Md Maniruzzaman, M.Sc. - Statistics Discipline, Khulna University, Khulna-9208, Bangladesh - Lecturer

Md Maniruzzaman

M.Sc.

Statistics Discipline, Khulna University, Khulna-9208, Bangladesh

Lecturer

Khulna, Khulna | Bangladesh

Main Specialties: Public Health, Statistics

ORCID logohttps://orcid.org/0000-0001-6151-8071


Top Author

Md Maniruzzaman, M.Sc. - Statistics Discipline, Khulna University, Khulna-9208, Bangladesh - Lecturer

Md Maniruzzaman

M.Sc.

Introduction

Curriculum Vitae
Of
Md. Maniruzzaman
Lecturer, Statistics Discipline, Khulna University
Khulna-9208, Bangladesh
&
MPhil Fellow, Department of Statistics,
University of Rajshahi, Rajshahi-6205, Bangladesh
Mobile: +880-1737095565
E-mail: monir.stat91@gmail.com
CAREER OBJECTIVE
I am looking for a job which is properly related to the research and teaching of statistics in any organizations in Bangladesh or any other countries. And, I am highly interested to be well established in a challenging field through hard work, honesty, sincerity, and real talent where presentation skill, equality and ethics are strongly evaluated.
CURRENT RESEARCH INSTEREST
Public Health, Bioinformatics, Biostatistics, Machine Learning, Data Mining, Image Analysis.
EMPLOYMENT RECORDS
January 1-February 4, 2016 ACT Mathematics, SEQUEP Project under World Bank.
April 16, 2017 to August 30
,2018
Biostatistician, JiVitA: Maternal and Child Health and Nutrition Project of John Hopkins University (Bangladesh) (JHU-B), Gaibandha, Bangladesh.
September 4, 2018 to Present Lecturer, Statistics Discipline, Khulna University, Khulna-9208
ACADEMIC QUALIFICATIONS

MPhil (Continue)
Institution Department of Statistics, University of Rajshahi.
Session 2017-2018
Thesis title Comparisons of Performances of Machine Learning Techniques
in Large Scale Dataset
Thesis Supervisor Dr. Md. Jahanur Rahman, Professor, Department of
Statistics, University of Rajshahi, Rajshahi, Bangladesh

M.Sc. (Thesis), 2014 (Exam held in 2015 and Result published in April 09, 2016)
Institution Department of Statistics, University of Rajshahi.
Session 2014-2015
Result 3.92 Out of 4.00.
Position First class second.
Subject studied Advanced Statistical Inference, Generalized Linear Models, Advanced Multivariate Analysis, Time Series Analysis and Forecasting, Statistical Genetics, Advanced Bioinformatics, Advanced Biostatistics, Advanced Statistical Data Mining
Thesis title A Study on Gaussian Process Based Regression and Classification
Thesis supervisor Dr. Mohammed Nasser, Professor, Department of Statistics,
University of Rajshahi, Bangladesh.
Inplant training title Socio and Demographic Determinants of Neonatal Mortality in
Bangladesh.
Medium of instruction English
B.Sc., 2013 (Exam held in 2013 and Result published in September 25, 2014)
Institution Department of Statistics, University of Rajshahi.
Session 2009-2010
Result 3.75 Out of 4.00.
Position First class second.
Subject studied First Year: Probability Theory, Principles of Statistics-I, Principles of Statistics-II, Algebra and Numerical Methods, Analytical Geometry and Calculus, Matrix Algebra, Introduction to Computer with Task-Oriented Software, and English for Statistics.
Second Year: Statistical Methods, Regression and Modeling, Analysis of Variance, Mathematical Economics, Real Analysis, Differential Equation and Fourier Series, and Computer Programming.
Third Year: Multinomial Distribution and Order Statistics, Estimation, Hypothesis Testing, Regression and Diagnostics, Stochastic Processes, Survey Methods and Sampling, Complex Variable and Matrix Analysis, and Simulation & Modeling.
Fourth Year: Multivariate Analysis, Measure and Modern Probability Theory, Demography, Biometrics, Economic Statistics and Econometrics Sampling and Methodology, Operations Research and Quality Control, and Social and Occupational Statistics.
Medium of instruction English
Higher Secondary Certificate (HSC), 2009
Institution Phulbari Government College, Phulbari, Dinajpur
Group Science
Broad Dinajpur
Results GPA 4.70 out of 5.00
Subject studied Bengali, English, Physics, Chemistry, Mathematics, Biology.
Medium of Instruction Bangla
Secondary School Certificate (SSC), 2007
Institution Gamirahat S.C High School, Chirirbandar, Dinajpur
Group Science
Broad Rajshahi
Results GPA 4.63 out of 5.00
Subject studied Bengali, English, Social Science, Mathematics (General and Higher), Physics, Chemistry, Biology and Islamic Studies.
Medium of Instruction Bangla.

