Overcoming Cross-Sensitivity for the Accurate Identification of Acetone, Isopropanol, and Clinical Mixtures Using a MEMS Dual-Sensor Array and Multi-task Deep Learning
- 25 September 2026
- journal article
- Published by American Chemical Society (ACS) in ACS Sensors
- Vol. 11 (10) , 9133-9143
Abstract
Accurate detection of exhaled acetone (ACE) and isopropanol (IPA) mixtures is critical for the non-invasive screening of diabetic ketoacidosis and the continuous monitoring of lipid metabolism in type 1 diabetes mellitus. However, the broad clinical application of this approach remains severely constrained by the inherent cross-sensitivity of metal oxide semiconductor (MOS) sensors. To address this, a microelectromechanical systems (MEMS) dual-sensor array integrating PdO-modified SnO2/ZnO and MoS2/ZIF-67 nanocomposites was developed for simultaneous gas identification and concentration regression. By pioneering the extraction of distinct transient thermokinetic responses of the materials, combined with a multi-task learning architecture featuring a 1D Convolutional Neural Network and a Bidirectional Long Short-Term Memory (CNN-BiLSTM) network, the system efficiently analyzed dynamic sensing data using a sliding time window (K). At an optimal 15-s window, the model demonstrated robust real-time predictive capabilities, achieving 95.4% classification accuracy and a regression mean absolute error (MAE) of 0.625 ppm across clinical IPA/ACE ratios. This deep learning-enabled framework circumvents traditional steady-state limitations, providing a scalable, low-power solution for precise clinical breathomics and metabolic disease screening.Keywords
Funding Information
- National Key Research and Development Program of China (2024YFB3614200)
- National Natural Science Foundation of China (U25A20491)
- Higher Education Discipline Innovation Project (B25033)
This publication has 59 references indexed in Scilit:
- Precision hydrogen detection in mixed atmospheres using temperature-modulated PdAu-In2O3 sensor arrays and machine learning algorithmsChemical Engineering Journal, 2025
- DMC-Net: Lightweight Dynamic Multi-scale and Multi-resolution convolution network for pancreas segmentation in CT imagesBiomedical Signal Processing and Control, 2025
- NiO nanoparticles-based gas sensors: A novel pulse-driven approach for enhanced and efficient hydrogen detectionInternational Journal of Hydrogen Energy, 2024
- Overcoming the Limits of Cross-Sensitivity: Pattern Recognition Methods for Chemiresistive Gas Sensor ArrayNano-Micro Letters, 2024
- Artificial olfactory sensor based on single metal atom oxide for intelligent nanoelectronicsApplied Surface Science, 2024
- SERS sensing for cancer biomarker: Approaches and directionsBioactive Materials, 2024
- Breath volatile organic compounds (VOCs) as biomarkers for the diagnosis of pathological conditions: A reviewBiomedical Journal, 2023
- Advances in Noble Metal-Decorated Metal Oxide Nanomaterials for Chemiresistive Gas Sensors: OverviewNano-Micro Letters, 2023
- Phosphorus-doped porous perovskite LaFe1-xPxO3-δ nanosheets with rich surface oxygen vacancies for ppb level acetone sensing at low temperatureChemical Engineering Journal, 2022
- Recent advances in engineered graphene and composites for detection of volatile organic compounds (VOCs) and non-invasive diseases diagnosisCarbon, 2016