En Es
Categories

Industry News

Scientists Use Machine Learning and MRI Scans to Predict Learning Difficulties

By Medimaging International staff writers
11 Oct 2018

Image: Researchers used AI and MRI to identify learning difficulties in children (Photo courtesy of iStock).A team of scientists from the Medical Research Council (MRC) Cognition and Brain Sciences Unit at the University of Cambridge (Cambridge, England, UK) used machine learning - a type of artificial intelligence - with data from hundreds of children who struggle at school to identify clusters of learning difficulties, which did not match their previous diagnosis. According to the researchers, this reinforces the need for children to receive detailed assessments of their cognitive skills to identify the best type of support.

For the study, the researchers recruited 550 children who had been referred to a clinic because they were struggling at school. Previous research on learning difficulties has focused on children who had already been diagnosed with a particular difficulty, such as attention deficit hyperactivity disorder (ADHD), an autism spectrum disorder, or dyslexia. The latest study included children with all difficulties, irrespective of their diagnosis, to better capture the range of difficulties within, and overlap between, the diagnostic categories.

The researchers applied machine learning to a broad spectrum of hundreds of struggling learners by supplying the computer algorithm with lots of cognitive testing data from each child, including measures of listening skills, spatial reasoning, problem solving, vocabulary, and memory. Based on these data, the algorithm suggested that the children best fit into four clusters of difficulties. These clusters aligned closely with other data on the children, such as the parents' reports of their communication difficulties, and educational data on reading and math.

However, there was no correspondence with their previous diagnoses. In order to check if these groupings corresponded to biological differences, the groups were checked against MRI brain scans from 184 children. The groupings mirrored patterns in connectivity within parts of the children's brains, suggesting that that the machine learning was identifying differences that partly reflect underlying biology. Two of the four groupings identified were: difficulties with working memory skills, and difficulties with processing sounds in words. The other two clusters identified were: children with broad cognitive difficulties in many areas, and children with typical cognitive test results for their age. The researchers noted that the children in the grouping that had cognitive test results that were typical for their age might still have had other difficulties that were affecting their schooling, such as behavioral difficulties, which had not been included in the machine learning.

"Our study is the first of its kind to apply machine learning to a broad spectrum of hundreds of struggling learners," said Dr Duncan Astle from the MRC Cognition and Brain Sciences Unit at the University of Cambridge, who led the study.

"These are interesting, early-stage findings which begin to investigate how we can apply new technologies, such as machine learning, to better understand brain function," said Dr Joanna Latimer, Head of Neurosciences and Mental Health at the MRC.

Related Links:
University of Cambridge



E-mail Print
FaceBook Twitter Google+ Linked in

Additional news

23 Nov 2018
AI Predicts Alzheimer’s Disease Years before Diagnosis
A new study on the application of deep learning (DL) to detect changes in brain metabolism predictive of Alzheimer’s disease (AD) has found that artificial intelligence (AI) improves the ability of brain imaging to predict AD.
Read More
23 Nov 2018
UK to Set Up New GBP 10 Million Centre for Medical Imaging and AI
The UK’s London Medical Imaging & Artificial Intelligence Centre for Value-Based Healthcare will train sophisticated artificial intelligence (AI) algorithms from NHS medical images and patient data, to create tools that will help clinicians speed up and improve diagnosis and care across a number of patient pathways, including dementia, heart failure and cancer.
Read More
23 Nov 2018
New AI Algorithm Enhances Polyp Detection in Colonoscopy Procedures
Researchers at Shanghai Wision AI Co., Ltd., a developer of computer-aided diagnostic algorithms and systems to improve the accuracy and effectiveness of diagnostic imaging, have announced results of a study validating a novel machine-learning algorithm that improves detection of adenomatous polyps during colonoscopy. The AI algorithm is built on the same network architecture that is used to develop self-driving cars and is designed to enable “self-driving” in colonoscopy procedures.
Read More
20 Nov 2018
Study Finds AI Falls Short When Analyzing Medical Data
A study conducted at the Icahn School of Medicine at Mount Sinai has found that artificial intelligence (AI) tools trained to detect pneumonia on chest X-rays suffered significant decreases in performance when tested on data from outside health systems. These findings suggest that unless AI in the medical space is carefully tested for performance across a wide range of populations, the deep learning models may not perform as accurately as expected.
Read More
20 Nov 2018
New AI Software for Brain Bleed Diagnosis Receives FDA Clearance
The US Food and Drug Administration (FDA) has given 510(k) clearance to the Accipio Ix intracranial hemorrhage (ICH) detection software developed by MaxQ AI, a clinical diagnostics intelligence platform company.
Read More
20 Nov 2018
Global Refurbished Medical Devices Market to Increase by 10% by 2023
The global refurbished medical devices market is expected to grow at a CAGR of over 10% during the forecast period 2019-2023, driven by the organized healthcare ecosystem in the developed economies. Moreover, privatization in the healthcare sector is increasing rapidly due to the inability of governments to invest efficiently in the sector, coupled with high demand for innovation and technology for superior healthcare services.
Read More
12 Nov 2018
ACR Data Science Institute Releases AI Use Cases to Accelerate AI Adoption
The American College of Radiology Data Science Institute has released a first-of-its-kind series of standardized artificial intelligence (AI) use cases that will accelerate medical imaging AI adoption. This continually updated, freely available use case series is the product of a previously missing and collaborative framework that enables efficient creation, implementation and ongoing improvement of radiological AI tools.
Read More
12 Nov 2018
Siemens Healthineers and Primary Health Care Enter Contract for In Vitro Diagnostics
Siemens Healthineers has entered into a strategic partnership with Australian integrated healthcare provider Primary Health Care to deploy more than 70 Atellica Solution immunoassay and clinical chemistry analyzers, marking the largest contract ever for in vitro diagnostics testing in the country.
Read More
12 Nov 2018
OpenSight Augmented Reality System for Microsoft HoloLens Cleared by FDA
The FDA has granted 510(k) clearance to the OpenSight Augmented Reality System, making it the first AR medical solution for Microsoft HoloLens to be cleared for use in pre-operative surgical planning. Developed by Novarad, a provider of specialized enterprise imaging and workflow solutions, OpenSight renders 2D, 3D and 4D images of patients interactively, while accurately overlaying them directly onto the patient’s body.
Read More
Copyright © 2000-2018 TradeMed.com. All rights reserved. | Terms And Conditions