COMPUTER LITERACY
Operating System Windows-8, Windows-7, XP
Office application MS Word, MS Excel, MS PowerPoint, MS Access, Latex and Internet Browsing.
Programming Maple, SPSS, C++, R- Language, Stata, Matlab, Eviews, Minitab.
ACADEMIC AWARDS
National Science and Technology Scholarship, Ministry of Science and Technology, Government of The People's Republic of Bangladesh.
WORKSHOPS, SEMINAR AND CONFERENCE
I actively participated in the following workshops:
1. ‘‘International Workshop on Health Statistics’’ during the period April 20-21, 2012, organized by the Department of Statistics, University of Rajshahi, Rajshahi-6205, Bangladesh.
2. ” Training on R Programming” during the period March 22-23, 2013, organized by the Department of Statistics, University of Rajshahi, Rajshahi-6205, Bangladesh.
3. “Workshop on Mathematics for Machine Learning “during the period November 13-14, 2014, organized by the Statistical Learning Group, Department of Statistics, University of Rajshahi, Rajshahi-6205, Bangladesh.
4. “Workshop on Advanced R Programming” during the period June 5-6, 2015 , organized by the Department of Statistics, University of Rajshahi, Rajshahi-6205 Bangladesh.
5. “Training Program on R-Programming and Application of R-packages”, during the period June 20-30, 2015, organized by the Department of Statistics, University of Rajshahi, Rajshahi-6205, Bangladesh.
6. “Training Program on C-Programming”, organized by the Department of Statistics, University of Rajshahi, Rajshahi-6205, Bangladesh.
7. “National Workshop on Bioinformatics for Sustainable Development in Agriculture Health and Environment”, during the period August 30–31, 2016, organized by the Department of Statistics, University of Rajshahi, Rajshahi-6205, Bangladesh.
8. “Interactive Data Analysis & Visualization” during the period September 1, 2016, organized by the Department of Statistics, University of Rajshahi, Rajshahi-6205, Bangladesh.
I also participated in the following international conferences on
1. “Statistical Data mining for Bioinformatics, Health, Agriculture and Environment” organized by Department of Statistics, University of Rajshahi, Rajshahi-6205, Bangladesh.
2. “First International Conference on Mathematics and its Application” organized by Mathematics Discipline, University of Khulna, Bangladesh.




