My current research explores machine learning for process manufacturing optimization. During my Ph.D., I concentrated on developing a variety of sensors, including electrochemical, fluorescent, and resistive types. Additionally, I investigated the use of nuclear magnetic resonance spectroscopy (NMR), combined with machine learning, as an innovative approach to prostate cancer diagnosis, offering an alternative to traditional methods like digital rectal examination and prostate-specific antigen tests. This work involved creating a Python package for NMR data preprocessing. My research was enriched by visits to the International School of Chemometrics at the University of Copenhagen and studies on thiophene-based monomers and their metal complexes at the Autonomous University of Barcelona for applications in electronic tongues.