Aycan Baş

Aycan Baş

Auto-generated profile, based on publicly available information

Aycan Baş

Department of Biophysics, Faculty of Medicine Afyonkarahisar Health Sciences University Afyonkarahisar Türkiye

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
12 March 2022 in Journal of Diabetes & Metabolic Disorders
Verified
Journal Article
Closed access
PDF file
ABAycan Baş
Aycan Baş
IAIşıl Albeniz
Işıl Albeniz

21 May 2026 in BMC Pregnancy and Childbirth
Verified
Journal Article
Open access
PDF file
ABAycan Baş
Aycan Baş
RDRıza Dur
Rıza Dur
Preeclampsia is a complex and heterogeneous complication during pregnancy, with oxidative stress and endothelial dysfunction also playing a role in its pat

28 October 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
ABAycan Baş
Aycan Baş
NONevzat OLGUN
Nevzat OLGUN
AYAhmet Haşim Yurttakal
Ahmet Haşim Yurttakal
ŞÇŞule Çilekar
Şule Çilekar
Obstructive Sleep Apnea Syndrome (OSAS) is a sleep disorder whose diagnosis and severity classification rely primarily on polysomnography (PSG); however, its use in large scale screening programmes is limited by high costs and restricted accessibility. In this study, we propose an interpretable machine learning framework for the automatic classification of OSAS severity by integrating overnight oxygen saturation (SpO₂) time series data with clinical and hematological variables at the feature level. In this retrospective study, 78 individuals who had undergone PSG were classified into four categories: simple snoring, mild, moderate, and severe OSAS. Continuous fingertip SpO₂ signals recorded at 16 Hz were divided into non overlapping 60 s segments. Time domain statistics and frequency domain features based on power spectral density estimated using the Welch method were extracted from each segment. Segment level features were aggregated at the individual level and combined through feature level (early) fusion with body mass index, Epworth Sleepiness Scale score, and selected haemogram parameters. The resulting feature vectors were evaluated using five fold stratified cross validation with Random Forest (RF), Extra Trees (ET), and k-Nearest Neighbour classifiers (kNN). Among the evaluated models, ET achieved the best performance, yielding an accuracy of 89.83% ± 5.45, a macro F1-score of 89.88% ± 5.60, and an ROC-AUC of 0.9881 ± 0.0131. In ten-times repeated five-fold cross-validation, an accuracy of 85.53% ± 2.40 was achieved, whereas nested cross-validation yielded an accuracy of 85.38% ± 1.93, indicating a modest reduction in performance under more rigorous validation. Ablation analyses showed that the principal improvement in performance resulted from the addition of PSD-based features together with BMI and ESS, whereas hematological parameters provided only limited incremental benefit in terms of accuracy and macro F1-score. SHAP-based explainability analysis showed that time- and frequency-domain features derived from the SpO₂ signal made the greatest relative contribution to model predictions. Clinical variables showed a moderate contribution, whereas hematological variables contributed to a lesser extent. These findings suggest that integrating SpO₂-derived features with clinical data may support the automated and interpretable classification of OSAS severity and complement clinical assessment.

8 November 2025 in Irish Journal of Medical Science (1971 -)
Verified
Journal Article
Closed access
PDF file
FYFulya Yukcu
Fulya Yukcu
MYMustafa Yildiz
Mustafa Yildiz
RARaziye Akcilar
Raziye Akcilar
ABAycan Bas
Aycan Bas
NNNazlı Dizen Namdar
Nazlı Dizen Namdar

12 February 2026
Verified
Book
Open access
PDF file
YKYunus Karakoç
Yunus Karakoç
BTBarış Türker
Barış Türker
YKYalçın Karabulut
Yalçın Karabulut
MAMehmet Aslan
Mehmet Aslan
SÜSimge Ünay
Simge Ünay
ASAbdullah Sarı
Abdullah Sarı

21 February 2026 in Biological Trace Element Research
Verified
Journal Article
Open access
RDRIZA DUR
RIZA DUR
ABAycan Baş
Aycan Baş
GDGAMZE DUR
GAMZE DUR
Objective: Gestational diabetes mellitus (GDM) is a multifactorial metabolic disorder in which redox imbalance and endothelial dysfunction may contribute to adverse maternal–fetal outcomes. We investigated whether maternal serum essential and toxic element profiles differ in GDM and whether these alterations are associated with oxidative stress indices and nitric oxide (NO) bioavailability. Methods: Serum samples from 50 women with GDM and 50 healthy pregnant controls were analyzed. Essential trace elements (Zn, Cu, Se, Fe, Mn, Cr, Mo, V) and toxic metals (Pb, Cd, As, Sn, Co) were quantified using inductively coupled plasma mass spectrometry (ICP–MS). Total antioxidant status (TAS), total oxidant status (TOS), asymmetric dimethylarginine (ADMA), and nitric oxide synthase (NOS)-related NO metabolites were measured by ELISA-based methods. Results: NOS levels were significantly reduced in GDM (p < 0.001), while TAS, TOS, and ADMA did not differ between groups. Zn, Cu, Se, Fe, Mo, and V were significantly higher in GDM, whereas toxic metals showed no group differences. In exploratory ROC analyses, selenium showed the highest discrimination for GDM (AUC = 0.754, p < 0.001), followed by iron (AUC = 0.714, p < 0.001) and vanadium (AUC = 0.700, p = 0.001). Molybdenum demonstrated modest discrimination (AUC = 0.662, p = 0.005), indicating potential—rather than strong stand-alone—predictive value. In logistic regression (per 1 SD increase), selenium and molybdenum were associated with higher odds of GDM in age-adjusted models, supporting the relevance of the multi-marker profile. Conclusion: The co-occurrence of elevated redox-active elements with reduced NO bioavailability in GDM supports a hypothesis-generating “Mo–Se–Fe–NOS signature” (an observational multi-marker profile) that warrants longitudinal and external validation to clarify mechanisms and clinical utility.