PUBLISHED CONFERENCE PAPER
1. Md. Shaykhul Islam, Md. Nazrul Islam Mondal, Md. Rafiqul Islam, Md. Menhazul Abedin, Md. Maniruzzaman (2015). Factor Related to the Occurrence of Diarrheal Disease among Under-Five Children in Bangladesh. Proceedings of First International Conference on Mathematics and its Application. 23 December 2015, organized by Mathematics Discipline, University of Khulna, Khulna-9208, Bangladesh.
2. Md. Menhazul Abedin, Dr. Md. Nazrul Islam Mondal , Dr. Mohammed Nasser, Md. Shaykhul Islam, Md. Maniruzzaman (2015). Misconception about HIV/AIDS Transmission among Married Men: A population based study in Bangladesh. Proceedings of First International Conference on Mathematics and its Application, during the period 23 December, 2015, organized by Mathematics Discipline, University of Khulna, Khulna-9208, Bangladesh.
3. Md. Maniruzzaman, Md. Menhazul Abedin, Dr. Mohammed Nasser, Md. Shaykhul Islam, (2016). “A Study on Gaussian Process Based Regression and Classification” on Professor Mohammed Nasser Memorial Seminar Statistics and Bioinformatics for Sustainable Development, 13 March, 2016, organized by the Department of Statistics, University of Rajshahi, Rajshahi-6205, Bangladesh.
4. Md. Menhazul Abedin, Dr. Mohammed Nasser, Md. Shaykhul Islam, Md. Maniruzzaman (2016). Regression and Classification: An Artificial Neural Network Approach. Proceedings on Professor Mohammed Nasser Memorial Seminar Statistics and Bioinformatics for Sustainable Development, 13 March 2016, organized by the Department of Statistics, University of Rajshahi, Rajshahi-6205, Bangladesh.
5. Md. Shaykhul Islam, Dr. Mohammed Nasser, Md. Menhazul Abedin, Md. Maniruzzaman (2016). Support Vector Machines for Supervised Learning on Real and Simulated Data. Professor Mohammed Nasser Memorial Seminar Statistics and Bioinformatics for Sustainable Development, during the period March 13, 2016, organized by the Department of Statistics, University of Rajshahi, Rajshahi-6205, Bangladesh.
6. Md. Maniruzzaman, Nishith Kumar, Md. Menhazul Abedin, Md. Jahanur Rahman (2017). Liver Disease Prediction Using Intelligent Techniques. Proceedings of International Conference on Bioinformatics and Biostatistics for Agriculture, Health and Environment. 20-23 January, 2017. ISBN: 978-984-34-0996-6
7. Md. Menhazul Abedin, Md. Maniruzzaman, Md. Shaykhul Islam, Mohammad Ali, Benojir Ahammed and N.A.M. Faisal Ahmed (2017). Comparative Study of Artificial Neural Network Regression and Classical regression. Proceedings of International Conference on Bioinformatics and Biostatistics for Agriculture, Health and Environment. 20-23 January, 2017. ISBN: 978-984-34-0996-6.



ABSTRACT SUBMISSION IN INTERNATIONAL CONFERENCE

1. Maniruzzaman M., Nishith Kumar, Abedin MM, Rahman MJ (2017). Liver Disease Prediction using Intelligent Techniques Proceedings of International Conference on Bioinformatics and Biostatistics for Agriculture, Health and Environment. 20-23 January, 2017. ISBN: 978-984-34-0996-6.
2. Md. Menhazul Abedin, Md. Maniruzzaman, Md. Shaykhul Islam, Mohammad Ali, Benojir Ahammed and N.A.M. Faisal Ahmed (2017). Comparative Study of Artificial Neural Network Regression and Classical regression. Proceedings of International Conference on Bioinformatics and Biostatistics for Agriculture, Health and Environment. 20-23 January, 2017. ISBN: 978-984-34-0996-6.

