Melola Discovery

← Melola Discovery

Jurnal Tanpa peringkat SINTA

Optimization of Coronary Heart Disease Risk Prediction Using Extreme Learning Machine Algorithm (Case Study: Patients of Dr. Soeselo Hospital)

Scientific Journal of Informatics · Vol. 12 No. 2 (2025) · hlm. 349–360

DOI
10.15294/sji.v12i2.24746
ISSN
2407-7658, 2460-0040
Terbit
2025-07-15
Penerbit
Universitas Negeri Semarang
Bahasa
eng

Abstrak

Purpose: Coronary heart disease (CHD) is the leading cause of death globally, with 17.8 million deaths reported by the WHO in 2021. Early detection remains a major challenge due to low public awareness and dependence on manual diagnostic procedures. These limitations necessitate the development of automated and accurate predictive models. This study aims to construct a CHD risk prediction model using the Extreme Learning Machine (ELM) algorithm. The research addresses a critical limitation in existing models, namely, poor performance on minority classes (CHD stages 2–4), caused by data imbalance. To overcome this, oversampling techniques such as Synthetic Minority Oversampling Technique (SMOTE) and Adaptive Synthetic Sampling (ADASYN) are applied. The objective is to improve classification performance, particularly in high-risk categories, and to enhance the model’s generalisation capability for real-world implementation. Methods: This research implements the Extreme Learning Machine (ELM) algorithm to achieve optimal prediction results. The data used in this study as the initial database of patients consists of gender, age, height, weight, whether they have diabetes or not, the number of cigarettes consumed daily, and blood pressure. The data will be the main component in building the heart disease prediction system. The prediction classes are: no heart disease, stage 1 heart disease, stage 2 heart disease, stage 3 heart disease, and stage 4 heart disease. The total number of dataset are 521 data points, with 70% of the training data amounting to 364 patients, and 30% of the test data amounting to 157 patients. The data collection process uses patient data from RSUD Dr. Soeselo, Tegal Regency, Central Java, for the years 2023 and 2024. Result: The research successfully developed and evaluated an Extreme Learning Machine (ELM) algorithm for Coronary Heart Disease (CHD) risk prediction using patient data from Dr. Soeselo Hospital. The model achieved an overall accuracy of 82% on the dataset of 157 patients, demonstrating a promising capability for automated risk assessment. Novelty: This predictive model can be utilised in the medical field to facilitate the early detection of heart disease or other risks. This model will soon be introduced in hospitals in the Tegal Regency and City area, Central Java.

Kata kunci

Jaringan kolaborasi para penulis

25 penulis · 43 tautan kepenulisan bersama · 6 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Diponegoro University
  • State University of Semarang
  • Politeknik Negeri Semarang
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Kusworo AdiDiponegoro University3
Oky Dwi NurhayatiDiponegoro University2
Ucky Pradestha NovettralitaDiponegoro University2
Budi WarsitoDiponegoro University2
Yulaikha MaratullatifahDiponegoro University1
Yusraka Dimas Al ImanDiponegoro University1
Munawar Agus RiyadiDiponegoro University1
Muhammad Fahmi AwajDiponegoro University1
Rahmat GernowoDiponegoro University1
Arief ArfriandiState University of Semarang1
Nouvel Izza FardanaDiponegoro University1
Dinar Mutiara Kusumo NugraheniDiponegoro University1
Ardian PamungkasDiponegoro University1
N IdrusDiponegoro University1
Sima MaulinaDiponegoro University1
Nanang SulaksonoDiponegoro University1
Dwi RochmayantiDiponegoro University1
Sri HandayaniState University of Semarang1
Sirli FahriahDiponegoro University1
PrayitnoPoliteknik Negeri Semarang1
Nurfaizah NurfaizahAfiliasi tidak diketahui1
Imam TahyudinAfiliasi tidak diketahui1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) https://journal.unnes.ac.id/journals/sji/oai, pertama di-harvest 6 Nov 2026, terakhir terlihat 8 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en">Optimization of Coronary Heart Disease Risk Prediction Using Extreme Learning Machine Algorithm (Case Study: Patients of Dr. Soeselo Hospital)</dc:title>
	<dc:creator xml:lang="en">Iswanti, Arie</dc:creator>
	<dc:creator xml:lang="en">Isnanto, R. Rizal </dc:creator>
	<dc:creator xml:lang="en">Widodo, Catur Edi </dc:creator>
	<dc:subject xml:lang="en">Coronary heart disease</dc:subject>
	<dc:subject xml:lang="en">Optimization</dc:subject>
	<dc:subject xml:lang="en">ANN algorithm</dc:subject>
	<dc:subject xml:lang="en">Extreme learning machine</dc:subject>
	<dc:subject xml:lang="en">Oversampling techniques</dc:subject>
	<dc:description xml:lang="en">Purpose: Coronary heart disease (CHD) is the leading cause of death globally, with 17.8 million deaths reported by the WHO in 2021. Early detection remains a major challenge due to low public awareness and dependence on manual diagnostic procedures. These limitations necessitate the development of automated and accurate predictive models. This study aims to construct a CHD risk prediction model using the Extreme Learning Machine (ELM) algorithm. The research addresses a critical limitation in existing models, namely, poor performance on minority classes (CHD stages 2–4), caused by data imbalance. To overcome this, oversampling techniques such as Synthetic Minority Oversampling Technique (SMOTE) and Adaptive Synthetic Sampling (ADASYN) are applied. The objective is to improve classification performance, particularly in high-risk categories, and to enhance the model’s generalisation capability for real-world implementation.
Methods: This research implements the Extreme Learning Machine (ELM) algorithm to achieve optimal prediction results. The data used in this study as the initial database of patients consists of gender, age, height, weight, whether they have diabetes or not, the number of cigarettes consumed daily, and blood pressure. The data will be the main component in building the heart disease prediction system. The prediction classes are: no heart disease, stage 1 heart disease, stage 2 heart disease, stage 3 heart disease, and stage 4 heart disease. The total number of dataset are 521 data points, with 70% of the training data amounting to 364 patients, and 30% of the test data amounting to 157 patients. The data collection process uses patient data from RSUD Dr. Soeselo, Tegal Regency, Central Java, for the years 2023 and 2024.
Result: The research successfully developed and evaluated an Extreme Learning Machine (ELM) algorithm for Coronary Heart Disease (CHD) risk prediction using patient data from Dr. Soeselo Hospital. The model achieved an overall accuracy of 82% on the dataset of 157 patients, demonstrating a promising capability for automated risk assessment.
Novelty: This predictive model can be utilised in the medical field to facilitate the early detection of heart disease or other risks. This model will soon be introduced in hospitals in the Tegal Regency and City area, Central Java.</dc:description>
	<dc:publisher xml:lang="en">Universitas Negeri Semarang</dc:publisher>
	<dc:date>2025-07-15</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.unnes.ac.id/journals/sji/article/view/24746</dc:identifier>
	<dc:identifier>10.15294/sji.v12i2.24746</dc:identifier>
	<dc:source xml:lang="en">Scientific Journal of Informatics; Vol. 12 No. 2: Regular Issue; 349-360</dc:source>
	<dc:source>2407-7658</dc:source>
	<dc:source>2460-0040</dc:source>
	<dc:source>10.15294/sji.v12i2</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journal.unnes.ac.id/journals/sji/article/view/24746/4948</dc:relation>
	<dc:rights xml:lang="en">Copyright (c) 2025 Scientific Journal of Informatics</dc:rights>
</oai_dc:dc>