SKSina Kardas

Sina Kardas

*This is an algorithmically generated author record based on publicly available information.

Sina Kardas has a total of 26 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Evaluation of explainable machine learning models for predicting mid-term stone recurrence after percutaneous nephrolithotomy: a retrospective observational cohort study

    by Mustafa Gokhan Kose, Dogan Altay, Ali Guler, Sina Kardas, Volkan Taskin, Burak Arslan, Enver Ozdemir

    To develop an explainable machine learning (ML) model to predict mid-term (3 years) stone recurrence (SR) after percutaneous nephrolithotomy (PCNL). This single-center retrospective observational cohort study compared nonlinear algorithms with logistic regression (LR) and evaluated the predictive value of systemic inflammatory markers, clinical and stone-related features. We retrospectively analyzed 412 PCNL patients with complete preoperative and 3-year follow-up data between 2014 and 2021. The patients were split chronologically into 70% training and 30% independent test sets. Random Forest (RF), Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGBoost), and LR models were trained using clinical, stone, and hematologic parameters, including inflammatory indices. Model performance and interpretability were evaluated using the area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, Cohen's kappa, and SHapley Additive exPlanations (SHAP). The RF model demonstrated the highest predictive performance (AUROC:0.92, accuracy:88%, kappa:0.773, p < 0.001) in the test set and outperformed the other algorithms. Residual stone size (RES) > 3 mm was the strongest predictor of SR (sensitivity, 96%; specificity, 72%). Inflammatory markers had limited independent predictive value. Decision curve analysis showed the net clinical benefit of RF, and SHAP analysis identified stone burden and RES as the most influential features. An explainable RF model effectively predicted 3-year recurrence after PCNL and emphasized the importance of achieving RES ≤ 3 mm. Although inflammatory markers contributed little to the prediction, this model has potential to enable personalized risk assessment to guide postoperative care if it is externally validated in multicenter cohorts before clinical implementation.

  • Kidney stabilization in supine percutaneous nephrolithotomy: impact on surgical efficiency and stone-free rates

    by Ali Ayten, Mert Kahraman, Oguzhan Cura, Mehmet Ozalevli, Mucahit Gelmis, Sina Kardas

    Kidney mobility during supine percutaneous nephrolithotomy (sPCNL) may negatively affect the accuracy of the approach and surgical efficacy. This study investigated the effects of kidney stabilization on surgical efficacy, stone-free rate (SFR), and complication profile. Eighty-five patients who underwent standard sPCNL for ≥ 2 cm kidney stones between January and August 2025 were retrospectively reviewed. Patients were divided into two groups: conventional sPCNL (Group C, n = 41) and sPCNL with external gel bag for kidney stabilization (Group F, n = 44). Demographic and stone characteristics, operative time, access time, fluoroscopy time, hemoglobin drop, transfusion rates, length of stay (LOS), complications, and SFR were compared. The groups were similar in terms of demographic and stone characteristics. In Group F, the operative time (74.7 ± 32.2 vs. 97.5 ± 38.0 min, p = 0.004), access time, and fluoroscopy time were significantly shorter (p < 0.001 for both). LOS was shorter in Group F (2.3 vs. 3.1 days, p = 0.001). Hemoglobin decline was less in Group F (1.20 ± 0.81 vs. 1.78 ± 1.31 g/dL, p = 0.017). Transfusion and major complication rates were similar. SFR was significantly higher in Group F (88.6% vs. 70.7%, p = 0.030). Multivariate analysis demonstrated that kidney stabilization was an independent predictor of achieving stone-free status (p = 0.032). Kidney stabilization reduces mobility during sPCNL, thereby shortening operative and fluoroscopy times, reducing blood loss, and improving SFR. These retrospective findings suggest that this simple technique may enhance surgical efficiency; however, its clinical value should be confirmed in prospective studies.

  • Open Access

    Comparing ChatGPT and MSKCC Nomogram for Prostate Cancer Risk Predictions: A Correlation Study

    by Serkan Gönültaş, Mustafa Gökhan Köse, Sina Kardaş, Serhat Yentür, Filip Paslanmaz, Engin Kandırali

    Objectives: Accurate prediction of risks such as extracapsular spread, seminal vesicle invasion and lymph node involvement is critical for treatment planning and patient prognosis in prostate cancer. Traditional nomograms are widely used for this risk stratification. In recent years, artificial intelligence (AI)-based Chabot’s have shown potential in this field. The aim of this study was to evaluate the correlation between AI chatbot (ChatGPT-4o) predictions and Memorial Sloan Kettering Cancer Center (MSKCC) nomogram predictions in prostate cancer patients according to risk groups. Materials and Methods: 40 synthetic patient scenarios representing low, intermediate, high and locally advanced risk groups were created. These scenarios were entered into both ChatGPT-4o and MSKCC nomogram and predictions of “Organ-Confined Disease”, “Extracapsular Extension”, “Seminal Vesicle Invasion” and “Lymph Node Involvement” were obtained. The obtained data were analyzed using Spearman Correlation Coefficient. Results: In general, there was a significant positive correlation between ChatGPT-4o and MSKCC nomogram in all prediction topics (p < 0.001). However, no significant correlation was found between the predictions of “Organ-Confined Disease” (r = 0.521, p = 0.123), “Seminal Vesicle Invasion” (r = 0.382, p = 0.276) and “Lymph Node Involvement” (r = 0.218, p = 0.546) in the high-risk patient group. Similarly, no significant correlation was found between the estimates of “Organ-Confined Disease” (r = 0.522, p = 0.122) and “Extracapsular Extension” (r = 0.524, p = 0.120) in the locally advanced patient group. Conclusion: An overall high correlation between an AI-based chatbot (ChatGPT-4o) and the MSKCC nomogram was demonstrated for prostate cancer risk prediction. However, no significant correlation was observed especially in high-risk and locally advanced patient groups. These findings suggest that while AI chatbots are a potential tool for prostate cancer risk stratification, they require extensive validation and development studies before they can be put into clinical use, especially in more complex and advanced cases.

