ANALYSIS OF NEUROONCOLOGICAL DATA TO PREDICT SUCCESS OF OPERATION THROUGH CLASSIFICATION

2016-10-05
Bagherzadi, Negin
BÖRCEK, ALP ÖZGÜN
TOKDEMİR, GÜL
ÇAĞILTAY, NERGİZ
MARAŞ, HADİ HAKAN
Data mining algorithms have been applied in various fields of medicine to get insights about diagnosis and treatment of certain diseases. This gives rise to more research on personalized medicine as patient data can be utilized to predict outcomes of certain treatment procedures. Accordingly, this study aims to create a model to provide decision support for surgeons in Neurooncology surgery. For this purpose, we have analyzed clinical pathology records of Neurooncology patients through various classification algorithms, namely Support Vector Machine, Multi Perceptron and Naive Bayes methods, and compared their performances with the aim of predicting surgery complication. A large number of factors have been considered to classify and predict percentage of patient's complication in surgery. Some of the factors found to be predictive were age, sex, clinical presentation, previous surgery type etc. For classification models built up using Support Vector Machine, Naive Bayes and Multi Perceptron, Classification trials for Support Vector Machine have shown %77.47 generalization accuracy, which was established by 5-fold cross-validation.

Suggestions

CAD for detection of microcalcification and classification in mammograms
AKBAY, Cansu; Gençer, Nevzat Güneri; GENÇER, Gülay (2014-10-17)
In this study, computer aided diagnosis (CAD) is developed to detect microcalficication cluster which is one of the important radiological findings of breast cancer diagnosis and classificiation. For this purpose, image processing and pattern recognition algorithms are applied on mamographic images. To make microcalcifications more visible wavelet transform and nonsubsampled contourlet transform (NSCT) methods are used for image enhancement. Their performances are compared. 52 features are extracted from th...
Score test for testing etiologic heterogeneity in two-stage polytomous logistic regression
Karagülle, Saygın; Kalaylıoğlu Akyıldız, Zeynep Işıl; Department of Statistics (2013)
Two-stage polytomous logistic regression was proposed by Chatterjee (2004) as an effective tool to analyze epidemiological data when disease subtype information is available. In this modeling approach, a classic logistic regression is employed in the first level of the model. In the second level, the first-stage regression parameters are modeled as a function of some contrast parameters in a somehow similar spirit of an ANOVA model. This modeling also enables a practical way of estimating the heterogeneity ...
MODELLING OF KERNEL MACHINES BY INFINITE AND SEMI-INFINITE PROGRAMMING
Ozogur-Akyuz, S.; Weber, Gerhard Wilhelm (2009-06-03)
In Machine Learning (ML) algorithms, one of the crucial issues is the representation of the data. As the data become heterogeneous and large-scale, single kernel methods become insufficient to classify nonlinear data. The finite combinations of kernels are limited up to a finite choice. In order to overcome this discrepancy, we propose a novel method of "infinite" kernel combinations for learning problems with the help of infinite and semi-infinite programming regarding all elements in kernel space. Looking...
Evaluation and Analysis of Different Aggregation and Hyperparameter Selection Methods for Federated Brain Tumor Segmentation
Polat, Görkem; Işık Polat, Ece; Koçyiğit, Altan; Temizel, Alptekin (2021-9-27)
Availability of large, diverse, and multi-national datasets is crucial for the development of effective and clinically applicable AI systems in the medical imaging domain. However, forming a global model by bringing these datasets together at a central location, comes along with various data privacy and ownership problems. To alleviate these problems, several recent studies focus on the federated learning paradigm, a distributed learning approach for decentralized data. Federated learning leverages all the ...
A test for detecting etiologic heterogeneity in epidemiological studies
Karagulle, S.; Kalaylıoğlu Akyıldız, Zeynep Işıl (2016-02-17)
Current statistical methods for analyzing epidemiological data with disease subtype information allow us to acquire knowledge not only for risk factor-disease subtype association but also, on a more profound account, heterogeneity in these associations by multiple disease characteristics (so-called etiologic heterogeneity of the disease). Current interest, particularly in cancer epidemiology, lies in obtaining a valid p-value for testing the hypothesis whether a particular cancer is etiologically heterogene...
Citation Formats
N. Bagherzadi, A. Ö. BÖRCEK, G. TOKDEMİR, N. ÇAĞILTAY, and H. H. MARAŞ, “ANALYSIS OF NEUROONCOLOGICAL DATA TO PREDICT SUCCESS OF OPERATION THROUGH CLASSIFICATION,” 2016, p. 485, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/68171.