ONCO-VISION: An Intelligent Cancer Care System Using Machine Learning and Data Analytics

Abstract

Early detection of cancer plays a critical role in improving survival rates and reducing mortality worldwide. This study presents ONCO-VISION, an intelligent cancer detection system that utilizes artificial intelligence and machine learning techniques to assist in the early diagnosis of lung and breast cancers. The proposed system is implemented as a web-based platform that supports dual input modalities, allowing users to upload medical reports in formats such as PDF, DOCX, and medical images, or manually enter relevant medical parameters including hemoglobin levels, blood pressure, body mass index (BMI), and clinical symptoms. The system employs an ensemble of machine learning algorithms, including Random Forest, Gradient Boosting, Support Vector Machine (SVM), and Neural Networks, to analyze more than twenty medical features for accurate cancer classification. The trained models predict cancer presence, type, and stage while generating diagnostic reports that include probability scores, confidence metrics, and stage differentiation between early and advanced conditions. In addition, the platform provides personalized treatment recommendations, including suggested medications, dosage guidance, and precautionary measures based on the patient\'s health profile. The application is developed using the Flask framework with a responsive Bootstrap-based interface that ensures usability and accessibility. Secure data handling mechanisms are implemented to protect sensitive medical information. Experimental evaluation demonstrates that the proposed system achieves high prediction accuracy and provides an efficient decision-support tool for early cancer detection. The modular architecture also supports future integration with hospital electronic health record systems and expansion to additional cancer types.

Introduction

The text discusses cancer as a serious disease caused by abnormal cell growth, with breast and lung cancer being among the most common and deadly types. Early detection is crucial for effective treatment, but traditional diagnostic methods are costly, time-consuming, and prone to human error.

To address these challenges, the proposed ONCO-VISION Cancer Detection System uses machine learning and artificial intelligence to detect and classify both breast and lung cancer within a single platform. It analyzes medical data such as patient records, test results, and symptoms to provide faster and more accurate predictions.

The system follows a structured methodology including data collection, preprocessing, feature selection, model training, and classification using algorithms like Random Forest, Gradient Boosting, SVM, and Neural Networks. It can also generate diagnostic reports, identify cancer stages, and suggest treatments through a web-based interface.

Results show that advanced models, especially ensemble and neural network methods, achieve high accuracy and effectively classify patients into healthy, breast cancer, or lung cancer categories.

Conclusion

This study presented ONCO-VISION, an intelligent cancer detection system designed to assist in the early diagnosis of breast and lung cancers using machine learning and artificial intelligence techniques. The system integrates advanced data analysis with a user-friendly web-based platform that allows users to upload medical reports or manually enter important medical parameters for analysis. By utilizing multiple machine learning algorithms such as Random Forest, Gradient Boosting, Support Vector Machine, and Neural Networks, the system is capable of analyzing several medical features to predict the presence and type of cancer with high accuracy. The proposed system provides a comprehensive diagnostic output that includes prediction results, probability scores, and stage classification of the detected cancer. In addition, it generates personalized treatment recommendations and precautionary measures based on the predicted condition. This helps healthcare professionals and patients understand the diagnosis more effectively and supports informed medical decision-making. One of the major advantages of the ONCO-VISION system is its accessibility and ease of use, as it allows users to upload blood reports and medical data through a simple interface. The system also ensures secure handling of medical information and efficient processing of uploaded reports. By combining intelligent algorithms with an accessible digital platform, the system reduces dependency on complex diagnostic infrastructure and enables faster preliminary analysis. Overall, the proposed system demonstrates how artificial intelligence can support modern healthcare by improving early cancer detection and assisting doctors in clinical decision-making. Early identification of cancer conditions can lead to timely treatment, reduced mortality rates, and improved patient outcomes. Therefore, the ONCO-VISION system has the potential to serve as an effective decision-support tool for cancer diagnosis and healthcare management.

References

[1] W. H. Wolberg, W. N. Street, and O. L. Mangasarian, “Machine learning techniques to diagnose breast cancer from fine-needle aspirates,” Cancer Letters, vol. 77, no. 2–3, pp. 163–171, 1994. [2] M. A. Hall, “Correlation-based feature selection for machine learning,” Ph.D. dissertation, Dept. Computer Science, University of Waikato, New Zealand, 1999. [3] D. Dua and C. Graff, “UCI Machine Learning Repository,” University of California, Irvine, School of Information and Computer Sciences, 2019. Available: http://archive.ics.uci.edu/ml [4] S. Singh and K. R., “Breast cancer detection using machine learning,” International Journal of Engineering and Computer Science, vol. 13, no. 3, pp. 25988–25992, 2024. [5] R. Shashidhar, B. N. Arunakumari, and S. M. Kumar, “Breast cancer detection using supervised machine learning algorithms,” Asian Journal for Convergence in Technology, vol. 4, no. 2, pp. 1–5, 2018. [6] A. Esteva et al., “A guide to deep learning in healthcare,” Nature Medicine, vol. 25, pp. 24– 29, Jan. 2019. [7] J. Litjens et al., “A survey on deep learning in medical image analysis,” Medical Image Analysis, vol. 42, pp. 60–88, 2017. [8] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in Proc. Advances in Neural Information Processing Systems, 2012, pp. 1097–1105.

Copyright

Copyright © 2026 B. Anusha , B. Laxmi Prasuna, D. Bharath Kumar, A. Anusha . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.