decision support tools to aid public health authorities and policymakers in making evidence-based decisions during and inter-epidemic periods. 

Place, publisher, year, edition, pages
Umeå: Umeå University, 2024. , p. 47
Series
Umeå University medical dissertations, ISSN 0346-6612 ; 2305
Keywords [en]
Epidemics, Data science, West Nile virus, Europe, case fatality ratio, human mobility, AI, XAI, SHAP, data-driven modelling, climate change, dengue, data-driven model, CFR, adaptation
National Category
Public Health, Global Health, Social Medicine and Epidemiology
Research subject
Epidemiology; Public health; Infectious Diseases
Identifiers
URN: urn:nbn:se:umu:diva-223582ISBN: 978-91-8070-385-7 (print)ISBN: 978-91-8070-386-4 (electronic)OAI: oai:DiVA.org:umu-223582DiVA, id: diva2:1855639
Public defence
2024-06-03, Sal B, Våning 9, Norrlands universitetssjukhus, Umeå, 09:00 (English)
Opponent
Supervisors
Note

För att delta digitalt via zoom: https://umu.zoom.us/j/62878331943

Passcode: 112233

Available from: 2024-05-13 Created: 2024-05-02 Last updated: 2024-05-03Bibliographically approved
List of papers
1. Artificial intelligence to predict West Nile virus outbreaks with eco-climatic drivers
Open this publication in new window or tab >>Artificial intelligence to predict West Nile virus outbreaks with eco-climatic drivers
Show others...
2022 (English)In: The Lancet Regional Health: Europe, E-ISSN 2666-7762, Vol. 17, article id 100370Article in journal (Refereed) Published
Abstract [en]

Background: In Europe, the frequency, intensity, and geographic range of West Nile virus (WNV)-outbreaks have increased over the past decade, with a 7.2-fold increase in 2018 compared to 2017, and a markedly expanded geographic area compared to 2010. The reasons for this increase and range expansion remain largely unknown due to the complexity of the transmission pathways and underlying disease drivers. In a first, we use advanced artificial intelligence to disentangle the contribution of eco-climatic drivers to WNV-outbreaks across Europe using decade-long (2010-2019) data at high spatial resolution. Methods: We use a high-performance machine learning classifier, XGBoost (eXtreme gradient boosting) combined with state-of-the-art XAI (eXplainable artificial intelligence) methodology to describe the predictive ability and contribution of different drivers of the emergence and transmission of WNV-outbreaks in Europe, respectively. Findings: Our model, trained on 2010-2017 data achieved an AUC (area under the receiver operating characteristic curve) score of 0.97 and 0.93 when tested with 2018 and 2019 data, respectively, showing a high discriminatory power to classify a WNV-endemic area. Overall, positive summer/spring temperatures anomalies, lower water availability index (NDWI), and drier winter conditions were found to be the main determinants of WNV-outbreaks across Europe. The climate trends of the preceding year in combination with eco-climatic predictors of the first half of the year provided a robust predictive ability of the entire transmission season ahead of time. For the extraordinary 2018 outbreak year, relatively higher spring temperatures and the abundance of Culex mosquitoes were the strongest predictors, in addition to past climatic trends. Interpretation: Our AI-based framework can be deployed to trigger rapid and timely alerts for active surveillance and vector control measures in order to intercept an imminent WNV-outbreak in Europe. Funding: The work was partially funded by the Swedish Research Council FORMAS for the project ARBOPREVENT (grant agreement 2018-05973).

Place, publisher, year, edition, pages
Elsevier, 2022
Keywords
Climate adaptation, Culex vectors, Early warning systems, Emerging infectious disease, Europe, forecasting, Outbreaks management, Preparedness, SHAP, West Nile virus, XGBoost
National Category
Public Health, Global Health, Social Medicine and Epidemiology
Identifiers
urn:nbn:se:umu:diva-193708 (URN)10.1016/j.lanepe.2022.100370 (DOI)000796373200002 ()35373173 (PubMedID)2-s2.0-85127132481 (Scopus ID)
Funder
Swedish Research Council Formas, 2018-05973
Available from: 2022-04-25 Created: 2022-04-25 Last updated: 2024-05-02Bibliographically approved
2. European projections of West Nile virus transmission under climate change scenarios
Open this publication in new window or tab >>European projections of West Nile virus transmission under climate change scenarios
Show others...
2023 (English)In: One Health, ISSN 2352-7714, Vol. 16, article id 100509Article in journal (Refereed) Published
Abstract [en]

