Hydrogel based flexible wearable sweat sensor for SERS-AI monitoring treatment effect of lung cancer

Abstract

Comfortable treatment of malignant tumors is the clinical orientation of cancer therapy at present, which puts forward a high demand for non-invasive, portable and high-frequency monitoring status of tumor in the treatment. Unlike traditional blood and X-ray technique, here we have developed hydrogel-based wearable sweat sensors, equipped with multiple molecular receptors for surface enhanced Raman spectroscopy (SERS) monitoring treatment effects of lung cancer. The SERS technique was utilized in combination with multiple artificial intelligence (AI) algorithms (LGB GNB, LDA, RF, and SVM) to develop a novel and precise diagnostic model for monitoring the treatment effect. Based on 12617 SERS spectras from clinical patients, the results successfully diagnosed three treatment effects (progressive disease, partial response, and no change) with an accuracy of 89.7 %. Benefiting from data mining in AI algorithms, key Raman spectra features in clinical spectra are identified to explore characteristic biomarkers of lung cancer associated with various comorbidities. The clinical data suggest that carbonyl biomarkers in sweat might be crucial for understanding complications such as diabetes and hypertension. Our results not only offer a novel and comfortable monitoring technique but also enable personalized treatment of lung cancer with complications, presenting significant potential for clinical application.