Prediction of malaria incidence using climate variability and machine learning

Odu, Nkiruka Bridget; Prasad, Rajesh; Clement, Onime

doi:10.1016/j.imu.2020.100508

Cited by 47 publications

(29 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fourth Industrial Revolution technologies such as artificial intelligence, machine learning, big data, remote sensing, wireless sensor networks, and mobile technologies have been widely used to develop early warning systems globally [22,62,71,72]. However, these tools are underutilized in predicting infectious diseases in Africa.…”

Section: Slow Adoption Of Fourth Industrial Revolution Technologiesmentioning

confidence: 99%

“…Only keywords with a minimum of four occurrences were considered in the keyword analysis, and none of the 4IR tools were represented. Even though researchers such as [15,71,72] used machine learning to predict malaria, the minimal presence of the keywords 'machine learning' in the search results indicates that machine learning in the prediction of infectious diseases in Africa remains modest. With the growth in big data, accurate medical and climate data analysis allows predicting and early detection of infectious diseases associated with climate change [73].…”

Section: Slow Adoption Of Fourth Industrial Revolution Technologiesmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Infectious Diseases: A Bibliometric Review on Africa

Phoobane

Masinde

Mabhaudhi

2022

IJERPH

View full text Add to dashboard Cite

Africa has a long history of novel and re-emerging infectious disease outbreaks. This reality has attracted the attention of researchers interested in the general research theme of predicting infectious diseases. However, a knowledge mapping analysis of literature to reveal the research trends, gaps, and hotspots in predicting Africa’s infectious diseases using bibliometric tools has not been conducted. A bibliometric analysis of 247 published papers on predicting infectious diseases in Africa, published in the Web of Science core collection databases, is presented in this study. The results indicate that the severe outbreaks of infectious diseases in Africa have increased scientific publications during the past decade. The results also reveal that African researchers are highly underrepresented in these publications and that the United States of America (USA) is the most productive and collaborative country. The relevant hotspots in this research field include malaria, models, classification, associations, COVID-19, and cost-effectiveness. Furthermore, weather-based prediction using meteorological factors is an emerging theme, and very few studies have used the fourth industrial revolution (4IR) technologies. Therefore, there is a need to explore 4IR predicting tools such as machine learning and consider integrated approaches that are pivotal to developing robust prediction systems for infectious diseases, especially in Africa. This review paper provides a useful resource for researchers, practitioners, and research funding agencies interested in the research theme—the prediction of infectious diseases in Africa—by capturing the current research hotspots and trends.

show abstract

Section: Slow Adoption Of Fourth Industrial Revolution Technologiesmentioning

confidence: 99%

Section: Slow Adoption Of Fourth Industrial Revolution Technologiesmentioning

confidence: 99%

Predicting Infectious Diseases: A Bibliometric Review on Africa

Phoobane

Masinde

Mabhaudhi

2022

IJERPH

View full text Add to dashboard Cite

show abstract

“…The model outperforms traditional time series and deep learning methods. Nkiruka et al 20 proposed a machine learning system to assess the association between climatic factors and malaria incidence and found that rainfall, surface radiation and temperature affect the outbreak of malaria disease.…”

Section: Introductionmentioning

confidence: 99%

Predicting the impact of climate change on the re-emergence of malaria cases in China using LSTMSeq2Seq deep learning model: a modelling and prediction analysis study

