Development of a predictive model for integrated medical and long-term care resource consumption based on health behaviour: application of healthcare big data of patients with circulatory diseases

Trends and status in resources security, ecological stability, and sustainable development research: a systematic analysis

Resources are essential for human survival and development, and resource security occupies an important position in national security. With the increasing resource shortage problem, ecological stability is facing severe challenges. All countries are actively seeking new sustainable development ways to deal with various issues and shocks caused by the shortage of resources. This study aims to systematically and comprehensively evaluate the knowledge structure, research hotspots, and resource security evolution trends. Based on the number of 6391 articles retrieved from the Web of Science database from 1990 to 2021, this article carried out a visual analysis of global resource security research from the perspectives of scientific output characteristics, keywords, and highly cited literature scientific collaboration networks and hotspot emergence analysis. The research results show that after humans have experienced new public safety incidents, their understanding of resource security and sustainable development has risen to a new height. The number of relevant documents is increasing rapidly. At present, the research on resource security is still dominated by developed countries in Europe and America. This study finds that "food supply chain," "water availability," and "soil resources suitability" are the frontiers and hotspots in the field of resource security. Besides, "biodiversity," "mineral resource security," "medical and health resources" are important topics and directions of current research. This study provides a theoretical basis for scholars to explore the future research direction and practice of resource security, to achieve ecological stability and sustainable development.

Identification and Prediction of Chronic Diseases Using Machine Learning Approach

Nowadays, humans face various diseases due to the current environmental condition and their living habits. The identification and prediction of such diseases at their earlier stages are much important, so as to prevent the extremity of it. It is difficult for doctors to manually identify the diseases accurately most of the time. The goal of this paper is to identify and predict the patients with more common chronic illnesses. This could be achieved by using a cutting-edge machine learning technique to ensure that this categorization reliably identifies persons with chronic diseases. The prediction of diseases is also a challenging task. Hence, data mining plays a critical role in disease prediction. The proposed system offers a broad disease prognosis based on patient's symptoms by using the machine learning algorithms such as convolutional neural network (CNN) for automatic feature extraction and disease prediction and K-nearest neighbor (KNN) for distance calculation to find the exact match in the data set and the final disease prediction outcome. A collection of disease symptoms has been performed for the preparation of the data set along with the person's living habits, and details related to doctor consultations are taken into account in this general disease prediction. Finally, a comparative study of the proposed system with various algorithms such as Naïve Bayes, decision tree, and logistic regression has been demonstrated in this paper.

Individualised prognosis for risk of developing abdominal obesity in the paediatric population

AIMS

To develop and validate risk scores for predicting abdominal obesity in South American children and adolescents based on extrinsic and intrinsic variables.

METHODS

Children (n = 358) and adolescents (n = 369) from seven South American cities from the South American Youth Cardiovascular and Environmental (SAYCARE) Study. The primary outcome was abdominal obesity. Potential predictors were based on sociodemographic, maternal, environmental, and behavioural factors and nutritional status. In multilevel logistic models, associated variables were tested to build the scores, which were internally validated.

RESULTS

We identified 120 children and 98 adolescents who were abdominally obese. We found at least five variables associated with the outcome in children with unacceptable predictive capacity. However, in adolescents, we found that biological sex, age, maternal body mass index (BMI), active commuting by bike, soft drink consumption (for risk score A), and weight (for score B) can predict abdominal obesity. Both scores, A and B, showed acceptable performance in the ROC curve [areas under curve: 0.70 (95% CI: 0.56-0.82) and 0.95 (95% CI: 0.89-1.00), respectively].

CONCLUSION

The SAYCARE risk scores present accurate, individualised estimates for identifying adolescents who are at risk of developing abdominal obesity. However, these have not been externally validated.