PUBLISHED ARTICLES IN INTERNATIONAL JOURNAL
1. Maniruzzaman, M., Kumar, N., Abedin, M. M., Islam, M. S., Suri, H. S., El-Baz, A. S., & Suri, J. S. (2017). Comparative Approaches for Classification of Diabetes Mellitus Data: Machine Learning Paradigm. Computer Methods and Programs in Biomedicine, 152, 23-34, doi: 10.1016/j.cmpb.2017.09.004.
2. Maniruzzaman, M., Harman, S., Kumar, N., Abedin, M, M., Rahman, M.J., El-Baz, A., Bhoot, M., Teji, J. S., & Suri, J. S (2018). Risk factors of neonatal mortality and child mortality in Bangladesh. Journal of Global Health, 8 (1), 1-16. doi:10.7189/jogh.08.010421.
3. Maniruzzaman, M., Rahman, M. J., Al-MehediHasan, M., Suri, H. S., Abedin, M. M., El-Baz, A., & Suri, J. S. (2018). Accurate Diabetes Risk Stratification Using Machine Learning: Role of Missing Value and Outliers. Journal of medical systems, 42(5), 92. https://doi.org/10.1007/s10916-018-0940-7.
4. Maniruzzaman, M., Rahman, M. J., Bhattacharjee, S. K., Rahman, S., Hoque, A., & Ali, A. (2017). Socio and Demographic Determinants of Neonatal Mortality in Bangladesh. International Journal of Engineering and Computer Science, 6(12), 22294-22301.
5. Cuadrado-Godia, E., Maniruzzaman, M., Araki, T., Puvvula, A., Rahman, M. J., Saba, L & Omerzu, T. (2018). Morphologic TPA (mTPA) and composite risk score for moderate carotid atherosclerotic plaque is strongly associated with HbA1c in diabetes cohort. Computers in Biology and Medicine.101, 128-145. doi.org/10.1016/j.compbiomed.2018.08.008.

LANGUAGE PROFICIENCY
English Speaking, Writing and Reading
Bangla Speaking, Writing and Reading
STRENGTHS
Able to adjust to new challenging situation quickly, enthusiastic and self- motivated to achieve success, hard working and dynamic, self –motivated & sincere, Ability to work under pressure.

INTEREST
Reading Book, Listening and singing song, playing cricket, Traveling.
PERSONAL DETAILS

Name Md. Maniruzzaman
Father’s Name Md. Abdur Sattar
Mother’s Name Mosa. Manjuara
Date of Birth 10 July 1991
Blood Group B+(ve)
Sex Male
Nationality Bangladeshi (by birth)
Religion Islam
Marital Status Married
Spouse Name Naznin Haque Bithi
NID No. 19912713071000300
Permanent Address Care of, Md. Abdur Sattar; Village: Tulshepur, Post: Gamirahat, Upzilla: Chirirbandar, District: Dinajpur, Bangladesh.
Present
Address Lecturer, Statistics Discipline, Khulna University, Khulna-9208, Bangladesh


REFERENCES

a. Dr. Md. Jahanur Rahman
Professor
Department of Statistics
University of Rajshahi
Rajshahi-6205, Bangladesh
Mobile: +8801915689855
E-mail: jahanurmj@gmail.com
b. Dr. Dual Chandra Roy
Professor
Department of Statistics
University of Rajshahi
Rajshahi-6205,Bangladesh
Mobile:+8801914-254993
E-mail: dulalroystat@yahoo.com


Primary Affiliation: Statistics Discipline, Khulna University, Khulna-9208, Bangladesh - Khulna, Khulna , Bangladesh

Specialties:

Research Interests:


View Md Maniruzzaman’s Resume / CV

Education

Oct 2018

Publications

10Publications

277Reads

7Profile Views

13PubMed Central Citations

Classification and prediction of diabetes disease using machine learning paradigm.

Health Inf Sci Syst 2020 Dec 3;8(1). Epub 2020 Jan 3.

1Statistics Discipline, Khulna University, Khulna, 9208 Bangladesh.

Background And Objectives: Diabetes is a chronic disease characterized by high blood sugar. It may cause many complicated disease like stroke, kidney failure, heart attack, etc. About 422 million people were affected by diabetes disease in worldwide in 2014. The figure will be reached 642 million in 2040. The main objective of this study is to develop a machine learning (ML)-based system for predicting diabetic patients.

