Why early diagnosis of autism should lead to early intervention

Research suggests children can be reliably diagnosed with autism before the age of two. It also shows that many of the behavioural symptoms of autism are present before the age of one.

These behaviours include decreased interest in social interaction, delayed development of speech and intentional communication, a lack of age-appropriate sound development, and unusual visual fixations.

Preliminary results of a study in the Wellington region indicate most children are diagnosed when they are around three years old. However, there is arguably little point of providing early diagnosis if it does not lead to evidence-based early intervention.

Early start

The Early Start Denver Model (ESDM) is a promising therapy for very young children (between one and five years) with, or at risk for, autism. ESDM uses play and games to build positive relationships in which the children are encouraged to boost language, social and cognitive skills.

Where ESDM differs most from traditional intervention is that behavioural teaching techniques are embedded within this play. This includes providing clear cues for a behaviour, and rewarding that behaviour. Parents, therapists and teachers can use ESDM techniques within the children’s play and daily routines to help them reach developmentally appropriate milestones.

For example, a child who does not yet talk, may be learning to reach for preferred items. A child who has a lot of language may be learning to answer questions like “what is your name?”.

Initial research conducted in the United States, where the model was developed, suggests that ESDM is particularly effective when implemented for more than 15 hours a week by trained therapists in the home environment.

Improved cognition in early childhood

The model was adopted in Australia where the government funds autism specific early childhood centres. Research conducted in these centres indicates that children receiving ESDM intervention from trained therapists show greater improvements in understanding and cognitive skills than children who were not receiving treatment.

In New Zealand there is no government funding for such therapy. As a result, the cost of providing this intensive level of early intervention is beyond the budget of most families. There is also a lack of trained professionals with the technical expertise to implement such therapies.

For these reasons, we are working with the Autism Intervention Trust and Autism New Zealand to develop a New Zealand-specific low-intensity approach to delivering ESDM. The team is using the research of what is effective overseas and is applying it within a New Zealand context.

Mainstream schooling

New Zealand takes an inclusive approach to education. The main goal of the research programme therefore is for children with autism and their families to receive support earlier so that they can get a better start in their development and go on to mainstream schools.

One project involves training kindergarten teachers in ESDM. Inclusion of ESDM strategies in kindergartens is the biggest unknown because there is little teacher training in New Zealand around how to best support children with autism in mainstream settings.

A second project involves providing parent coaching and then adding on a small amount of one-on-one therapy. This will provide some preliminary evidence as to whether adding a minimal amount of one-on-one therapy is any more beneficial that just coaching parents.

Each project involves examining specific measures of communication, imitation (a key early learning skill children with autism typically struggle with) and social engagement with others.

Source: Read Full Article

Artificial intelligence predicts Alzheimer’s years before diagnosis

Artificial intelligence (AI) technology improves the ability of brain imaging to predict Alzheimer’s disease, according to a study published in the journal Radiology.

Timely diagnosis of Alzheimer’s disease is extremely important, as treatments and interventions are more effective early in the course of the disease. However, early diagnosis has proven to be challenging. Research has linked the disease process to changes in metabolism, as shown by glucose uptake in certain regions of the brain, but these changes can be difficult to recognize.

“Differences in the pattern of glucose uptake in the brain are very subtle and diffuse,” said study co-author Jae Ho Sohn, M.D., from the Radiology & Biomedical Imaging Department at the University of California in San Francisco (UCSF). “People are good at finding specific biomarkers of disease, but metabolic changes represent a more global and subtle process.”

The study’s senior author, Benjamin Franc, M.D., from UCSF, approached Dr. Sohn and University of California, Berkeley, undergraduate student Yiming Ding through the Big Data in Radiology (BDRAD) research group, a multidisciplinary team of physicians and engineers focusing on radiological data science. Dr. Franc was interested in applying deep learning, a type of AI in which machines learn by example much like humans do, to find changes in brain metabolism predictive of Alzheimer’s disease.

The researchers trained the deep learning algorithm on a special imaging technology known as 18-F-fluorodeoxyglucose positron emission tomography (FDG-PET). In an FDG-PET scan, FDG, a radioactive glucose compound, is injected into the blood. PET scans can then measure the uptake of FDG in brain cells, an indicator of metabolic activity.

The researchers had access to data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), a major multi-site study focused on clinical trials to improve prevention and treatment of this disease. The ADNI dataset included more than 2,100 FDG-PET brain images from 1,002 patients. Researchers trained the deep learning algorithm on 90 percent of the dataset and then tested it on the remaining 10 percent of the dataset. Through deep learning, the algorithm was able to teach itself metabolic patterns that corresponded to Alzheimer’s disease.

Finally, the researchers tested the algorithm on an independent set of 40 imaging exams from 40 patients that it had never studied. The algorithm achieved 100 percent sensitivity at detecting the disease an average of more than six years prior to the final diagnosis.

“We were very pleased with the algorithm’s performance,” Dr. Sohn said. “It was able to predict every single case that advanced to Alzheimer’s disease.”

Although he cautioned that their independent test set was small and needs further validation with a larger multi-institutional prospective study, Dr. Sohn said that the algorithm could be a useful tool to complement the work of radiologists—especially in conjunction with other biochemical and imaging tests—in providing an opportunity for early therapeutic intervention.

“If we diagnose Alzheimer’s disease when all the symptoms have manifested, the brain volume loss is so significant that it’s too late to intervene,” he said. “If we can detect it earlier, that’s an opportunity for investigators to potentially find better ways to slow down or even halt the disease process.”

Future research directions include training the deep learning algorithm to look for patterns associated with the accumulation of beta-amyloid and tau proteins, abnormal protein clumps and tangles in the brain that are markers specific to Alzheimer’s disease, according to UCSF’s Youngho Seo, Ph.D., who served as one of the faculty advisors of the study.

Source: Read Full Article