Funda Tuzun

Funda Tuzun

Auto-generated profile, based on publicly available information

Funda Tuzun

Department of Neonatology, School of Medicine, Dokuz Eylul University, Izmir, Turkey

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
10 April 2025 in BMC Ophthalmology
Verified
Journal Article
Open access
PDF file
CECeren Durmaz Engin
Ceren Durmaz Engin
TOTaylan Ozturk
Taylan Ozturk
OOOzlem Ozkan
Ozlem Ozkan
AOAli Oztas
Ali Oztas
ASAlper Selver
Alper Selver
FTFunda Tuzun
Funda Tuzun
To evaluate the effectiveness of machine learning (ML) models in predicting the occurrence of retinopathy of prematurity (ROP) and treatment need. Four ML models were created using 49 parameters known within the first 24 h post-birth and obtained during the initial screening examination, encompassing demographic, maternal, clinical, and neonatal intensive care unit-related data. The models’ performances were assessed using five machine learning (ML) classifier algorithms: logistic regression (LR), decision tree (DT), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost). Performance metrics were calculated, and the top ten parameters with the highest predictive value were identified. In the cohort of 355 preterm infants, Model I, predicting ROP development using birth data, achieved a balanced accuracy of 80%, with gestational age (GA), birth weight (BW) and mean corpuscular volume (MCV) as the top predictive parameters. Model II, predicting treatment-requiring ROP using birth data, exhibited a balanced accuracy of 81%. Key predictive parameters included low GA, BW, 1-minute and 5-minute APGAR scores, and low erythrocyte counts. For Model III, predicting ROP using the first screening examination data, and Model IV, predicting treatment-requiring ROP using the same data, the accuracy values were 80% and 66%, respectively, with BW, daily weight gain, total O2 support duration, and platelet/lymphocyte ratio emerged as the most significant predictive parameters in both models. This study demonstrates the potential of ML models to predict ROP development and treatment need. Incorporating clinical and intensive care-related parameters can enhance ROP screening and clinical decision-making.

17 November 2025 in European Journal of Pediatrics
Verified
Journal Article
Closed access
PDF file
NDNuray Duman
Nuray Duman
MTMehtap Durukan Tosun
Mehtap Durukan Tosun
FTFunda Tuzun
Funda Tuzun
TETugba Egeli
Tugba Egeli
ABAhmet Yagmur Bas
Ahmet Yagmur Bas
HÖHasan Özkan
Hasan Özkan

1 September 2025 in Turkish Archives of Pediatrics
Verified
Journal Article
Open access
MCMustafa Canbeldek
Mustafa Canbeldek
CACoşkun Armağan
Coşkun Armağan
HŞHüseyin Bahadır Şenol
Hüseyin Bahadır Şenol
HBHüseyin Burak Baykara
Hüseyin Burak Baykara
ABAyşen Bahar Baykara
Ayşen Bahar Baykara
HÖHasan Özkan
Hasan Özkan
Objective: This study aims to evaluate the long-term neurological outcomes of neonates diagnosed with mild hypoxic-ischemic encephalopathy (HIE) and compare them with moderate/ severe cases, hypothesizing that a significant proportion of mild HIE cases may experience adverse neurodevelopmental sequelae. Materials and Methods: This was a cross-sectional observational study evaluating the neurodevelopmental outcomes of neonates with mild versus moderate/severe HIE. Maternal, perinatal, and neonatal characteristics along with treatments were documented. Neurological outcomes were assessed via brain MRI, the Ankara Developmental Screening Inventory (ADSI), and developmental milestones. Results: The study included 42 infants, 20 (47.6%) were classified as having mild HIE and 22 (52.4%) as moderate/severe HIE. Baseline characteristics were similar except that moderate/ severe cases had lower 1-minute Apgar scores (median 4 vs. 6; P = .02) and more frequent need for advanced resuscitation (68% vs. 25%; P = .006). All moderate/severe infants received TH vs. none in the mild group. Invasive mechanical ventilation and adjuvant neuroprotective agents were also more frequently used in the moderate/severe group. Magnetic resonance imaging abnormalities consistent with HIE were present in 2/12 mild cases (16.7%) vs. 8/19 (42.1) in moderate/severe cases. There were no significant differences in HIE injury pattern between the 2 groups (P = .197). On ADSI screening, 8/12 (66.7%) mild HIE survivors showed gross motor delay compared with 5/7 (71.4%) moderate/severe survivors. Conclusion: Even infants with mild HIE are at risk of adverse neurological outcomes. The development of more sensitive diagnostic tools could improve treatment strategies and early interventions, ultimately impacting prognosis. With proper recognition, tailored follow-up, and appropriate therapeutic approaches, potential neurodevelopmental impairments in mild HIE cases could be mitigated. Cite this article as: Canbeldek M, Armağan C, Şenol HB, et al. Challenging mild hypoxic–ischemic encephalopathy: insights into neurological outcomes.Turk Arch Pediatr. 2025;60(5):507-514.

