Yazar "Kadry, Seifedine" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Cancer Metastasis Prediction and Genomic Biomarker Identification through Machine Learning and eXplainable Artificial Intelligence in Breast Cancer Research
    (Mdpi, 2023) Yagin, Burak; Yagin, Fatma Hilal; Colak, Cemil; Inceoglu, Feyza; Kadry, Seifedine; Kim, Jungeun
    Aim: Method: This research presents a model combining machine learning (ML) techniques and eXplainable artificial intelligence (XAI) to predict breast cancer (BC) metastasis and reveal important genomic biomarkers in metastasis patients. Method: A total of 98 primary BC samples was analyzed, comprising 34 samples from patients who developed distant metastases within a 5-year follow-up period and 44 samples from patients who remained disease-free for at least 5 years after diagnosis. Genomic data were then subjected to biostatistical analysis, followed by the application of the elastic net feature selection method. This technique identified a restricted number of genomic biomarkers associated with BC metastasis. A light gradient boosting machine (LightGBM), categorical boosting (CatBoost), Extreme Gradient Boosting (XGBoost), Gradient Boosting Trees (GBT), and Ada boosting (AdaBoost) algorithms were utilized for prediction. To assess the models' predictive abilities, the accuracy, F1 score, precision, recall, area under the ROC curve (AUC), and Brier score were calculated as performance evaluation metrics. To promote interpretability and overcome the black box problem of ML models, a SHapley Additive exPlanations (SHAP) method was employed. Results: The LightGBM model outperformed other models, yielding remarkable accuracy of 96% and an AUC of 99.3%. In addition to biostatistical evaluation, in XAI-based SHAP results, increased expression levels of TSPYL5, ATP5E, CA9, NUP210, SLC37A1, ARIH1, PSMD7, UBQLN1, PRAME, and UBE2T (p <= 0.05) were found to be associated with an increased incidence of BC metastasis. Finally, decreased levels of expression of CACTIN, TGFB3, SCUBE2, ARL4D, OR1F1, ALDH4A1, PHF1, and CROCC (p <= 0.05) genes were also determined to increase the risk of metastasis in BC. Conclusion: The findings of this study may prevent disease progression and metastases and potentially improve clinical outcomes by recommending customized treatment approaches for BC patients.
  • Küçük Resim Yok
    Öğe
    Game-theoretic DEA optimization for sustainable agricultural carbon trading: Evidence from Türkiye's maize production
    (Pergamon-Elsevier Science Ltd, 2026) Hamidoglu, Ali; Candemir, Serhan; Bayramoglu, Zeki; Dogan, Hasan Gokhan; Agizan, Kemalettin; Kadry, Seifedine
    Effective agricultural carbon policy requires reliable monitoring and frameworks that consider efficiency, welfare, and adoption. Although monitoring systems are typically stronger in developed countries, they are costly to maintain, whereas in developing countries they are often limited or insufficient. We hypothesize that a performance-based carbon policy integrated with welfare and farm decision behavior improves suitability for heterogeneous agricultural settings under limited emissions data. This paper proposes a Forward-Looking Cooperative Cap-and-Trade Carbon Pricing (FCTCP), policy that assesses farms' carbon performance using carbon-equivalent resource, operational, and agrochemical inputs instead of direct carbon emission data, while integrating farm-level decision-making, cooperative carbon trading, and a welfare indicator aligned with emission performance. In this framework, farms are classified using Data Envelopment Analysis into efficient, near-efficient, and inefficient categories, and their policy participation is modeled through a cooperative Nash game. Nonlinear strategic interactions are solved using a hybrid optimization scheme consisting of four metaheuristic algorithms, including Particle Swarm Optimization, Artificial Bee Colony, Grey Wolf Optimizer, and Genetic Algorithm, and a nonlinear quasi-Newton optimization method, L-BFGS-B, to identify robust Nash equilibria. A case study of 104 maize farms in T & uuml;rkiye shows green welfare improvements of 9.65% for near-efficient farms and 15.23% for inefficient farms while achieving the low-carbon benchmark. Key determinants of adoption include efficiency-based caps, asymmetric trading rules, and carbon exchange without discounting. The results demonstrate that FCTCP is a practical, welfare-linked, and forward-looking policy mechanism capable of guiding early-stage carbon transitions in agricultural systems lacking mature carbon monitoring infrastructure.