Machine Learning‐Driven Ultrasensitive WSe <sub>2</sub> /MWCNT Hybrid‐Based E‐Nose Sensor Array for Volatiles Amines Mixture
Snehraj Gaur, Sukhwinder Singh, A. Bhatia, Vansh Bhutani, Mohit Verma, Hossam Haick, Vishakha Pareek, Ritu Gupta
Abstract
Abstract Volatile amines in breath act as biomarkers for kidney and liver diseases. Monitoring these amines, especially when present as a mixture, provides insights into the metabolic state of the body. This study focuses on differentiating volatile amines by systematically modulating the conductivity and sensitivity of WSe 2 /Multiwalled Carbon Nanotubes composite‐based sensors. The fabricated chemiresistive sensor array demonstrates high selectivity, sensitivity (7.67% ppm −1 ), fast response and recovery kinetics (32 s/137 s), and accurate discrimination among target amines, even in the presence of other VOCs (volatile organic compounds). The sensor array operates at room temperature and achieves a theoretical limit of detection (LOD) of 387 ppt, 206, 157, and 202 ppb for triethylamine (TEA), dimethylamine (DMA), methylamine (MA), and ammonia (NH 3 ), respectively, demonstrating its suitability for breath sensing and diagnostics. Machine learning (ML) analysis is employed to differentiate between the volatile amines and mixtures with 94% accuracy. The ability to detect these amines at such low ppt and ppb levels underscores the potential of this e‐nose technology for high‐performance applications in early‐stage disease diagnostics.