Discovering latent knowledge in medical papers on acute myeloid Leukemia

• Grant number: 21/13054-8
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: January 01, 2022
• End date: April 10, 2023
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Tiago Agostinho de Almeida
• Grantee: Matheus Vargas Volpon Berto
• Host Institution: Centro de Ciências em Gestão e Tecnologia (CCGT). Universidade Federal de São Carlos (UFSCAR). Campus de Sorocaba. Sorocaba , SP, Brazil
• Associated scholarship(s): 22/07236-9 - Deep bidirectional transformers for discovering latent knowledge in medical papers on Acute Myeloid Leukemia, BE.EP.IC

Abstract

The volume of information produced and accessed through the Internet is large and growing. The amount of information available in scientific papers follows the same trend, making manual analysis of all existing content unfeasible. Thus, several strategies and architectures for artificial neural networks have emerged to represent texts using dense vectors, called word vectors. These techniques are continually evolving and are capable of processing increasingly more significant sets of texts with less computational resources. With this, text representation models started to be created for specific knowledge areas, as is the case of PubMedBERT. Using a corpus of a single domain, the model could better capture the relationships between words. Recently, when creating representation models from prefaces of scientific papers in the field of materials science, Tshitoyan et al. (2019) observed that the knowledge of certain relationships between elements was latent. Furthermore, they demonstrated that the relationships existed in the texts years before they were discovered. In this context, this research project proposes to train word vectors from scientific papers in a specific medical field, to capture and analyze whether it is possible to obtain latent knowledge that can accelerate the discovery of new diagnoses, prognoses, and treatments. (AU)