Yazar "Aydin, N." seçeneğine göre listele
Listeleniyor 1 - 3 / 3
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Comparison of the outcomes of spinal and general anesthesia for cesarean section in pregnant women with COVID-19(Ondokuz Mayis Universitesi, 2024) Aydin, N.; Esen, O.; Tüten, N.We aimed to examine the efficacy and safety of spinal or general anesthesia for cesarean section (C/S) delivery in parturient with coronavirus illness (COVID-19). We carried out a retrospective cohort in our tertiary care centre's anesthesiology and reanimation department. We gathered the data from the medical files of 108 pregnant women (average age: 33.44±12.65 years) with COVID-19 who underwent cesarean section (C/S) with either general (Group I, n=30) or spinal anesthesia (Group II, n=78). We compared preoperative, intraoperative, postoperative respiratory, cardiac, hematological, and biochemical indicators between spinal and general anesthesia groups. Patients in Group I were significantly older (p<0.001), had longer APTT (p=0.015), PT (p=0.005), INR (p=0.003), higher levels of AST (p=0.012), CK (p=0.001), CRP (p<0.001), as well as longer duration of ICU stay (p<0.001), and hospitalization (p<0.001). Group II had higher preoperative levels of troponin T (p=0.001). In Group I, the levels of procalcitonin (p=0.002), lactate (p<0.001), AST (p<0.010), ALT (p=0.001), CRP (p<0.001), and total bilirubin (p<0.001) were significantly higher than Group II. Group II displayed increased levels of white blood cell count (p=0.023), CK (p=0.047), and LDH (p=0.001). Our data demonstrated that the selection of the mode of anesthesia must provide safe, patient-centered care and safeguard every member of the obstetric team from COVID-19 infection. During planning for cesarean section (C/S), certain care and special precautions should be employed, and the type of anesthesia must be selected on an individualized basis. © 2024 Ondokuz Mayis Universitesi. All rights reserved.Öğe Evaluation of demographic characteristics and laboratory results of patients with Covid-19 treated in the intensive care unit(Ondokuz Mayis Universitesi, 2022) Aydin, N.; Esen, O.; Karayalçin, U.We aimed to investigate the clinical features, hemodynamic and respiratory profiles as well as prognostic outcomes of critically sick COVID-19 patients admitted to intensive care units (ICUs). This retrospective study was performed using data derived from 99 adult patients treated in the ICU. Demographic and clinical data as well as hemodynamic and respiratory profiles, therapeutic outcomes were recorded. The relationship between these features and ICU stay was sought. The average age was 65.94 ± 14.93 years (24 to 96), and 73 patients (73.7%) had comorbidities. Smokers constituted 13.1% of the Covid-19 patient population (n=13) in ICU. Thirty-one cases (31.3%) had received at least one dose of Covid-19 vaccine and 63 patients (63.6%) died in the ICU after their initial hospitalization. Blood products were utilized in 29 patients (29.3%) and delta mutation was detected in 23 (23.2%) of ICU patients. The mean duration of ICU stay was 16.90 ± 11.41 days (1 to 60). The duration of ICU stay was remarkably different between groups receiving different antibiotic regimens (p<0.001). There was no significant relationship between the duration of ICU stay and blood groups (p=0.052), systolic (p=0.572) and diastolic blood pressure (p=0.098) and initial arterial oxygen saturation (p=0.223). We detected a high mortality rate in our series with severe COVID-19 infection treated in ICU. These data are critical for understanding the impact of COVID-19 on our hospitals, identifying areas for clinical management improvement, and allowing for continuous international and temporal comparisons of COVID-19 patient outcomes. © 2022 Ondokuz Mayis Universitesi. All rights reserved.Öğe Tuning hyperparameters of machine learning algorithms and deep neural networks using metaheuristics: A bioinformatics study on biomedical and biological cases(Elsevier, 2022) Nematzadeh, S.; Kiani, F.; Torkamanian-Afshar, M.; Aydin, N.The performance of a model in machine learning problems highly depends on the dataset and training algorithms. Choosing the right training algorithm can change the tale of a model. While some algorithms have a great performance in some datasets, they may fall into trouble in other datasets. Moreover, by adjusting hyperparameters of an algorithm, which controls the training processes, the performance can be improved. This study contributes a method to tune hyperparameters of machine learning algorithms using Grey Wolf Optimization (GWO) and Genetic algorithm (GA) metaheuristics. Also, 11 different algorithms including Averaged Perceptron, FastTree, FastForest, Light Gradient Boost Machine (LGBM), Limited memory Broyden Fletcher Goldfarb Shanno algorithm Maximum Entropy (LbfgsMxEnt), Linear Support Vector Machine (LinearSVM), and a Deep Neural Network (DNN) including four architectures are employed on 11 datasets in different biological, biomedical, and nature categories such as molecular interactions, cancer, clinical diagnosis, behavior related predictions, RGB images of human skin, and X-rays images of Covid19 and cardiomegaly patients. Our results show that in all trials, the performance of the training phases is improved. Also, GWO demonstrates a better performance with a p-value of 2.6E-5. Moreover, in most experiment cases of this study, the metaheuristic methods demonstrate better performance and faster convergence than Exhaustive Grid Search (EGS). The proposed method just receives a dataset as an input and suggests the best-explored algorithm with related arguments. So, it is appropriate for datasets with unknown distribution, machine learning algorithms with complex behavior, or users who are not experts in analytical statistics and data science algorithms. © 2022 Elsevier Ltd