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

Maniruzzaman, Md.; Kumar, Nishith; Abedin, Md. Menhazul; Islam, Md. Shaykhul; Suri, Harman S.; El-Baz, Ayman; Suri, Jasjit S.

doi:10.1016/j.cmpb.2017.09.004

Cited by 198 publications

(116 citation statements)

References 20 publications

Supporting

Mentioning

112

Contrasting

Unclassified

Order By: Relevance

“…In a very recent report, the direct and indirect economic costs of diabetes in the United States of America in 2017 were as high as 327 billion dollars [2]. People with diabetes could easily carry a financial burden of about $13,700 per year [3].…”

Section: Introductionmentioning

confidence: 99%

Identification of Potential Type II Diabetes in a Chinese Population with a Sensitive Decision Tree Approach

Pei

Zhang

et al. 2019

Journal of Diabetes Research

View full text Add to dashboard Cite

Background Diabetes mellitus is a chronic disease with a steadfast increase in prevalence. Due to the chronic course of the disease combining with devastating complications, this disorder could easily carry a financial burden. The early diagnosis of diabetes remains as one of the major challenges medical providers are facing, and the satisfactory screening tools or methods are still required, especially a population- or community-based tool. Methods This is a retrospective cross-sectional study involving 15,323 subjects who underwent the annual check-up in the Department of Family Medicine of Shengjing Hospital of China Medical University from January 2017 to June 2017. With a strict data filtration, 10,436 records from the eligible participants were utilized to develop a prediction model using the J48 decision tree algorithm. Nine variables, including age, gender, body mass index (BMI), hypertension, history of cardiovascular disease or stroke, family history of diabetes, physical activity, work-related stress, and salty food preference, were considered. Results The accuracy, precision, recall, and area under the receiver operating characteristic curve (AUC) value for identifying potential diabetes were 94.2%, 94.0%, 94.2%, and 94.8%, respectively. The structure of the decision tree shows that age is the most significant feature. The decision tree demonstrated that among those participants with age ≤ 49, 5497 participants (97%) of the individuals were identified as nondiabetic, while age > 49, 771 participants (50%) of the individuals were identified as nondiabetic. In the subgroup where people were 34 < age ≤ 49 and BMI ≥ 25, when with positive family history of diabetes, 89 (92%) out of 97 individuals were identified as diabetic and, when without family history of diabetes, 576 (58%) of the individuals were identified as nondiabetic. Work-related stress was identified as being associated with diabetes. In individuals with 34 < age ≤ 49 and BMI ≥ 25 and without family history of diabetes, 22 (51%) of the individuals with high work-related stress were identified as nondiabetic while 349 (88%) of the individuals with low or moderate work-related stress were identified as not having diabetes. Conclusions We proposed a classifier based on a decision tree which used nine features of patients which are easily obtained and noninvasive as predictor variables to identify potential incidents of diabetes. The classifier indicates that a decision tree analysis can be successfully applied to screen diabetes, which will support clinical practitioners for rapid diabetes identification. The model provides a means to target the prevention of diabetes which could reduce the burden on the health system through effective case management.

show abstract

Section: Introductionmentioning

confidence: 99%

Identification of Potential Type II Diabetes in a Chinese Population with a Sensitive Decision Tree Approach

Pei

Zhang

et al. 2019

Journal of Diabetes Research

View full text Add to dashboard Cite

show abstract

“…This algorithm is used to find the most important independent variable and is first set at the root node and then introduces the next optimal fitting variable (known as bifurcation). The tree flows in a top-tobottom manner, from the root node to internal nodes (independent variables) and then to terminal leaf nodes (class prediction) [12][13][14][15][16][17]. In the decision tree, the first variable (root) is the most important factor, and the variable furthest from the root is the next most important factor for the data classification [18].…”

Section: Analysis Methodsmentioning

confidence: 99%

Decision Tree Analysis on the Factors Influencing the COI of Infantile Bronchopneumonia Inpatients in a Northern Hospital of China

