AI for early detection of pancreatic cancer.
Posted by giorgiobertin on January 19, 2024
Scientists at the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) have developed two machine learning models for the early detection of pancreatic ductal adenocarcinoma (PDAC), the most common form of cancer. To access a large and diverse database, the team synchronized with a federated network company, using electronic health record data from various institutions across the United States.
The two models, the neural network “PRISM” and the model of logistic regression (a statistical technique for probability), have outperformed current methods.
Using AI to detect cancer risk is not a new phenomenon: Algorithms analyze mammograms, CT scans for lung cancer, and aid in the analysis of Pap smears and HPV testing, to name a few applications. “PRISM models are notable for their development and validation on a large database of more than 5 million patients, exceeding the scope of most previous research in the field”, afferma Kai Jia.
Despite the promise of PRISM models, like all research, some parts are still a work in progress. Only US data represents the current basis of the models, which require testing and adaptation for global use. The path forward, the team notes, involves expanding the model’s applicability to international datasets and integrating additional biomarkers for more refined risk assessment.
Read the full text of the article:
A pancreatic cancer risk prediction model (Prism) developed and validated on large-scale US clinical data
Kai Jia,… et al.
eBiomedicine Volume 98, December 2023, 104888
Fonte: MIT Computer Science and Artificial Intelligence Laboratory
This entry was posted on gennaio 19, 2024 a 6:43 am and is filed under Intelligenza Artificiale, News-ricerca.
Contrassegnato da tag: diagnostica, gastroenterologia, Intelligenza Artificiale, oncologia, statistica. You can follow any responses to this entry through the RSS 2.0 feed.
You can leave a response, oppure trackback from your own site.