Forecasting Modelling for Early Detection of Heart Diseases Utilizing The Machine Learning Neuroevolution Model.

Hadiprayitno, Nadhif Bhagawanta (2024) Forecasting Modelling for Early Detection of Heart Diseases Utilizing The Machine Learning Neuroevolution Model. Other thesis, Universiti Teknologi Petronas, Institut Teknologi Sepuluh Nopember.

[thumbnail of 05111942000029 -Undergraduate_Thesis.pdf] Text
05111942000029 -Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 April 2027.

Download (2MB) | Request a copy

Abstract

Heart disease remains as a leading cause of mortality worldwide, even with the current advances in medical technology, it highlights the need for early detection to prevent or mitigate complications in the future. This project aims to develop a robust and accurate predictive model for early detection of heart disease disease by utilizing machine learning, specifically a neuroevolution model which was trained on the Cleveland dataset. By comparing the neuroevolution model's performance against established models such as Random Forest and Gradient Boosting, this study evaluates each model's accuracy, adaptability, and computational complexity to see whether or not the Neuroevolution model is viable or not. The results of the project show that the Neuroevolution model managed to outperform the other models in these metrics, indicating that the Neuroevolution model has potential in predictive diagnostics, particularly for heart disease detection. These findings suggest that Neuroevolution could play a valuable role in advancing AI-driven healthcare solutions for the futre, and offering a robust and efficient tool for early risk assessment in the medical world.
==================================================================================================================================
Penyakit jantung masih menjadi penyebab utama kematian di seluruh dunia, bahkan hingga saat ini kemajuan teknologi medis, hal ini menyoroti perlunya deteksi dini untuk mencegah atau mengurangi komplikasi di masa depan. Proyek ini bertujuan untuk mengembangkan yang kuat dan akurat model prediktif deteksi dini penyakit jantung dengan memanfaatkan pembelajaran mesin, khususnya model neuroevolusi yang dilatih pada kumpulan data Cleveland. Oleh membandingkan kinerja model neuroevolusi dengan model yang sudah ada seperti Random Forest dan Gradient Boosting, penelitian ini mengevaluasi akurasi setiap model, kemampuan beradaptasi, dan kompleksitas komputasi untuk melihat layak tidaknya model Neuroevolution apakah layak atau tidak. Hasil proyek menunjukkan bahwa model Neuroevolution berhasil mengungguli model lain dalam metrik ini, yang menunjukkan bahwa model Neuroevolution memiliki kinerja yang sama potensi dalam diagnostik prediktif, khususnya untuk deteksi penyakit jantung. Temuan ini menyarankan bahwa Neuroevolution dapat memainkan peran penting dalam memajukan layanan kesehatan berbasis AI solusi untuk masa depan, dan menawarkan alat yang kuat dan efisien untuk penilaian risiko awal di masa depan dunia medis.

Item Type: Thesis (Other)
Uncontrolled Keywords: Neuroevolution Model Viability, AI-Driven Healthcare Solutions, Computational Complexity in Medical AI, Heart Disease Risk Assessment, Evolutionary Computing in Medicine, Comparative Model Performance in Healthcare AI, AI-Based Early Diagnosis
Subjects: T Technology > T Technology (General) > T174 Technological forecasting
T Technology > T Technology (General) > T385 Visualization--Technique
T Technology > T Technology (General) > T57.5 Data Processing
Divisions: Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis
Depositing User: Nadhif Bhagawanta Hadiprayitno
Date Deposited: 19 Feb 2025 01:21
Last Modified: 19 Feb 2025 01:21
URI: http://repository.its.ac.id/id/eprint/118798

Actions (login required)

View Item View Item