Skripsi

MACHINE LEARNING MODEL ARTIFICIAL NEURAL NETWORK UNTUK PREDIKSI RISIKO OBESITAS DAN PREDIABETES PADA DEWASA

---

Penilaian

---

Background: Obesity is a clinical condition characterized by abnormal fat accumulation and has significantly increased in prevalence since 1980. Obesity and prediabetes are complexly related to factors such as age, gender, and lifestyle. Obesity contributes to insulin resistance, dyslipidemia, and beta-cell dysfunction, which progresses to type 2 diabetes mellitus. These conditions may occur concomitantly. Predictive analysis of obesity and prediabetes often involves complex statistical processes, making machine learning, particularly Artificial Neural Networks (ANN), a valuable tool to enhance predictive accuracy. This study aims to evaluate the accuracy of the ANN model in predicting obesity and prediabetes in adult populations. Methods: This observational analytic study used a cross-sectional design and secondary data. The sample consisted of adults aged 19–65 years living in Palembang, who visited primary healthcare services. Data were collected using purposive sampling and analyzed with multinomial logistic regression and ANN model from Orange Data Mining software. Results: Of the 1212 respondents, 63 (5.2%) had both obesity and prediabetes, 182 (15%) were obese, 125 (10.3%) had prediabetes, and 842 (69.5%) were normal. The ANN model demonstrated an accuracy of 91.7% in predicting obesity and prediabetes, 89.2% for obesity, and 81.3% for prediabetes. Key predictors included age, gender, family history of obesity, income level, consumption of sugary foods, fruits, and physical activity. Conclusion: Artificial Neural Network is accurate in predicting obesity and or prediabetes in adults. Keywords: Obesity, Prediabetes, Insulin Resistance, Concomitant, Machine Learning, Artificial Neural Network

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2407006749	T160928	T1609282024	Central Library (REFERENCE)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1609282024

Publisher

Indralaya : Prodi Pendidikan Kedokteran, Fakultas Kedokteran Universitas Sriwijaya., 2024

Collation

xiv, 58 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.310 7

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Pendidikan Kedokteran
Prediksi risiko kesehatan; Obesitas; Prediabetes

Specific Detail Info

-

Statement of Responsibility

TUTI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment