Nevruz İlHanli

Nevruz İlHanli

Auto-generated profile, based on publicly available information

Nevruz İlHanli

Akdeniz University

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 February 2024 in JMIR Medical Informatics
Verified
Journal Article
Open access
NINevruz İlHanlı
Nevruz İlHanlı
SPSe Yoon Park
Se Yoon Park
JKJaewoong Kim
Jaewoong Kim
JRJee An Ryu
Jee An Ryu
AYAhmet Yardımcı
Ahmet Yardımcı
DYDukyong Yoon
Dukyong Yoon
Background: The early prediction of antibiotic resistance in patients with a urinary tract infection (UTI) is important to guide appropriate antibiotic therapy selection. Objective: In this study, we aimed to predict antibiotic resistance in patients with a UTI. Additionally, we aimed to interpret the machine learning models we developed. Methods: The electronic medical records of patients who were admitted to Yongin Severance Hospital, South Korea were used. A total of 71 features extracted from patients’ admission, diagnosis, prescription, and microbiology records were used for classification. UTI pathogens were classified as either sensitive or resistant to cephalosporin, piperacillin-tazobactam (TZP), carbapenem, trimethoprim-sulfamethoxazole (TMP-SMX), and fluoroquinolone. To analyze how each variable contributed to the machine learning model’s predictions of antibiotic resistance, we used the Shapley Additive Explanations method. Finally, a prototype machine learning–based clinical decision support system was proposed to provide clinicians the resistance probabilities for each antibiotic. Results: The data set included 3535, 737, 708, 1582, and 1365 samples for cephalosporin, TZP, TMP-SMX, fluoroquinolone, and carbapenem resistance prediction models, respectively. The area under the receiver operating characteristic curve values of the random forest models were 0.777 (95% CI 0.775-0.779), 0.864 (95% CI 0.862-0.867), 0.877 (95% CI 0.874-0.880), 0.881 (95% CI 0.879-0.882), and 0.884 (95% CI 0.884-0.885) in the training set and 0.638 (95% CI 0.635-0.642), 0.630 (95% CI 0.626-0.634), 0.665 (95% CI 0.659-0.671), 0.670 (95% CI 0.666-0.673), and 0.721 (95% CI 0.718-0.724) in the test set for predicting resistance to cephalosporin, TZP, carbapenem, TMP-SMX, and fluoroquinolone, respectively. The number of previous visits, first culture after admission, chronic lower respiratory diseases, administration of drugs before infection, and exposure time to these drugs were found to be important variables for predicting antibiotic resistance. Conclusions: The study results demonstrated the potential of machine learning to predict antibiotic resistance in patients with a UTI. Machine learning can assist clinicians in making decisions regarding the selection of appropriate antibiotic therapy in patients with a UTI.

10 May 2022 in Educational Gerontology
Verified
Journal Article
Closed access
EIEmin İbİlİ
Emin İbİlİ
NINevruz İlHanli
Nevruz İlHanli
NZNeşe Zayİm
Neşe Zayİm
AYAhmet Yardımcı
Ahmet Yardımcı
This study was aimed at determining the factors that affect the intentions of University of the Third Age (UTA) students toward e-learning systems by using Structural Equation Modeling. For this purpose, factors such as Self-Efficacy, Experience, Social Norms, Enjoyment, and Anxiety, suggested as external factors in the General Extended Technology Acceptance Model for E-Learning (GETAMEL) model, were included in the UTATAM model developed within the scope of this research. The research was carried out with a total of 210 students studying at The University of the Third Age at Akdeniz University and Ege University. The results of the study indicate that the Experience factor has a strong effect on Anxiety, Self-efficacy, and Perceived Enjoyment. In addition, it was found that Anxiety, Self-efficacy, and Social Norms were effective on perceived Ease of Use, while Perceived Enjoyment and Social Norms were effective on Perceived Usefulness. On the other hand, while the mean scores of Perceived Usefulness and Social Norms were higher in favor of female, the mean scores of Experiences were higher in favor of male. The results indicated that participants’ age and lifestyle did not affect the mean scores of individuals in terms of all factors. In terms of Behavioral Intentions, the average population of countries has been increasing rapidly in recent years. The results of this research study are crucial for shedding light on educational institutions and other relevant institutions in order to determine the factors that affect the intentions of UTA students toward the use of e-learning systems.

