Year: 2025
Type: article
Abstract: Cancer remains one of the most critical health concerns worldwide, with the number of cases rising each year due to lifestyle changes, genetic factors, and limited access to early diagnostic services.Delayed detection continues to be a major reason for increased mortality, as many patients are identified only when the disease has already progressed.This challenge highlights the need for fast, reliable, and accessible tools that can support early screening.In response to this demand, the present study introduces an integrated machinelearning-based system capable of predicting multiple cancer types, including lung, blood, breast, and brain cancer.The proposed framework employs a set of refined machine learning algorithms that analyze clinical records, diagnostic attributes, and image-based inputs to detect subtle patterns associated with early cancer development.By extracting key features and evaluating them through optimized models, the system offers improved prediction accuracy and consistency across different cancer categories.Beyond diagnosis, the platform incorporates a patient-centered support ecosystem that provides personalized yoga routines, diet suggestions, and lifestyle guidance to assist users in managing physical and emotional well-being.An AIenabled health chatbot is also included to answer medical queries, guide users through symptoms, and promote health awareness.Additionally, the system connects individuals to nearby hospitals, government healthcare schemes, NGOs, and potential donors through an interactive mapping and assistance module.By combining predictive analytics with supportive healthcare features, the proposed solution aims to enhance early detection, strengthen user engagement, and improve overall access to cancer-related resources
Authors: Samruddhi, Sakshi Hattikar, Vaishnavi Yalgulkar, Pishanna Patil
Institution: Jain College of Engineering and Research
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W4417459671
FWCI:
Cites:
Cited by:
Related to: