We were inspired by the potential of quantum computing to enhance real-world applications, especially in critical fields like healthcare. Our project explores a hybrid quantum-classical machine learning approach for breast cancer classification. Using Qiskit, we built quantum circuits for feature encoding and paired them with classical algorithms like Random Forest to compare performance. Along the way, we learned how to preprocess data for quantum input, construct meaningful quantum circuits, and interpret results from quantum simulations. Challenges included limited scalability due to qubit constraints and long simulation times, but the project highlighted both the promise and current limitations of quantum machine learning.

Built With

After Ishan applied his traditional machine learning practices to our dataset, I took the cases labeled as ambiguous and reprocessed them with a Variational Quantum Classifier featured in Qiskit, then explored whether this process improved our results. Finally, I looked into the quantum circuit that was happening "behind the scenes" when using the VQC.

thomasgilbert481 Gilbert
I focused on the machine learning component, specifically implementing the Random Forest model to classify tumor data. I was also responsible for preparing and managing the training and testing datasets, as well as generating the prediction percentages and accuracy scores. This work laid the foundation for Thomas to build and integrate the quantum model in the later stages of the project.

Ishan Ghosh

Leave feedback in the comments!

Log in or sign up for Devpost to join the conversation.