Optoelectronic and spectral analysis of urine can be performed on site by low-cost portable technology, interfaced to signal processing and machine learning algorithm. These algorithms, trained on a set of previously known diagnostic outputs, can correlate the urine optoelectronic measured parameters with the person's health status. The proposed solution is the development of an optoelectronic setup, suitable to be embedded in a portable configuration, capable of performing on site and in a short amount of time a urine screening based on a set of techniques of increasing three levels of complexity. The proposed parameters to be measured are dominant color and turbidity (1st level), UV induced fluorescence (2nd level), Raman Spectroscopy (3rd level). The system can be used to perform a set of measurements on a set of urine samples of already known health condition to carry out the training of a machine learning algorithm for assessing the risk of developing Acute Kidney Injury. All the technical information is public open access, available at https://github.com/ISEL-DEETC/PhotoAKI/tree/main/LUMINA.