Materials And Methods: Logistic regression (LR) is used to identify the risk factors for diabetes disease based on p value and odds ratio (OR). We have adopted four classifiers like naïve Bayes (NB), decision tree (DT), Adaboost (AB), and random forest (RF) to predict the diabetic patients. Three types of partition protocols (K2, K5, and K10) have also adopted and repeated these protocols into 20 trails. Performances of these classifiers are evaluated using accuracy (ACC) and area under the curve (AUC).

Results: We have used diabetes dataset, conducted in 2009-2012, derived from the National Health and Nutrition Examination Survey. The dataset consists of 6561 respondents with 657 diabetic and 5904 controls. LR model demonstrates that 7 factors out of 14 as age, education, BMI, systolic BP, diastolic BP, direct cholesterol, and total cholesterol are the risk factors for diabetes. The overall ACC of ML-based system is . The combination of LR-based feature selection and RF-based classifier gives ACC and AUC for K10 protocol.

Conclusion: The combination of LR and RF-based classifier performs better. This combination will be very helpful for predicting diabetic patients.

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1007/s13755-019-0095-zDOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6942113PMC
December 2020

Prevalence of undernutrition in Bangladeshi children.

J Biosoc Sci 2020 Jul 29;52(4):596-609. Epub 2019 Oct 29.

Development Studies Discipline, Khulna University, Khulna, Bangladesh.

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1017/S0021932019000683DOI Listing
July 2020
1 Read

Determinants of depressive symptoms among older people in Bangladesh.

J Affect Disord 2020 Mar 16;264:157-162. Epub 2019 Dec 16.

Institute for Physical Activity and Nutrition, School of Exercise and Nutrition Sciences, Faculty of Health, Deakin University, Victoria, 3125, Australia.

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jad.2019.12.025DOI Listing
March 2020
3.383 Impact Factor

Determinants of early age of mother at first birth in Bangladesh: a statistical analysis using a two-level multiple logistic regression model

Journal of Public Health

Aim

The timing of a woman's first birth is significant because motherhood involves a substantial commitment of time and resources. Early age at first birth is a factor that significantly influences the rapid population growth in Bangladesh. In addition, early age at first birth has a negative effect on occupational achievements, marital stability, and maternal and neonatal health. The aim of this study was to determine the factors influencing early age at first birth.

Subjects and methods

Data were collected from the Bangladesh Demographic and Health Survey (BDHS) 2014. The BDHS 2014 data were obtained from 17,863 ever-married women using two-stage stratified sampling. Chi-square test and two-level multiple binary logistic regression models were performed to analyze the data.

Results

A total of 15,842 ever-married women with mean age of 18.22 ± 0.389 years were included in this study. Muslim women (AOR = 1.32, 95% CI: 1.11–1.56, p < 0.001), early marriage (AOR = 13.25, 95% CI: 11.83–14.76, p < 0.001) and women currently using contraceptives (AOR = 2.39, 95% CI: 1.25–1.55, p < 0.01) were more likely to have early age at first birth, whereas women from higher income households (AOR = 0.72, 95% CI: 0.57–0.91, p < 0.05), with higher education (AOR = 0.25, 95% CI: 0.21–0.31, p < 0.001), employed (AOR = 0.87, 95% CI: 0.78–0.98, p < 0.05) and whose husbands had higher education levels (AOR = 0.61, 95% CI: 0.48–0.76, p < 0.001) or were service holders (AOR = 0.74, 95% CI: 0.58–0.93, p < 0.05) were less likely than their counterparts to have their first birth at an early age.

Conclusion

The government should take the necessary steps to make policies to control the occurrence of women having their first birth at an early age by emphasizing the significant factors obtained from this study.

View Article
February 2020
1 Read

Statistical characterization and classification of colon microarray gene expression data using multiple machine learning paradigms.

Comput Methods Programs Biomed 2019 Jul 10;176:173-193. Epub 2019 Apr 10.

Advanced Knowledge Engineering Centre, Global Biomedical Technologies, Inc., Roseville, CA, USA; AtheroPoint, Roseville, CA, USA. Electronic address:

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.cmpb.2019.04.008DOI Listing
July 2019
32 Reads
1.897 Impact Factor

Morphologic TPA (mTPA) and composite risk score for moderate carotid atherosclerotic plaque is strongly associated with HbA1c in diabetes cohort.

