Summary: Nowadays, document classification has become an interesting research field. Partly, this is due to the increasing availability of biomedical information in digital form which is necessary to catalogue and organize. In this context, machine learning techniques are usually applied to text classification by using a general inductive process that automatically builds a text classifier from a set of pre-classified documents. Related with this domain, imbalanced data is a well-known problem in many practical applications of knowledge discovery and its effects on the performance of standard classifiers are remarkable. In this paper, we investigate the application of a Bayesian Network (BN) model for the triage of documents, which are represented by the association of different MeSH terms. Our results show that BNs are adequate for describing conditional independencies between MeSH terms and that MeSH ontology is a valuable resource for representing Medline documents at different abstraction levels. Moreover, we perform an extensive experimental evaluation to investigate if the classification of Medline documents using a BN classifier poses additional challenges when dealing with class-imbalanced prediction. The evaluation involves two methods, under-sampling and cost-sensitive learning. We conclude that BN classifier is sensitive to both balancing strategies and existing techniques can improve its overall performance.

A novel ecosystem to promote the physical, emotional and psychic health and well-being of the elderly is presented. Our proposal was designed to add several services developed to meet the needs of the senior population, namely services to improve social inclusion and increase contribution to society. Moreover, the solution monitors the vital signs of elderly individuals, as well as environmental parameters and behavior patterns, in order to seek eminent danger situations and predict potential hazardous issues, acting in accordance with the various alert levels specified for each individual. The platform was tested by seniors in a real scenario. The experimental results demonstrated that the proposed ecosystem was well accepted and is easy to use by seniors.

Black alder (Alnus glutinosa (L.) Gaertn.) is a species of tree widespread along Europe and belongs to mixed hardwood forests. In urban environments, the tree is usually located along watercourses, as is the case in the city of Ourense. This taxon belongs to the betulaceae family, so it has a high allergenic potential in sensitive people. Due to the high allergenic capacity of this pollen type and the increase in global temperature produced by climate change, which induces a greater allergenicity, the present study proposes the implementation of a Machine Learning (ML) model capable of accurately predicting high-risk periods for allergies among sensitive people. The study was carried out in the city of Ourense for 28 years and pollen data were collected by means of the Hirst trap model Lanzoni VPPS-2000. During the same period, meteorological data were obtained from the meteorological station of METEOGALICIA in Ourense. We observed that Alnus airborne pollen was present in the study area during winter months, mainly in January and February. We found statistically significant trends for the end of the main pollen season with a lag trend of 0.68 days per year, and an increase in the annual pollen integral of 112 pollen grains per year and approximately 12 pollen grains/m³ per year during the pollen peak. A Spearman correlation test was carried out in order to select the variables for the ML model. The best ML model was Random Forest, which was able to detect those days with medium and high labels.

Nowadays, document classification has become an interesting research field. Partly, this is due to the increasing availability of biomedical information in digital form which is necessary to catalogue and organize. In this context, machine learning techniques are usually applied to text classification by using a general inductive process that automatically builds a text classifier from a set of pre-classified documents. Related with this domain, imbalanced data is a well-known problem in many practical applications of knowledge discovery and its effects on the performance of standard classifiers are remarkable. In this paper, we investigate the application of a Bayesian Network (BN) model for the triage of documents, which are represented by the association of different MeSH terms. Our results show that BNs are adequate for describing conditional independencies between MeSH terms and that MeSH ontology is a valuable resource for representing Medline documents at different abstraction levels. Moreover, we perform an extensive experimental evaluation to investigate if the classification of Medline documents using a BN classifier poses additional challenges when dealing with class-imbalanced prediction. The evaluation involves two methods, under-sampling and cost-sensitive learning. We conclude that BN classifier is sensitive to both balancing strategies and existing techniques can improve its overall performance.