Diagnosis of Diabetes Mellitus in Women of Reproductive Age using the Prediction Methods of Naive Bayes, Discriminant Analysis, and Logistic Regression

Diabetes is a chronic disease that can cause serious illness. Women are four times more likely to develop heart problems caused by diabetes. Women are also more prone to experience complications due to diabetes, such as kidney problems, depression, and decreased vision quality. Nearly 200 million women worldwide are affected by diabetes, with two out of five affected by the disease being women of reproductive age. This paper aims to predict women with at least 21 years of age having diabetes based on eight diagnostic measurements using the statistical learning methods; Multinomial Naive Bayes, Fisher Discriminant Analysis, and Logistic Regression. Model validation is built based on dividing the data into training data and test data based on 5-fold cross-validation. The model validation performance shows that the Gaussian Naïve Bayes is the best method in predicting diabetes diagnosis. This paper’s contribution is that all performance measures of the Multinomial Naïve Bayes method have a value greater than 93 %. These results are beneficial in predicting diabetes status with the same explanatory variables.

Download Full-text

Financial Statement Audit Utilising Naive Bayes Networks, Decision Trees, Linear Discriminant Analysis and Logistic Regression

The Importance of New Technologies and Entrepreneurship in Business Development: In The Context of Economic Diversity in Developing Countries - Lecture Notes in Networks and Systems ◽

10.1007/978-3-030-69221-6_97 ◽

2021 ◽

pp. 1305-1320

Author(s):

Aram Khalaf Nawaiseh ◽

Maysam F. Abbod

Keyword(s):

Logistic Regression ◽

Discriminant Analysis ◽

Linear Discriminant Analysis ◽

Decision Trees ◽

Naive Bayes ◽

Naïve Bayes ◽

Financial Statement ◽

Linear Discriminant ◽

Financial Statement Audit ◽

Bayes Networks

Download Full-text

Prevalence of Goiter and Associated Factors among Women of Reproductive Age Group in Demba Gofa Woreda, Gamo Gofa Zone, Southwest Ethiopia: A Community-Based Cross-Sectional Study

Journal of Nutrition and Metabolism ◽

10.1155/2020/5102329 ◽

2020 ◽

Vol 2020 ◽

pp. 1-9

Author(s):

Befikaduwa Zekarias ◽

Frehiwot Mesfin ◽

Bezatu Mengiste ◽

Adane Tesfaye ◽

Lemma Getacher

Keyword(s):

Logistic Regression ◽

Iodine Deficiency ◽

Associated Factors ◽

Sampling Technique ◽

Iodized Salt ◽

Reproductive Age ◽

Age Group ◽

Women Of Reproductive Age ◽

Cross Sectional ◽

Reproductive Age Group

Background. Iodine deficiency disorder is a major public health problem in Ethiopia that is more common in women of reproductive age. However, it is not well addressed and there is a lack of information on its prevalence and associated factors in women of reproductive age group. Therefore, the objective of this study was to assess goiter prevalence and associated factors among women of reproductive age in the Demba Gofa woreda, Gamo Gofa Zone, Southwest Ethiopia. Methods. A community-based cross-sectional study was used among 584 randomly selected women in the reproductive age group from February 05 to April 20, 2016. A simple random sampling technique was used to select the study kebeles, and a systematic random sampling technique was used to select the study samples. Data were collected through a pretested questionnaire, and the goiter examination was done clinically for each participant. The collected data were coded and entered into a computer for statistical analysis using EpiData version 3.2 and analyzed using SPSS version 20. Variables with a P value ≤0.25 in bivariate logistic regression analysis were entered into multivariate logistic regression analysis, and finally, variables with a P value <0.05 in multivariate logistic regression were considered significantly associated with the dependent variable. Results. The total goiter rate was 43%, 95% CI = 39.2–46.9. Cassava consumption (AOR: 2.02, 95% CI: 1.03–4), salt wash before use (AOR: 3.14, 95% CI: 1.1–11.3), salt use after >2 months of purchase (AOR: 11, 95% CI: 5–26), family history of goiter (AOR: 4.6, 95% CI: 1.4–15.8), and poor knowledge of iodized salt (AOR: 2.7, 95% CI: 1.4–5.5) were significant factors associated with goiter. Conclusion. Iodine deficiency was found to be severe in women of reproductive age in the study area. This showed that women of reproductive age, especially during pregnancy, are exposed to iodine deficiency and its adverse effects at delivery. Thus, they need urgent supplementation with iodine, improved access to foods rich in iodine, and intake of iodized salt. Additionally, health education should focus on the importance of iodized salt, the proper method of use, and the prevention of iodine deficiency, which are highly recommended to minimize the problem.

