Fatma Özdemir

Dr. Fatma Özdemir

ICU, Bakırköy Dr. Sadi Konuk Training and Research Hospital, University of Health Sciences, Istanbul, İstanbul, Turkey (Türkiye)
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
DBDicle Birtane
Dicle Birtane
Fatma ÖzdemirFatma Özdemir
Fatma Özdemir
DYDamla Yavuz
Damla Yavuz
ZCZafer Cukurova
Zafer Cukurova
Background: In critically ill patients, tracheostomy decisions are driven by heterogeneous and dynamic clinical trajectories, and no universally accepted scoring system exists to reliably predict tracheostomy requirement. An accurate and interpretable prediction model could help earlier decision-making and potentially reduce prolonged mechanical ventilation (MV) and failed weaning. Methods: In this retrospective study, data from 6507 mechanically ventilated intensive care unit (ICU) patients were analyzed using an electronic clinical decision support system; 1049 patients required tracheostomy and 5458 did not. The primary outcome was the prediction of tracheostomy occurrence during ICU stay based on invasive mechanical ventilation (IMV) parameters obtained within the first five days. The secondary outcome was the identification of the most influential parameters guiding tracheostomy decision-making during early IMV. Ten machine learning algorithms were developed using an 80/20 train–test split. Model performance was assessed using discrimination, calibration, and clinical performance metrics. Explainability was evaluated using SHapley Additive exPlanations (SHAP) analysis. Results: Among all models, Gradient Boosting demonstrated strong discrimination and calibration performance (AUROC 0.92, AUPRC 0.56, specificity 97%, F1 score 0.46, Brier score 0.078). In the Gradient Boosting model, feature importance analysis demonstrated that secretion count was the strongest predictor of tracheostomy requirement, accounting for 14.72% of the model’s predictive contribution. This was followed by lactate level (6.12%), arterial pH (3.74%), and peak airway pressure (3.57%). SHAP-based analyses consistently identified secretion count as the strongest predictor of tracheostomy requirement, followed by lactate level, Glasgow Coma Scale (GCS), and arterial pH. In addition, SHAP provided clinically interpretable insights into the direction and magnitude of the effects of individual predictors. Conclusions: Machine learning models integrating early-phase ventilatory and physiological data may enable clinically meaningful prediction of tracheostomy requirement. The combination of strong performance and explainability suggests potential utility as a decision-support tool in critically ill patients requiring prolonged MV.

1 January 2022 in Acta Clinica Croatica
Verified
Journal Article
Open access
PDF file
Fatma ÖzdemirFatma Özdemir
Fatma Özdemir
AŞAyça Sultan Şahin
Ayça Sultan Şahin
Ziya SalihogluZiya Salihoglu
Ziya Salihoglu
Transversus abdominis plane (TAP) block is used to provide analgesia after lower abdominal surgery operations. TAP block has been shown to reduce postoperative pain scores and side effects of opioids after cesarean section. Generally, TAP block was...

14 February 2026 in Medicina
Verified
Journal Article
Open access
PDF file
Fatma ÖzdemirFatma Özdemir
Fatma Özdemir
DBDicle Birtane
Dicle Birtane
NYNURDAN YILMAZ
NURDAN YILMAZ
ZCZafer Cukurova
Zafer Cukurova
Background and Objectives: Neuroleptic malignant syndrome (NMS) is a rare but high-mortality clinical condition. The aim of this study was to describe the demographic characteristics, clinical and laboratory findings, management strategies, and clinical outcomes of adult patients with NMS treated in an adult intensive care unit. Materials and Methods: This retrospective descriptive study included adult patients admitted to a tertiary care ICU with a diagnosis of NMS. Data were obtained from medical records and included demographic characteristics, suspected NMS-related drug exposures, clinical and laboratory findings at ICU admission, disease severity indicators, treatments administered, and clinical outcomes. Continuous variables were expressed as median and interquartile range (IQR), and categorical variables as number and percentage. Results: A total of 42 patients were included. The median age was 48 years (IQR: 24.1–75.5), and 61.9% were male. Atypical antipsychotics were the most frequently implicated agents (69.0%). Altered mental status was observed in 92.9% of patients, tachycardia in 61.9%, and hyperthermia in 47.6%. Creatine kinase levels >1000 U/L were present in 57.1%, and leukocytosis in 71.4%. Mechanical ventilation was required in 59.5% of patients. Acute kidney injury developed in 31%, and continuous renal replacement therapy (CRRT) was initiated in 21.4%. Bromocriptine was administered in 54.8% of cases, dantrolene in 4.8%, and amantadine in 11.9%. The ICU mortality rate was 9.5%. Conclusions: Patients with neuroleptic malignant syndrome often present with a severe clinical course requiring advanced organ support in the intensive care unit. However, with early diagnosis and appropriate intensive care management, mortality can be maintained at acceptable levels.

28 September 2021 in Medical Journal of Bakırkoy
Verified
Journal Article
Closed access
MSMehmet Süleyman Sabaz
Mehmet Süleyman Sabaz
Fatma ÖzdemirFatma Özdemir
Fatma Özdemir
OÖOğuz Özakın
Oğuz Özakın
ÜTÜlkü Aygen Türkmen
Ülkü Aygen Türkmen
VDVeysel DİNÇ
Veysel DİNÇ

1 January 2021 in Annals of Medical Research
Verified
Journal Article
Open access
NKNurdan Kamilcelebi
Nurdan Kamilcelebi
Fatma ÖzdemirFatma Özdemir
Fatma Özdemir
SOSener Okul
Sener Okul

2 September 2025 in Bagcilar Medical Bulletin
Verified
Journal Article
Open access
PDF file
SSSerpil Sehirlioglu
Serpil Sehirlioglu
Fatma ÖzdemirFatma Özdemir
Fatma Özdemir
MTMelike Tezdönen
Melike Tezdönen
ÜTÜlkü Aygen Türkmen
Ülkü Aygen Türkmen
DMDöndü Genç Moralar
Döndü Genç Moralar
Evaluation of the Efficacy of Tocilizumab in Cytokine Release Syndrome in Patients with COVID-19 (SARS-CoV-2) Pneumonia Followed in the Intensive Care Unit - Bagcilar Medical Bulletin