Construcción de recursos de texto para la identificación automática de información clínica en narrativas no estructuradas / Construction of text resources for automatic identification of clinical information in unstructured narratives

Background: A significant proportion of the clinical record is in free text format, making it difficult to extract key information and make secondary use of patient data. Automatic detection of information within narratives initially requires humans, following specific protocols and rules, to identify medical entities of interest. Aim: To build a linguistic resource of annotated medical entities on texts produced in Chilean hospitals. Material and Methods: A clinical corpus was constructed using 150 referrals in public hospitals. Three annotators identified six medical entities: clinical findings, diagnoses, body parts, medications, abbreviations, and family members. An annotation scheme was designed, and an iterative approach to train the annotators was applied. The F1-Score metric was used to assess the progress of the annotator's agreement during their training. Results: An average F1-Score of 0.73 was observed at the beginning of the project. After the training period, it increased to 0.87. Annotation of clinical findings and body parts showed significant discrepancy, while abbreviations, medications, and family members showed high agreement. Conclusions: A linguistic resource with annotated medical entities on texts produced in Chilean hospitals was built and made available, working with annotators related to medicine. The iterative annotation approach allowed us to improve performance metrics. The corpus and annotation protocols will be released to the research community.

Concentrations of organic contaminants in industrial and municipal bioresources recycled in agriculture in the UK.

Many types of bioresource materials are beneficially recycled in agriculture for soil improvement and as alternative bedding materials for livestock, but they also potentially transfer contaminants into plant and animal foods. Representative types of industrial and municipal bioresources were selected to assess the extent of organic chemical contamination, including: (i) land applied materials: treated sewage sludge (biosolids), meat and bone meal ash (MBMA), poultry litter ash (PLA), paper sludge ash (PSA) and compost-like-output (CLO), and (ii) bedding materials: recycled waste wood (RWW), dried paper sludge (DPS), paper sludge ash (PSA) and shredded cardboard. The materials generally contained lower concentrations of polychlorinated dibenzo-p-dioxins/dibenzofurans (PCDD/Fs) and dioxin-like polychlorinated biphenyls (PCBs) relative to earlier reports, indicating the decline in environmental emissions of these established contaminants. However, concentrations of polycyclic aromatic hydrocarbons (PAHs) remain elevated in biosolids samples from urban catchments. Polybrominated dibenzo-p-dioxins/dibenzofurans (PBDD/Fs) were present in larger amounts in biosolids and CLO compared to their chlorinated counterparts and hence are of potentially greater significance in contemporary materials. The presence of non-ortho-polychlorinated biphenyls (PCBs) in DPS was probably due to non-legacy sources of PCBs in paper production. Flame retardent chemicals were one of the most significant and extensive groups of contaminants found in the bioresource materials. Decabromodiphenylether (deca-BDE) was the most abundant polybrominated diphenyl ether (PBDE) and may explain the formation and high concentrations of PBDD/Fs detected. Emerging flame retardant compounds, including: decabromodiphenylethane (DBDPE) and organophosphate flame retardants (OPFRs), were also detected in several of the materials. The profile of perfluoroalkyl substances (PFAS) depended on the type of waste category; perfluoroundecanoic acid (PFUnDA) was the most significant PFAS for DPS, whereas perfluorooctane sulfonate (PFOS) was dominant in biosolids and CLO. The concentrations of polychlorinated alkanes (PCAs) and di-2-ethylhexyl phthalate (DEHP) were generally much larger than the other contaminants measured, indicating that there are major anthropogenic sources of these potentially hazardous chemicals entering the environment. The study results suggest that continued vigilance is required to control emissions and sources of these contaminants to support the beneficial use of secondary bioresource materials.

School related factors and 1yr change in physical activity amongst 9-11 year old English schoolchildren.

BACKGROUND: Activity levels are known to decline with age and there is growing evidence of associations between the school environment and physical activity. In this study we investigated how objectively measured one-year changes in physical activity may be associated with school-related factors in 9- to 10-year-old British children. METHODS: Data were analysed from 839 children attending 89 schools in the SPEEDY (Sport, Physical Activity, and Eating behaviours: Environmental Determinants in Young People) study. Outcomes variables were one year changes in objectively measured sedentary, moderate, and vigorous physical activity, with baseline measures taken when the children were 9-10 years old. School characteristics hypothesised to be associated with change in physical activity were identified from questionnaires, grounds audits, and computer mapping. Associations were examined using simple and multivariable multilevel regression models for both school (9 am - 3 pm) and travel (8-9 am and 3-4 pm) time. RESULTS: Significant associations during school time included the length of the morning break which was found to be supportive of moderate (ß coefficient: 0.68 [p: 0.003]) and vigorous (ß coefficient: 0.52 [p: 0.002]) activities and helps to prevent adverse changes in sedentary time (ß coefficient: -2.52 [p: 0.001]). During travel time, positive associations were found between the presence of safe places to cross roads around the school and changes in moderate (ß coefficient: 0.83 [p:0.022]) and vigorous (ß coefficient: 0.56 [p:0.001]) activity, as well as sedentary time (ß coefficient: -1.61 [p:0.005]). CONCLUSION: This study suggests that having longer morning school breaks and providing road safety features such as cycling infrastructure, a crossing guard, and safe places for children to cross the road may have a role to play in supporting the maintenance of moderate and vigorous activity behaviours, and preventing the development of sedentary behaviours in children.