summary: Researchers have developed a breakthrough model called the Brain Language Model (BrainLM) that uses generative artificial intelligence to map brain activity and its impact on behavior and disease. BrainLM leverages her 80,000 scans from 40,000 subjects to create a foundational model that captures the dynamics of brain activity without the need for specific disease-related data.
This model significantly reduces the cost and scale of data required for traditional brain research and provides a robust framework that can predict conditions such as depression, anxiety, and PTSD more effectively than other tools. . BrainLM has demonstrated strong application in clinical trials and has the potential to halve costs by identifying patients most likely to benefit from new treatments.
Important facts:
- Generative AI model: BrainLM uses generative AI to analyze brain activity patterns from extensive datasets and learn the underlying dynamics without specific patient details.
- Research costs and efficiency: This model has the potential to significantly reduce costs by reducing the need for large-scale patient enrollment in clinical trials and using its predictive capabilities to select suitable candidates for research.
- Wide applicability: BrainLM has been tested in a variety of scanners and demographics and has shown excellent performance in predicting a variety of mental health issues, and is expected to aid future research and treatment strategies.
sauce: Baylor College of Medicine
A research team from Baylor College of Medicine and Yale University incorporated generative artificial intelligence (AI) to create a basic model of brain activity. The Brain Language Model (BrainLM) was developed to model the brain in computers and determine how brain activity is related to human behavior and brain diseases.
This research was presented as a conference paper at ICLR 2024.
“We've known for a long time that brain activity is related to human behavior and many diseases, such as seizures and Parkinson's disease,” said Chady, associate professor in the Menninger School of Psychiatry and Behavioral Sciences at Baylor University. Dr. Abdallah says. Co-corresponding author of the paper.
“While functional brain imaging and functional MRI allow us to observe brain activity throughout the brain, traditional data analysis tools cannot fully capture the dynamics of these activities in time and space. was.
“More recently, people have begun to use machine learning to understand the complexity of the brain and how it relates to specific diseases, which can be done by looking at thousands of people with specific behaviors or diseases. It turned out to be a very expensive process, requiring patients to be enrolled and fully tested.”
The power of new generative AI tools is that they can be used to create fundamental models that are independent of specific tasks or specific patient populations. Generative AI acts as a detective, uncovering hidden patterns within datasets.
By analyzing data points and the relationships between them, these models can learn about the underlying dynamics: how and why things change or evolve.
These basic models are fine-tuned to understand a variety of topics. Researchers used generative AI to capture how brain activity functions regardless of a specific disorder or disease.
It can be applied to any population without requiring knowledge of the subject's behavior, illness, medical history, or age. Brain activity is all that is needed to teach computers and AI models how brain activity evolves over space and time.
The team acquired 80,000 scans from 40,000 subjects and trained a model to understand how these brain activities are interconnected over time, creating the BrainLM Foundational Model of Brain Activity. has been established. Researchers can now use her BrainLM to fine-tune specific tasks or ask other research questions.
“For example, if you want to conduct a clinical trial to develop a drug to treat depression, it can cost hundreds of millions of dollars because you need to enroll large numbers of patients and treat them over long periods of time.
“By leveraging BrainLM's capabilities, we could potentially cut this cost in half by enrolling only half of the subjects using BrainLM's capabilities to select individuals who would most benefit from treatment. . BrainLM can therefore apply the knowledge gained from 80,000 scans to specific research subjects,” Abdallah said.
The first step, preprocessing, summarizes the signal and removes noise unrelated to brain activity. The researchers fed the summaries into a machine learning model and masked part of each person's data. Once the model learned the dynamics, it was tested on an excluded test group.
They also tested this on different samples to understand how well the model generalizes to data acquired with different scanners and different populations, such as older and younger people.
They found that BrainLM performed well on a variety of samples. We also found that BrainLM can more accurately predict the severity of depression, anxiety, and PTSD than other machine learning tools that don't use generative AI.
“We found that BrainLM performed very well. Not only was it able to predict brain activity on new samples that were occluded during training, but it also predicted well on data from new scanners and new populations.” Abdallah said.
“These impressive results were achieved with scans from 40,000 subjects. We are currently working on significantly increasing our training dataset.
“The more powerful the models we can build, the more we can do to support patient care, whether it’s developing new treatments for mental illness or guiding neurosurgery for seizures and DBS.”
The researchers plan to apply the model to studies that predict future brain-related diseases.
About this AI and neuroscience research news
author: Homa Warren
sauce: Baylor College of Medicine
contact: Homa Warren – Baylor College of Medicine
image: Image credited to Neuroscience News
Original research: The results of this study will be presented at ICLR 2024
