Data Mining Classification Algorithms for Diabetes Dataset Using Weka Tool

Fitria, Rahma; Yulisda, Desvina; Ula, Mutammimul

doi:10.29103/sisfo.v5i2.6236

Cited by 3 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, the process of selecting a machine learning algorithm should also be guided by the nature of the task at hand. In this study, the popular Naïve Bayes classifier performed so poorly with an error rate of 0.66 (Fitria, Yulisda, and Ula, 2021;Abdollahi and Nouri-Moghaddam, 2022). On the other hand, the results of the DBSCAN algorithm were also very shocking, as all 652 records of cases of diabetes were classified as noise.…”

Section: Model Performance For the Fuzzy C-means Algorithmmentioning

confidence: 66%

“…Artificial neural networks remain one of the top-performing classification algorithms, and the results produced definitely depend on their architectural design (Fitria, Yulisda, and Ula, 2021). Even though the overall performance of the random forest seemed to be better than all the MLP models, the MLP with 3 hidden layers had a lower type I error compared to the case of the random forest.…”

Section: Model Performance For the Fuzzy C-means Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of machine learning methods for the prediction of type 2 diabetes in primary care setting using EHR data

Olwendo,

Ochieng,

Rucha

2023

jagst

View full text Add to dashboard Cite

Diabetes remains a major global public health challenge, thus the need for better methods for managing diabetes. Machine learning could provide reliable solutions to the need for early detection and management of diabetes. This study conducted experiments to compare a number of selected machine learning approaches to determine their suitability for early detection of diabetes in the primary care setting. A retrospective study was conducted using EHR dataset of confirmed cases of diabetes collected during routine care at Nairobi Hospital. Institutional ethical approvals were obtained, and data were retrieved from the database through stratified sampling based on gender. Diagnoses were confirmed using the ICD-10 codes. Records with 5% or so of missing values were excluded from this analysis. Data were processed by correction of errors and replacement of missing values using measures of central tendency. The data were transformed through normalization using the decimal-scaling method. Data analysis was conducted using selected supervised and unsupervised learning algorithms. Model performances were validated using metrics for the evaluation of classification and clustering results, respectively. Random Forest had the highest accuracy (0.95) and error rate (0.05), while Gradient Boosting and Multilayer Perceptron (MLP) with 3 hidden layers obtained accuracy (0.94) and error rate (0.06), respectively. The process of selecting machine learning algorithms needs to explore both supervised and unsupervised learning techniques. In addition, an appropriate architectural design of an MLP could present astounding results for classification tasks in primary care settings.

show abstract

Section: Model Performance For the Fuzzy C-means Algorithmmentioning

confidence: 66%

Section: Model Performance For the Fuzzy C-means Algorithmmentioning

confidence: 99%

Comparison of machine learning methods for the prediction of type 2 diabetes in primary care setting using EHR data

Olwendo,

Ochieng,

Rucha

2023

jagst

View full text Add to dashboard Cite

show abstract

“…Selanjutnya model K-means dapat terbagi dalam satu atau lebih cluster/grup. Metode ini membagi data menjadi cluster atau kelompok, mengelompokkan data dengan karakteristik yang sama ke dalam cluster yang sama, dan mengelompokkan data dengan karakteristik yang berbeda kedalam kelompok lain [16], [17].…”

Section: Algoritma Clustering K-meansunclassified

Penerapan Machine Learning Clustering K-Means dan Linear Regression Dalam Penentuan Tingkat Resiko Tuberkulosis Paru

Ula

Zulfikri

Ulva

et al. 2023

ijcs

View full text Add to dashboard Cite

Penyakit tuberkulosis paru yang paling banyak disebarkan oleh bakteri Mycobacterium dan tipe penyakit ini menular pada bagian paru. tercatat pada tahun 2019 tercatat ada sekitar 400.000 jiwa penduduk Bireuen dengan jumlah kasus sekiar 755 jiwa yang menderita penyakit TB paru. Penelitian ini bertujuan untuk melihat daerah rawan terkena penyakit TB paru dan prediksi berdasarkan pertumbuhan penduduk. Data Penelitian diambil dari rumah sakit dr Fauziah Bireun Dinas kesehatan yang terdapat pada 17 Kecamatan. berdasarkan hasil tersebut terdapat hasil analisis dalam melihat daerah yang tersebar penyakit Tb Paru menggunakan algoritma K-Means dan Metode Clusterwise Regression. Hasil yang diperoleh dalam pengklusteran daerah rawan tuberkulosis paru yang terdapat dua daerah yang tergolong ke dalam cluster satu, enam daerah tergolong ke dalam cluster dua dan sembilan daerah tergolong ke dalam cluster tiga.Hasil prediksi dengan algoritma Regresi Linier 0,5740 dan hasil prediksi berpengaruh terhadap variabel lain adalah 9,481456817. Hasil penelitian ini dapat dijadikan rujukan dinas kesehatan dalam menindaklanjuti penyakit paru.

show abstract

“…The steps of this research are data mining knearest neighbors in monitoring the nutritional status of children and stunting in the form of primary data taken directly at the puskesmas in North Aceh. [12].…”

Section: Data Collection Stepsmentioning

confidence: 99%

Implementation of Data Mining Models With Algorithms K-Nearest Neighbor in Monitoring the Nutritional Status of Children and Stunting

Fachrurrazi,

Rizal

et al. 2023

JUSIKOM PRIMA

View full text Add to dashboard Cite

Information systems are needed in the development of children in the developmental period and especially in the world of health. Monitoring of children's nutritional status and stunting is necessary to determine children's weight and meet the criteria for children's nutritional status. Pukesmas Muara Satu, North Aceh District, is an implementing element or assistant to the duties of Poskesdes and Midwives in the Health of children's nutritional status and stunting in Paloh Punti Village, which is one of the agencies under the Ministry of Health. This study aims to monitor the growth and development of children such as measuring weight, height, measured to detect early if unwanted things occur such as malnutrition. The problem in this study is designing and monitoring an Information system for child nutritional status and stunting that is integrated with a web application. The purpose of this study is to find out staff and employees in managing, monitoring and accessing data. So that the data at the puskesmas is recorded in the system, and can quickly determine data on the nutritional status of children and stunting. The results of this study are to be able to find out an information system that is able to reduce problems that occur in managing data on the nutritional status of children and stunting at the Muara Satu Health Center. This system is very important because it can make it easier for staff to record the nutritional status of children and stunting at the Health Center. then the results of the KNN (K-Nearest Neighbor) model classification with the recapitulation of the value of new cases with old cases in the first test section is 0.6944, the second test is 0.6388, the third test is 0.555, the fifth test is 0.6388.

show abstract

Data Mining Classification Algorithms for Diabetes Dataset Using Weka Tool

Cited by 3 publications

References 9 publications

Comparison of machine learning methods for the prediction of type 2 diabetes in primary care setting using EHR data

Comparison of machine learning methods for the prediction of type 2 diabetes in primary care setting using EHR data

Penerapan Machine Learning Clustering K-Means dan Linear Regression Dalam Penentuan Tingkat Resiko Tuberkulosis Paru

Implementation of Data Mining Models With Algorithms K-Nearest Neighbor in Monitoring the Nutritional Status of Children and Stunting

Contact Info

Product

Resources

About