  • Chatbots’ performance in premature ejaculation questions: a comparative analysis of reliability, readability, and understandability

    by S. Gonultas, S. Kardas, M. Gelmis, A. H. Kinik, M. Ozalevli, M. G. Kose, S. Sulejman, S. Yentur, B. Arslan

    This study aimed to evaluate the reliability, readability, and understandability of chatbot responses to frequently asked questions about premature ejaculation, and to assess the contributions, potential risks, and limitations of artificial intelligence. Fifteen questions were selected using data from Google Trends and posed to the chatbots Copilot, Gemini, ChatGPT4o, ChatGPT4oPlus, and DeepSeek-R1. Reliability was evaluated using the Global Quality Scale(GQS) by two experts, readability was assessed with the Flesch Kincaid Reading Ease(FKRE), Flesch Kincaid Grade Level(FKGL), Gunning Fog Index(GFI), and Simple Measure of Gobbledygook(SMOG), and understandability was evaluated using the Patient Educational Materials Assessment Tool for Printable Materials(PEMAT-P). Additionally, the consistency of source citations was examined. The GQS were as follows: Copilot: 3.96 ± 0.66, Gemini: 3.66 ± 0.78, ChatGPT4o: 4.83 ± 0.23, ChatGPT4oPlus: 4.83 ± 0.29, DeepSeek-R1:4.86 ± 0.22 (p < 0.001). The PEMAT-P were as follows: Copilot: 0.70 ± 0.05, Gemini: 0.72 ± 0.04, ChatGPT4o: 0.83 ± 0.03, ChatGPT4oPlus: 0.77 ± 0.06, DeepSeek-R1:0.79 ± 0.06 (p < 0.001). While ChatGPT4oPlus and DeepSeek-R1 scored higher for reliability and understandability, all chatbots performed at an acceptable level (≥70%). However, readability scores were above the recommended level for the target audience. Instances of low reliability or unverified sources were noted, with no significant differences between the chatbots. Chatbots provide highly reliable and informative responses regarding premature ejaculation; however, it is evident that there are significant limitations that require improvement, particularly concerning readability and the reliability of sources.


  • Open Access

    Etiology of Hematospermia in Turkish Men: Multicentric Study

    by Serkan Gönültaş, Numan Baydilli, Mehmet Solakhan, Ahmet Güzel, Sina Kardaş, Aykut Demirci, Suhejb Sulejman, Serhat Yentür, Kemal Ertaş, Mustafa Gökhan Köse, et al.

    Hematospermia is defined as the presence of blood in the semen. The data regarding its etiology and management is variable across the literature. To investigate the etiology of hematospermia in Türkiye so as to contribute to the current management strategies for hematospermia. An online study protocol was published through the Turkish Urology Association communication network, and the centers that met the criteria were included in the study. All patients who presented with hematospermia complaints in the past 1 year were subjected to detailed anamnesis, physical examination, and routine laboratory tests. Based on the results, the patients were assigned to Group 1 (patients aged < 40 years with only one episode of hematospermia in the past 6 months) or Group 2 (patients with concomitant symptoms or ≥ 40 years or ≥ 2 times in the past 6 months). Radiological imaging was performed for the patients in Group 2. A total of 199 patients (Group 1: 44, Group 2: 155; mean age: 43.07 ± 14.73 years; age range: 16-73 years) from across 42 cities and 22 different centers were enrolled in this study. In the etiological classification, inflammation was identified as the most common cause (n = 76, 38.1%). Idiopathic hematospermia was higher in Group 1 than in Group 2 (70.4% vs. 112.2%, respectively), and hematospermia was associated with malignancy in 9 (5.8%) Group 2 patients. Positivity was detected in urine or semen cultures in 20 (12.9%) patients, and hematospermia occurred after COVID-19 infection in 2 patients. A significant correlation was noted between patients showing no-concomitant symptoms and those showing idiopathic hematospermia, inflammation, malignancy, varicocele, and multiple etiological factors (p = 0.004, p = 0.028, p = 0.002, p = 0.001, p = 0.026, p = 0.016). The most common radiological findings were an increase in the prostate volume (n = 48, 30.9%) and changes in the signal intensities of the seminal vesicles (n = 29, 18.7%). Despite the use of different approaches to manage idiopathic hematospermia, the patients' survey results were generally similar. Hematospermia in all age groups occurs generally due to self-limiting benign causes. Diagnostic imaging should therefore evaluate the elucidate etiology in patients with identified risk factors so as to avoid unnecessary treatments in idiopathic patients.