The influence of vancomycin on renal functions, the predictors and associated factors for nephrotoxicity

Prediction of Acute Kidney Injury in Intracerebral Hemorrhage Patients Using Machine Learning

Background

Acute kidney injury (AKI) is prevalent in patients with intracerebral hemorrhage (ICH) and is associated with mortality. This study aimed to verify the predictive accuracy of different machine learning algorithms for AKI in patients with ICH using a large dataset.

Methods

A total of 1366 ICH patients received treatments between 2001 and 2012 from the Medical Information Mart for Intensive Care-III (MIMIC-III) database were identified based on the ICD-9 code: 431. The main outcome of AKI during hospitalizations was confirmed based on the KDIGO criteria. Overall, ICH patients were randomly divided into the training cohort and validation cohort with the ratio of 7:3. Six machine learning algorithms including extreme gradient boosting, logistic, light gradient boosting machine, random forest, adaptive boosting, support vector machine were trained in the training cohort with the 5-fold cross-validation method to predict the AKI. The predictive accuracy of those algorithms was compared by area under the receiver operating characteristics curve (AUC).

Results

A total of 1213 ICH patients were included with the incidence of AKI being 29.3%. The incidence of AKI was 29.3% among the 1213 patients with ICH. The AKI group had higher 30-day mortality (p<0.001), longer ICU stay (p<0.001), and longer hospital stay (p<0.001). Among the six machine learning algorithms, the random forest performed the best in predicting AKI in both the training cohort (AUC=1.000) and the validation cohort (AUC=0.698). The top five features in the random forest algorithm-based model were platelets, serum creatinine, vancomycin, hemoglobin, and hematocrit.

Conclusion

The random forest algorithm-based predictive model we developed incorporating important features, including platelet count, serum creatinine level, vancomycin level, hemoglobin level, and hematocrit level, performed the best in predicting AKI among patients with ICH.

Antimicrobial Synergistic Effects of Linezolid and Vancomycin with a Small Synthesized 2-Mercaptobenzothiazole Derivative: A Challenge for MRSA Solving

Methicillin-resistant Staphylococcus aureus (MRSA) emerged as one of the leading causes of persistent human infections and makes it difficult to treat bacteremia, especially with biofilm formation. In this work, we investigated the in vitro synergism between Linezolid (LNZ) and Vancomycin (VAN) with a 2-mercaptobenzothiazole derivative, resulting in a new small-molecule antibacterial compound that we named BTZ2e, on several clinical MRSA, MRSE (methicillin-resistant Staphylococcus epidermidis) and control (ATCC Collection) strains in their planktonic and biofilms cultures. The broth microdilution method evaluated the susceptibility of planktonic cells to each investigated antibiotic combined with BTZ2e. The biofilm's metabolic activity was studied with the XTT reduction assay. As a result, in this study, biofilm formation was significantly suppressed by the BTZ2e treatment. In terms of minimal biofilm inhibitory concentration (MBIC), BTZ2e revealed an MBIC50 value of 32 μg/mL against methicillin-susceptible S. aureus (MSSA) and 16 μg/mL against methicillin-resistant S. aureus ATCC 43300 biofilms. An inhibition range of 32 μg/mL and 256 μg/mL was registered for the clinical isolates. Interestingly, a synergistic effect (FICI ≤ 0.5) was encountered for the combination of BTZ2e with LNZ and VAN on several planktonic and sessile strains. In particular, the best result against planktonic cells emerged as a result of the synergistic association between LNZ and BTZ2e, while against sessile cells, the best synergistic association resulted from VAN and BTZ2e. The consistent results indicate BTZ2e as a promising adjuvant against multi-resistant strains such as MRSA and MRSE.