Using a Machine Learning Logistic Regression Algorithm to Classify Nanomedicine Clinical Trials in a Known Repository

Today, the nanotechnology is the most critical technology that helps in many scientific advances, because this science allows us to work with molecular structures and their atoms, obtaining material that acts chemical and biologically different to those manifesting in bigger longitudes. Many sciences join nanotechnology to improve their researches, and one of them is medicine. In nanomedicine, many researchers are looking for a way to obtain information about these nanometric materials to enhance their studies that lead in many occasions to prove these methods or to create a new compound that helps modern medicine against dominant diseases. Years after years the world increase trials with these nanomaterials and in this work the authors are going to demonstrate this issue, using the clinical trials repository in one of the most famous trials web pages. Many scientists that work with these trials, wish to obtain only the ones those that need, but in these repositories, they have to search and read each one to make sure that the trial is about what they are researching. The authors implement an application for build a train model that involved a new method of pre-processing text to classify through logistic regression in these trials. For this classification, the authors downloaded an entire database (www.clinicaltrials.gov ) and used nanoinformatic with an artificial intelligence machine learning supervised algorithm to classify them. The authors classified trials that are about nanomedicine and trials that not. And finally present the results of the number of clinical trials that are about nanomedicine.