Fakülteler / Faculties
Permanent URI for this communityhttps://hdl.handle.net/11727/1395
Browse
6 results
Search Results
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; 37217407Background: 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.Item Serum Interleukin-18 As an Early Marker of Acute Kidney Injury Following Open Heart Surgery(2014) Unal, Ertekin Utku; Ozen, Anil; Boysan, Emre; Tak, Sercan; Basar, Veysel; Turkcan, Basak Soran; Durukan, Elif; Tutun, Ufuk; Birincioglu, Cemal Levent; https://orcid.org/0000-0002-8579-5564; AAJ-8621-2021Background: This study aims to investigate whether serum interleukin (IL)-18 is an early biomarker of acute kidney injury (AKI). Methods: Thirty consecutive patients (22 males, 8 females; mean age 62.4 +/- 9.0 years; range 49 to 78 years) who underwent open-heart surgery were enrolled in this prospective study. Serum IL-18 concentrations were analyzed prior to induction of anesthesia, at weaning from cardiopulmonary bypass (CPB) and two hours after weaning from CPB. Serum creatinine levels were analyzed in the postoperative first, second, and third days. Acute kidney injury was defined as creatinine levels exceeding 50% of the basal value or exceeding the basal value by 0.3 mg/dl at 48 hours postoperatively. The patients were classified into two groups including AKI (n=12) and non-AKI (n=18). Serum IL-18 levels were compared between the groups. Results: Twelve patients (40%) developed AKI. The diagnosis was able to be made using the serum creatinine levels at 24 to 48 hours postoperatively. Although IL-18 concentrations at weaning from CPB decreased slightly in the AKI group, the decrease in the non-AKI presenting group was higher. Using univariate analyses, IL-18 concentrations at two hours after weaning from CPB were found to be related to AKI (p=0.031). The difference in serum IL-18 concentrations between the preoperative period and two hours after weaning from CPB were found to be statistically significant (p=0.017). According to the Receiver operating characteristic curve analysis, the threshold value for AKI prediction of serum IL-18 concentrations at two hours after weaning from CPB was 353.7 pg/ml with a sensitivity of 58.3% and a specificity of 83.3% (AUC=0.736). Conclusion: Serum IL-18 concentration may be used as a biochemical indicator for early detection of acute kidney injury following open heart surgery.Item A Comparison of Two Coronary Artery Bypass Graft Surgery Techniques with Respect to Acute Kidney Injury(2015) Beyazpinar, Deniz Sarp; Gultekin, Bahadir; Kayipmaz, Afsin Emre; Kayipmaz, Cagri; Sezgin, Atilla; Giray, Tufan Akin; Kavalci, Cemil; 0000-0003-2529-2946; 0000-0003-4619-4034; AAC-2597-2020; AGG-1308-2022; ABA-7388-2021; ABA-9675-2021; AGQ-5015-2022Background: This study aims to compare the conventional coronary artery bypass graft (CABG) surgery and on-pump beating heart bypass grafting (OPBHB) with respect to acute kidney injury and subsequent dialysis requirement. Methods: Between January 2012 and October 2013, medical records of 77 patients who underwent conventional CABG and 76 patients who underwent OPBHB for coronary artery disease in our clinic were retrospectively analyzed. Results: There was no significant difference in preoperative renal function test results between the groups. However, there was a significant difference in cardiopulmonary bypass time and length of intensive care unit stay (p<0.05). Seven (9.21%) of 76 patients in OPBHB group and 11 (14.28%) of 77 patients in CABG group developed acute kidney injury; however, it did not indicate a statistically significant difference between the groups (p>0.05). One patient in OPBHB group and four patients in CABG group also needed dialysis. Conclusion: Our study results suggest that OPBHB is superior to the conventional CABG in terms of acute kidney injury and, more importantly, development of acute renal failure in patients with a serum creatinine level of 1-1.3 mg/dL.Item Incidence and Patient Outcomes in Renal Replacement Therapy After Orthotopic Liver Transplant(2017) Ayhan, Asude; Ersoy, Zeynep; Ulas, Aydin; Zeyneloglu, Pinar; Pirat, Arash; Haberal, Mehmet; 0000-0003-0767-1088; 0000-0003-3299-6706; 0000-0002-3462-7632; 0000-0003-2312-9942; 0000-0002-8130-9901; 28260481; AAF-3066-2021; AAJ-2066-2021; AAJ-8097-2021; AAJ-2057-2021; C-3736-2018Objectives: Our objective was to evaluate the incidence of renal replacement therapy after orthotopic liver transplant and to evaluate and analyze patient outcomes. Materials and Methods: We performed a retrospective analysis of 177 consecutive patients at a tertiary care unit who underwent orthotopic liver transplant between January 2010 and June 2016. Patients who were admitted to the intensive care unit after orthotopic liver transplant and who required renal replacement therapy were included. Results: A total of 177 (79 adult, 98 pediatric) orthotopic liver transplants were performed during the study period. Of these, 35 patients (19%) required renal replacement therapy during the early posttrans plantation period. After excluding 5 patients with previous chronic renal failure, 30 patients (17%; 20 adult [25%], 10 pediatric [10%]) with acute kidney injury required renal replacement therapy. The mean patient age was 31.1 +/- 20.0 years, with a mean Model for End-stage Liver Disease score of 16.7 +/- 12.3. Of the patients with acute kidney injury who underwent renal replacement therapy, in-hospital mortality was 23.3% (7 of 