ABSTRACT
BACKGROUND: In this research, an astute system has been developed by using machine learning and data mining approach to predict the risk level of cervical and ovarian cancer in association to stress. RESULTS: For functioning factors and subfactors, several machine learning models like Logistics Regression, Random Forest, AdaBoost, Naïve Bayes, Neural Network, kNN, CN2 rule Inducer, Decision Tree, Quadratic Classifier were compared with standard metrics e.g., F1, AUC, CA. For certainty info gain, gain ratio, gini index were revealed for both cervical and ovarian cancer. Attributes were ranked using different feature selection evaluators. Then the most significant analysis was made with the significant factors. Factors like children, age of first intercourse, age of husband, Pap test, age are the most significant factors of cervical cancer. On the other hand, genital area infection, pregnancy problems, use of drugs, abortion, and the number of children are important factors of ovarian cancer. CONCLUSION: Resulting factors were merged, categorized, weighted according to their significance level. The categorized factors were indexed using ranker algorithm which provides them a weightage value. An algorithm has been formulated afterward which can be used to predict the risk level of cervical and ovarian cancer in relation to women's mental health. The research will have a great impact on the low incoming country like Bangladesh as most women in low incoming nations were unaware of it. As these two can be described as the most sensitive cancers to women, the development of the application from algorithm will also help to reduce women's mental stress. More data and parameters will be added in future for research in this perspective.
Subject(s)
Machine Learning , Neoplasms , Algorithms , Bayes Theorem , Child , Female , Humans , Logistic Models , Neural Networks, Computer , PregnancyABSTRACT
BACKGROUND: Worldwide, more than 80% of identified lung cancer cases are associated to the non-small cell lung cancer (NSCLC). We used microarray gene expression dataset GSE10245 to identify key biomarkers and associated pathways in NSCLC. RESULTS: To collect Differentially Expressed Genes (DEGs) from the dataset GSE10245, we applied the R statistical language. Functional analysis was completed using the Database for Annotation Visualization and Integrated Discovery (DAVID) online repository. The DifferentialNet database was used to construct Protein-protein interaction (PPI) network and visualized it with the Cytoscape software. Using the Molecular Complex Detection (MCODE) method, we identify clusters from the constructed PPI network. Finally, survival analysis was performed to acquire the overall survival (OS) values of the key genes. One thousand eighty two DEGs were unveiled after applying statistical criterion. Functional analysis showed that overexpressed DEGs were greatly involved with epidermis development and keratinocyte differentiation; the under-expressed DEGs were principally associated with the positive regulation of nitric oxide biosynthetic process and signal transduction. The Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway investigation explored that the overexpressed DEGs were highly involved with the cell cycle; the under-expressed DEGs were involved with cell adhesion molecules. The PPI network was constructed with 474 nodes and 2233 connections. CONCLUSIONS: Using the connectivity method, 12 genes were considered as hub genes. Survival analysis showed worse OS value for SFN, DSP, and PHGDH. Outcomes indicate that Stratifin may play a crucial role in the development of NSCLC.
ABSTRACT
In this article, dataset and detailed data analysis results of Type-1 Diabetes has been given. Now-a-days Type-1 Diabetes is an appalling disease in Bangladesh. Total 306 person data (Case group- 152 and Control Group- 154) has been collected from Dhaka based on a specific questioner. The questioner includes 22 factors which were extracted by research studies. The association and significance level of factors has been elicited by using Data mining and Statistical Approach and shown in the Tables of this article. Moreover, parametric probability along with decision tree has been formed to show the effectiveness of the data was provided. The data can be used for future work like risk prediction and specific functioning on Type-1 Diabetes.
ABSTRACT
BACKGROUND: In this article, a hybrid photonic crystal fiber has been proposed for chemical sensing. A FEM has been applied for numerical investigation of some propagation characteristics of the PCF at a wider wavelength from 0.7 to 1.7 µm. The geometrical parameters altered to determine the optimized values. The proposed PCF contains three rings of circular holes in the cladding where the core is formulated with microstructure elliptical holes. RESULTS: The simulation result reveals that our proposed PCF exhibits high sensitivity and low confinement loss for benzene, ethanol and water than the prior PCFs. We have also shown that our proposed PCF shows high birefringence for benzene 1.544 × 10(-3), for ethanol 1.513 × 10(-3) and for water 1.474 × 10(-3) at λ = 1.33 µm. CONCLUSION: The proposed PCF is simple with three rings which can be used for the sensing applications of industrially valuable lower indexed chemicals.
ABSTRACT
BACKGROUND: In the low incoming country Bangladesh, breast cancer is second most common neoplasm and is increasing at an alarming rate among females. Lack of awareness and illiteracy are contributory factors for late presentation and therefore mortality. PURPOSE: To examine associations of different factors with breast cancer mortality and to raise awareness among the women of society in Bangladesh. MATERIALS AND METHODS: This descriptive case-control study was conducted on 160 participants from April 2011 till July 2014. Through a valid questionnaire covering personal and family history, data were collected by face to face interview. For analyzing correlations among factors with breast cancer data, binary logistic regression, Pearson's χ2- value, odd ratios and p-value tests were conducted with SPSS version 20. RESULTS: The mean age of the patients was 43.0 (SD= ± 11.12). In ascending order the leading significant factors were hormone therapy (p<0.0000, OR=4.897), abortion (p<0.0001, OR=3.452), early start menarche (p<0.0002, OR=3.500), family history (p<0.0022, OR=3.235), and late menopause (p<0.0093, OR=3.674) with both χ2 test and logistic regression analyses. Non-significant factors were cancer experience, fatty food habits, marital status and taking alcohol. CONCLUSIONS: Regarding the investigation of this study, significant and insignificant factor's correlation visualization with breast cancer will be helpful to increase awareness among Bangladeshi women as well as all over the world.
