A new survival status prediction system for severe trauma patients based on a multiple classifier system.

BACKGROUND AND OBJECTIVE: Severe trauma patients are those who have several injuries implying a death risk. Prediction systems consider the severity of these injuries to predict whether the patients are likely to survive or not. These systems allow one to objectively compare the quality of the emergency services of trauma centres across different hospitals. However, even the most accurate existing prediction systems are based on the usage of a single model. The aim of this paper is to combine several models to make the prediction, since this methodology usually improves the performance of single models. MATERIALS AND METHODS: The two currently used prediction systems by the Hospital of Navarre, which are based on logistic regression models, besides the C4.5 decision tree are combined to conform our proposed multiple classifier system. The quality of the method is tested using the major trauma registry of Navarre, which stores information of 462 trauma patients. A 10x10-fold cross-validation model is applied using as performance measures the specificity, sensitivity and the geometric mean between the two former ones. The results are supported by the usage of the Mann-Whitney's U statistical test. RESULTS: The proposed method provides 0.8908, 0.6703 and 0.7661 for sensitivity, specificity and geometric mean, respectively. It slightly decreases the sensitivity of the currently used systems but it notably increases the specificity, which implies a large enhancement on the geometric mean. The same behaviour is found when it is compared versus four classical ensemble approaches and the random forest. The statistical analysis supports the quality of our proposal, since the obtained p-values are less than 0.01 in all the cases. CONCLUSIONS: The obtained results show that the multiple classifier systems is the best choice among the considered methods to obtain a trade-off between sensitivity and specificity.

Major trauma registry of Navarre (Spain): the accuracy of different survival prediction models.

OBJECTIVE: To determine which factors predict death among trauma patients who are alive on arrival at hospital. METHODS: Design prospective cohort study method. Data were collected on 378 trauma patients who were initially delivered by the emergency medical services of Navarre (Spain) with multiple injuries with a new injury severity score of 15 or more in 2011-2012. These data related to age, gender, presence of premorbid conditions, abbreviated injury score, injury severity score, new injury severity score (NISS), revised trauma score (RTS), and prehospital and hospital response times. Bivariate analysis was used to show the association between each variable and time until death. Mortality prediction was modeled using logistic regression analysis. RESULTS: The variables related to the end result were the age of the patient, associated comorbidity, NISS, and hospital RTS. Two models were formulated: in one, the variables used were quantitative, while in the other model these variables were converted into dichotomous qualitative variables. The predictive capability of the two models was compared with the trauma and injury severity score using the area under the curve. The predictive capacities of the three models had areas under the curve of 0.93, 0.88, and 0.87. The response times of the Navarre emergency services system, measured as the sum of the time taken to reach the hospital (median time of 65 min), formulate computed tomography (46 min), and perform crucial surgery (115 min), when required, were not taken into account. CONCLUSION: Age, premorbid conditions, hospital RTS, and NISS are significant predictors of death after trauma. The time intervals between the accident and arrival at the hospital, arrival at the hospital and the first computed tomography scan or the first crucial emergency intervention, do not appear to affect the risk of death.

Extravasation of radiographic contrast material and compartment syndrome in the hand: a case report.

Radiocontrast agents are a type of medical contrast material used to improve the visibility of internal bodily structures in X-ray based imaging techniques such as computed tomography (CT) or radiography. Radiocontrast agents are typically iodine or barium compounds.Extravasation of contrast is a possible complication of imaging studies performed with contrasts. Most extravasations cause minimal swelling or erythema, however, skin necrosis, ulceration and compartment syndrome may occur with extravasation of large volumes of contrast. A case report is presented in which significant extravasation of contrast was caused while injecting the contrast intravenously into the back of the hand of a 50 year old patient during computed tomography. The patient was undergoing chemotherapy. The patient developed a compartment syndrome and a fasciotomy was required. Treatment options are outlined and emphasis is made on prevention of this iatrogenic complication.Some of the preventive measures to avoid these complications include use of non-ionic contrast (low osmolarity), careful choice of the site of intravenous administration, and close monitoring of the patient during injection of contrast to minimize or prevent extravasation injuries. Clear information to patients and prompt recognition of the complication can allow for other non-surgical treatment options than the one required in this case.

[Quality and accreditation of emergency departments]. / Calidad y acreditación de los servicios de urgencias.

The concept of quality has been linked to the health care world since the remote past and is one of the strategic elements on which the transformation and improvement of modern health systems is based. Study of quality in health care involves different approaches given that it holds different meanings for patients, professionals and managers. In recent years formal systems of quality management have been progressively introduced, such as certification according to the ISO-9000 Norms, the system of accreditation of the Joint Commission on Accreditation of Healthcare Organizations (JCAHO) and the European Model of Excellence (EFQM). Management by processes is another tool directed towards achieving the aims of total quality in the care process and tackling health problems centred on the patient. Quality health care involves evidence based clinical practice; based on current scientific knowledge, following clinical practice guidelines based on evidence, with the least risk for patients and relatives, involving greater efficiency and greater satisfaction for users and health personnel. The accreditation of health care centres and services is, without doubt, the most widely accepted method for guaranteeing quality. It can be defined as the process of external evaluation to which a health organisation is subjected, based on a review of certain accepted criteria and standards, whose fulfillment demonstrates that that centre is developing its functions within parameters of quality that at least approach excellence.