30 patients), and 40% remained on dialysis. No significant difference was seen in mortality between early versus delayed initiation of renal replacement therapy in patients with stage 3 acute kidney injury (P = .17). Conclusions: Of liver transplant recipients who present with acute kidney injury, 19% require renal replacement therapy, and in-hospital mortality is 20% in the early postoperative period.Item Evaluation of acute kidney injury after surgery for congenital heart disease in neonates: a tertiary hospital experience(2022) Oktener Anuk, Ezgi; Erdogan, Ilkay; Ozkan, Murat; Baskin, Esra; Varan, Birgul; Tokel, Kursad N.; 0000-0001-6887-3033; 0000-0003-3991-8479; 35382696; ABB-2220-2021Purpose of the article Acute kidney injury (AKI) after cardiac surgery in children with congenital heart disease (CHD) is a serious complication closely associated with high morbidity and mortality. Despite numerous studies on AKI in children, most studies have excluded neonates. We sought to characterize AKI associated with cardiac surgery in neonates, determine its incidence, perioperative and postoperative risk factors, and short-term results. Materials and methods This retrospective study included 177 neonates who were operated on for CHD in our hospital between January 2015 and December 2019. Data of the patients were analyzed according to nKDIGO (neonatal Kidney Disease Improving Global Outcomes) and nRIFLE (neonatal Risk, Injury, Failure, Loss of function, End-stage kidney disease) criteria for evaluating AKI retrospectively. Data of groups with and without AKI were analyzed. Results The average age of 177 neonates were 8.2 +/- 6.1 (1-28) days. Twenty-two (12.4%) neonates had CS-AKI defined according to nKDIGO criteria. Four (2.3%) neonates reached nKDIGO stage I, 1 (0.6%) reached stage II, 17 (9.6%) reached stage III. Thirty-eight (21.5%) neonates had CS-AKI defined according to nRIFLE criteria. Twenty-four (13.6%) neonates reached nRIFLE stage risk(R), 6 (3.4%) reached stage injury(I), 8 (4.5%) reached stage failure (F). The incidence of cardiac surgery-associated acute kidney injury (CS-AKI) in neonates was 12.5% and 21.5% for nKDIGO and nRIFLE, respectively. The percentage difference between nKDIGO and nRIFLE for AKI assessment was due to the criteria for nRIFLE stage risk(R) urine output < 1.5 mL/kg/h for 24 h. In both classifications, the duration of cardiopulmonary bypass, operation, inotropic treatment, and mechanical ventilation, length of intensive care unit (ICU), and hospital stay were significantly higher in the AKI group than those without AKI group (p<.05). The mortality rate in the groups with AKI was found to be significantly higher (p<.05) than in the groups without AKI. In Kappa analysis, when two classifications were compared according to AKI stages, a significant agreement was found between nKDIGO and nRIFLE classifications (p<.05) (Kappa: 0.299). Conclusion AKI and mortality rates were similar between groups according to the nKDIGO and nRIFLE criteria. For early prediction of AKI and adverse outcomes, diagnostic reference intervals might be specified in more detail in neonates undergoing cardiac surgery for CHD.Item A model for acute kidney injury in severe burn patients(2022) Karakaya, Emre; Akdur, Aydincan; Aydogan, Cem; Turk, Emin; Sayin, Cihat Burak; Soy, Ebru Ayvazoglu; Yucebas, Sait Can; Alshalabi, Omar; Haberal, Mehmet; 0000-0002-4879-7974; 0000-0002-8726-3369; 0000-0002-8726-3369; 0000-0002-0993-9917; 0000-0002-3462-7632; 33879373; AAD-5466-2021; AAA-3068-2021; AAA-3068-2021; AAC-5566-2019; AAJ-8097-2021Introduction: In patients with severe burns, morbidity and mortality are high. One factor related to poor prognosis is acute kidney injury. According to the AKIN criteria, acute kidney injury has 3 stages based on urine output, serum creatinine level, and renal replacement therapy. In this study, we aimed to create a decision tree for estimating risk of acute kidney injury in patients with severe burn injuries. Methods: We retrospectively evaluated 437 adult patients with >20% total burn surface area injury who were treated at the Baskent University Ankara and Konya Burn Centers from January 2000 to March 2020. Patients who had high-voltage burn and previous history of kidney disease were excluded. Patient demographics, medical history, mechanism of injury, presence of inhalation injury, depth of burn, laboratory values, presence of oliguria, need for renal replacement therapy, central venous pressure, and prognosis were evaluated. These data were used in a "decision tree method" to create the Baskent University model to estimate risk of acute kidney injury in severe burn patients. Results: Our model provided an accuracy of 71.09% for risk estimation. Of 172 patients, 78 (45%) had different degrees of acute kidney injury, with 26 of these (15.1%) receiving renal replacement therapy. Our model showed that total burn surface area was the most important factor for estimation of acute kidney injury occurrence. Other important factors included serum creatinine value, burn injury severity score, hemoglobin value, neutrophil-tolymphocyte ratio, and platelet count. Conclusion: The Baskent University model for acute kidney injury may be helpful to determine risk of acute kidney injury in burn patients. This determination would allow appropriate treatment to be given to high-risk patients in the early period, reducing the incidence of acute kidney injury. (c) 2021 Published by Elsevier Ltd.