A disease network-based recommender system framework for predictive risk modelling of chronic diseases and their comorbidities

The prediction of chronic diseases and their comorbidities is an essential task in healthcare, aiming to predict patients’ future disease risk based on their previous medical records. The accumulation of administrative data has laid a solid foundation for applying deep learning approaches in healthcare. Existing studies focused on the patients’ characteristics such as gender, age and location to predict the risk of the different diseases. However, there are high dimensional, incomplete and noisy problems in the administrative data. In this research, using administrative health data, we implemented graph theory and content-based recommender system approaches to analyse and predict chronic diseases and their comorbidities. Firstly, we used bipartite graphs to represent the relationships between patients and diseases. Then, we projected this graph to a one-mode graph, namely ‘disease network’. After that, six recommender system models with patient features and network features were trained. The outputs of these models are the severity levels of diseases and the predicted diseases with rank. Finally, we evaluated the performance of these models against the same models without network features. The results demonstrated that the models with network features have lower prediction error and better performances for predicting chronic diseases and their latent comorbidities on large administrative data. Among these models, the graph convolution matrix completion model reveals the least amount of error and the best performance for prediction. Further, using a case study of a specific patient, we demonstrated the application of these models in predictive disease risk analysis. Thus, this study showed the potential application of the recommender system approaches to the health sector utilising administrative claim data, which could significantly contribute to healthcare services and stakeholders.

     

Integration of GIS and multicriteria decision analysis for urban aquaculture development in Bangladesh

Site selection is a key factor in any aquaculture operation, affecting both success and sustainability as well as solving land or water use conflicts. This study was conducted to identify suitable sites for carp farming development in urban water bodies (UWBs) of Chittagong, Bangladesh using Geographical Information Systems (GIS) based MultiCriteria Evaluation (MCE) of water, soil and infrastructure database. ASTER imagery and 14 thematic layers were analyzed with ENVI and GIS capabilities, and developed a series of GIS models to identify and prioritize the appropriate UWBs for carp farming. The study identified 487 UWBs occupying 362 ha and revealed 280 ha (77%) is the most suitable, 36 ha (10%) is moderately suitable and 46 ha (13%) is not suitable which was consistent with field verification. The results are encouraging for extension of carp culture and diversify the economic activities of the urban dwellers.     

Aloe vera gel: a new thickening agent for pigment printing

An attempt was made to print cotton fabric with pigments using a new thickening agent based on Aloe vera gel in combination with sodium alginate. The results were compared with the standard conventional printing recipe containing synthetic thickener, and a favourable effect of Aloe vera introduction was achieved. The results show that the properties of the printed fabric (sharpness, colour yield, overall fastness properties, softness, and water vapour transmission) are dependent on the percentage of Aloe vera gel in the thickener combination, the concentration of printing auxiliaries, and the curing conditions. Optimal printing properties were achieved by using a printing paste containing 80% Aloe vera/20% sodium alginate (700 g kg^?1), pigment (50 g kg^?1), binder (145 g kg^?1), fixer (10 g kg^?1), and ammonium sulfate (5 g kg^?1), followed by drying at 85 °C for 5 min and curing at 150 °C for 3 min. The sample printed with the new recipe showed superior rubbing fastness and handle properties, with a slightly lower colour yield, when compared with the sample printed with synthetic thickener. Finally, economic issues arising from synthetic thickener substitution are highlighted.     

A patient network-based machine learning model for disease prediction: The case of type 2 diabetes mellitus

Applied Intelligence - In recent years, the prevalence of chronic diseases such as type 2 diabetes mellitus (T2DM) has increased, bringing a heavy burden to healthcare systems. While regular...     

Belief‐rule‐based expert systems for evaluation of e‐government: a case study

Little knowledge exists on the impact and results associated with e‐government projects in many specific‐use domains. Therefore, it is necessary to evaluate the efficiency and effectiveness of e‐government systems. Because the development of e‐government is a continuous process of improvement, it requires continuous evaluation of the overall e‐government system as well as evaluation of its various dimensions such as determinants, characteristics and results. E‐government development is often complex, with multiple stakeholders, large user bases and complex goals. Consequently, even experts have difficulties in evaluating these systems, especially in an integrated and comprehensive way, as well as on an aggregate level. Expert systems are a candidate solution to evaluate such complex e‐government systems. However, it is difficult for expert systems to cope with uncertain evaluation data that are vague, inconsistent, highly subjective or in other ways, challenging to formalize. This paper presents an approach that can handle uncertainty in e‐government evaluation: the combination of Belief Rule Base knowledge representation and Evidential Reasoning. This approach is illustrated with a concrete prototype, known as the Belief Rule Based Expert System (BRBES) and implemented in the local e‐government of Bangladesh. The results have been compared with a recently developed method of evaluating e‐government, and it is demonstrated that the results of the BRBES are more accurate and reliable. The BRBES can be used to identify the factors that need to be improved to achieve the overall aim of an e‐government project. In addition, various ‘what if’ scenarios can be generated, and developers and managers can obtain a foretaste of the outcomes. Thus, the system can be used to facilitate decision‐making processes under uncertainty.     

