DFT and machine learning investigation of Au/Pt-decorated SnS2 monolayers for asthma and COPD diagnosis
Clinical Snapshot
PICO Framework
| P — Population | Computational/materials science study — no human participants enrolled; clinical relevance framed around patients with asthma and COPD who exhale elevated NO2 concentrations |
| I — Intervention | Au/Pt-decorated tin disulfide (SnS2) monolayer heterostructures evaluated as gas-sensing platforms for exhaled NO2 detection, characterised via density functional theory (DFT) simulations and five machine learning (ML) models |
| C — Comparator | Pristine (undecorated) SnS2 monolayer as the baseline sensing material; comparative performance across Au-SnS2 and Pt-SnS2 configurations |
| O — Outcomes | Primary: adsorption energy, charge transfer, and electronic band-structure changes upon NO2 binding (DFT); ML model predictive accuracy (R²) for gas-sensing behaviour. Secondary: discrimination of NO2 from other analyte gases; ppb-level detection feasibility |
Bottom Line
This computational study proposes Au/Pt-decorated tin disulfide (SnS2) monolayers as candidate materials for ppb-level exhaled NO2 sensing, with potential relevance to asthma and COPD diagnosis. Using density functional theory and machine learning (XGBoost R²=0.9961), the authors identify Pt-SnS2 as the optimal configuration. The science is methodologically interesting as a materials discovery exercise, but the clinical claims are substantially overstated. There are no experimental prototypes, no exhaled breath matrix validation, no selectivity data against humidity or physiological interferents, and no patient data of any kind. The ML model's near-perfect R² on an undisclosed training set raises legitimate overfitting concerns. Clinicians should note that exhaled NO2 sensing in real-world conditions — 100% relative humidity, complex gas matrices, variable tidal volumes — presents challenges entirely unaddressed here. This work sits at the earliest stage of the translational pipeline and should not influence clinical practice, procurement decisions, or diagnostic guideline development. It may, however, inform future experimental sensor design programs. Independent laboratory validation of the proposed Pt-SnS2 sensor is the essential next step before any clinical relevance can be claimed.
Key Findings
P Value: Not applicable to DFT results; not reported for ML model performance metrics
Effect Size: Not quantified in clinical terms; DFT adsorption energies and charge transfer magnitudes reported but specific numerical values not provided in abstract
Primary Outcome: Pt-SnS2 monolayer demonstrated optimal adsorption energy and charge transfer characteristics for NO2 detection among pristine, Au-decorated, and Pt-decorated SnS2 configurations by DFT analysis
Nnt Or Sensitivity: Not applicable — no clinical sensitivity, specificity, AUC, or NNT calculable from computational data; ML model R²=0.9961 (XGBoost) is the primary performance metric reported
Confidence Interval: Not reported for any outcome
Clinical Application
Technology Readiness Level 1–2 (basic principles observed, concept formulated). Substantial development milestones remain: physical prototype fabrication, bench-top gas-sensing validation, humidity and interferent testing, exhaled breath matrix studies, animal safety studies, and multi-phase clinical trials. Commercial feasibility is speculative. Noble-metal (Au/Pt) decoration introduces significant material cost barriers. Asthma affects approximately 2.8 million Australians and COPD approximately 600,000, representing a substantial disease burden (AIHW). Current standard for exhaled inflammatory biomarker testing in Australia is FeNO measurement (e.g., NIOX VERO), which is not PBS-subsidised for routine use. A validated, low-cost exhaled NO2 sensor could theoretically complement spirometry and FeNO in primary care respiratory assessment aligned with RACGP asthma guidelines. However, this study provides no evidence to support TGA submission, PBS listing consideration, or integration into RACGP or Lung Foundation Australia clinical pathways. Australian clinicians should regard this as early-stage materials science research only. Not currently applicable to any clinical population. The theoretical target population would be adults with suspected or confirmed asthma or COPD requiring non-invasive exhaled biomarker monitoring. Exhaled NO2 (as a proxy for airway inflammation) is already measured clinically via fractional exhaled nitric oxide (FeNO) — the relationship between FeNO and exhaled NO2 in this sensor context is not clarified.
Abstract
Asthma and chronic obstructive pulmonary disease (COPD) are among the most prevalent chronic respiratory diseases worldwide, affecting hundreds of millions of people and contributing significantly to global morbidity and mortality. This work introduces a novel Au/Pt-decorated SnS2heterostructure for exhaled NO2detection, representing the new study to explore its role in lung disease diagnostics. It demonstrates ppb level NO2detection, a key biomarker for asthma and COPD, enabling early and differentiation of lung conditions by providing quantitative analysis of trace-level gases, which are often elevated in inflamed airways. While two-dimensional (2D) SnS2offers strong potential as a sensing platform, prior studies relied mainly on density functional theory (DFT) based gas sensing. Here, we present unprecedented integration of DFT and machine learning (ML) to investigate the gas sensing performance of pristine and Au/Pt-decorated SnS2monolayers. DFT analysis revealed enhanced adsorption and charge transfer upon noble-metal decoration, with Pt-SnS2showing optimal characteristics for asthma and COPD detection. Five ML models were trained on DFT and experimental-derived descriptors to rapidly predict the sensing behaviour of multiple gases, including NO2, among which XGBoost achievingR2= 0.9961. Both ML and DFT methods consistently identified NO2as the most sensitive analyte. This novel DFT-ML synergy not only validates fundamental adsorption mechanisms but also provides a scalable pathway for accelerated screening and design of high-performance gas sensors. Our findings establish a new prototype for integrating ML with first-principles simulations in the design of next-generation 2D material-based sensing devices.
References
- 1.Kulshreshtha, K., Bansal, D., Raj, M., & Goel, N. (2026). DFT and machine learning investigation of Au/Pt-decorated SnS2 monolayers for asthma and COPD diagnosis. Nanotechnology. https://doi.org/10.1088/1361-6528/ae8672
Related Research
Sleep medicine
Concordance of wearable device sleep metrics with patient-reported sleep quality: A systematic review
3 Aug 2026
Bioelectrochemistry (Amsterdam, Netherlands)
From data to diagnosis: A comprehensive review of machine learning-driven wearable sensors in healthcare.
2 Aug 2026
JMIR mHealth and uHealth
Wearable Devices for Monitoring and Management of Comorbid Obstructive Sleep Apnea and Hypertension: Scoping Review
1 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service