Data mining and model-predicting a global disease reservoir for low-pathogenic Avian Influenza (A) in the wider pacific rim using big data sets

With super SDMs (machine learning, open access big data, and the cloud) towards more holistic global squirrel hotspots and coldspots

Species-habitat associations are correlative, can be quantified, and used for powerful inference. Nowadays, Species Distribution Models (SDMs) play a big role, e.g. using Machine Learning and AI algorithms, but their best-available technical opportunities remain still not used for their potential e.g. in the policy sector. Here we present Super SDMs that invoke ML, OA Big Data, and the Cloud with a workflow for the best-possible inference for the 300 + global squirrel species. Such global Big Data models are especially important for the many marginalized squirrel species and the high number of endangered and data-deficient species in the world, specifically in tropical regions. While our work shows common issues with SDMs and the maxent algorithm ('Shallow Learning'), here we present a multi-species Big Data SDM template for subsequent ensemble models and generic progress to tackle global species hotspot and coldspot assessments for a more inclusive and holistic inference.

Herbivore species coexistence in changing rangeland ecosystems: First high resolution national open-source and open-access ensemble models for Iceland

Rangeland ecosystems are changing worldwide with the abandonment of extensive pastoralism practices and greater interest for species coexistence. However, the lack of compiled data on current changes in the abundance and distribution of herbivores challenges rangeland management decisions. Here we gathered and made available for the first time the most extensive set of occurrence data for rangeland herbivores in Iceland in an Open Access framework for transparent and repeatable science-based decisions. We mapped fine scale species distribution overlap to identify areas at risk for wildlife-livestock conflict and overgrazing. Nationwide and long term (1861-2021) occurrence data from 8 independent datasets were used alongside 11 predictor raster layers ("Big Data") to data mine and map the distribution of the domestic sheep (Ovis aries), feral reindeer (Rangifer tarandus tarandus), pink-footed geese (Anser brachyrhynchus), and rock ptarmigan (Lagopus muta islandorum) over the country during the summer. Using algorithms of Maxent in R, RandomForest, TreeNet (stochastic gradient boosting) and MARS (Splines) in Minitab-SPM 8.3, we computed 1 km pixel predictions from machine learning-based ensemble models. Our high-resolution models were tested with alternative datasets, and Area Under the Curve (AUC) values that indicated good (reindeer: 0.8817 and rock ptarmigan: 0.8844) to high model accuracy (sheep: 0.9708 and pink-footed goose: 0.9143). Whenever possible, source data and models are made available online and described with ISO-compliant metadata. Our results illustrate that sheep and pink-footed geese have the greatest overlap in distribution with potential implication for wildlife-livestock conflicts and continued ecosystem degradation even under diminishing livestock abundance at higher elevation. These nationwide models and data are a global asset and a first step in making available the best data for science-based sustainable decision-making about national herbivores affecting species coexistence and environmental management.

Rabies Elimination: Is It Feasible without Considering Wildlife?

Rabies is a vaccine-preventable fatal viral disease that is zoonotic in nature. In this article, we provide a justification why the agreement of the World Health Organization (WHO), the Food and Agriculture Organization (FAO), the World Organization for Animal Health (OIE), and Global Alliance for Rabies Control (GARC) on The Global Strategic Plan to End Human Deaths from Dog-mediated Rabies by 2030 should also include a more holistic approach and ecologic views.

Data-driven computational intelligence applied to dengue outbreak forecasting: a case study at the scale of the city of Natal, RN-Brazil

Dengue is recognized as a health problem that causes significant socioeconomic impacts throughout the world, affecting millions of people each year. A commonly used method for monitoring the dengue vector is to count the eggs that Aedes aegypti mosquitoes have laid in spatially distributed ovitraps. Given this approach, the present study uses a database collected from 397 ovitraps allocated across the city of Natal, RN—Brazil. The Egg Density Index for each neighborhood was computed weekly, over four complete years (from 2016 to 2019), and simultaneously analyzed with the dengue case incidence. Our results illustrate that the incidence of dengue is related to the socioeconomic level of the neighborhoods in the city of Natal. A deep learning algorithm was used to predict future dengue case incidence, either based on the previous weeks of dengue incidence or the number of eggs present in the ovitraps. The analysis reveals that ovitrap data allows earlier prediction (four to six weeks) compared to dengue incidence itself (one week). Therefore, the results validate that the quantification of Aedes aegypti eggs can be valuable for the early planning of public health interventions.

Semi-Scavenging Poultry as Carriers of Avian Influenza Genes

Ducks are the natural reservoir of influenza A virus and the central host for the avian influenza virus (AIV) subtype H5N1, which is highly pathogenic. Semi-scavenging domestic ducks allow for the reemergence of new influenza subtypes which could be transmitted to humans. We collected 844 cloacal swabs from semi-scavenging ducks inhabiting seven migratory bird sanctuaries of Bangladesh for the molecular detection of avian influenza genes. We detected the matrix gene (M gene) using real-time RT-PCR (RT-qPCR). Subtyping of the AIV-positive samples was performed by RT-qPCR specific for H5, H7, and H9 genes. Out of 844 samples, 21 (2.488%) were positive for AIV. Subtyping of AIV positive samples (n = 21) revealed that nine samples (42.85%) were positive for the H9 subtype, five (23.80%) were positive for H5, and seven (33.33%) were negative for the three genes (H5, H7, and H9). We detected the same genes after propagating the virus in embryonated chicken eggs from positive samples. Semi-scavenging ducks could act as carriers of pathogenic AIV, including the less pathogenic H9 subtype. This can enhance the pathogenicity of the virus in ducks by reassortment. The large dataset presented in our study from seven areas should trigger further studies on AIV prevalence and ecology.

Modeling Eastern Russian High Arctic Geese (Anser fabalis, A. albifrons) during moult and brood rearing in the 'New Digital Arctic'

Many polar species and habitats are now affected by man-made global climate change and underlying infrastructure. These anthropogenic forces have resulted in clear implications and many significant changes in the arctic, leading to the emergence of new climate, habitats and other issues including digital online infrastructure representing a ‘New Artic’. Arctic grazers, like Eastern Russian migratory populations of Tundra Bean Goose Anser fabalis and Greater White-fronted Goose A. albifrons, are representative examples and they are affected along the entire flyway in East Asia, namely China, Japan and Korea. Here we present the best publicly-available long-term (24 years) digitized geographic information system (GIS) data for the breeding study area (East Yakutia and Chukotka) and its habitats with ISO-compliant metadata. Further, we used seven publicly available compiled Open Access GIS predictor layers to predict the distribution for these two species within the tundra habitats. Using BIG DATA we are able to improve on the ecological niche prediction inference for both species by focusing for the first time specifically on biological relevant population cohorts: post-breeding moulting non-breeders, as well as post-breeding parent birds with broods. To assure inference with certainty, we assessed it with 4 lines of evidence including alternative best-available open access field data from GBIF.org as well as occurrence data compiled from the literature. Despite incomplete data, we found a good model accuracy in support of our evidence for a robust inference of the species distributions. Our predictions indicate a strong publicly best-available relative index of occurrence (RIO). These results are based on the quantified ecological niche showing more realistic gradual occurrence patterns but which are not fully in agreement with the current strictly applied parsimonious flyway and species delineations. While our predictions are to be improved further, e.g. when synergetic data are made freely available, here we offer within data caveats the first open access model platform for fine-tuning and future predictions for this otherwise poorly represented region in times of a rapid changing industrialized ‘New Arctic’ with global repercussions.

A lossless compression method for multi-component medical images based on big data mining

In disease diagnosis, medical image plays an important part. Its lossless compression is pretty critical, which directly determines the requirement of local storage space and communication bandwidth of remote medical systems, so as to help the diagnosis and treatment of patients. There are two extraordinary properties related to medical images: lossless and similarity. How to take advantage of these two properties to reduce the information needed to represent an image is the key point of compression. In this paper, we employ the big data mining to set up the image codebook. That is, to find the basic components of images. We propose a soft compression algorithm for multi-component medical images, which can exactly reflect the fundamental structure of images. A general representation framework for image compression is also put forward and the results indicate that our developed soft compression algorithm can outperform the popular benchmarks PNG and JPEG2000 in terms of compression ratio.