Comput Biol Med 2018 10 8;101:128-145. Epub 2018 Aug 8.

Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA, USA. Electronic address:

Background: This study examines the association between six types of carotid artery disease image-based phenotypes and HbA1c in diabetes patients. Six phenotypes (intima-media thickness measurements (cIMT (ave.), cIMT (max.), cIMT (min.)), bidirectional wall variability (cIMTV), morphology-based total plaque area (mTPA), and composite risk score (CRS)) were measured in an automated setting using AtheroEdge™ (AtheroPoint, CA, USA).

Method: Consecutive 199 patients (157?M, age: 68.96?±?10.98 years), L/R common carotid artery (CCA; 398 US scans) who underwent a carotid ultrasound (L/R) were retrospectively analyzed using AtheroEdge™ system. Two operators (novice and experienced) manually calibrated all the US scans using AtheroEdge™. Logistic regression (LR) and Odds ratio (OR) was computed and phenotypes were ranked.

Results: The baseline results showed 150 low-risk patients (HbA1c? 1.0 (P?
Conclusions: All phenotypes using AtheroEdge™, except cIMTV, showed a strong association with HbA1c. mTPA and CRS were equally strong phenotypes as cIMT. The CRS phenotype showed the strongest relationship to HbA1c.

View Article

Download full-text PDF

Source
https://linkinghub.elsevier.com/retrieve/pii/S00104825183022
Publisher Site
http://dx.doi.org/10.1016/j.compbiomed.2018.08.008DOI Listing
October 2018
52 Reads
1 Citation
2.115 Impact Factor

Risk factors of neonatal mortality and child mortality in Bangladesh.

J Glob Health 2018 Jun;8(1):010417

AtheroPoint LLC, Roseville, California, USA.

Background: Child and neonatal mortality is a serious problem in Bangladesh. The main objective of this study was to determine the most significant socio-economic factors (covariates) between the years 2011 and 2014 that influences on neonatal and child mortality and to further suggest the plausible policy proposals.

Methods: We modeled the neonatal and child mortality as categorical dependent variable (alive vs death of the child) while 16 covariates are used as independent variables using ? statistic and multiple logistic regression (MLR) based on maximum likelihood estimate.

Findings: Using the MLR, for neonatal mortality, diarrhea showed the highest positive coefficient (??=?1.130; ?
Conclusions: In 2014, mother's age and father's education were also still significant covariates for child mortality. This study allows policy makers to make appropriate decisions to reduce neonatal and child mortality in Bangladesh.

View Article

Download full-text PDF

Source
http://dx.doi.org/10.7189/jogh.08.010421DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5928324PMC
June 2018
12 Reads
1 Citation
4.195 Impact Factor

Accurate Diabetes Risk Stratification Using Machine Learning: Role of Missing Value and Outliers.

J Med Syst 2018 Apr 10;42(5):92. Epub 2018 Apr 10.

Stroke Monitoring and Diagnostic Division, AtheroPoint LLC, Roseville, CA, USA.

