Risma Dhiya Ulhaq Maharany
22 Oktober 2024
As public awareness of health increases, many individuals are starting to seek information about diseases, even when experiencing only minor symptoms. To facilitate access to health information, an AI-based health recommendation system has been developed. This system is designed to predict or provide diagnoses based on the symptoms experienced, as well as recommend appropriate medications, diets, and activities. Thus, users can perform early self-diagnosis before consulting a doctor.
With the rise of public health awareness, many people are seeking independent information regarding medical conditions they may be experiencing. Online resources are often too broad or imprecise. Therefore, the development of an AI-based health recommendation system becomes highly relevant. This system aims to help users obtain more accurate and personalized information about disease predictions and related health recommendations.
This system was developed using eight different datasets, including data on symptoms and diseases, disease descriptions, medications, diets, exercises, and preventive measures. These datasets were obtained from reputable health sources and publicly available health datasets. Each dataset was processed and cleaned to ensure compatibility with the system’s requirements.
Several machine learning algorithms were tested during the system development, including, Support Vector Classification (SVC), Random Forest, Gradient Boosting, K-Neighbors, Multinomial Naive Bayes. Ultimately, Support Vector Machine (SVM) was selected as the best model due to its high-performance capabilities in handling high-dimensional data and the variability of symptoms. SVM is well-suited for both binary and multi-class classification, making it ideal for this system, which predicts various diseases based on combinations of symptoms.
The system allows users to input the symptoms they are experiencing into the application. After selecting the symptoms, users can press the prediction button to receive information that includes:
The system was deployed using Streamlit , an open-source framework that enables developers to quickly create interactive web applications. With Streamlit, the system can be accessed directly by users via a web browser, without the need for additional software installation. The user interface is designed to be user-friendly, with intuitive symptom input features and clear prediction result displays.
Artikel Lainnya
Cheva Wahyu Noerhuda
10 September 2024
Library Python gTTS untuk Pemanggilan Antrian
Eriko Syah Putra Friyadi
16 Oktober 2024
Sistem Rekomendasi Makanan Berdasarkan Nutrisi
Hidayat Tri Winasis
15 Oktober 2024
Predicting Doctor Consultation Fees
Dengan teknologi yang adaptif dan solusi yang inovatif, kami siap membantu bisnis Anda meraih potensi terbaiknya.
AD Premier Lantai 17 Suite 04 B, Jl. TB. SImatupang No. 5 Desa/Kel. Ragunan, Kec. Pasar Minggu, Kota ADM. Jakarta Selatan.
Perum D Livia Gading No. 3, Kel. Kalisegoro, Kec. Gunungpati, Kota Semarang
copyright Serpihan Tech Solution © 2024 - All Right Reserved
