Project Overview

Introduction

In response to the critical challenge of cancer detection and prognisis, our initiative harnesses the power of machine learning and artificial intelligence. The primary objective is to develop a highly accurate AI model, targeting a minimum accuracy of 70% (tentative), specifically designed to detect the likely prognosis of cancer in patients. Given that cancer contributes to approximately 600,000 fatalities in the United States each year, our project seeks to provide medical professionals with a valuable tool for improving cancer recurrence prognosis.

Key Objectives

1. Precision in Prognosis: Develop an AI model with a focus on precision, aiming for a minimum accuracy of 70% in detecting a cancer prognosis. This accuracy threshold is set to ensure reliable and actionable prognostic information.
2. Medical Professional Utilization: Tailor the product for seamless integration into the workflows of medical professionals. The AI model's outputs should serve as a valuable resource for healthcare providers in enhancing their ability to predict cancer recurrence.
3. Impact on Mortaility Rates: Address the urgent need to reduce cancer-related fatalities. By providing an advanced tool for cancer prognosis, our project aims to contribute to early intervention and improved patient outcomes.

Target Audience

Our primary users are medical professionals involved in cancer care. The AI model's insights will empower these professionals with enhanced predictive capabilities.

Scope and Significance

The scope of our project encompasses the development of a robust AI model capable of analyzing patient data to identify a likely prognosis. The significance lies in the potential to revolutionize cancer care by providing timely and accurate prognostic information, ultimately leading to more targeted and effective interventions.

Expected Impact

By achieving our objectives, we anticipate the following impact:

1. Early Intervention: Facilitating early detection of recurrence, enabling timely intervention and personalized treatment plans.
2. Improved Patient Outcomes: Enhancing patient outcomes through more accurate and tailored prognostic information.
3. Reduced Healthcare Costs: Potentially reducing long-term healthcare costs by minimizing the need for extensive and repetitive treatments.
4. Advancing Medical Knowledge: Contributing valuable insights to the broader medical community, advancing knowledge in the field of cancer care.

Design Tools

We will utilize the following tools:

1. Tensorflow: Google's machine learning library.
2. Keras: Neural network API with premade ML models.
3. Google Colab: Free jupyter notebook for developing ML models that has access to Google hardware.
4. AWS: Amazon cloud computing platform.
5. TKinter: Python UI building kit.

Design Diagram