Download Full-text

Structure Extension of Tree-Augmented Naive Bayes

Entropy ◽

10.3390/e21080721 ◽

2019 ◽

Vol 21 (8) ◽

pp. 721 ◽

Cited By ~ 1

Author(s):

YuGuang Long ◽

LiMin Wang ◽

MingHui Sun

Keyword(s):

Naive Bayes ◽

Classification Performance ◽

Naïve Bayes ◽

Training Data ◽

Conditional Probability Distribution ◽

Independence Assumption ◽

Bayesian Network Classifiers ◽

Leibler Divergence ◽

The Difference ◽

Structure Extension

Due to the simplicity and competitive classification performance of the naive Bayes (NB), researchers have proposed many approaches to improve NB by weakening its attribute independence assumption. Through the theoretical analysis of Kullback–Leibler divergence, the difference between NB and its variations lies in different orders of conditional mutual information represented by these augmenting edges in the tree-shaped network structure. In this paper, we propose to relax the independence assumption by further generalizing tree-augmented naive Bayes (TAN) from 1-dependence Bayesian network classifiers (BNC) to arbitrary k-dependence. Sub-models of TAN that are built to respectively represent specific conditional dependence relationships may “best match” the conditional probability distribution over the training data. Extensive experimental results reveal that the proposed algorithm achieves bias-variance trade-off and substantially better generalization performance than state-of-the-art classifiers such as logistic regression.

Download Full-text

Prevalence and Associated Factors of Vitamin A Deficiency among Children and Women in Senegal

Journal of Nutritional Health & Food Science ◽

10.15226/jnhfs.2020.001176 ◽

2020 ◽

Vol 8 (2) ◽

pp. 1-11

Author(s):

Mane Hélène Faye ◽

Nicole Idohou-Dossou ◽

Abdou Badiane ◽

Anta Agne-Djigo ◽

Papa Mamadou DD Sylla ◽

...

Keyword(s):

Socioeconomic Status ◽

Logistic Regression ◽

Vitamin A ◽

Pregnant Women ◽

Vitamin A Deficiency ◽

Plasma Concentrations ◽

Reproductive Age ◽

Subclinical Inflammation ◽

Women Of Reproductive Age ◽

Factors Associated

Background: Like many developing countries, Senegal does not have data on the extent of vitamin A deficiency (VAD) that is representative of its population. The present survey was conducted to fill this gap and to identify factors associated with VAD, prior to the introduction of a large-scale vitamin A oil fortification program. Procedures: A nationwide representative cross-sectional survey involving 1887 children 12 to 59 months old and 1316 women of reproductive age (WRA) was conducted. Blood samples were collected and plasma concentrations of retinol (PR), C-reactive protein (CRP), and alpha-1-acidglycoprotein were measured. PR was adjusted for subclinical inflammation using the BRINDA regression methodology. Multivariate logistic regression was used to identify factors associated with VAD. Findings: The adjusted prevalence of VAD (PR ≤ 0.7 μmol/L) in children was 15.3% and differed by age group, area of residence, and socioeconomic status and half of them had subclinical inflammation. Among WRA, VAD was low (2.3%) and 18.1% had vitamin A insufficiency (VAI). Pregnant women were more affected by VAI (28.4%) and Dakar had lower figures compared with other cities and rural strata. Prevalence of VAI decreased with increasing wealth quintile. In logistic regression, abnormal CRP, poverty, scarce consumption of poultry, oysters, melon, red palm oil, palm kernel oil, Saba senegalensis fruit pulp (Maad) and cowpea, frequent consumption of leeks and consumption of Leptadenia hastata leaves (Mbuum tiakhat), were associated with VAD in children. For women, lower socioeconomic status, fair or poor health status and anemia were negatively associated with VAI. Conclusions: In Senegal, VAD is a moderate public health problem in children and slight among women. Particular attention should be paid to children older than 23 months, pregnant women, rural populations, and poorest households. Nutritional interventions should be implemented alongside morbidity prevention and control. Keywords: vitamin A deficiency, children 12-59 months, women of reproductive age, Senegal.

