Utilizing Quantum Support Vector for Classification of Parkinson’s Disease

Utilizing Quantum Support Vector Machines For Classification of Parkinson's Disease

Project Description

I focused on building a QML algorithm to identify whether a patient has Parkinson’s disease based on their speech features. I conducted a 9-qubit simulation on IBM’s quantum simulators utilizing a quantum support vector machine.

Purpose
Parkinson’s disease affects 10 million people worldwide. It is a brain disorder that eventually takes away a patient’s ability to walk and talk. There is no cure but if it’s detected early, the symptoms can be managed so the patient can live a relatively normal life. This algorithm can help doctors detect and begin treatment earlier to save lives all over the world. 
The Project

I focused on building a quantum support vector machine algorithm to identify whether a patient has Parkinson’s disease based on their speech features. It is traditionally a machine learning algorithm but I built it on a quantum circuit to efficiently run on a quantum computer. I, then, ran the 9-qubit quantum support vector machine on IBM’s qasm simulator to obtain the results. 

Results

The results I received demonstrated that the algorithm was successful. The final run was for 500 shots. The end results showed that the algorithm has the ability to predict whether or not each of 9 patients have Parkinson’s disease with a 0.75 accuracy rate. Fortunately, in coming years, with a larger Parkinson’s dataset and more stable hardware, the accuracy rate will only go up.

Still Interested?

Read my article for more information

Github for reference to QML algorithm: