Artificial Intelligence Diagnoses Alzheimer’s With Near-Perfect Accuracy

Original article was published by Eshan Samaranayake on Artificial Intelligence on Medium

Artificial Intelligence Diagnoses Alzheimer’s With Near-Perfect Accuracy

The algorithm can detect subtle differences in the way people with Alzheimer’s disease use language. Photo by Robina Weermeijer on Unsplash

A team from Stevens Institute of Technology has developed an artificial intelligence tool that can diagnose Alzheimer’s disease with more than 95 percent accuracy. This also reduces cost as it eliminates the need for expensive scans or in-person testing. In addition, the algorithm is also able to explain its conclusions, enabling human experts to check the accuracy of its diagnosis.

What Is Alzheimer’s and Dementia?

Dementia is a general term for a decline in mental ability severe enough to interfere with daily life. Alzheimer’s is the most common cause of Dementia accounting for 60–80% of dementia cases. Although prominent among the older population (the majority of people with Alzheimer’s are 65 and older), Dementia is not a normal part of ageing. It is caused by damage to brain cells that affects their ability to communicate, which can affect thinking, behaviour and feelings.

Alzheimer’s is a progressive disease, where dementia symptoms gradually worsen over a number of years. In its early stages, memory loss is mild, but with late-stage Alzheimer’s, individuals lose the ability to carry on a conversation and respond to their environment. Alzheimer’s is the sixth leading cause of death in the United States.

Alzheimer’s is the most common cause of Dementia. Image credits:

Alzheimer’s disease can impact a person’s use of language, the researchers noted. People with Alzheimer’s tend to replace nouns with pronouns, and they can express themselves in a very roundabout way.

And it is this subtle differences in language is what the team is trying to detect.

So, how did they do it?

The Study

The team designed an explainable AI tool. Explainable AI is a set of tools and frameworks to help you understand and interpret predictions made by your machine learning models. This tool uses attention mechanisms and a convolutional neural network. Convolutional Neural Network (ConvNets or CNNs) is a category of neural networks that have proven very effective in areas such as image recognition and classification. The tool used in this study can accurately identify well-known signs of Alzheimer’s, as well as subtle linguistic patterns that were previously overlooked.

How Did They Train the Algorithm?

First, the researchers asked both healthy subjects and known Alzheimer’s sufferers to describe a drawing of children stealing cookies from a jar. Then, the team converted each individual sentence into a unique numerical sequence representing a specific point in a 512-dimensional space. This kind of approach allows complex sentences to be assigned numerical values. This makes it easier to analyze structural and thematic relationships between sentences. The AI gradually learned to spot differences between sentences composed by healthy or unhealthy individuals and was able to determine with significant accuracy how likely any given text was to have been produced by a person with Alzheimer’s.

People with Alzheimer’s tend to replace nouns with pronouns, and they can express themselves in a very roundabout way. Photo by Josh Riemer on Unsplash

What Is the Significance of the Study?

“This is a real breakthrough. We’re opening an exciting new field of research, and making it far easier to explain to patients why the AI came to the conclusion that it did, while diagnosing patients. This addresses the important question of trustability of AI systems in the medical field.”

– K.P. Subbalakshmi, the tool’s creator, founding director of Stevens Institute of Artificial Intelligence

The AI system can also incorporate new criteria that may be identified by other research teams in the future, making the algorithm increasingly more accurate over time.

The team designed the system to be both modular and transparent. When other researchers identify new markers of Alzheimer’s, the team can simply plug those into the architecture to generate even better results. This breeds collaboration among the scientific community. Thus speeding up progress.

What Does It Mean for the Future of AI in Alzheimer’s?

The team is hopeful that in the future, AI tools may be able to diagnose Alzheimer’s using any text, from emails to social media posts. This would require the team to train the model on many different kinds of texts produced by known Alzheimer’s sufferers.

While this kind of data is not yet available, increasing access to this kind of information could lead to the development of accurate, comprehensive AI tools.

The researchers’ next steps will be gathering new data that will help the algorithm diagnose patients with Alzheimer’s disease based on speech in languages other than English.

The team is also looking at ways in which other neurological conditions, such as aphasia, stroke, traumatic brain injuries, and depression, can impact language use.

“This method is definitely generalizable to other diseases,” “As we acquire more and better data, we’ll be able to create streamlined, accurate diagnostic tools for many other illnesses too.” said Subbalakshmi.

“The algorithm itself is incredibly powerful. We’re only constrained by the data available to us.” said Subbalakshmi.

In theory, A.I. systems could one day diagnose Alzheimer’s based on any text, from a personal email to a social media post. First, though, an algorithm would need to be trained using many different kinds of texts produced by known Alzheimer’s sufferers, rather than just picture descriptions, and that kind of data isn’t yet available.

Hopefully, the AI tool will more accurately diagnose Alzheimer’s, leading to earlier treatment and reduced healthcare costs.