Light-Activated Virtual Sensor Array with Machine Learning for Non-Invasive Diagnosis of Coronary Heart Disease.

Early non-invasive diagnosis of coronary heart disease (CHD) is critical. However, it is challenging to achieve accurate CHD diagnosis via detecting breath. In this work, heterostructured complexes of black phosphorus (BP) and two-dimensional carbide and nitride (MXene) with high gas sensitivity and photo responsiveness were formulated using a self-assembly strategy. A light-activated virtual sensor array (LAVSA) based on BP/Ti3C2Tx was prepared under photomodulation and further assembled into an instant gas sensing platform (IGSP). In addition, a machine learning (ML) algorithm was introduced to help the IGSP detect and recognize the signals of breath samples to diagnose CHD. Due to the synergistic effect of BP and Ti3C2Tx as well as photo excitation, the synthesized heterostructured complexes exhibited higher performance than pristine Ti3C2Tx, with a response value 26% higher than that of pristine Ti3C2Tx. In addition, with the help of a pattern recognition algorithm, LAVSA successfully detected and identified 15 odor molecules affiliated with alcohols, ketones, aldehydes, esters, and acids. Meanwhile, with the assistance of ML, the IGSP achieved 69.2% accuracy in detecting the breath odor of 45 volunteers from healthy people and CHD patients. In conclusion, an immediate, low-cost, and accurate prototype was designed and fabricated for the noninvasive diagnosis of CHD, which provided a generalized solution for diagnosing other diseases and other more complex application scenarios.

Smell cancer by machine learning-assisted peptide/MXene bioelectronic array.

Non-invasive detection of tumors is of utmost importance to save lives. Nonetheless, identifying tumors through gas analysis is a challenging task. In this work, biosensors with remarkable gas-sensing characteristics were developed using a self-assembly method consisting of peptides and MXene. Based on these biosensors, a mimetic biosensor array (MBA) was fabricated and integrated into a real-time testing platform (RTP). In addition, machine learning (ML) algorithms were introduced to improve the RTP's detection and identification capabilities of exhaled gas signals. The synthesized biosensor, with the ability to specifically bind to targeted gas molecules, demonstrated higher performance than the pristine MXene, with a response up to 150% greater. Besides, the MBA successfully detected 15 odor molecules affiliated with five categories of alcohols, ketones, aldehydes, esters, and acids by pattern recognition algorithms. Furthermore, with the ML assistance, the RTP detected the breath odor samples from volunteers of four categories, including healthy populations, patients of lung cancer, upper digestive tract cancer, and lower digestive tract cancer, with accuracies of 100%, 94.1%, 90%, and 95.2%, respectively. In summary, we have developed a cost-effective and precise model for non-invasive tumor diagnosis. Furthermore, this prototype also offers a versatile solution for diagnosing other diseases like nephropathy, diabetes, etc.