Linezolid induced thrombocytopenia in critically ill patients: Risk factors and development of a machine learning-based prediction model.

INTRODUCTION: Linezolid is an antimicrobial with broad activity against Gram-positive bacteria. Thrombocytopenia is one of its most common side effects often leading to severe complications. The aim of this study is to identify factors related with development of this condition in critically ill patients and to develop and evaluate a predictive machine learning-based model considering easy-to-obtain clinical variables. METHODS: Data was obtained from the Medical Information Mart for Intensive Care III. Patients who received linezolid for over three days were considered, excluding those under 18 years and/or lacking laboratory data. Thrombocytopenia was considered as a platelet decrease of at least 50% from baseline. RESULTS: Three hundred and twenty patients met inclusion criteria of which 63 developed thrombocytopenia and presented significant greater duration of treatment, aspartate-aminotransferase, bilirubin and international normalized ratio; and lower renal clearance and platelet count at baseline. Thrombocytopenia development was associated with a worse outcome (30 days mortality [OR: 2.77; CI95%: 1.87-5.89; P < .001], 60 days mortality [OR: 3.56; CI95%: 2.18-7.26; P < .001]). Thrombocytopenia was also correlated with higher length of hospital stays (35.56 [20.40-52.99] vs 22.69 [10.05-38.61]; P < .001). Median time until this anomaly was of 23 days (CI95%:19.0-NE). Two multivariate models were performed. Accuracy, sensitivity, specificity and AUROC obtained in the best of them were of 0.75, 0.78, 0.62 and 0.80, respectively. CONCLUSION: Linezolid associated thrombocytopenia entails greater mortality rates and hospital stays. Although the proposed predictive model has to be subsequently validated in a real clinical setting, its application could identify patients at risk and establish screening and surveillance strategies.

Comparative Study of Different Classification Models in Renal-Cell Carcinoma.

The aim of this study was to compare the Memorial Sloan-Kettering Cancer Center (MSKCC) and the Cleveland Clinic Foundation (CCF) models of classification of aRCC patients. In addition, the model developed from the pivotal trial of temsirolimus and those proposed by Motzer et al. in 2004, Escudier et al., Heng et al., Choueiri et al. and Bamias et al. were examined. An observational, retrospective study of patients starting first-line systemic therapy was conducted between 2008 and 2011. The variables used to evaluate the classification models were median overall survival (mOS) and median progression-free survival (mPFS). The comparison of different classification models was performed by comparing the area under the ROC (Receiver Operating Characteristic) curve (AUC) for time-dependent variables proposed by Heagerty. Eighty-eight patients were included. When the different models were compared, it was found that although based on the mOS, the Escudier model had better short-term (1-year) prognostic value, followed by the Heng model; in the long term, the models that presented a higher prognosis capacity were the Hudes and CCF models, closely followed by the Heng model. In addition, the Heng model had a slightly higher predictive ability than the other models. Based on the results, and in line with the European society for medical oncology (ESMO) guidelines, it appears that the model of Heng could be the best model to classify patients with aRCC and combines good short- and long-term prognostics while possessing better predictive ability and a more equal distribution of patients.

Cost-effectiveness analysis of the bevacizumab-irinotecan regimen in the treatment of primary glioblastoma multiforme recurrences.

The purpose of the present study was to calculate the cost-effectiveness of the inclusion of the bevacizumab (BVZ) + irinotecan (CPT-11) regimen in the second-line of treatment for primary glioblastoma multiforme. A retrospective cohort study with a control group was performed in which the cost-effectiveness of a course of chemotherapy was calculated based on survival time and the incremental cost between the two lines of treatment. A total of 77 patients were included, 36 of who formed the BVZ/CPT-11 cohort. The median survival time for the non-BVZ control cohort was 13.23 months [95% confidence interval (CI), 11.79-14.68], while for the BVZ/CPT-11 treatment cohort, the median survival time was 17.63 months (95% CI, 15.38-19.89). Overall, each year of life gained for each patient treated with BVZ/CPT-11 would cost €46,401.99. These results demonstrate the effectiveness of the BVZ/CPT-11 combination, but its incremental cost compared with other lines of treatment or the best care available does not appear to be acceptable for public health systems in the current situation of budgetary adjustments.