Digital and technological innovation in vector-borne disease surveillance to predict, detect, and control climate-driven outbreaks

Pley, Caitlin; Evans, Megan; Lowe, Rachel; Montgomery, Hugh; Yacoub, Sophie

doi:10.1016/s2542-5196(21)00141-8

Cited by 37 publications

(26 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Aedes aegypti is the main vector of CHIKV and DENV in Brazil (25). An increase in vector population density has been associated with the rise of dengue incidence (26, 27); thus, we sought to determine whether a recent increase in Ae. aegypti population density could correlate with the increase in CHIKV transmission.…”

Section: Resultsmentioning

confidence: 99%

Spatial-temporal dynamics and recurrence of chikungunya virus in Brazil

Souza

Lima

Mello

et al. 2022

Preprint

View full text Add to dashboard Cite

Chikungunya virus (CHIKV) is an Aedes mosquito-borne virus that has caused explosive epidemics linked to acute, chronic, and severe clinical outcomes. Since 2014, Brazil has had the highest number of chikungunya fever (CHIKF) cases in the Americas. Here, we report and contextualize the spatiotemporal dynamic of CHIKF in Brazil and combine genomic, epidemiological, and vector analyses to investigate CHIKF recurrence in several Brazilian states. From 2013 to 2022, CHIKV caused seven epidemic waves across Brazil, affecting 59.5% (3,316 of 5,570) of the country's municipalities. To date, Ceara State in the northeast has been the most affected, with 81,274 cases during the two largest epidemic waves in 2016 and 2017, and the ongoing third wave in 2022. The 2022 CHIKF recurrence was associated with a new introduction of an East/Central/South African strain. Also, the CHIKV recurrences in Ceara, Tocantins, and Pernambuco States were limited to municipalities with few or no prior reported cases in the previous epidemic waves, suggesting that spatial heterogeneity of CHIKV spread and population immunity may explain the recurrence pattern in the country. In addition, the population density metrics of main CHIKV vector in Brazil, Ae. aegypti, were not correlated spatially with locations of CHIKF recurrence in Ceara and Tocantins States. Also, we show that CHIKF disproportionally affected females, and we estimated the case-fatality ratio in Ceara at ~1.3 deaths per 1,000 cases. These findings more comprehensively describe CHIKV epidemics in Brazil and contribute to understanding CHIKF recurrence in urban settings. Overall, this information may help guide public health policy to mitigate and reduce the burden of urban arboviruses.

show abstract

Section: Resultsmentioning

confidence: 99%

Spatial-temporal dynamics and recurrence of chikungunya virus in Brazil

Souza

Lima

Mello

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Clinical prediction models have traditionally focused only on patient variables, but machine learning approaches are inherently scalable systems and can integrate large datasets from diverse sources. The future coupling of clinical machine learning models with these diverse, non-clinical datasets including climate, vector, environmental, and behavioural data could ultimately enable greater understanding and allow for better decision support ( 13 ). However, these increasingly complex models which make use of ecological data are also likely to restrict interpretability, particularly in terms causality between data and outcomes.…”

Section: Discussionmentioning

confidence: 99%

“…There is a role particularly for digital health interventions in healthcare settings with cellular connectivity but limited access to laboratory testing services, as found in many regions around the world ( 12 ). Further integration of these systems for passive real-time epidemiology could provide added-value and facilitate early outbreak detection and public health responses ( 13 ).…”

Section: Introductionmentioning

confidence: 99%

The Diagnosis of Dengue in Patients Presenting With Acute Febrile Illness Using Supervised Machine Learning and Impact of Seasonality

Ming

Tuấn

Hernandez

et al. 2022

Front. Digit. Health

Self Cite

View full text Add to dashboard Cite

BackgroundSymptomatic dengue infection can result in a life-threatening shock syndrome and timely diagnosis is essential. Point-of-care tests for non-structural protein 1 and IgM are used widely but performance can be limited. We developed a supervised machine learning model to predict whether patients with acute febrile illnesses had a diagnosis of dengue or other febrile illnesses (OFI). The impact of seasonality on model performance over time was examined.MethodsWe analysed data from a prospective observational clinical study in Vietnam. Enrolled patients presented with an acute febrile illness of <72 h duration. A gradient boosting model (XGBoost) was used to predict final diagnosis using age, sex, haematocrit, platelet, white cell, and lymphocyte count collected on enrolment. Data was randomly split 80/20% into a training and hold-out set, respectively, with the latter not used in model development. Cross-validation and hold out set testing was used, with performance over time evaluated through a rolling window approach.ResultsWe included 8,100 patients recruited between 16th October 2010 and 10th December 2014. In total 2,240 (27.7%) patients were diagnosed with dengue infection. The optimised model from training data had an overall median area under the receiver operator curve (AUROC) of 0.86 (interquartile range 0.84–0.86), specificity of 0.92, sensitivity of 0.56, positive predictive value of 0.73, negative predictive value (NPV) of 0.84, and Brier score of 0.13 in predicting the final diagnosis, with similar performances in hold-out set testing (AUROC of 0.86). Model performances varied significantly over time as a function of seasonality and other factors. Incorporation of a dynamic threshold which continuously learns from recent cases resulted in a more consistent performance throughout the year (NPV >90%).ConclusionSupervised machine learning models are able to discriminate between dengue and OFI diagnoses in patients presenting with an early undifferentiated febrile illness. These models could be of clinical utility in supporting healthcare decision-making and provide passive surveillance across dengue endemic regions. Effects of seasonality and changing disease prevalence must however be taken into account—this is of significant importance given unpredictable effects of human-induced climate change and the impact on health.

show abstract

“…Various models can predict dengue incidence based on climatic variables ( 40 ). Several studies carried out have used different models are described along with the results.…”

Section: Analytical Review Of Predicting Dengue Outbreakmentioning

confidence: 99%

A Retrospective Study of Climate Change Affecting Dengue: Evidences, Challenges and Future Directions

Bhatia

Bansal

Patil

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

Climate change is unexpected weather patterns that can create an alarming situation. Due to climate change, various sectors are affected, and one of the sectors is healthcare. As a result of climate change, the geographic range of several vector-borne human infectious diseases will expand. Currently, dengue is taking its toll, and climate change is one of the key reasons contributing to the intensification of dengue disease transmission. The most important climatic factors linked to dengue transmission are temperature, rainfall, and relative humidity. The present study carries out a systematic literature review on the surveillance system to predict dengue outbreaks based on Machine Learning modeling techniques. The systematic literature review discusses the methodology and objectives, the number of studies carried out in different regions and periods, the association between climatic factors and the increase in positive dengue cases. This study also includes a detailed investigation of meteorological data, the dengue positive patient data, and the pre-processing techniques used for data cleaning. Furthermore, correlation techniques in several studies to determine the relationship between dengue incidence and meteorological parameters and machine learning models for predictive analysis are discussed. In the future direction for creating a dengue surveillance system, several research challenges and limitations of current work are discussed.

show abstract

Digital and technological innovation in vector-borne disease surveillance to predict, detect, and control climate-driven outbreaks

Cited by 37 publications

References 37 publications

Spatial-temporal dynamics and recurrence of chikungunya virus in Brazil

Spatial-temporal dynamics and recurrence of chikungunya virus in Brazil

The Diagnosis of Dengue in Patients Presenting With Acute Febrile Illness Using Supervised Machine Learning and Impact of Seasonality

A Retrospective Study of Climate Change Affecting Dengue: Evidences, Challenges and Future Directions

Contact Info

Product

Resources

About