Tıp Fakültesi / Faculty of Medicine
Permanent URI for this collectionhttps://hdl.handle.net/11727/1403
Browse
3 results
Search Results
Item Machine Learning Insights Into Uric Acid Elevation With Thiazide Therapy Commencement and Intensification(2023) Ozdede, Murat; Guven, Alper T.; 38274913Background Elevated serum uric acid, associated with cardiovascular conditions such as atherosclerotic heart disease, hypertension, and heart failure, can be elevated by thiazide or thiazide-like drugs (THZ), essential in hypertension management. Identifying clinical determinants affecting THZ-related uric acid elevation is critical. Methods In this retrospective cross-sectional study, we explored the clinical determinants influencing uric acid elevation related to THZ, focusing on patients where THZ was initiated or the dose escalated. A cohort of 143 patients was analyzed, collecting baseline and control uric acid levels, alongside basic biochemical studies and clinical data. Feature selection was conducted utilizing criteria based on mean squared error increase and enhancement in node purity. Four machine learning algorithms - Random Forest, Neural Network, Support Vector Machine, and Gradient Boosting regressions - were applied to pinpoint clinical influencers. Results Significant features include uncontrolled diabetes, index estimated Glomerular Filtration Rate (eGFR) level, absence of insulin, action of indapamide, and absence of statin treatment, with absence of Sodium -glucose cotransporter 2 inhibitors (SGLT2i), low dose aspirin exposure, and older age also being noteworthy. Among the applied models, the Gradient Boosting regression model outperformed the others, exhibiting the lowest Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE) values, and the highest R2 value (0.779). While Random Forest and Neural Network regression models were able to fit the data adequately, the Support Vector Machine demonstrated inferior metrics. Conclusions Machine learning algorithms are adept at accurately identifying the factors linked to uric acid fluctuations caused by THZ. This proficiency aids in customizing treatments more effectively, reducing the need to unnecessarily avoid THZ, and providing guidance on its use to prevent instances where uric acid levels could become problematic.Item Searching For The Urine Osmolality Surrogate: An Automated Machine Learning Approach(2022) Topcu, Deniz Ilhan; Bayraktar, Nilufer; https://orcid.org/0000-0002-1219-6368; https://orcid.org/0000-0002-7886-3688; 000819864400001; E-3717-2019; Y-8758-2018Objectives Automated machine learning (AutoML) tools can help clinical laboratory professionals to develop machine learning models. The objective of this study was to develop a novel formula for the estimation of urine osmolality using an AutoML tool and to determine the efficiency of AutoML tools in a clinical laboratory setting. Methods Three hundred routine urinalysis samples were used for reference osmolality and urine clinical chemistry analysis. The H2O AutoML engine completed the machine learning development steps with minimum human intervention. Four feature groups were created, which include different urinalysis measurements according to the Boruta feature selection algorithm. Method comparison statistics including Spearman correlation, Passing-Bablok regression analysis were performed, and Bland Altman plots were created to compare model predictions with the reference method. The minimum allowable bias (24.17%) from biological variation data was used as the limit of agreement. Results The AutoML engine developed a total of 183 ML models. Conductivity and specific gravity had the highest variable importance. Models that include conductivity, specific gravity, and other urinalysis parameters had the highest R-2 (0.70-0.83), and 70-84% of results were within the limit of agreement. Conclusions Combining urinary conductivity with other urinalysis parameters using validated machine learning models can yield a promising surrogate. Additionally, AutoML tools facilitate the machine learning development cycle and should be considered for developing ML models in clinical laboratories.Item A novel prediction method for lymph node involvement in endometrial cancer: machine learning(2019) Gunakan, Emre; Atan, Suat; Haberal, Asuman Nihan; Kucukyildiz, Irem Alyazici; Gokce, Ehad; Ayhan, Ali; 30718313Objective The necessity of lymphadenectomy and the prediction of lymph node involvement (LNI) in endometrial cancer (EC) have been hotly-debated questions in recent years. Machine learning is a broad field that can produce results and estimations. In this study we constructed prediction models for EC patients using the Naive Bayes machine learning algorithm for LNI prediction. Methods The study assessed 762 patients with EC. Algorithm models were based on the following histopathological factors: V1: final histology; V2: presence of lymphovascular space invasion (LVSI); V3: grade; V4: tumor diameter; V5: depth of myometrial invasion (MI); V6: cervical glandular stromal invasion (CGSI); V7: tubal or ovarian involvement; and V8: pelvic LNI. Logistic regression analysis was also used to evaluate the independent factors affecting LNI. Results The mean age of patients was 59.1 years. LNI was detected in 102 (13.4%) patients. Para-aortic LNI (PaLNI) was detected in 54 (7.1%) patients, of which four patients had isolated PaLNI. The accuracy rate of the algorithm models was found to be between 84.2% and 88.9% and 85.0% and 97.6% for LNI and PaLNI, respectively. In multivariate analysis, the histologic type, LVSI, depth of MI, and CGSI were independently and significantly associated with LNI (p<0.001 for all). Conclusions Machine learning may have a place in the decision tree for the management of EC. This is a preliminary report about the use of a new statistical technique. Larger studies with the addition of sentinel lymph node status, laboratory findings, or imaging results with machine learning algorithms may herald a new era in the management of EC.