Synthesis and characterization of lignin-copper nanohybrids for colorimetric acetaminophen detection: a combined physical chemistry and machine learning study.

Acetaminophen ranks among the most widely used pharmaceutical and personal care products today. Following consumption, the drug and its metabolites are excreted into sewage systems, wastewater treatment plants, and various aquatic environments, leading to significant ecological and health impacts. In this context, the study introduced novel and easily synthesized hybrid structures through the self-polymerization and coordination of lignin with copper (Cu@lignin·HSs) for the specific and sensitive detection of acetaminophen. The sensor exhibited high sensitivity with a detection limit (LOD) of 0.5 mM and good precision, with a relative standard deviation (RSD) of 1.1%. The recovery of acetaminophen ranged from 97.0% to 98.8%, and the method showed excellent linearity with an value of 0.996, indicating high accuracy and reproducibility. The proposed portable colorimetric sensor exhibited excellent selectivity, stability, and reproducibility, with its performance in analyzing actual samples showing no significant difference compared to high-performance liquid chromatography (HPLC) ( > 0.05). In the machine learning analysis, ensemble models (random forest, gradient boosting, and XGBoost) effectively predicted acetaminophen detection efficiency using the prepared sensor in real wastewater. XGBoost demonstrated superior performance, achieving excellent predictive correlation and minimal error, thereby highlighting the robustness of ensemble learning for this application. In the future, the synthesized HSs could serve as a promising sensing technique for quality control in pharmaceutical wastewater.