Skip to Main Content

An official website of the United States government

Principal Investigator
Dr. Mansi Verma
IILM University, Gurugram
Position Title
Assistant Professor
About this CDAS Project
PLCO (Learn more about this study)
Project ID
Initial CDAS Request Approval
Nov 7, 2023
Leveraging Data Mining and Neural Networks for Early Ovarian Cancer Detection
Breast cancer remains a significant health challenge, often diagnosed at advanced stages, leading to poor prognosis. Early detection is pivotal for improving patient outcomes. This proposal aims to harness the capabilities of data mining and neural network technologies to enhance the timely and accurate diagnosis of breast cancer. Data mining, as a core component, will play a crucial role in extracting valuable insights from large datasets, enabling the identification of potential markers and patterns associated with breast cancer. Recognising the challenges in early breast cancer diagnosis, the proposal acknowledges the need to unveil hidden information within extensive datasets. The research leverages the power of neural networks, specifically Artificial neural networks (ANNs), which have proven their efficacy in medical applications. To train these neural network models effectively, a comprehensive dataset encompassing ovarian cancer-related patient records and medical imagery will be employed. The primary objective is to advance the early detection of breast malignancies and improve the accuracy of breast cancer diagnosis. Successful implementation of this initiative holds the potential not only to empower healthcare professionals in making more informed decisions but also to facilitate accessible and cost-effective screening for breast cancer. This proposal signifies a significant advancement in the realms of medical imaging and oncology and has the potential to bring about positive impacts on patient care and outcomes.

* Develop accurate neural network models for early breast cancer detection.
* Identify key biomarkers and patterns in patient data to enhance diagnosis.
* Optimize model performance to reduce false positives and improve sensitivity.
* Validate the models in clinical settings to ensure practicality and reliability.
* Investigate cost-effective and accessible screening solutions for wider adoption.
* Maintain a patient-centric approach, focusing on improved outcomes and well-being.


Priya Dubey