Integration of dual-emission fluorescent nanosensor and machine learning for simultaneous detection of dopamine and homovanillic acid

Dopamine (DA) is a crucial neurotransmitter involved in various brain functions, including the regulation of mood, management of reward pathways, and control of movement. Homovanillic acid (HVA), which is a major metabolite of dopamine serves as an indicator of dopamine metabolism in the body. Simultaneous detection of DA and HVA together can help researchers gain insights into DA dynamics and their impact on neuropsychological disorders such as schizophrenia and Parkinson's disease. In this study, we designed a ratiometric fluorescent probe based on the quenching of red quantum dots for the quantification and discrimination of DA and HVA in urine samples. The ratiometric technique employs blue carbon dots as a reference, and machine learning techniques, pattern recognition, and regression were used to statistically assess the collected data. Principal component analysis and linear discriminant analysis were utilized to classify the dataset into several groups. Partial least-squares regression was employed to assess the analytes quantitatively. The results demonstrated a linear relationship between the gathered responses and concentrations throughout broad ranges of 2.76–20 μg mL -1 for DA and 3.09–20 μg mL -1 for HVA, with detection limits of 0.92 and 1.03 μg mL -1 for DA and HVA, respectively. Through successful validation in intricate urine matrices, the practical application of this ratiometric fluorescent probe was confirmed. Our ratiometric fluorescent probe enables accurate quantification and effective visual detection, assisting in the early diagnosis of neurological diseases. Several neurological and mental problems may be identified simultaneously by combining machine learning techniques with the proposed fluorometric sensor.