2022

View full text Add to dashboard Cite

ObjectivesMalaria is a vector-borne disease that remains a serious public health problem due to its climatic sensitivity. Accurate prediction of malaria re-emergence is very important in taking corresponding effective measures. This study aims to investigate the impact of climatic factors on the re-emergence of malaria in mainland China.DesignA modelling study.Setting and participantsMonthly malaria cases for four Plasmodium species (P. falciparum, P. malariae, P. vivax and other Plasmodium) and monthly climate data were collected for 31 provinces; malaria cases from 2004 to 2016 were obtained from the Chinese centre for disease control and prevention and climate parameters from China meteorological data service centre. We conducted analyses at the aggregate level, and there was no involvement of confidential information.Primary and secondary outcome measuresThe long short-term memory sequence-to-sequence (LSTMSeq2Seq) deep neural network model was used to predict the re-emergence of malaria cases from 2004 to 2016, based on the influence of climatic factors. We trained and tested the extreme gradient boosting (XGBoost), gated recurrent unit, LSTM, LSTMSeq2Seq models using monthly malaria cases and corresponding meteorological data in 31 provinces of China. Then we compared the predictive performance of models using root mean squared error (RMSE) and mean absolute error evaluation measures.ResultsThe proposed LSTMSeq2Seq model reduced the mean RMSE of the predictions by 19.05% to 33.93%, 18.4% to 33.59%, 17.6% to 26.67% and 13.28% to 21.34%, for P. falciparum, P. vivax, P. malariae, and other plasmodia, respectively, as compared with other candidate models. The LSTMSeq2Seq model achieved an average prediction accuracy of 87.3%.ConclusionsThe LSTMSeq2Seq model significantly improved the prediction of malaria re-emergence based on the influence of climatic factors. Therefore, the LSTMSeq2Seq model can be effectively applied in the malaria re-emergence prediction.

show abstract

“…In this paper, we used two machine learning methods, Random Forest and XGBoost, to perform our analysis and prediction on HFMD incidence. There have been a large number of studies focusing on machine learning methods to analyze different infectious diseases, and to perform prediction about the incidence of diseases, such as dengue [ 30 , 33 – 35 ], polio [ 36 ], human brucellosis [ 37 ], malaria [ 38 ], and COVID-19 [ 39 , 40 ]. It is also applied for the prediction of HFMD from meteorological factors in a single province in China [ 41 ].…”

Section: Discussionmentioning

confidence: 99%

“…We noticed that a study excluded average pressure factor when analyzing the influential factors on the incidence of infectious diseases [ 38 ]. In our initial research, we have taken average pressure factor along with other meteorological factors into account.…”

Section: Discussionmentioning

confidence: 99%

Analysis and prediction of hand, foot and mouth disease incidence in China using Random Forest and XGBoost

Meng

Zhao

2021

PLoS ONE

View full text Add to dashboard Cite

Hand, foot and mouth disease (HFMD) is an increasingly serious public health problem, and it has caused an outbreak in China every year since 2008. Predicting the incidence of HFMD and analyzing its influential factors are of great significance to its prevention. Now, machine learning has shown advantages in infectious disease models, but there are few studies on HFMD incidence based on machine learning that cover all the provinces in mainland China. In this study, we proposed two different machine learning algorithms, Random Forest and eXtreme Gradient Boosting (XGBoost), to perform our analysis and prediction. We first used Random Forest to examine the association between HFMD incidence and potential influential factors for 31 provinces in mainland China. Next, we established Random Forest and XGBoost prediction models using meteorological and social factors as the predictors. Finally, we applied our prediction models in four different regions of mainland China and evaluated the performance of them. Our results show that: 1) Meteorological factors and social factors jointly affect the incidence of HFMD in mainland China. Average temperature and population density are the two most significant influential factors; 2) Population flux has different delayed effect in affecting HFMD incidence in different regions. From a national perspective, the model using population flux data delayed for one month has better prediction performance; 3) The prediction capability of XGBoost model was better than that of Random Forest model from the overall perspective. XGBoost model is more suitable for predicting the incidence of HFMD in mainland China.

show abstract

Prediction of malaria incidence using climate variability and machine learning

Cited by 47 publications

References 22 publications

Predicting Infectious Diseases: A Bibliometric Review on Africa

Predicting Infectious Diseases: A Bibliometric Review on Africa

Predicting the impact of climate change on the re-emergence of malaria cases in China using LSTMSeq2Seq deep learning model: a modelling and prediction analysis study

Analysis and prediction of hand, foot and mouth disease incidence in China using Random Forest and XGBoost

Contact Info

Product

Resources

About