WoS İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.14627/6

Browse

Filters

2025 - 20262

Settings

Author: search.filters.author.Aydin, IrfanScopus Q: search.filters.scopusQuartile.Q2

Search Results

Now showing 1 - 2 of 2
  • Article
    Machine Learning Model for Predicting Multidrug Resistance in Clinical Klebsiella pneumoniae Isolates
    (MDPI, 2026) Akkaya, Yuksel; Aydin, Irfan; Tanyildizi-Kokkulunk, Handan; Erturk, Ayse; Kilic, Ibrahim Halil
    Background/Objectives: Klebsiella pneumoniae is an opportunistic pathogen increasingly resistant to carbapenems and broad-spectrum antibiotics, complicating timely infection management. In critical cases like septic shock, where initiating effective antibiotics within 3 h improves survival, culture-based resistance testing is often too slow. This study evaluates machine learning (ML) algorithms for faster antimicrobial resistance prediction than conventional methods. Methods: In this retrospective study, antibiogram results of 607 Klebsiella pneumoniae isolates collected between 2017 and 2024 were combined with demographic and clinical information of the patients from whom the isolates were obtained. Four different ML algorithms, namely Decision Tree (DT), Support Vector Classifier (SVC), K-Nearest Neighbors (KNN) and Random Forest (RF), were applied to classify the resistance status for 22 antibiotics. Model performances were evaluated using accuracy, precision, recall, F-score, AUC and feature importance metrics. Results: The RF model showed the highest overall performance in accurately predicting resistance to 22 antibiotics, achieving an average AUC value of 0.96. In particular, it predicted resistance to treatment-critical antibiotics such as Ertapenem (100%), Imipenem (93%) and Meropenem (95%) with high accuracy. Conclusions: ML models, especially RF, offer a powerful tool for rapid antibiotic resistance prediction, supporting accurate empirical treatment decisions and antimicrobial stewardship.
  • Article
    Citation - Scopus: 1
    Detection of Candida (Candidozyma) Auris by Molecular Methods and Investigation of Clinical Symptoms of Patients in a Tertiary Hospital in Istanbul
    (K Faisal Spec Hosp Res Centre, 2025) Akkaya, Yuksel; Erdin, Begum Nalca; Aydin, Irfan; Ozel, Ayse Serra; Yilmaz, Ahmet Munir; Cilkiz, Mustafa; Toraman, Zulal Asci
    BACKGROUND: Candidozyma auris is resistant to many antifungals, spreads rapidly and causes deaths in patient groups with comorbid factors. OBJECTIVES: The aim of this study was to determine the virulence of C. auris, antifungal resistance genes and clinical characteristics of the patients. DESIGN: Retrospective cohort SETTING: Single-center MATERIAL AND METHODS: This study was conducted between August 2022 and December 2023 at & Uuml;mraniye Training and Research Hospital. ITS1-5.8S-ITS2 and ITS1-ITS4 gene regions of the rDNA gene of C. auris isolates identified by VITEK MS v.3.2 were amplified by polymerase chain reaction (PCR) method. These regions were partially sequenced using the Sanger method. The presence of C. aurisspecific CDR1, ERG11, MDR1, ACT1, SAP5, HYR3, ALS5, IFF4, FUR1, PLB3, PGA26 and PGA52 gene regions were determined by PCR. Antifungal susceptibility testing of C. auris was performed with VITEK 2 Compact AST YS08 and SYO. MAIN OUTCOME MEASURES: Variations in C. auris isolates, antifungal resistance and clinical characteristics of patients SAMPLE SIZE: Forty-four isolates from 31 patients RESULTS: According to gene regions, nine different variations were identified in our hospital, with VAR-1 being the most common. Twenty-five (80.6%) of the patients died and isolation of the causative agent was between days 1-30 in 13 (41.9%) patients. Antibiotic use, ICU admission rate, and central venous catheter use in patients were 29 (93.6%), 28 (90.3%), and 21 (67.7%), respectively. Hypertension, diabetes mellitus (DM) and septic shock were found in 14 (45.2%), 13 (41.9%) and 10 (32.3%) patients, respectively. Antifungal resistance rates of the isolates were determined as 97.7% and 84.1% for amphotericin B and fluconazole, respectively. No resistance to micafungin and caspofungin was detected. The survival rate with echinocandin use was 22% (4 patients). CONCLUSION: Identification of gene regions is valuable in determining the pathogenicity of C. auris. . Due to the presence of comorbidi- ties in patients with C. auris, , it is not possible to determine the exact proportion of deaths attributable to C. auris alone. LIMITATIONS: Single center setting; gene regions could not be ex- pressed.