Browsing by Author "Sener, Yusuf Ziya"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Baseline Sodium-Glucose Cotransporter-2 Inhibitor Use Strongly Attenuates the Uric Acid-Elevating Effect of Thiazide Exposure
    (2023) Guven, Alper Tuna; Ozdede, Murat; Sener, Yusuf Ziya; 0000-0002-6310-4240
    Objective: Thiazide diuretics are among the major anti-hypertensive medications. However, their hyperuricemic effect restricts their use in patients with gout. Sodium glucose co-transporter 2 inhibitor (SGLT-2i) initiation lowers serum uric acid (SUA) levels. It is not known whether existing SGLT-2i use affects the SUA increasing effect of thiazides. Methods: Post-hoc data analysis of our published study was conducted. Hypertensive patients who were initiated on thiazide diuretics or whose dose escalated were included (thiazide exposure). Demographic, clinical, and laboratory data were acquired via an electronic database. Patients were grouped according to SGLT-2i presence at the time of thiazide exposure. Since the number of SGLT-2i users was low, bootstrapping via simple random sampling was performed. Results: 144 patients were included in the study, of whom 13 were on SGLT-2i. Initial sample analysis revealed that while baseline SUA levels were similar between groups, SUA change was significantly lower after thiazide exposure among patients receiving SGLT-2i (0.6 vs. 0.2, p = 0.039). Similarly, baseline SUA levels were similar, but SUA change after thiazide exposure was significantly lower among patients receiving SGLT-2 on bootstrapped data (0.13 [-0.25 - 0.57, 95%CI], vs. 0.61 [0.45 - 0.78, 95%CI], mean difference = 0.48, [0.04 - 0.91, 95%CI], p = 0.029). Conclusion: This study revealed that thiazide diuretics may be a safe anti-hypertensive medication in terms of hyperuricemia among patients using SGLT-2i. Further studies with similar outcomes may result in the elimination of restrictive recommendations for the use of thiazides in patients with hyperuricemia or gout, provided patients are on SGLT-2i.
  • No Thumbnail Available
    Item
    Evaluation of Machine Learning Algorithms for Renin-Angiotensin-Aldosterone System Inhibitors Associated Renal Adverse Event Prediction
    (2023) Guven, Alper Tuna; Ozdede, Murat; Sener, Yusuf Ziya; Yildirim, Ali Osman; Altintop, Sabri Engin; Yesilyurt, Berkay; Uyaroglu, Oguz Abdullah; Tanriover, Mine Durusu; 0000-0002-6310-4240; 37217407
    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), naive 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.