Early Detection of Diabetes with Quantum Machine Learning and Causal Inference Techniques

• A novel quantum machine learning technique proposed for early diabetes estimation • Adding causal inference, predict diabetes risk and proper reasoning in individuals • Enhancing diagnosis efficiency with subtle symptoms, suitable for easy monitoring • Addressing diabetes progression with a personalized healthcare plan Diabetes has become one of the most common chronic diseases in the United States. It is also the one that remains either undiagnosed or misdiagnosed over the years, leading a patient to life threatening conditions. The main reasons behind this are- lack of awareness among patients, food habits, sedentary lifestyles and lack of clinical services. There are common symptoms found in a person who is leading toward diabetes, and they can be easily identified at an early stage to help them maintain a healthy lifestyle. In this paper, we focus on finding out the most basic but significant features to detect diabetes in an undiagnosed person, providing the reasons of why diabetes happens in any person. We also implement quantum machine learning algorithms to dive deeper into the patterns of the features, bringing out any future possibilities of a healthy person becoming diabetic. Our proposed model, which is an ensemble of causal inference and quantum machine learning, suggests an appropriate feature set for diabetes estimation with better efficiency than others.