Evolutionary dynamics of scientific collaboration networks: multi-levels and cross-time analysis

Several studies exist which use scientific literature for comparing scientific activities (e.g., productivity, and collaboration). In this study, using co-authorship data over the last 40 years, we present the evolutionary dynamics of multi level (i.e., individual, institutional and national) collaboration networks for exploring the emergence of collaborations in the research field of “steel structures”. The collaboration network of scientists in the field has been analyzed using author affiliations extracted from Scopus between 1970 and 2009. We have studied collaboration distribution networks at the micro-, meso- and macro-levels for the 40 years. We compared and analyzed a number of properties of these networks (i.e., density, centrality measures, the giant component and clustering coefficient) for presenting a longitudinal analysis and statistical validation of the evolutionary dynamics of “steel structures” collaboration networks. At all levels, the scientific collaborations network structures were central considering the closeness centralization while betweenness and degree centralization were much lower. In general networks density, connectedness, centralization and clustering coefficient were highest in marco-level and decreasing as the network size grow to the lowest in micro-level. We also find that the average distance between countries about two and institutes five and for authors eight meaning that only about eight steps are necessary to get from one randomly chosen author to another.     

An exploration of nitrate concentrations in groundwater aquifers of central-west region of Bangladesh

Groundwater and river water samples were collected from the study area to investigate the spatial distribution of nitrate (NO(3)(-)) in the central-west region of Bangladesh. The shallow and deep groundwater nitrate concentrations ranged from <0.10 to 75.12 and <0.10 to 40.78 mg/L, respectively. Major river water NO(3)(-) concentrations were ranged from 0.98 to 2.32 mg/L with an average of 1.8 mg/L. The average Cl(-)/NO(3)(-) ratio (4.9) of major river water has been considered as reference point to delineate denitrification processes. The alluvial fan, alluvial, deltaic and coastal deposits shallow groundwater having C1(-)/NO(3)(-) values less than that of the average river water value (4.9), suggested denitrification processes within the aquifers. On the other hand, denitrification processes are insignificant in the Pleistocene terraces area aquifers related to relatively higher concentrations of nitrate. Iron pyrite has been found as insignificant effect on denitrification.     

Removal of toxic metal ions by using composite cation-exchange material

Polyanilinezirconium(IV) arsenate composite cation exchange material was synthesized under different experimental conditions by the incorporation of polyaniline into the matrices of inorganic precipitate (zirconium(IV)arsenate). The experimental parameters such as concentration, mixing volume ratio, and pH were established for the synthesis of the material. Ion-exchange material that was synthesized at pH 1.0 showed an ion exchange capacity of 1.33 meq g⁻¹ for Na⁺ ions. The composite material exhibits improved ion-exchange capacity along with chemical and thermal stability. The exchanger was characterized based on FTIR, TGA, XRD, and SEM analysis. The X-ray diffraction study shows semi-crystalline nature of the material. The distribution coefficient studies (K_d) of metal ions on the material were performed in diverse solvent systems. Based on K_d values the material was found to be selective for Pb(II) and Hg(II) ions. Some analytically important binary separations of metal ions in synthetic mixtures viz. Ba²⁺-Pb²⁺, Pb²⁺-Ni²⁺, Cd²⁺-Hg²⁺, Ni²⁺-Hg²⁺, Zn²⁺-Pb²⁺, Ca²⁺-Bi³⁺, Al³⁺-Hg²⁺, and Ca²⁺-Pb²⁺ were achieved on the columns of polyanilinezirconium(IV) arsenate cation exchanger. © 2012 Wiley Periodicals, Inc. J Appl Polym Sci, 2012     

A research framework to explore knowledge evolution and scholarly quantification of collaborative research

Scientometrics - Most of the present research problems require the participation of scientists who can bring complementary skills. For this reason, research collaboration among scientists from...