SERS-based AI diagnosis of lung and gastric cancer via exhaled breath.

Distinct diagnosis between Lung cancer (LC) and gastric cancer (GC) according to the same biomarkers (e.g. aldehydes) in exhaled breath based on surface-enhanced Raman spectroscopy (SERS) remains a challenge in current studies. Here, an accurate diagnosis of LC and GC is demonstrated, using artificial intelligence technologies (AI) based on SERS spectrum of exhaled breath in plasmonic metal organic frameworks nanoparticle (PMN) film. In the PMN film with optimal structure parameters, 1780 SERS spectra are collected, in which 940 spectra come from healthy people (n = 49), another 440 come from LC patients (n = 22) and the rest 400 come from GC patients (n = 8). The SERS spectra are trained through artificial neural network (ANN) model with the deep learning (DL) algorithm, and the result exhibits a good identification accuracy of LC and GC with an accuracy over 89 %. Furthermore, combined with information of SERS peaks, the data mining in ANN model is successfully employed to explore the subtle compositional difference in exhaled breath from healthy people (H) and L/GC patients. This work achieves excellent noninvasive diagnosis of multiple cancer diseases in breath analysis and provides a new avenue to explore the feature of disease based on SERS spectrum.

Wearable intelligent sweat platform for SERS-AI diagnosis of gout.

For the past few years, sweat analysis for health monitoring has attracted increasing attention benefiting from wearable technology. In related research, the sensitive detection of uric acid (UA) in sweat with complex composition based on surface-enhanced Raman spectroscopy (SERS) for the diagnosis of gout is still a significant challenge. Herein, we report a visualized and intelligent wearable sweat platform for SERS detection of UA in sweat. In this wearable platform, the spiral channel consisted of colorimetric paper with Ag nanowires (AgNWs) that could capture sweat for SERS measurement. With the help of photos from a smartphone, the pH value and volume of sweat could be quantified intelligently based on the image recognition technique. To diagnose gout, SERS spectra of human sweat with UA are collected in this wearable intelligent platform and analyzed by artificial intelligence (AI) algorithms. The results indicate that the artificial neural network (ANN) algorithm exhibits good identification of gout with high accuracy at 97%. Our work demonstrates that SERS-AI in a wearable intelligent sweat platform could be a feasible strategy for diagnosis of gout, which expands research on sweat analysis for comfortable and noninvasive health monitoring.

Early-stage oral cancer diagnosis by artificial intelligence-based SERS using Ag NWs@ZIF core-shell nanochains.

Surface-enhanced Raman spectroscopy (SERS) has great potential in the early diagnosis of diseases by detecting the changes of volatile biomarkers in exhaled breath, because of its high sensitivity, rich chemical molecular fingerprint information, and immunity to humidity. Here, an accurate diagnosis of oral cancer (OC) is demonstrated using artificial intelligence (AI)-based SERS of exhaled breath in plasmonic-metal organic framework (MOF) nanoparticles. These plasmonic-MOF nanoparticles were prepared using a zeolitic imidazolate framework coated on Ag nanowires (Ag NWs@ZIF), which offers Raman enhancement from the plasmonic nanowires and gas enrichment from the ZIF shells. Then, the core-shell nanochains of Ag NWs@ZIF prepared with 0.5 mL Ag NWs were selected to capture gaseous methanethiol, which is a tumor biomarker, from the exhalation of OC patients. The substrate was used to collect a total of 400 SERS spectra of exhaled breath of simulated healthy people and simulated OC patients. The artificial neural network (ANN) model in the AI algorithm was trained with these SERS spectra and could classify them with an accuracy of 99%. Notably, the model predicted OC with an area under the curve (AUC) of 0.996 for the simulated OC breath samples. This work suggests the great potential of the combination of breath analysis and AI as a method for the early-stage diagnosis of oral cancer.

Prediction for odor gas generation from domestic waste based on machine learning.

Domestic waste is prone to produce a variety of volatile organic compounds (VOCs), which often has unpleasant odors. A key process in treating odor gases is predicting the production of odors from domestic waste. In this study, four factors of domestic waste (weight, wet composition, temperature, and fermentation time) were adopted to be the prediction indicators in the prediction for domestic waste odor gases. Machine learning models (Random Forest, XGBoost, LightGBM) were established using the odor intensity values of 512 odor gases from domestic waste. Based on these data, the regression prediction with supervised machine learning was achieved, in which three different algorithmic models were evaluated for prediction performance. A Random Forest model with a R2 value of 0.8958 demonstrated the most accurate prediction of the production of domestic waste odor gas based on our data. Furthermore, the prediction results in the Random Forest model were further discussed based on the microbial fermentation of domestic waste. In addition to enhancing our knowledge of the production of odor from domestic waste, we also explore the application of machine learning to odor pollution in our study.