Feature mining and predictive model construction from severe trauma patient's data.

In management of severe trauma patients, trauma surgeons need to decide which patients are eligible for damage control. Such decision may be supported by utilizing models that predict the patient's outcome. The study described in this paper investigates the possibility to construct patient outcome prediction models from retrospective patient's data at the end of initial damage control surgery by using feature mining and machine learning techniques. As the data used comprises rather excessive number of features, special attention was paid to the problem of selecting only the most relevant features. We show that a small subset of features may carry enough information to construct reasonably accurate prognostic models. Furthermore, the techniques used in our study identified two factors, namely the pH value when admitted to ICU and the worst partial active thromboplastin time, to be of highest importance for prediction. This finding is pathophysiologically reasonable and represents two of three major problems with severe trauma patients, metabolic acidosis, hypothermia, and coagulopathy.

Preliminary testing of a just-in-time, user-defined values clarification exercise to aid lower literate women in making informed breast cancer treatment decisions.

OBJECTIVE: To report on the initial testing of a values clarification exercise utilizing a jewellery box within a computerized patient decision aid (CPtDA) designed to assist women in making a surgical breast cancer treatment decision. DESIGN: Pre-post design, with patients interviewed after diagnosis, and then after completing the CPtDA sometime later at their preoperative visit. SAMPLE: Fifty-one female patients, who are low literate and naïve computer users, newly diagnosed with early stage breast cancer from two urban public hospitals. INTERVENTION: A computerized decision aid that combines entertainment-education (edutainment) with enhanced (factual) content. An interactive jewellery box is featured to assist women in: (1) recording and reflecting over issues of concern with possible treatments, (2) deliberating over surgery decision, and (3) communicating with physician and significant others. OUTCOMES: Patients' use of the jewellery box to store issues during completion of the CPtDA, and perceived clarity of values in making a treatment decision, as measured by a low literacy version of the Decisional Conflict Scale (DCS). RESULTS: Over half of the participants utilized the jewellery box to store issues they found concerning about the treatments. On average, users flagged over 13 issues of concern with the treatments. Scores on the DCS Uncertainty and Feeling Unclear about Values subscales were lower after the intervention compared to before the decision was made. CONCLUSIONS: A values clarification exercise using an interactive jewellery box may be a promising method for promoting informed treatment decision making by low literacy breast cancer patients.