AI Breakthrough: Researchers Develop Tool for Near Real-Time Cancer Surveillance

Word count: 871 Estimated reading time: 4 minutes

Attention, medical professionals and tech enthusiasts! In a groundbreaking collaboration, researchers from Oak Ridge National Laboratory (ORNL), Louisiana State University, and the National Cancer Institute (NCI) have developed an AI-driven tool that could revolutionize cancer surveillance and reporting.

Key Points:

1. The AI transformer model, called Path-BigBird, can process millions of pathology reports to provide more accurate information on cancer reporting.

2. The model has the potential to streamline the speed and accuracy of pathology information extraction, outperforming traditional deep learning approaches.

3. By effectively processing information from pathology reports, Path-BigBird could help identify cancer sites, histology, and improve the precision of cancer incidence reporting at a population level.

4. The turning point in the research came when the team incorporated a broader scope of clinical language along with pathology reports, leading to dramatic improvements in accuracy and performance.

A Game-Changer for Cancer Surveillance

Currently, cancer registries are updated by hand, resulting in a two-year gap between cancer incidence and reporting. This means that if there is an increase in cancer rates nationally, researchers have to wait two years before recognizing this area of concern.

Path-BigBird aims to change that. By processing 2.7 million cancer pathology reports from six Surveillance, Epidemiology and End Results (SEER) cancer registries, the AI model can provide near real-time cancer surveillance. This could help researchers identify trends and potential public health interventions much more quickly.

Interdisciplinary Collaboration

The success of Path-BigBird is a testament to the power of interdisciplinary collaboration. The team behind the project included experts from natural language processing, high-performance computing, and epidemiology, who worked together for two years to develop the AI model.

Mayanka Chandra Shekar, a research scientist at ORNL, emphasized the importance of this collaboration, saying, "Our team included people from natural language processing experts, high-performance computing scientists and epidemiologists, so we were a group of completely interdisciplinary parts where we had to understand, 'What is being asked and can we run it securely at scale?'"

The Potential for Broader Applications

The Path-BigBird model has already shown impressive results, autocoding around 23% of reports processed by cancer registries and saving researchers valuable time. But the potential applications go far beyond just identifying cancer sites and histology.

Researchers believe that the model could be extended to extract biomarkers and other recurrent cancer issues, opening up a whole new world of possibilities for cancer research and treatment. As Chandrashekar noted, "Usage of this model opens up a whole new world. We can extend to extract biomarkers and other recurrent cancer issues using the same model because now it's able to understand pathology specific language. We can expand it beyond the focus of what we started."

The Future of AI in Cancer Research

The development of Path-BigBird is a significant milestone in the fight against cancer. By harnessing the power of AI and machine learning, researchers can process vast amounts of data more quickly and accurately than ever before, leading to faster identification of trends and potential interventions.

As the team behind Path-BigBird continues to refine and expand the model's capabilities, we can expect to see even more exciting developments in the field of cancer research. From identifying biomarkers to predicting recurrence rates, the possibilities are truly endless.

What do you think about the potential of AI in cancer research? Share your thoughts and opinions in the comments below!

And if you want to stay up-to-date on the latest developments in AI and healthcare, be sure to check out our other articles:

• AI in Medical Imaging: Enhancing Diagnosis and Treatment

• The Future of Personalized Medicine: How AI is Transforming Healthcare

• Ethical Considerations in AI-Driven Healthcare: Balancing Innovation and Responsibility

Source: https://medicalxpress.com/news/2024-03-ai-driven-tool-real-cancer.html

AI Insight | AI Quick Takes | RoboReports | TutorialBots | RoboRoundup | GadgetGear

This site might contain product affiliate links. We may receive a commission if you make a purchase after clicking on one of these links.