No abstract

Survival prediction of poly-trauma patients measure the quality of emergency services by comparing their predictions with the real outcomes. The aim of this paper is to tackle this problem applying C4.5 since it achieves accurate results and it provides interpretable models. Furthermore, we use sampling techniques because, among the 378 patients treated at the Hospital of Navarre, the number of survivals excels that of deaths. Logistic regressions are used in the comparison, since they are an standard in this domain.

Overall, 40 % of the patients who met the inclusion criteria of the TR were not included in the registry. Our results can be generalized to other trauma records based on Utstein style, because we think probably that this fact is also happening in other databases.

No abstract

Oncology patients do not form a large proportion within the overall figures of an emergency service, but their clinical characteristics mean that attending to them is often complex. The elaboration of a complete clinical history, specifying the characteristics and stage of the tumoural disease, is a basic weapon for taking decisions when an emergency arises. According to the data from our centre, oncology patients account for 5% of the total of emergency cases. The most frequent type of tumour that we deal with is pulmonary, followed by breast and colon. It is often the case that these patients come to the emergency department several times in the same month and pain is the most frequent reason for consultation, although it is normal for them to mention several causes on each occasion. In a high percentage of cases the reason for the consultation is related to the disease itself, but on as many as 35% of occasions it is an intercurrent pathology. The index of admissions is high (around 50%), especially if the patient has come for a reason related to the disease. In global terms, they account for 14% of total admissions from emergencies.