Evaluation of machine learning algorithms for renin-angiotensin-aldosterone system inhibitors associated renal adverse event prediction.

BACKGROUND: Renin-angiotensin-aldosterone system inhibitors (RAASi) are commonly used medications. Renal adverse events associated with RAASi are hyperkalemia and acute kidney injury. We aimed to evaluate the performance of machine learning (ML) algorithms in order to define event associated features and predict RAASi associated renal adverse events. MATERIALS AND METHODS: Data of patients recruited from five internal medicine and cardiology outpatient clinics were evaluated retrospectively. Clinical, laboratory, and medication data were acquired via electronic medical records. Dataset balancing and feature selection for machine learning algorithms were performed. Random forest (RF), k-nearest neighbor (kNN), naïve Bayes (NB), extreme gradient boosting (xGB), support vector machine (SVM), neural network (NN), and logistic regression (LR) were used to create a prediction model. RESULTS: 409 patients were included, and 50 renal adverse events occurred. The most important features predicting the renal adverse events were the index K and glucose levels, as well as having uncontrolled diabetes mellitus. Thiazides reduced RAASi associated hyperkalemia. kNN, RF, xGB and NN algorithms have the highest and similar AUC (≥ 98%), recall (≥ 94%), specifity (≥ 97%), precision (≥ 92%), accuracy (≥ 96%) and F1 statistics (≥ 94%) performance metrics for prediction. CONCLUSION: RAASi associated renal adverse events can be predicted prior to medication initiation by machine learning algorithms. Further prospective studies with large patient numbers are needed to create scoring systems as well as for their validation.

Comparison of warm fluid and cold fluid resuscitation during uncontrolled hemorrhagic shock model in rats.

BACKGROUND: This study was designed to compare the effects of resuscitation with cold and warm fluid on survival time, rate and volume of hemorrhage, hemodynamics, hypothermia, coagulopathy, acid-base balance, hematocrit, lactate, and base deficit during uncontrolled hemorrhagic shock (HS) model in rats. METHODS: HS model was created with splenic vascular and parenchymal injury in 29 rats under ketamine and xylazine anesthesia. Thirty minutes after the hemorrhage, the rats were randomized to receive 14.5 mL/kg 0.9% sodium chloride solution at either 24ºC (Group 1; n=9) or 4ºC (Group 2; n=10) for 20 minutes. Groups 1 and 2 were compared with group that did not receive fluid (Group 3; n=10). Statistical data were represented as mean±SD. SPSS for Windows, Version 15.0 (SPSS, Inc., Chicago, IL, USA) software, Bonferroni-adjusted Mann-Whitney U test and Kaplan-Meier procedure were used to perform statistical data analysis. P value of ≤0.05 was considered statistically significant. RESULTS: Cold fluid resuscitation decreased survival time due to increased rate and volume of hemorrhage, acidosis, hypothermia, lactate, and base deficit and decreased blood pressure and hematocrit. CONCLUSION: There is a great need for further experimental and clinical trials on fluid resuscitation in trauma in order to define which fluid should be administered, temperature of the fluid, quantity to be delivered, and duration.

The Relation Between No-Reflow Phenomenon and Complete Blood Count Parameters.

The no-reflow (NR) phenomenon represents an acute reduction in coronary blood flow without coronary vessel obstruction, coronary vessel dissection, spasm, or thrombosis. No reflow is an important complication among patients with acute ST-segment elevation myocardial infarction (STEMI) undergoing primary percutaneous coronary intervention (pPCI). The complete blood count (CBC) is one of the most frequently ordered laboratory tests in clinical practice. Various studies have evaluated the performance of CBC parameters to predict disease severity and mortality risk. Automated cell counters are routinely available in many clinical laboratories and can be used to determine red blood cell distrubiton width (RDW), platetecrit, platelet count, and and some ratios like the neutrophil-lymphocyte ratio and RDW-platelet ratio. These hematological markers have been reported to be independent predictors of impaired angiographic reperfusion and long-term mortality among patients with STEMI undergoing pPCI. In this context, we reviewed the role of admission CBC parameters for the prediction of NR in patients with STEMI undergoing pPCI.

Obstrucción coronaria durante el implante percutáneo de válvula aórtica: ¿relacionada con calcificación o con trombo? / Coronary obstruction during transcatheter aortic valve replacement: related to calcification or thrombus?

No disponible