Abstract

ABSTRAKKanker paru merupakan penyebab utama kematian akibat kanker di seluruh dunia. Prediksi dini kanker paru-paru telah banyak dilakukan, baik berbasis citra maupun data mentah. Prediksi kanker paru berbasis citra memberikan dampak positif dalam diagnosis dini, namun pendekatan berbasis data mentah juga penting dalam memahami faktor risiko dan kondisi yang dapat mempengaruhi perkembangan kanker. Penelitian ini mengusulkan sistem prediksi dini kanker paru dengan basis data klinis dan demografi, menggunakan Multi-Layer Perceptron (MLP) dan logistic regression dengan pemanfaatan grid search optimizer. Kedua model mencapai tingkat akurasi, presisi, recall, dan f1-score sebesar 1, optimal dalam melakukan prediksi data. Pada logistic regression, solver liblinear, penalty L1, dan nilai C yang lebih tinggi berkontribusi pada peningkatan akurasi. Sedangkan pada MLP, konfigurasi aktivasi tanh dan solver adam menghasilkan akurasi yang lebih baik. Hasil ini memberikan keyakinan implementasi MLP dan logistic regression, memiliki potensi dalam mendukung prediksi kanker paru-paru.Kata kunci: kanker paru, multi-layer perceptron, logistic regression, grid search ABSTRACTLung cancer is a leading cause of cancer-related deaths worldwide. Early prediction of lung cancer has been widely conducted, both based on images and raw data. Image-based lung cancer prediction has a positive impact on early diagnosis, but a raw data-driven approach is also crucial for understanding risk factors and conditions that can influence cancer development. This research proposes an early lung cancer prediction system using clinical and demographic data, employing Multi-Layer Perceptron (MLP) and logistic regression with the utilization of grid search. Both models achieved an accuracy, precision, recall, and f1-score of 1, optimal in classifying data. In logistic regression, the liblinear solver, L1 penalty, and higher C values contributed to increased accuracy. Meanwhile, in MLP, the configuration of tanh activation and adam solver yielded better accuracy. Theseresults instill confidence that the implementation of MLP and logistic regression has significant potential in supporting lung cancer prediction.Keywords: lung cancer, multi-layer perceptron, logistic regression, grid search

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.