Speaker
Description
Nanomedicine is currently a rapidly growing interdisciplinary field that integrates nanotechnology with medical science, including drug delivery systems, diagnostics, and nanoparticle-based therapies. In addition, research trends in the field of nanomedicine are increasingly difficult and time-consuming if done manually. This study proposes a machine learning approach to classify nanomedicine research trends automatically. In the process, the research was conducted using a dataset of article abstracts collected from the PubMed database through the NCBI E-utilities API, with search keywords that include nanomedicine, drug delivery nanoparticle, and related terms. The collected abstract data were processed through standard natural language processing stages, including text cleaning, tokenization, stopword removal, and vectorization. Then, classification was carried out using machine learning including Support Vector Machine, Radom Forest, and Logistic Regression, trained to group abstracts into nanomedicine subcategories (e.g., cancer drug delivery, nanotoxicology, nanodiagnostics, and regenerative nanotherapy). Model performance was evaluated using metrics of accuracy, precision, recall, and F1-score, with comparisons between algorithms to determine the best classification model. The results of this study are expected to provide a scalable and efficient framework for automatically mapping nanomedicine literature, thereby assisting researchers, healthcare practitioners, and policymakers in identifying research development directions and innovation opportunities in the field of nanomedicine. This research is expected to contribute to the multidisciplinary field of Natural Language Processing (NLP) and biomedicine.