Geospatial modelling to estimate the territory at risk of establishment of influenza type A in Mexico - An ecological study

The aim of this study was to estimate the territory at risk of establishment of influenza type A (EOITA) in Mexico, using geospatial models. A spatial database of 1973 outbreaks of influenza worldwide was used to develop risk models accounting for natural (natural threat), anthropic (man-made) and environmental (combination of the above) transmission. Then, a virus establishment risk model; an introduction model of influenza A developed in another study; and the three models mentioned were utilized using multi-criteria spatial evaluation supported by geographically weighted regression (GWR), receiver operating characteristic analysis and Moran's I. The results show that environmental risk was concentrated along the Gulf and Pacific coasts, the Yucatan Peninsula and southern Baja California. The identified risk for EOITA in Mexico were: 15.6% and 4.8%, by natural and anthropic risk, respectively, while 18.5% presented simultaneous environmental, natural and anthropic risk. Overall, 28.1% of localities in Mexico presented a High/High risk for the establishment of influenza type A (area under the curve=0.923, P<0.001; GWR, r2=0.840, P<0.001; Moran's I =0.79, P<0.001). Hence, these geospatial models were able to robustly estimate those areas susceptible to EOITA, where the results obtained show the relation between the geographical area and the different effects on health. The information obtained should help devising and directing strategies leading to efficient prevention and sound administration of both human and financial resources.

Using data mining techniques to fight and control epidemics: A scoping review

The main objective of this survey is to study the published articles to determine the most favorite data mining methods and gap of knowledge. Since the threat of pandemics has raised concerns for public health, data mining techniques were applied by researchers to reveal the hidden knowledge. Web of Science, Scopus, and PubMed databases were selected for systematic searches. Then, all of the retrieved articles were screened in the stepwise process according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses checklist to select appropriate articles. All of the results were analyzed and summarized based on some classifications. Out of 335 citations were retrieved, 50 articles were determined as eligible articles through a scoping review. The review results showed that the most favorite DM belonged to Natural language processing (22%) and the most commonly proposed approach was revealing disease characteristics (22%). Regarding diseases, the most addressed disease was COVID-19. The studies show a predominance of applying supervised learning techniques (90%). Concerning healthcare scopes, we found that infectious disease (36%) to be the most frequent, closely followed by epidemiology discipline. The most common software used in the studies was SPSS (22%) and R (20%). The results revealed that some valuable researches conducted by employing the capabilities of knowledge discovery methods to understand the unknown dimensions of diseases in pandemics. But most researches will need in terms of treatment and disease control.

Application of Artificial Intelligence-Based Regression Methods in the Problem of COVID-19 Spread Prediction: A Systematic Review

COVID-19 is one of the greatest challenges humanity has faced recently, forcing a change in the daily lives of billions of people worldwide. Therefore, many efforts have been made by researchers across the globe in the attempt of determining the models of COVID-19 spread. The objectives of this review are to analyze some of the open-access datasets mostly used in research in the field of COVID-19 regression modeling as well as present current literature based on Artificial Intelligence (AI) methods for regression tasks, like disease spread. Moreover, we discuss the applicability of Machine Learning (ML) and Evolutionary Computing (EC) methods that have focused on regressing epidemiology curves of COVID-19, and provide an overview of the usefulness of existing models in specific areas. An electronic literature search of the various databases was conducted to develop a comprehensive review of the latest AI-based approaches for modeling the spread of COVID-19. Finally, a conclusion is drawn from the observation of reviewed papers that AI-based algorithms have a clear application in COVID-19 epidemiological spread modeling and may be a crucial tool in the combat against coming pandemics.

Computational Method for Classification of Avian Influenza A Virus Using DNA Sequence Information and Physicochemical Properties

Accurate and fast characterization of the subtype sequences of Avian influenza A virus (AIAV) hemagglutinin (HA) and neuraminidase (NA) depends on expanding diagnostic services and is embedded in molecular epidemiological studies. A new approach for classifying the AIAV sequences of the HA and NA genes into subtypes using DNA sequence data and physicochemical properties is proposed. This method simply requires unaligned, full-length, or partial sequences of HA or NA DNA as input. It allows for quick and highly accurate assignments of HA sequences to subtypes H1–H16 and NA sequences to subtypes N1–N9. For feature extraction, k-gram, discrete wavelet transformation, and multivariate mutual information were used, and different classifiers were trained for prediction. Four different classifiers, Naïve Bayes, Support Vector Machine (SVM), K nearest neighbor (KNN), and Decision Tree, were compared using our feature selection method. This comparison is based on the 30% dataset separated from the original dataset for testing purposes. Among the four classifiers, Decision Tree was the best, and Precision, Recall, F1 score, and Accuracy were 0.9514, 0.9535, 0.9524, and 0.9571, respectively. Decision Tree had considerable improvements over the other three classifiers using our method. Results show that the proposed feature selection method, when trained with a Decision Tree classifier, gives the best results for accurate prediction of the AIAV subtype.