Download Full-text

Association between food insecurity and anemia among women of reproductive age

PeerJ ◽

10.7717/peerj.1945 ◽

2016 ◽

Vol 4 ◽

pp. e1945 ◽

Cited By ~ 15

Author(s):

Bishwajit Ghose ◽

Shangfeng Tang ◽

Sanni Yaya ◽

Zhanchun Feng

Keyword(s):

Logistic Regression ◽

Food Insecurity ◽

Hemoglobin Concentration ◽

Reproductive Age ◽

Household Food Insecurity ◽

Women Of Reproductive Age ◽

Cross Sectional Survey ◽

Wealth Status ◽

Cross Sectional ◽

Household Food

Background:Food insecurity and hidden hunger (micronutrient deficiency) affect about two billion people globally. Household food insecurity (HFI) has been shown to be associated with one or multiple micronutrient (MMN) deficiencies among women and children. Chronic food insecurity leads to various deficiency disorders, among which anemia stands out as the most prevalent one. As a high malnutrition prevalent country, Bangladesh has one of the highest rates of anemia among all Asian countries. In this study, we wanted to investigate for any association exists between HFI and anemia among women of reproductive age in Bangladesh.Methodology:Information about demographics, socioeconomic and anemia status on 5,666 married women ageing between 13 and 40 years were collected from a nationally representative cross-sectional survey Bangladesh Demographic and Health Survey (BDHS 2011). Food security was measured by the Household Food Insecurity Access Scale (HFIAS). Capillary hemoglobin concentration (Hb) measured by HemoCue® was used as the biomarker of anemia. Data were analysed using cross-tabulation, chi-square tests and multiple logistic regression methods.Results:Anemia prevalence was 41.7%. Logistic regression showed statistically significant association with anemia and type of residency (p = 0.459; OR = 0.953, 95%CI = 0.840–1.082), wealth status (Poorest: p < 0.001; OR = 1.369, 95%CI = 1.176–1.594; and average: p = 0.030; 95%CI = 1.017–1.398), educational attainment (p < 0.001; OR = 1.276, 95%CI = 1.132–1.439) and household food insecurity (p < 0.001; 95%CI = 1.348–1.830). Women who reported food insecurity were about 1.6 times more likely to suffer from anemia compared to their food secure counterparts.Conclusion:HFI is a significant predictor of anemia among women of reproductive age in Bangladesh. Programs targeting HFI could prove beneficial for anemia reduction strategies. Gender aspects of food and nutrition insecurity should be taken into consideration in designing national anemia prevention frameworks.

Download Full-text

Peringkasan dan Support Vector Machine pada Klasifikasi Dokumen

JURNAL INFOTEL ◽

10.20895/infotel.v9i4.312 ◽

2017 ◽

Vol 9 (4) ◽

pp. 416 ◽

Cited By ~ 1

Author(s):

Nelly Indriani Widiastuti ◽

Ednawati Rainarli ◽

Kania Evita Dewi

Keyword(s):

Support Vector Machine ◽

Naive Bayes ◽

Naïve Bayes ◽

Training Data ◽

Support Vector ◽

Good Reputation ◽

Multiclass Support Vector Machine ◽

Simple Logistic ◽

Better Than

Classification is the process of grouping objects that have the same features or characteristics into several classes. The automatic documents classification use words frequency that appears on training data as features. The large number of documents cause the number of words that appears as a feature will increase. Therefore, summaries are chosen to reduce the number of words that used in classification. The classification uses multiclass Support Vector Machine (SVM) method. SVM was considered to have a good reputation in the classification. This research tests the effect of summary as selection features into documents classification. The summaries reduce text into 50%. A result obtained that the summaries did not affect value accuracy of classification of documents that use SVM. But, summaries improve the accuracy of Simple Logistic Classifier. The classification testing shows that the accuracy of Naïve Bayes Multinomial (NBM) better than SVM

Download Full-text

COMPARISON OF NAIVE BAYES ALGORITHM AND C.45 ALGORITHM IN CLASSIFICATION OF POOR COMMUNITIES RECEIVING NON CASH FOOD ASSISTANCE IN WANASARI VILLAGE KARAWANG REGENCY