Diabetes mellitus is a group of metabolic diseases in which blood sugar levels are too high. About 8.8% of the world was diabetic in 2017. It is projected that this will reach nearly 10% by 2045. The major challenge is that when machine learning-based classifiers are applied to such data sets for risk stratification, leads to lower performance. Thus, our objective is to develop an optimized and robust machine learning (ML) system under the assumption that missing values or outliers if replaced by a median configuration will yield higher risk stratification accuracy. This ML-based risk stratification is designed, optimized and evaluated, where: (i) the features are extracted and optimized from the six feature selection techniques (random forest, logistic regression, mutual information, principal component analysis, analysis of variance, and Fisher discriminant ratio) and combined with ten different types of classifiers (linear discriminant analysis, quadratic discriminant analysis, naïve Bayes, Gaussian process classification, support vector machine, artificial neural network, Adaboost, logistic regression, decision tree, and random forest) under the hypothesis that both missing values and outliers when replaced by computed medians will improve the risk stratification accuracy. Pima Indian diabetic dataset (768 patients: 268 diabetic and 500 controls) was used. Our results demonstrate that on replacing the missing values and outliers by group median and median values, respectively and further using the combination of random forest feature selection and random forest classification technique yields an accuracy, sensitivity, specificity, positive predictive value, negative predictive value and area under the curve as: 92.26%, 95.96%, 79.72%, 91.14%, 91.20%, and 0.93, respectively. This is an improvement of 10% over previously developed techniques published in literature. The system was validated for its stability and reliability. RF-based model showed the best performance when outliers are replaced by median values.

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1007/s10916-018-0940-7DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5893681PMC
April 2018
30 Reads
3 Citations
2.098 Impact Factor

Comparative approaches for classification of diabetes mellitus data: Machine learning paradigm.

Comput Methods Programs Biomed 2017 Dec 8;152:23-34. Epub 2017 Sep 8.

Diabetic Care Division, AtheroPoint LLC, Roseville, CA, USA; Department of Electrical Engineering, Idaho State University (Affl.), Idaho, USA. Electronic address:

Background And Objective: Diabetes is a silent killer. The main cause of this disease is the presence of excessive amounts of metabolites such as glucose. There were about 387 million diabetic people all over the world in 2014. The financial burden of this disease has been calculated to be about $13,700 per year. According to the World Health Organization (WHO), these figures will more than double by the year 2030. This cost will be reduced dramatically if someone can predict diabetes statistically on the basis of some covariates. Although several classification techniques are available, it is very difficult to classify diabetes. The main objectives of this paper are as follows: (i) Gaussian process classification (GPC), (ii) comparative classifier for diabetes data classification, (iii) data analysis using the cross-validation approach, (iv) interpretation of the data analysis and (v) benchmarking our method against others.

Methods: To classify diabetes, several classification techniques are used such as linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and Naive Bayes (NB). However, most of the medical data show non-normality, non-linearity and inherent correlation structure. So in this paper we adapted Gaussian process (GP)-based classification technique using three kernels namely: linear, polynomial and radial basis kernel. We also investigate the performance of a GP-based classification technique in comparison to existing techniques such as LDA, QDA and NB. Performances are evaluated by using the accuracy (ACC), sensitivity (SE), specificity (SP), positive predictive value (PPV), negative predictive value (NPV) and receiver-operating characteristic (ROC) curves.

Results: Pima Indian diabetes dataset is taken as part of the study. This consists of 768 patients, of which 268 patients are diabetic and 500 patients are controls. Our machine learning system shows the performance of GP-based model as: ACC 81.97%, SE 91.79%, SP 63.33%, PPV 84.91% and NPV 62.50% which are larger compared to other methods.

View Article

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.cmpb.2017.09.004DOI Listing
December 2017
138 Reads
8 Citations
2.674 Impact Factor

Top co-authors

Md Menhazul Abedin
Md Menhazul Abedin

Khulna University

6
Harman S Suri
Harman S Suri

Monitoring and Diagnostic Division

6
Jasjit S Suri
Jasjit S Suri

University of Idaho (Affl.)

6
Md Jahanur Rahman
Md Jahanur Rahman

University of Rajshahi

5
Md Sazedur Rahman
Md Sazedur Rahman

Bangladesh Agricultural University

2
Elisa Cuadrado-Godia
Elisa Cuadrado-Godia

Hospital del Mar

2
Narendra N Khanna
Narendra N Khanna

Indraprastha Apollo Hospitals

2
Luca Saba
Luca Saba

Azienda Ospedaliero Universitaria (A.O.University)

2
Ajay Gupta
Ajay Gupta

Weill Cornell Medical College

2