Injury Surveillance Systems based on traditional hospital records or clinical data have the advantage of being a well established, highly reliable source of information for making an active surveillance on specific injuries, like choking in children. However, they suffer the drawback of delays in making data available to the analysis, due to inefficiencies in data collection procedures. In this sense, the integration of clinical based registries with unconven-tional data sources like newspaper articles has the advan-tage of making the system more useful for early alerting. Usage of such sources is difficult since information is only available in the form of free natural-language documents rather than structured databases as required by traditional data mining techniques. Information Extraction (IE) addresses the problem of transforming a corpus of textual documents into a more structured database. In this paper, on a corpora of Italian newspapers articles related to choking in children due to ingestion/inhalation of foreign body we compared the performance of three IE algorithms-(a) a classical rule based system which requires a manual annotation of the rules; (ii) a rule based system which allows for the automatic building of rules; (b) a machine learning method based on Support Vector Machine. Although some useful indications are extracted from the newspaper clippings, this approach is at the time far from being routinely implemented for injury surveillance pur-poses.

This paper describes the Safe Community concept and how communities aspired to safety through a structured, collaborative approach rather than a community that is already perfectly safe. The Safe Community movement started in Sweden at the end of the 1980s and was based on community-based injury prevention activities. Safe Communities are the communities that meet a set of 12 criteria (later changed to six indicators) set out by the WHO Collaborating Centre (WHO CC) on Community Safety Promotion at Karolinska Institutet in Stockholm. The communities may apply to the WHO CC to be designated as an official member of the WHO International Safe Community Network. To date, 83 communities around the world have been designated as members of the Safe Community Network, ranging in population from 1000 to nearly 2 million. Lidkjöping in Sweden was the first designated safe community in 1989 and Rapla in Estonia was the last, designated in October 2004. The movement recognizes that it is the people who not only live, learn, work and play in a community but also best understand their community's specific problems, needs, assets and capacities. Their involvement and commitment are critical factors in identifying and mobilizing resources so as to create an effective, comprehensive and coordinated community-based action on unintentional and intentional injuries.

Home injuries together, with road traffic accidents, are estimated to be the third cause of death in Italy (Arokiasamy and Krishnan 1994). However, as in most other countries, in Italy there is a lack of information on home injuries and on how differences in geographical patterns may influence the scope and magnitude of this phenomenon. By analysing a multipurpose large survey (Multiscopo) carried out annually, geographical heterogeneity in home injuries incidence rate can be investigated. The aim of this study is the assessment of possible differences in geographical patterns among the Italian regions making use of a re-analysis of Multiscopo home injury data. The study results show that Italian regions differ greatly in the number of home injuries. The geographical heterogeneity may be due to the unemployment rate and the incidence of poverty that is greater in the Southern and Insular regions than in other zones. Other socio-economic variables such as alcohol consumption can increase the risk of injury in the home. To prevent them it could be useful to organize campaigns aimed at increasing the awareness among people about this problem.

No abstract

No abstract