West Nile virus (WNV), a mosquito-borne zoonosis, has emerged as a disease of public health concern in Europe. Recent outbreaks have been attributed to suitable climatic conditions for its vectors favoring transmission. However, to date, projections of the risk for WNV expansion under climate change scenarios is lacking. Here, we estimate the WNV-outbreaks risk for a set of climate change and socioeconomic scenarios. We delineate the potential risk-areas and estimate the growth in the population at risk (PAR). We used supervised machine learning classifier, XGBoost, to estimate the WNV-outbreak risk using an ensemble climate model and multi-scenario approach. The model was trained by collating climatic, socioeconomic, and reported WNV-infections data (2010−22) and the out-of-sample results (1950–2009, 2023–99) were validated using a novel Confidence-Based Performance Estimation (CBPE) method. Projections of area specific outbreak risk trends, and corresponding population at risk were estimated and compared across scenarios. Our results show up to 5-fold increase in West Nile virus (WNV) risk for 2040-60 in Europe, depending on geographical region and climate scenario, compared to 2000-20. The proportion of disease-reported European land areas could increase from 15% to 23-30%, putting 161 to 244 million people at risk. Across scenarios, Western Europe appears to be facing the largest increase in the outbreak risk of WNV. The increase in the risk is not linear but undergoes periods of sharp changes governed by climatic thresholds associated with ideal conditions for WNV vectors. The increased risk will require a targeted public health response to manage the expansion of WNV with climate change in Europe.

Place, publisher, year, edition, pages
Elsevier, 2023
Keywords
Artificial intelligence, Climate change, Climate impacts, Confidence-based performance estimation (CBPE) method, Europe, West Nile virus, WNV risk projections, XGBoost, Zoonoses
National Category
Public Health, Global Health, Social Medicine and Epidemiology
Identifiers
urn:nbn:se:umu:diva-205369 (URN)10.1016/j.onehlt.2023.100509 (DOI)001004031000001 ()2-s2.0-85148667157 (Scopus ID)
Funder
Vinnova, 2020-03367Swedish Research Council Formas, 2018-01754European Commission, 101057554
Available from: 2023-03-29 Created: 2023-03-29 Last updated: 2024-05-02Bibliographically approved
3. Optimizing case fatality ratio estimates in ongoing pandemics through case-to-death time distribution analysis
Open this publication in new window or tab >>Optimizing case fatality ratio estimates in ongoing pandemics through case-to-death time distribution analysis
(English)Manuscript (preprint) (Other academic)
National Category
Public Health, Global Health, Social Medicine and Epidemiology
Research subject
Epidemiology; Public health; Infectious Diseases
Identifiers
urn:nbn:se:umu:diva-223583 (URN)
Available from: 2024-04-20 Created: 2024-04-20 Last updated: 2024-05-02
4. Assessing transcontinental threats of dengue outbreaks using human mobility and climatic suitability
Open this publication in new window or tab >>Assessing transcontinental threats of dengue outbreaks using human mobility and climatic suitability
Show others...
(English)Manuscript (preprint) (Other academic)
National Category
Public Health, Global Health, Social Medicine and Epidemiology
Research subject
Epidemiology; Public health; Infectious Diseases
Identifiers
urn:nbn:se:umu:diva-223586 (URN)
Available from: 2024-04-20 Created: 2024-04-20 Last updated: 2024-05-03

Open Access in DiVA

fulltext(13763 kB)33 downloads
File information
File name SUMMARY01.pdfFile size 13763 kBChecksum SHA-512
9fb71f73c93ffa6d9b429e6684b02ec3cb94649d787f013a620d778bd4e8af35ba6c5380bc2714cc517c6548ff0b2ddea8463ed0af89044def877b395fe036c8
Type fulltextMimetype application/pdf
spikblad(229 kB)19 downloads
File information
File name SPIKBLAD03.pdfFile size 229 kBChecksum SHA-512
4624119720360b174d649c1b49b94515f353893ec97ea2c2c78a860f8fb1b0f00c02d7156c3666175f39a600406d9e83dcddf7714911bdd1ef8d5f36eeb7e551
Type spikbladMimetype application/pdf

Authority records

Farooq, Zia

Search in DiVA

By author/editor
Farooq, Zia
By organisation
Section of Sustainable Health
Public Health, Global Health, Social Medicine and Epidemiology

Search outside of DiVA

GoogleGoogle Scholar
Total: 0 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 367 hits
910111213141512 of 18
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf