Klasifikasi Faktor-Faktor Penyebab Penyakit Diabetes Melitus Di Rumah Sakit Unhas Menggunakan Algoritma C4.5

Ente, Dewi Rahma; Thamrin, Sri Astuti; Arifin, Samsul; Kuswanto, Hedi; Andreza, Andreza

doi:10.29244/ijsa.v4i1.330

Cited by 17 publications

(14 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There are several studies that have discussed the implementation of machine learning in the scope of Health, namely regarding the diagnosis of diabetes using classification mining techniques, the results of this study are that diabetes detection in the early stages is the key to treatment, things that need to be detected are plasma glucose concentration, body mass index, age, and diabetes pedigree function [8]. In addition, regarding the classification of factors causing diabetes mellitus using the C4.5 algorithm, the results of this study indicate that the factors that substantially affect the status of diabetes mellitus are fasting blood glucose, LDL cholesterol, age, and weight [9].…”

Section: Introductionmentioning

confidence: 83%

Application of Resampling and Boosting Methods Using the C5.0 Algorithm

Kuswanto

Sunusi

Siswanto

et al. 2022

icdsos

Self Cite

View full text Add to dashboard Cite

Hypertension is a non-communicable disease that is characterized by an increase in systolic and diastolic blood pressure of more than 140 mmHg and or 90 mmHg. Hypertension needs to get more attention the condition is because hypertension will cause complications in the target organs and this disease does not appear to show significant symptoms at the beginning of the disease because it is called "silent disease". The study discusses the integration method of resampling and boosting in predicting hypertension status using the C5.0 algorithm. Classification of the C5.0 Algorithm by applying to resample increases performance specificity and AUC. Random oversampling (ROS) increased the specificity by 95.67% and AUC increased by 91.11%. Random over-under sampling (ROUS) increased specificity by 88.84% and AUC increased by 87.13%. In addition, applying boosting to the C5.0 algorithm that has been reapplied increases the accuracy performance. Random oversampling (ROS) increased accuracy by 93.86% and random over-under sampling (ROUS) increased accuracy by 89.98%. The response variables that contributed the most were high cholesterol and heart problems. The application of resampling and boosting to the contribution of high cholesterol and heart problems always topped the list.

show abstract

Section: Introductionmentioning

confidence: 83%

Application of Resampling and Boosting Methods Using the C5.0 Algorithm

Kuswanto

Sunusi

Siswanto

et al. 2022

icdsos

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ada beberapa algoritma pohon klasifikasi yang bisa digunakan diantaranya algoritma C4.5 dan algoritma C5.0. (Ente et al, 2020) menggunakan algoritma C4.5 dalam mengklasifikasi penyakit diabetes mellitus dengan menggunakan teknik Cross validation untuk menentukan model terbaik yang dihasilkan. Teknik Cross validation akan mengkombinasikan beberapa kelompok data pengamatan yang telah dipartisi ke dalam dua bagian, yakni data untuk membangun model dan data untuk verifikasi model (Blockeel & Struyf, 2002).…”

Section: Pendahuluanunclassified

Comparison of C4.5 and C5.0 Algorithm Classification Tree Models for Analysis of Factors Affecting Auction

Fajri

Utami

Maruf

2022

IJSA

View full text Add to dashboard Cite

Auction in Indonesia is carried out by the Office of State Assets and Auction Services (KPKNL). Goods auctioned at KPKNL are quite diverse including land, wood, inventory, vehicles, and other goods. However, not all of the items auctioned were sold. Because not a few items have been auctioned but no one has made an offer. The Purpose of this study is to compare two classification methods, C4.5 and C5.0 algorithm and to determine which items were successfully auctioned with those that did not and its factors. The methods that used were comparing the classification tree C4.5 algorithm and C5.0 algorithm with cross validation. From the results of the comparison of the two methods, it was found that the C5.0 Algorithm method was rated better than the C4.5 algorithm in classifying the auction results with an accuracy of 96.43% and 92.86% respectively. In this case, C5.0 has a higher precision than C4.5.

show abstract

“…Diabetes tipe 2 terjadi karena obstruksi insulin, yaitu ketika sel tubuh menjadi kebal atau tidak responsif terhadap insulin atau kondisi kronis yang mempengaruhi cara tubuh memproses (glukosa) (Desi et al, 2018b) (Ente et al, 2020).…”

Section: Machineunclassified

Analisis Determinan Dan Prediksi Penyakit Diabetes Melitus Tipe 2 Menggunakan Metode Machine Learning: Scoping Review

et al. 2022

View full text Add to dashboard Cite

The prevalence of diabetes mellitus is increasing globally, nationally, and regionally, and most of them are type 2 diabetes mellitus, which can cause complications, economic losses, and death. The purpose of this study is to examine the analysis of determinants and predictions of type 2 diabetes mellitus using machine learning methods. This study uses the scoping review method to view, accumulate and synthesize the results of previous studies on the analysis of determinants and predictions of type 2 diabetes mellitus using machine learning methods. The inclusion criteria in this study were articles published in the indexed journal database PubMed, Google Scholar, Crossref in English and Indonesian, journals published in the 2017-2021 range and 15 articles that met the inclusion criteria. The search results were a total of 860 articles from 3 databases (PubMed, Google Scholar, Crossref) in which 98 of them were duplicate articles and were excluded. Of the remaining 762 articles, 142 were not full text and 605 were excluded after eligibility screening because they were irrelevant. The remaining 15 articles were systematically reviewed and qualitatively analyzed using the NVIVO-12 Plus application. From the analysis of previous studies concluded that age, obesity, family history of disease, and lack of physical activity are risk factors for type 2 diabetes mellitus, while the gender variable from the analysis of previous research shows that there is no significant relationship between gender and type 2 diabetes. With early prediction of type 2 diabetes mellitus preventive measures, treatment can be carried out immediately and reduce the incidence of complications that can worsen the condition of people with type 2 diabetes.

show abstract

Klasifikasi Faktor-Faktor Penyebab Penyakit Diabetes Melitus Di Rumah Sakit Unhas Menggunakan Algoritma C4.5

Cited by 17 publications

References 12 publications

Application of Resampling and Boosting Methods Using the C5.0 Algorithm

Application of Resampling and Boosting Methods Using the C5.0 Algorithm

Comparison of C4.5 and C5.0 Algorithm Classification Tree Models for Analysis of Factors Affecting Auction

Analisis Determinan Dan Prediksi Penyakit Diabetes Melitus Tipe 2 Menggunakan Metode Machine Learning: Scoping Review

Contact Info

Product

Resources

About