20 November 2023 in Therapeutic Apheresis and Dialysis
Verified
Journal Article
Closed access
MYMehmet Yilmaz
Mehmet Yilmaz
VKVolkan Karakus
Volkan Karakus
EKEgemen Kaya
Egemen Kaya
NINevruz İlHanlı
Nevruz İlHanlı
BHBülent Huddam
Bülent Huddam

1 October 2019
Verified
Conference Paper
Closed access
NINevruz İlhanlı
Nevruz İlhanlı
AYAhmet Yardimci
Ahmet Yardimci
Prostate cancer biopsy decision is a complex process which is based on various variables but no definitive cut-off value can be used. Due to this limitation, a person who does not actually have the disease may undergo biopsy, a difficult process with infection risk. The aim of this study is to determine the risk of prostate cancer and to provide support to the physician during a biopsy decision and to determine the performance of the fuzzy logic approach in determining prostate cancer risk. As a result of the interviews with urologists, it was not possible to establish a common opinion about the input variables of the system and their evaluation in a single system. Therefore, the risk of cancer was determined by fuzzy models designed with different approaches and fuzzy models were integrated to each other according to their performance in determining prostate cancer risk. As a result of this integration, a fuzzy system was developed. The fuzzy system developed with this study identified the risk of prostate cancer with 0.710 AUC.

30 July 2024 in Journal of Health Sciences and Medicine
Verified
Journal Article
Open access
PDF file
TKTarık Keçeli
Tarık Keçeli
NINevruz İlhanlı
Nevruz İlhanlı
KGKemal Hakan Gülkesen
Kemal Hakan Gülkesen
Aims: Development of a machine learning model on an electronic health record (EHR) dataset for predicting retinopathy in people with diabetes mellitus (DM), analysis of its explainability. Methods: A public dataset based on EHR records of patients diagnosed with DM located in İstanbul, Turkiye (n=77724) was used. The categorical variable indicating a retinopathy-positive diagnosis was chosen as the target variable. Variables were preprocessed and split into training and test sets with the same ratio of class distribution for model training and evaluation respectively. Four machine learning models were developed for comparison: logistic regression, decision tree, random forest and eXtreme Gradient Boosting (XGBoost). Each algorithm’s optimal hyperparameters were obtained using randomized search cross validation with 10-folds followed by the training of the models based on the results. The receiver operating characteristic (ROC) area under curve (AUC) score was used as the primary evaluation metric. SHapley Additive exPlanations (SHAP) analysis was done to provide explainability of the trained models. Results: The XGBoost model showed the best results on retinopathy classification on the test set with a low amount of overfitting (AUC: 0.813, 95% CI: 0.808-0.819). 15 variables that had the highest impact on the prediction were obtained for explainability, which include eye-ear drugs, other eye diseases, Disorders of refraction, Insulin aspart and hemoglobin A1c (HbA1c). Conclusion: Early detection of retinopathy based on EHR data can be successfully detected in people with diabetes using machine learning. Our study reports that the XGBoost algorithm performed best in this research, with the presence of other eye diseases, insulin dependence and high HbA1c being observed as important predictors of retinopathy.

10 October 2025 in Marmara Medical Journal
Verified
Journal Article
Closed access
NINevruz İlHanlı
Nevruz İlHanlı
SÖSalih Özçobanoğlu
Salih Özçobanoğlu
KGKemal Hakan Gülkesen
Kemal Hakan Gülkesen
Objective: The main symptom of ischemic heart disease (IHD) is chest pain and diabetic patients are likely to not perceive chest pain due to neuropathy. Therefore, the prediction of IHD in patients with diabetes mellitus is crucial. In this study, we aimed to predict IHD in patients with diabetes mellitus using various machine learning techniques. Additionally, we aimed to interpret the machine learning model. Materials and Methods: We used eXtreme Gradient Boosting (XGBoost), logistic regression, Multi-Layer Perceptron (MLP), random forest, decision tree and K-Nearest Neighbors (KNN) algorithms to predict IHD in patients with diabetes mellitus. Additionally, we used the SHapley Additive exPlanations (SHAP) method to interpret our machine learning model. Results: According to performance analysis, the XGBoost model had a superior performance with 0.814 area under the curve (AUC) on the training set and 0.795 AUC on the test set. The Brier score of the XGBoost model was 0.153. SHAP analysis results showed that the presence of hypertension has the highest contribution to the presence of IHD in patients with diabetes mellitus. Conclusion: Machine learning has the potential to provide decision support to clinicians in the identification of IHD in patients with diabetes mellitus.