Jurnal Techno Nusa Mandiri ◽

10.33480/techno.v17i1.1191 ◽

2020 ◽

Vol 17 (1) ◽

pp. 37-42

Author(s):

Yuris Alkhalifi ◽

Ainun Zumarniansyah ◽

Rian Ardianto ◽

Nila Hardi ◽

Annisa Elfina Augustia

Keyword(s):

Decision Tree ◽

Naive Bayes ◽

Confusion Matrix ◽

Total Sample ◽

Naïve Bayes ◽

Food Assistance ◽

Training Data ◽

Naive Bayes Classifier ◽

Bayes Classifier ◽

Naïve Bayes Classifier

Non-Cash Food Assistance or Bantuan Pangan Non-Tunai (BPNT) is food assistance from the government given to the Beneficiary Family (KPM) every month through an electronic account mechanism that is used only to buy food at the Electronic Shop Mutual Assistance Joint Business Group Hope Family Program (e-Warong KUBE PKH ) or food traders working with Bank Himbara. In its distribution, BPNT still has problems that occur that are experienced by the village apparatus especially the apparatus of Desa Wanasari on making decisions, which ones are worthy of receiving (poor) and not worthy of receiving (not poor). So one way that helps in making decisions can be done through the concept of data mining. In this study, a comparison of 2 algorithms will be carried out namely Naive Bayes Classifier and Decision Tree C.45. The total sample used is as much as 200 head of household data which will then be divided into 2 parts into validation techniques is 90% training data and 10% test data of the total sample used then the proposed model is made in the RapidMiner application and then evaluated using the Confusion Matrix table to find out the highest level of accuracy from 2 of these methods. The results in this classification indicate that the level of accuracy in the Naive Bayes Classifier method is 98.89% and the accuracy level in the Decision Tree C.45 method is 95.00%. Then the conclusion that in this study the algorithm with the highest level of accuracy is the Naive Bayes Classifier algorithm method with a difference in the accuracy rate of 3.89%.

Download Full-text

Perbandingan Metode Klasifikasi Berita Hoaks Berbahasa Indonesia Berbasis Pembelajaran Mesin

Repositor ◽

10.22219/repositor.v2i5.692 ◽

2020 ◽

Vol 2 (5) ◽

pp. 675

Author(s):

Muhammad Athaillah ◽

Yufiz Azhar ◽

Yuda Munarko

Keyword(s):

Test Data ◽

Naive Bayes ◽

Naïve Bayes ◽

Training Data ◽

Features Selection ◽

Comparison Of Algorithms ◽

Bayes Algorithm

AbstrakKlasifiaksi berita hoaks merupakan salah satu aplikasi kategorisasi teks. Berita hoaks harus diklasifikasikan karena berita hoaks dapat mempengaruhi tindakan dan pola pikir pembaca. Dalam proses klasifikasi pada penelitian ini menggunakan beberapa tahapan yaitu praproses, ekstraksi fitur, seleksi fitur dan klasifikasi. Penelitian ini bertujuan membandingkan dua algoritma yaitu algoritma Naïve Bayes dan Multinomial Naïve Bayes, manakah dari kedua algoritma tersebut yang lebih efektif dalam mengklasifikasikan berita hoaks. Data yang digunakan dalam penelitian ini berasal dari www.trunbackhoax.id untuk data berita hoaks sebanyak 100 artikel dan data berita non-hoaks berasal dari kompas.com, detik.com berjumlah 100 artikel. Data latih berjumlah 140 artikel dan data uji berjumlah 60 artikel. Hasil perbandingan algoritma Naïve Bayes memiliki nilai F1-score sebesar 0,93 dan nilai F1-score Multinomial Naïve Bayes sebesar 0,92. Abstarct Classification hoax news is one of text categorizations applications. Hoax news must be classified because the hoax news can influence the reader actions and thinking patterns. Classification process in this reseacrh uses several stages, namely preprocessing, features extraxtion, features selection and classification. This research to compare Naïve Bayes algorithm and Multinomial Naïve Bayes algorithm, which of the two algorithms is more effective on classifying hoax news. The data from this research from turnbackhoax.id as hoax news of 100 articles and non-hoax news from kompas.com, detik.com of 100 articles. Training data 140 articles dan test data 60 articles. The result of the comparison of algorithms Naïve Bayes has an F1-score value of 0,93 and Naïve Bayes has an F1-score value of 0,92.

Download Full-text