Вештачка интелигенција

The Impact of Machine Learning on Brain Research and Clinical Applications

Summary

Machine learning, a branch of Artificial Intelligence (AI), has revolutionized data analysis by enabling computers to analyze complex datasets. Researchers are now applying machine learning algorithms to study the human brain and make predictions based on neurological information. Recent studies […]

The Impact of Machine Learning on Brain Research and Clinical Applications

Machine learning, a branch of Artificial Intelligence (AI), has revolutionized data analysis by enabling computers to analyze complex datasets. Researchers are now applying machine learning algorithms to study the human brain and make predictions based on neurological information.

Recent studies have shown that:

– Researchers have successfully identified the activity between the thalamus and brain regions associated with motor functions as being linked to symptoms of depression, using neuroimaging techniques to detect abnormal brain regions in psychiatric disorders. (Source: Advanced Telecommunications Research Institute International)
– Machine learning models that utilize patient data can predict the progression from mild cognitive impairment (MCI) to Alzheimer’s disease (AD); their study focuses on the use of kPCA (kernel Principal Components Analysis). (Source: University of Southern California)
– Novel applications of artificial neural networks can uncover how cells in the visual cortex interpret light signals from the retina and translate that data into vision. (Source: University of Maryland)
– Researchers have applied machine learning models to deep brain recordings and combined them with traditional control theory methods to create a tool for predicting targets for deep brain stimulation (DBS), aiding in the treatment of dystonia in children. (Source: University of California, Irvine)

“The advancements in artificial intelligence and machine learning are transforming brain research and clinical treatments,” said Terry Sejnovski, Professor Francis Crick at the Salk Institute for Biological Studies and distinguished professor at the University of California, San Diego, who will moderate the press conference. “Brain imaging produces massive datasets that can be analyzed using machine learning. Predictive modeling, brain-machine interfaces, and neuroimaging/neuromodulation are areas with special potential for developing new therapeutic methods and treatment plans for patients.”

This research is supported by national funding institutions, including the National Institutes of Health, as well as private funding organizations. Learn more about artificial intelligence and brain research at BrainFacts.org.

Monday, November 13, 2023.

14:00-15:00 EST

Walter E. Washington Convention Center, Room 202B

Press Conference Summary

These presentations explore the wealth of data that can be extracted and analyzed using machine learning. These topics range from predictive modeling that identifies brain activity in disorders such as Alzheimer’s disease and depression (first two studies) to the analysis of the complex visual system of the brain and the application of deep brain network models for therapy enhancement (third and fourth studies, respectively).

Feature selection based on semi-supervised learning reliably extracts resting-state functional connectivity associated with major depressive disorder

Researchers used neuroimaging techniques in conjunction with machine learning to identify brain biomarkers. To determine how accurately and reliably these techniques detect damaged brain regions in psychiatric disorders, researchers employed three types of feature selection methods related to major depressive disorder. Among these three methods, they found that the feature selection method based on semi-supervised learning reliably extracted functional connections with larger effects in test data. Using MRI data from 1,162 patients, including 334 with depression, the researchers extracted coordinated activity between brain regions (particularly the thalamus and regions associated with motor functions) that were linked to depression symptoms.

Predicting future conversion from mild cognitive impairment (MCI) to Alzheimer’s disease using machine learning and 3D brain MRI

Predictive models utilize machine learning to attempt to determine who will develop brain diseases such as Alzheimer’s disease. Researchers used various models to see which model could predict mild cognitive impairment (MCI) that would progress to Alzheimer’s disease. They used MRI scans along with demographic and genetic data from over 2,448 individuals. The most accurate model they developed employed kPCA (kernel Principal Components Analysis) to generate new features by combining scanning data with genetic risk data for Alzheimer’s disease, as well as patient demographic data.

Biophysically constrained deep neural networks for analysis of visual computations in the primary visual cortex

Researchers employed a new application of artificial neural networks called convolutional deep neural networks (CNNs) to understand how cells in the visual cortex of the brain interpret light signals captured by the retina. By utilizing machine learning, researchers are beginning to unravel how visual information travels through cells in the visual cortex.

FAQ:

Q: What is machine learning?
A: Machine learning is a branch of artificial intelligence that focuses on computers’ ability to analyze data in increasingly complex ways.

Q: How is machine learning applied in brain research?
A: Machine learning algorithms are used to analyze large datasets containing information about the human brain, allowing researchers to make predictions based on that data.

Q: What are some examples of machine learning in brain research?
A: Machine learning has been used to identify brain activity related to psychiatric disorders, predict the progression of cognitive impairment to Alzheimer’s disease, understand visual computations in the brain, and enhance deep brain stimulation therapy for dystonia.

Q: How is machine learning advancing clinical treatments?
A: Machine learning has the potential to develop new therapeutic methods and treatment plans for patients by analyzing brain imaging data and creating predictive models, brain-machine interfaces, and neuroimaging/neuromodulation techniques.

Q: What organizations support this research?
A: This research is supported by national funding institutions, such as the National Institutes of Health, as well as private funding organizations.