Determining selection for indexing MEDLINE articles using Neural Network Architecture with a Convolutional Neural Network (CNN)

Using the article title, abstract, journal, publication year, and indexing year of indexed and non-indexed articles that were submitted to MEDLINE in 2018, methods to automate the selection of indexed articles was researched. A classifier was developed that combines the predictions of many traditional machine learning algorithms and a Convolutional Neural Network (CNN). The final classification layer uses a sigmoid activation function to generate a single output value between zero and one, which can be interpreted as the probability of an article being in-scope for MEDLINE.