Esperienza di analisi testuale di documentazione clinica e di flussi informativi sanitari, di utilità nella ricerca epidemiologica e per indagare la qualità dell'assistenza.

This study finds reason in the now wide availability of clinical documentation stored in electronic form to track the patient's health status during his care path or for sending information to other institutions on the activities carried out for administrative purposes. The diffusion of these methods now makes available many biomedical collections of electronic data, easily accessible at low cost that can be used for research purposes in the field of observational epidemiological studies, in analogy with what was historically already practiced in studies based on the reviewing of medical records. However, since these collections are not organized according to specific survey schemes, they sometimes do not allow the index events to be discriminated with the necessary reliability between one source and another. It has always been believed that the critical re-reading of texts can partially help these informative shortcomings with the aim of bringing back - according to possibility - the words or segments contained in the texts, to statistically analyzable categories. The recent transfer of these collections from paper to electronic forms opens the possibility of carrying out this process automatically, reducing time and costs of the process and perhaps increasing its reliability. It is proposed to address the problem, showing study criteria and an example of analysis ased on an empirical experience, consistent with the needs of a biomedical context.