Machine Learning-Enabled Gas Sensor Based on MOF-Derived In 2 O 3 –CuO for Exhaled CO Detection
- 5 June 2026
- journal article
- research article
- Published by American Chemical Society (ACS) in ACS Sensors
- Vol. 11 (6) , 4763-4774
Abstract
Noninvasive, precise breath analysis holds significant importance for the screening and monitoring of neonatal jaundice, with its core challenge lying in the specific detection of the key biomarker carbon monoxide (CO) within complex breath matrices. This research employed a controlled process to fabricate five sets of In2O3–CuO sensors derived from bimetallic metal–organic frameworks (Bi MOFs). These were assembled into a microsensor array, and by incorporating a linear discriminant analysis algorithm, an electronic nose system was constructed. This approach utilizes thermodynamic feature engineering to enhance data validity and optimize algorithm selection, thereby reducing reliance on large-scale data and computational resources. By integrating thermodynamically feature-driven machine learning, the electronic nose system-comprising merely five In2O3–CuO sensors-ultimately achieved accurate discrimination between CO and acetone. Concurrently, the single 3In2O3–CuO sensor exhibits excellent reproducibility, moisture resistance, and stability, with a low detection limit of 1 ppm and relatively rapid response/recovery times (5/21 s). By introducing machine learning algorithms to analyze the multidimensional response signals from the sensor array, the study successfully addressed the cross-sensitivity issue between CO and coexisting interfering gas C3H6O in clinical environments, achieving qualitative identification of CO ranging from 1 to 50 ppm (cross-validation accuracy reached 82%), providing a highly reliable technical platform for noninvasive screening of neonatal bilirubin metabolic abnormalities.Keywords
Funding Information
- Science and Technology Planning Project of Shenzen Municipality (ZDCYKCX20250901092759010)
- Shenzhen Key Industrial R&D Programme ‘Key Technology Development for Combustible Gas Leakage Explosion Risk Monitoring, Early Warning and Emergency Prevention System’ (ZDCYKCX20250901092759010)
- International Joint Laboratory for MicroNano Manufacturing and Measurement Technologies
This publication has 41 references indexed in Scilit:
- Dealloying the Ir–P Bond Coordination to Strengthen d–p Orbital Affinity for Efficient Anion Exchange Membrane Water ElectrolyzerAdvanced Functional Materials, 2026
- Probing the Structural Dynamics of In 2 O 3 Using in Situ Raman Spectroscopy: Bridging Material Dynamics and Sensor FunctionalityAngewandte Chemie International Edition, 2025
- A ratiometric fluorescent probe for the specific detection of carbon monoxide released from CORM-3 and induced by heme in living cellsAnalytica Chimica Acta, 2025
- Materials‐Algorithm Co‐Optimization for Specific and Quantitative Gas DetectionInterdisciplinary Materials, 2025
- Chemiresistive sensor array for quantitative prediction of CO and NO2 gas concentrations in their mixture using machine learning algorithmsMicrochimica Acta, 2024
- Surface modification of In2O3 porous nanospheres with Au single atoms for ultrafast and highly sensitive detection of COApplied Surface Science, 2022
- Microwave‐assisted hydrothermal synthesis of copper oxide‐based gas‐sensitive nanostructuresRare Metals, 2020
- Enhanced CO sensing properties of Pd modified ZnO porous nanosheetsChinese Chemical Letters, 2020
- Mechanism and characteristics of Au-functionalized SnO2/In2O3 nanofibers for highly sensitive CO detectionJournal of Alloys and Compounds, 2020
- Carbon monoxide analysis method in human blood by Airtight Gas Syringe – Gas Chromatography – Mass Spectrometry (AGS-GC-MS): Relevance for postmortem poisoning diagnosisJournal of Chromatography B, 2018