Yazar "Canbolat, Zehra Nur" seçeneğine göre listele
Listeleniyor 1 - 6 / 6
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A machine learning approach to predict creatine kinase test results(Ital Publication, 2020) Canbolat, Zehra Nur; Silahtaroğlu, Gökhan; Doğuç, Özge; Yılmaztürk, NevinMost of the research done in the literature are based on statistical approaches and used for deriving reference limits based on lab results. As more data are available to the researchers, ML methods are more effectively used by the clinicians and practitioners to reduce cost and provide more accurate diagnoses. This study aims to contribute to the medical laboratory processes by providing an automated method in order to predict the lab results accurately by machine learning from the previous test results. All patient data obtained have been anonymized, and a total of 449,471 test results have been used to build an integrated dataset. A total of 107,646 unique patients’ data has been used. This study aims to predict the value range of the Creatine Kinase tests, which are taken in separate tubes and usually needs more processing time than the other tests do. Using the lab results and the Random Forest Algorithm, this study reports that the outcome of the Creatine Kinase test can be determined with 97% accuracy by using the AST and ALT test values. This is an important achievement for the practitioners and the patients, as this study submits significant reduction in Creating Kinase test evaluation time.Öğe A strategic approach to reduce energy imports of E7 countries: Use of renewable energy(IGI Global, 2021) Dinçer, Hasan; Yüksel, Serhat; Canbolat, Zehra NurHigher technological developments, product diversity, international trade, and population growth have greatly increased the energy demand of countries. It is very significant that this growing demand should be satisfied with a safe and accessible energy source. Because of this issue, it is thought that countries should be directed towards renewable energy sources so that these countries can meet their rising energy demand without increasing their energy imports. This chapter aims to identify the causal relationship between the use of renewable energy and energy imports. Within this framework, the data between 1990 and 2015 of E7 countries (Brazil, China, Indonesia, India, Mexico, Russia, and Turkey) is taken into the consideration by using the Pedroni panel cointegration method and the Dumitrescu Hurlin panel causality analysis. Results show that there is a long-term relationship between energy imports and renewable energy usage, but there is no causal relationship between energy imports and renewable energy usage. This situation gives information that the use of renewable energy is important and effective in order to reduce imports, but using only this method is not sufficient to remove the import problem for these countries.Öğe An early prediction and diagnosis of sepsis in intensive care units: An unsupervised machine learning model(Mugla University, 2020) Canbolat, Zehra Nur; Silahtaroğlu, GökhanSepsis infection, which is one of the most important causes of death in intensive care units, is seen as a severe global health crisis. If an early diagnosis of sepsis infection cannot be made, and treatment is not started rapidly, septic shock may result in multiple organ failure and death is almost inevitable. Therefore, it is vital to establish an early diagnosis and start the treatment at once. This study aims to accomplish a new model of unsupervised machine learning using lactate and Ph laboratory test values, which are considered to be important parameters to diagnose sepsis infection. The data used in the study have been obtained from MIMIC-III international clinical database. Unsupervised machine learning has been performed via the Fuzzy-C algorithm along with validity indexes like Xie Beni on patients’ data diagnosed sepsis and non-sepsis. The machine-generated ten labels at the end of the training session considering-designed validity indexes. The labelled cluster representatives have been reduced to two dimensions by Principal Component Analysis method in order to monitor the learning in a two-dimensional space. The study contributes to the literature by conducting unsupervised learning through two parameters (Lactate and Ph) and leading to multi-parameter studies. In addition, the study reports that there are five types of sepsis patterns in terms of Lactate and PH laboratory tests.Öğe Data mining-based evaluating the customer satisfaction for the mobile applications: An analysis on Turkish banking sector by using IT2 fuzzy dematel(IGI Global, 2019) Dinçer, Hasan; Yüksel, Serhat; Canbolat, Zehra Nur; Pınarbaşı, FatihThe aim of this study is to evaluate the customer satisfaction for mobile applications in the Turkish banking industry. For this purpose, the last 500 customer comments of 24 different Turkish deposit banks' mobile applications are analyzed with data mining approach. In this process, the most frequent one keyword, two keywords and three keywords are identified, and the most important dimensions are classified into four different categories. Secondly, IT2 fuzzy DEMATEL methodology is considered to weight these dimensions. The findings show that operational and usability are the most important dimensions regarding the customer satisfaction in mobile applications. This situation explains that customers give importance to the quality and variability of the services given by the mobile applications. Hence, it is recommended that different services, such as credit card payment and money transferring should be provided in these applications by the banks. Another important point is that these applications should.Öğe Diagnosis of Covid-19 via patient breath data using artificial intelligence(Ital Publication, 2023) Doğuç, Özge; Silahtaroğlu, Gökhan; Canbolat, Zehra Nur; Hambarde, Kailash; Yiğitbaşı, Ahmet Alperen; Gökay, Hasan; Yılmaz, MesutUsing machine learning algorithms for the rapid diagnosis and detection of the COVID-19 pandemic and isolating the patients from crowded environments are very important to controlling the epidemic. This study aims to develop a point-of-care testing (POCT) system that can detect COVID-19 by detecting volatile organic compounds (VOCs) in a patient's exhaled breath using the Gradient Boosted Trees Learner Algorithm. 294 breath samples were collected from 142 patients at Istanbul Medipol Mega Hospital between December 2020 and March 2021. 84 cases out of 142 resulted in negatives, and 58 cases resulted in positives. All these breath samples have been converted into numeric values through five air sensors. 10% of the data have been used for the validation of the model, while 75% of the test data have been used for training an AI model to predict the coronavirus presence. 25% have been used for testing. The SMOTE oversampling method was used to increase the training set size and reduce the imbalance of negative and positive classes in training and test data. Different machine learning algorithms have also been tried to develop the e-nose model. The test results have suggested that the Gradient Boosting algorithm created the best model. The Gradient Boosting model provides 95% recall when predicting COVID-19 positive patients and 96% accuracy when predicting COVID-19 negative patients.Öğe Recent applications of data mining in medical diagnosis and prediction(Elsevier, 2022) Doğuç, Özge; Canbolat, Zehra Nur; Silahtaroğlu, GökhanBig data has been used in the health sector to improve the quality of life, predict epidemics, cure diseases, and avoid preventable deaths, beyond increasing profits or reducing the burden of excess labor. Data sources in healthcare have become quite diversified and accessible to individuals, such as wearable and implantable devices, smartphones, and real-time sensors. When combined with existing health data, daily (even instantaneous) data from these devices can be used to predict future health conditions of individuals and to identify necessary intervention points. This chapter discusses a number of recent studies that introduces methods for using big data to create intelligent systems for patient diagnosis, triage, predicting lab results, and even detecting tumors. These studies open ways for researchers in the healthcare sector to improve the quality of services provided to the patients as well as reducing costs for the healthcare institutions.