Pei¹,

Yue²,

guo³

et al. 2019

Preprint

View full text Add to dashboard Cite

Background: Bronchopneumonia is a disease with a high death rate for children in developing countries. It not only affects the healthy growth of children, but also puts economic pressure and additional burdens on their families and society. Social development and advancement may change the factors influencing the hospitalization costs. This study aimed to explore reasonable cost control approaches by analyzing the factors related to unreasonable increases in medical costs, so as to standardize the diagnosis and treatment behaviors and determine management methods for scientific medical costs. Methods: Using the decision tree analysis method combined with the characteristic variables of inpatients, data mining and analysis were performed on the assortment of charges for15,980infantile bronchopneumonia inpatients in a northern hospital of China during January 2013 to December 2017. Results: The medical costs of infantile bronchopneumonia inpatients tended to decrease year by year. Various factors influencing the hospitalization costs were sequenced in order of decreasing importance: salvage, complications, admission condition, discharge condition, hospital stay, age and medical payment mode. The hospitalization cost of 623(78.5%) patients with salvage during hospitalization was >RMB 10,000. Hospitalization cost of

show abstract

“…Penggunaan Metode C4.5 [11], [12], [13]. Metode Naive Bayes dilakukan oleh dkk [11], [14], [12], dan [13]. Metode SVM dilakukan oleh Zheng dkk [11], [12], [15] dan [16].…”

Section: Pendahuluanunclassified

Perbandingan Hasil Analisis Teknik Data Mining “Metode Decision Tree, Naive Bayes, Smo Dan Part” Untuk Mendiagnosa Penyakit Diabetes Mellitus

Nurahman

Prihandoko

2019

Inf. J. Ilm. Bid. Teknol. Inf. dan Komun.

View full text Add to dashboard Cite

Diabetes Mellitus (DM) is one of the diseases that can bring a person to death. The main cause of this disease is irregular or excessive lifestyle and food. Someone who develops diabetes will be marked by increased sugar levels. This happens because of a disruption in insulin secretion and insulin action or even in both. In many countries more and more patients with diabetes, if not stopped soon, it is estimated that people with diabetes will reach 642 by 2040 [1]. This study aims to choose the best data mining clasifiers in diagnosing Diabetes Mellitus (DM). Diagnosis is based on computer systems using the feature selection method and classification of the Pima Indians Diabetes dataset. The feature selection method used is Correlation based Featured Selection (CFS). The data mining classification results in this study indicate that SMO has the highest value of accuracy compared to other Classifiers.Abstrak-Diabetes Mellitus (DM) merupakan salah satu penyakit yang dapat membawa seseorang berujung pada suatu kematian. Peyebab utama dari penyakit ini adalah pola hidup dan makanan yang tidak teratur atau berlebihan. Seseorang yang terserang penyakit diabetes akan ditandai dengan meningkat kadar gula. Hal ini terjadi karena adanya gangguan pada sekresi insulin dan kerja insulin atau bahkan pada keduanya. Di diberbagai negara semakin banyak pasien penyakit diabetes, jika tidak segera dihentikan maka diperkirakan penderita penyakit diabetes akan mencapai 642 jiwa pada tahun 2040 [1]. Penelitian ini bertujuan untuk memilih Clasifiers data mining yang terbaik dalam melakukan diagnosis terhadap penyakit Diabetes Mellitus (DM). Diagnosis yang dilakukan berbasis sistem komputer dengan menggunakan metode seleksi fitur dan klasifikasi terhadap Dataset Pima Indians Diabetes. Metode seleksi fitur yang digunakan adalah Correlation based Featured Selection (CFS). Hasil klasifikasi data mining pada penelitian ini menunjukkan bahwa SMO memiliki nilai akurasi tertinggi dibanding Classifiers yang lainnya.

show abstract

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

Cited by 198 publications

References 20 publications

Identification of Potential Type II Diabetes in a Chinese Population with a Sensitive Decision Tree Approach

Identification of Potential Type II Diabetes in a Chinese Population with a Sensitive Decision Tree Approach

Decision Tree Analysis on the Factors Influencing the COI of Infantile Bronchopneumonia Inpatients in a Northern Hospital of China

Perbandingan Hasil Analisis Teknik Data Mining “Metode Decision Tree, Naive Bayes, Smo Dan Part” Untuk Mendiagnosa Penyakit Diabetes Mellitus

Contact Info

Product

Resources

About