Multimodal biosensor system for exhaled breath based lung cancer diagnosis

Exhaled breath analysis offers non-invasive lung cancer diagnosis potential by detecting specific volatile organic compounds (VOCs) produced during metabolic processes in patients. Researchers are developing and using gas sensors for this purpose. However, the concentration of lung cancer VOCs markers in exhaled breath is generally low, and individual commercial gas sensors often lack the necessary sensitivity and selectivity to accurately diagnose lung cancer. In this study, we propose a multimodal biosensor system designed to differentiate lung cancer VOCs characteristics among multiple VOCs, enabling exhalation-based lung cancer diagnosis. Initially, we developed multimodal biosensors using 10 gas sensors, each exhibiting varying sensitivity profiles for complex gas mixtures. Additionally, we designed a classification algorithm based on feed-forward neural networks (FFNN) to distinguish between lung cancer patients and healthy individuals using the output from these diverse gas sensors. To evaluate the system's performance, we collected exhaled air samples from 46 lung cancer patients and 45 normal subjects, conducting clinical trials with our developed system. The results of these tests confirmed that our system achieved a high predictive accuracy of over 90% in classifying lung cancer patients. The simplicity of the sensor configuration in our developed system makes it suitable for large-scale screening tests to identify potential candidates for precise lung cancer diagnosis. This technology has the potential to contribute to reduced national welfare costs and improved patient survival rates through early diagnosis.