Quantum machine learning assisted lung cancer telemedicine

Abstract

The rapidly increasing human population, the high cost of medical equipment, and the spread of multifactor diseases have transformed the entire healthcare industry into an electronic consulting, telediagnosis, delivery, and treatment model to avoid the physical personalization of patients. Despite this, we face many challenges, including low sensitivity of medical instruments, signal losses, and security of medical records. This study aims to develop a lung cancer telemedicine platform that utilizes classical and quantum computing models to classify lung cancer subtypes and stages and develop effective telemedicine techniques. By using optoplasmonic biosensors, the biosignals (that show lung cancer) were extracted and correlated with cloud datasets (containing patient information) to determine the dose of laser interstitial thermal therapy (LITT). Then, applying quantum teleportation, the biosignals and doses of LITT were teleported between two healthcare stations. From the numerical result, we observed the maximum sensitivity (10 421 nm/RIU) of the proposed biosensor, a minimum degree of the loss function and maximum correlation of data from the quantum machine learning model, and high teleportation fidelity (96% transmission fidelity for biosignals and 98% teleportation fidelity for doses LITT). This shows the proposed telemedicine schemes anticipated solutions for the long-distance faithful lung cancer telemedicine.