Skip to Main Content
An official website of the United States government
Login Change: CDAS is now using the NIH Researcher Auth Service (RAS) to manage our existing login options. When logging into CDAS, you will be taken to RAS, where you can select your preferred login provider to access CDAS.

Retraining Large Language Models for Cancer Diagnosis and Treatment

Principal Investigator

Name
Alejandro Alvarez

Degrees
M.C

Institution
Tecnológico Nacional de Mexico campus CENIDET

Position Title
maestria en ciencias

Email
alejandro.juarezc137@gmail.com

About this CDAS Project

Study
PLCO (Learn more about this study)

Project ID
PLCO-1795

Initial CDAS Request Approval
Jan 27, 2025

Title
Retraining Large Language Models for Cancer Diagnosis and Treatment

Summary
Cancer, responsible for 10.6% of deaths in Mexico according to INEGI data in 2022, is a growing challenge. Thyroid cancer is notable for being one of the most common in the country. This work seeks to develop a specialized language model in Spanish, retrained with medical data, to improve diagnoses and treatments in the Mexican context.

Aims

Identify characteristics of different cancer diagnoses and treatments by retraining LLM models, from databases and medical information, to generate information on cancer diagnoses and treatments, completing the retraining and validation of the model will comprise a period equal to the duration of the master's degree.

Collaborators

Ph.D. Máximo López Sánchez
Ph.D. Nimrod González Franco