Preferred Language
Articles
/
bRfWXJMBVTCNdQwC29Le
Comparative study of logistic regression and artificial neural networks on predicting breast cancer cytology

<p>Currently, breast cancer is one of the most common cancers and a main reason of women death worldwide particularly in<strong> </strong>developing countries such as Iraq. our work aims to predict the type of tumor whether benign or malignant through models that were built using logistic regression and neural networks and we hope it will help doctors in detecting the type of breast tumor. Four models were set using binary logistic regression and two different types of artificial neural networks namely multilayer perceptron MLP and radial basis function RBF. Evaluation of validated and trained models was done using several performance metrics like accuracy, sensitivity, specificity, and AUC (area under receiver operating characteristic ROC).   Dataset was downloaded from UCI ml repository; it is composed of 9 attributes and 699 samples. The findings are clearly showing that the RBF NN classifier is the best in prediction of the type of breast tumors since it had recorded the highest performance in terms of correct classification rate (accuracy), sensitivity, specificity, and AUC (area under Receiver Operating Characteristic ROC) among all other models.</p>

Scopus Crossref
View Publication
Publication Date
Sun Jan 02 2011
Journal Name
Journal Of The Faculty Of Medicine Baghdad
Comparative demographic and clinicopathological study on the behavior of mammary carcinoma in three Iraqi governorates (Baghdad, Hilla and Karbala)

Background: Breast cancer is the most common malignant tumor in women worldwide. In Iraq, there is a tendency for this disease to be diagnosed in younger ages, at advanced stages with a prevalence of more aggressive tumor behavior.
Patients and Methods: The study included a total of 216 women with breast lumps and proven breast cancer who visited the Main Referral Training Center for Early Detection of Breast Tumors in the Medical City Teaching Hospital in Baghdad (85 patients) and the Specialized Clinics belonging to the major hospitals of Hilla (62 patients) and Karbala (69 patients) complaining of apparent breast lumps.
Results: 31% of patients was in the age category (40-49 years), 38.4% of patients who

... Show More
Crossref (2)
Crossref
View Publication Preview PDF
Publication Date
Fri Jan 01 2021
Journal Name
Journal Of Economics And Administrative Sciences
Comparison of survival models to study determinants liver cancer

Cancer is one of the dangerous diseases that afflict a person through injury to cells and tissues in the body, where a person is vulnerable to infection in any age group, and it is not easy to control and multiply between cells and spread to the body. In spite of the great progress in medical studies interested in this aspect, the options for those with this disease are few and difficult, as they require significant financial costs for health services and for treatment that is difficult to provide.

This study dealt with the determinants of liver cancer by relying on the data of cancerous tumours taken from the Iraqi Center for Oncology in the Ministry of Health 2017. Survival analysis has been used as a m

... Show More
Crossref
View Publication Preview PDF
Publication Date
Wed Jan 13 2021
Journal Name
Iraqi Journal Of Science
MRI Probabilistic Neural Network Screening System: a benign and malignant recognition case study

This work is aimed to design a system which is able to diagnose two types of tumors in a human brain (benign and malignant), using curvelet transform and probabilistic neural network. Our proposed method follows an approach in which the stages are preprocessing using Gaussian filter, segmentation using fuzzy c-means and feature extraction using curvelet transform. These features are trained and tested the probabilistic neural network. Curvelet transform is to extract the feature of MRI images. The proposed screening technique has successfully detected the brain cancer from MRI images of an almost 100% recognition rate accuracy.

Scopus Crossref
View Publication Preview PDF
Publication Date
Thu Mar 24 2022
Journal Name
Arab World English Journal
Collocation Networks of Selected Words in Academic Writing: A Corpus-Based Study

This study aims at shedding light on the linguistic significance of collocation networks in the academic writing context. Following Firth’s principle “You shall know a word by the company it keeps.” The study intends to examine three selected nodes (i.e. research, study, and paper) shared collocations in an academic context. This is achieved by using the corpus linguistic tool; GraphColl in #LancsBox software version 5 which was announced in June 2020 in analyzing selected nodes. The study focuses on academic writing of two corpora which were designed and collected especially to serve the purpose of the study. The corpora consist of a collection of abstracts extracted from two different academic journals that publish for writ

... Show More
Clarivate Crossref
View Publication
Publication Date
Tue Jun 14 2016
Journal Name
Al-academy
Idealism and Realism in The Design: A Comparative Study

