The future of cortisol detection: Molecularly imprinted polymers enhanced by artificial intelligence

Cortisol, a key biomarker of physiological stress, plays a central role in metabolic regulation, immune function, and circadian rhythm regulation. Accurate, real-time detection of cortisol is therefore critical for monitoring stress-related disorders and endocrine diseases. However, traditional methods such as immunoassays remain limited by cost, complexity, scalability, and long turnaround times. Recent advances in molecu larly imprinted polymers (MIPs) offer promising synthetic alternatives to conventional methods with similar selectivity, higher stability, and an increased compatibility with wearable technologies. This review surveys current progress in MIP-based cortisol sensing—with a particular emphasis on electropolymerization strategies—and contrasts them with conventional techniques such as ELISA (enzyme-linked immunosorbent assay). In addition, it explores the integration of artificial intelligence through machine learning algorithms, and digital twins to enhance sensor design, optimize experimental conditions, and enable advanced data interpretation. Together, these developments point toward a new generation of biosensing platforms that combine material innovation with computational intelligence, paving the way for reliable, personalized health monitoring and precision stress management.