PubMed İndeksli Yayınlar Koleksiyonu / PubMed Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7645
Browse
2 results
Search Results
Now showing 1 - 2 of 2
Article A Machine Learning Model for Predicting Oligoclonal Band Positivity Using Routine Cerebrospinal Fluid and Serum Biochemical Markers(Oxford University Press Inc, 2025) Gözgöz, Hazar; Orhan, Oğuzhan; Akan Konuk, Başak; Akan, PınarOBJECTIVE: To develop and validate a machine learning model for predicting oligoclonal band (OCB) positivity using routine cerebrospinal fluid (CSF) and serum biochemical markers to improve the diagnostic accuracy and efficiency of assessing intrathecal immunoglobulin G (IgG) synthesis. METHODS: In this retrospective study (n = 1709), an ensemble model was developed using 8 refined CSF and serum parameters. Combining optimized CatBoost, XGBoost, and LightGBM classifiers, the model was trained and evaluated using a 2-phase workflow, including 5-fold cross-validation and validation on independent internal (n = 342) and external (n = 49) cohorts. RESULTS: The developed ensemble model achieved a receiver operating characteristic-area under the curve (ROC-AUC) of 0.902 on the internal test set, significantly outperforming the conventional IgG index (ROC-AUC, 0.795). At its optimal threshold, the model demonstrated an accuracy of 0.830, with a sensitivity of 0.714 and a specificity of 0.916. On the external validation cohort, it achieved 90% accuracy and 96% sensitivity. CONCLUSIONS: A novel machine learning ensemble model accurately predicts OCB positivity using routine laboratory data and demonstrates superior performance compared with the IgG index. This approach represents a significant step in applying artificial intelligence in laboratory medicine, with the potential to enhance diagnostic efficiency. Prospective, multicenter validation is essential for broader clinical implementation. © The Author(s) 2025.Article Citation - Scopus: 4Quasi-Supervised Strategies for Compound-Protein Interaction Prediction(John Wiley and Sons Inc, 2022) Çakı, O.; Karaçalı, B.In-silico compound-protein interaction prediction addresses prioritization of drug candidates for experimental biochemical validation because the wet-lab experiments are time-consuming, laborious and costly. Most machine learning methods proposed to that end approach this problem with supervised learning strategies in which known interactions are labeled as positive and the rest are labeled as negative. However, treating all unknown interactions as negative instances may lead to inaccuracies in real practice since some of the unknown interactions are bound to be positive interactions waiting to be identified as such. In this study, we propose to address this problem using the Quasi-Supervised Learning (QSL) algorithm. In this framework, potential interactions are predicted by estimating the overlap between a true positive dataset of compound-protein pairs with known interactions and an unknown dataset of all the remaining compound-protein pairs. The potential interactions are then identified as those in the unknown dataset that overlap with the interacting pairs in the true positive dataset in terms of the associated similarity structure. We also address the class-imbalance problem by modifying the conventional cost function of the QSL algorithm. Experimental results on GPCR and Nuclear Receptor datasets show that the proposed method can identify actual interactions from all possible combinations. © 2021 Wiley-VCH GmbH.