At the beginning of the twentieth century distorting handling totalitarian phenomena of art, which can be called the stage of the test, transition from the theory of ideal theory and other realistic is not cushy, since it requires vision and reading and other concepts, and in light of this dialectic manifested research problem by asking the following Is affected by the design idealism and realism. Through the above mentioned questions, the researcher found rationale for addressing this problem, the study through his research, which is marked (idealism and realism in a comparative study design). And demonstrated the importance of research in the identification of the concept and the effectiveness of the two theories idealism and realism a

... Show More
Crossref
View Publication Preview PDF
Publication Date
Thu Apr 20 2023
Journal Name
Ibn Al-haitham Journal For Pure And Applied Sciences
A Comparative Biochemical Study Between Patient’s Obese and Healthy

Objectives: Obesity rates have increased globally with increase in the incidence of comorbidities especially type 2 diabetes mellitus. A cross-sectional study was conducted on healthy obese adults to estimate: (i) comparisons of anthropometric indicators, lipid profile, and glycemic profile in obese compared with non-obese, and (ii) the association of anthropometrics and lipid profile with glycemic profile in obese adults. Methods: The study includes 120 individual with aged ranged (25 – 55) years were enrolled in this study. They were divided into two groups: group one (G1) consist of 90 patients with a body mass index (BMI) of more than 25 kg/m2. Group two (G2) of 30 healthy adults as a co

... Show More
Crossref
View Publication Preview PDF
Publication Date
Sat Jul 31 2021
Journal Name
Journal Of Legal Sciences
Suicide attempt between criminalization and legalization: A comparative study

Hardly a day passes without hearing the news of a person’s suicide here or there, as if life no longer has value for a person, and this fact is what prompted the World Health Organization to sound the alarm, after it found that suicide had become widespread in the world and published its report Under the title (Suicide Prevention - A Global Necessity), and announced the need to take care of mental Health as part of public health, because what psychological human crises are exposed to may lead to suicide.

      A quick look at the position of the various legislations on suicide, we find there is a great difference, some legislations recognize the human right to death, while other legislation punishes the

... Show More
Crossref
View Publication Preview PDF
Publication Date
Sun Mar 12 2017
Journal Name
Ibn Al-haitham Journal For Pure And Applied Sciences
Comparative Anatomical Study between Typha domengensis and Phragmites communis

       Both of the species Typha domengensis and Phragmites communis among the most important plant endemic in flora of Iraq from monocotyledon.  Due to the similarity of the two species with each other in many morphological characteristics such as the environment where they live and the form of leaves and type of leaf venation and type of stomata….ets, also both of species belong to monocots plant therefore this research work was conducted find anatomical differences that have the same as taxonomic value to help distinguishing between both species under study.     Through this research, we found great importance to the anatomical characteristics which we reached by studying th

... Show More
View Publication Preview PDF
Publication Date
Tue Feb 28 2023
Journal Name
Iraqi Journal Of Science
Studying some cytotoxic and cytogenetic potentials of Dandelion methanolic extract on MCF-7 cancer cell line: an in vitro study

      This study aimed to evaluate the anticancer activity and cell division arresting by dandelion methanolic extract on breast cancer cell line MCF-7 cancer cell line. For achieving this goal, cytotoxicity assay (MTT assay), multipara system assay: High Content Screening (HCS) which include (viable cell count VCC; membrane permeability MP; cellular mitochondrial permeability CMP; nuclear intensity NI and cytochrome C releasing ), reactive oxygen species detection and cell cycle phases division were tested. The results of this study showed the ability of the plant to reduce cancer cell viability in a dose-dependant manner within IC50 (141.0) in comparison to IC50 of (334.4) on the

... Show More
Scopus (4)
Crossref (1)
Scopus Crossref
View Publication Preview PDF
Publication Date
Sun Feb 25 2024
Journal Name
Baghdad Science Journal
Exploring Important Factors in Predicting Heart Disease Based on Ensemble- Extra Feature Selection Approach

Heart disease is a significant and impactful health condition that ranks as the leading cause of death in many countries. In order to aid physicians in diagnosing cardiovascular diseases, clinical datasets are available for reference. However, with the rise of big data and medical datasets, it has become increasingly challenging for medical practitioners to accurately predict heart disease due to the abundance of unrelated and redundant features that hinder computational complexity and accuracy. As such, this study aims to identify the most discriminative features within high-dimensional datasets while minimizing complexity and improving accuracy through an Extra Tree feature selection based technique. The work study assesses the efficac

... Show More
Scopus (1)
Scopus Crossref
View Publication Preview PDF