Year: 2024
Type: article
Abstract: The diagnosis of critical diseases like breast cancer, diabetes, malaria, and pneumonia is challenging, especially in under-resourced healthcare settings due to infrastructure limitations and time-consuming methods. To address these issues, we propose a web-based Multiple Disease Predictor platform, a centralized diagnostic tool powered by machine learning algorithms. The platform processes medical images, blood test results, and clinical data to deliver accurate, real-time disease predictions. By consolidating multiple diagnostic capabilities into one interface, the system reduces reliance on specialized equipment, improves efficiency, and enhances diagnostic accuracy, particularly in resource-limited areas. Advanced machine learning and deep learning techniques enable rapid, accurate data analysis, minimizing diagnostic errors and misdiagnosis risks, which is crucial in underserved regions with limited access to specialized equipment. The platform also supports early detection and timely treatment, improving patient outcomes. By integrating diverse diagnostic data sources, healthcare providers can make faster, informed decisions. This system democratizes access to advanced diagnostic technology, promoting cost-effective healthcare. Key Words: Diagnosis, Diabetes, Machine Learning, Decision tree, Logistic Regression and Accuracy.
DOI: 10.55041/ijsrem39910
Authors: Ayesha Siddiqa, Kavana G S, Manish S Patel, Lisha M, Madhushree J S
Institution: Jawaharlal Nehru New College of Engineering
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: bronze
OpenAlex ID: W4405609973