17 July 2023 in Dokuz Eylül Üniversitesi Tıp Fakültesi Dergisi
Verified
Journal Article
Closed access
YAYağmur Damla AKÇURA
Yağmur Damla AKÇURA
CACoşkun Armağan
Coşkun Armağan
CACan Akyildiz
Can Akyildiz
BDBurak Deli̇loğlu
Burak Deli̇loğlu
NDNuray Duman
Nuray Duman
HÖHasan Özkan
Hasan Özkan
Introduction and methods: Thanks to developments in perinatal and neonatal care, the survival rate of premature babies has increased. Depending on the development level of countries and units, some of the morbidity rates may increase, while others may decrease. In this retrospective cross-sectional study; the morbidity and mortality results of very low birth weight (VLBW) infants were evaluated by comparing the results of the infants in our previous study and the data of developed countries. Results: 203 infants were included in the last group. The mean birth weight of these babies was 976±308 g and the mean gestational age was 27.8±2.5 weeks. The rate of babies with a gestational age of 28 weeks and above were significantly lower than the first group containing 173 infants. Regarding major morbidities, the rates of bronchopulmonary dysplasia (moderate to severe) and necrotizing enterocolitis (>stage 2) were significantly higher in the last group; while the rates of retinopathy of prematurity (>grade 2), intraventricular hemorrhage (>grade 2) and periventricular leukomalacia were also similar among the two groups. While survival rates were found to be similar, the survival rate without major morbidity was significantly lower in the last group. Conclusion: While the survival rates remained unchanged despite the observation of smaller babies in terms of birth weight and gestational age in the last period when mortality and morbidity data were compared with developed countries, the study demonstrated a need for improvement in mortality rates especially in small gestational weeks, while major morbidity rates were generally encouraging.


6 September 2023 in Dokuz Eylül Üniversitesi Tıp Fakültesi Dergisi
Verified
Journal Article
Closed access
CACan Akyildiz
Can Akyildiz
FTFunda Tüzün
Funda Tüzün
YAYağmur Damla AKÇURA
Yağmur Damla AKÇURA
NDNuray Duman
Nuray Duman
PKPembe Keski̇nOğlu
Pembe Keski̇nOğlu
HÖHasan Özkan
Hasan Özkan
Background: Currently, no practical biomarker has been discovered for early recognition of the development of bronchopulmonary dysplasia(BPD). This study aimed to evaluate the predictive value of early complete blood count (CBC) indices along with red blood cell transfusion(RBCT) frequency for the development of moderate/severe BPD, and to identify a promising predictive risk model for BPD. Methods: In this cross-sectional study, one-hundred-sixty-two neonates born before the 32nd weeks of gestation were retrospectively. Predictive role of CBC parameters in the first three postnatal days(PD) and the number of RBCTs on weekly basis were evaluated by univariate/multivariate analysis as well as multivariate data mining processing. Results: Despite several factors affected BPD development in univariate analysis, gestational age, PD3 haemoglobin level and frequency of RBCT were found to be the independent predictors of BPD in multivariate analysis. The haemoglobin<155 g/L in the PD3 predicted moderate/severe BPD with 60% sensitivity and 88% specificity(AUC 0.80). Having received at least one RBCT during the first three postnatal weeks had AUC 0.81(sensitivity 0.91,and specificity 0.81). During hospitalisation, more than four RBCT predicted moderate/severe BPD with 0.83 sensitivity and 0.93 specificity(AUC0.96). A model including gestational age, PD3 haemoglobin value, and number of RBCT predicted BPD risk with 87% sensitivity and 86% precision using data mining methods. Conclusion: Results emphasise that even just one blood transfusion in the first weeks is an independent risk factor for BPD. Even though BPD is multifactorial, initial haemoglobin value and RBCT frequency may serve as non-invasive and practical parameters to estimate BPD development risk.