The future of depression diagnosis is already here, the expert says

Artificial intelligence (AI) is poised to revolutionize the way we diagnose and treat diseases. It can be especially useful in the treatment of depression because it can make more accurate diagnoses and determine which treatments are more likely to work.

About 20% of us suffer from depression at least once in our lives. 300 million people worldwide currently suffer from depression, and 1.5 million Australians are likely to be depressed at any one time.

Because of this, the World Health Organization has described depression as the biggest single cause of illness around the world.

How could artificial intelligence help?

Depression can be difficult to detect

Despite its prevalence, depression is difficult to diagnose. So difficult, in fact, that GPs accurately detect depression in less than half of cases.

This is because there is no single test for depression: doctors use self-reported symptoms, questionnaires and clinical observations to make a diagnosis. But the symptoms of depression are not the same for everyone.

Some people may sleep more, others less; Some people lack energy and interest in activities, while others may feel sad or irritable.

For those with accurately diagnosed depression, there are several treatment options, including talk therapy, medication, and lifestyle changes. However, each person’s treatment response is different, and we have no way of knowing in advance which treatments will work and which ones won’t.

Artificial intelligence trains computers to think like humans, focusing specifically on three human-like behaviors: learning, reasoning, and self-correction (fine-tuning and improving performance over time).

One area of ‚Äč‚Äčartificial intelligence is machine learning, the goal of which is to train computers to learn, find patterns in data, and make data-informed predictions without human guidance.

In recent years, there has been increased research into the application of artificial intelligence to diseases such as depression, which can be difficult to diagnose and treat.

What they’ve found so far

Scientists have compared ChatGPT diagnoses and medical recommendations with results given by real-life doctors. ChatGPT recommended talk therapy when given information about fictitious patients of varying depression severity, gender, and socioeconomic status. In contrast, doctors recommended antidepressants.

The US, UK and Australian guidelines recommend speech therapy as the first treatment option before medication.

This suggests that ChatGPT may be more likely to adhere to clinical guidelines, whereas GPs may have a tendency to overprescribe antidepressants.

ChatGPT is also less affected by gender and socio-economic biases, while doctors are statistically more likely to prescribe antidepressants to men, especially those in work.

How depression affects the brain

Depression affects certain parts of the brain. My research has shown that the areas of the brain involved in depression are very similar in different people. So much so, we can predict whether or not someone has depression with over 80% accuracy just by looking at these brain structures on MRIs.

Other studies using advanced AI models have supported this finding, suggesting that brain structure may be a useful direction for AI-based diagnosis.

Studies using magnetic resonance imaging (MRI) data on brain activity at rest can also correctly predict depression more than 80% of the time.

However, combining functional and structural information from MRI provides the best accuracy, correctly predicting depression in over 93% of cases. This suggests that using multiple brain imaging techniques to detect depression may be the most viable way forward.

MRI-based AI tools are currently only used for research purposes. But as MRI scans become cheaper, faster, and more portable, it’s likely that such technology will soon become part of your doctor’s toolbox, helping them improve diagnosis and improve patient care.

Diagnostic tools you may already have

While MRI-based AI applications are promising, a simpler and easier method to detect depression may be at hand, quite literally.

Wearable devices such as smart watches are being studied for their ability to detect and predict depression. Smartwatches are particularly useful because they can collect a wide range of data, such as heart rate, step count, metabolic rate, sleep data, and social interaction.

A recent review of all studies to date on using wearables to assess depression found that depression was correctly predicted 7089% of the time. Because they are commonly used and used 24/7, this research suggests that wearables can provide unique information that might otherwise be difficult to collect.

However, there are some drawbacks, such as the considerable cost of smart devices, which may be out of reach for many. Others include the questionable ability of smart devices to detect biological data from people of color and the lack of diversity in study populations.

Studies have also turned to social media to detect depression. Using artificial intelligence, researchers have predicted the presence and severity of depression based on the language of our posts and community memberships on our social media platforms.

The exact words used predicted depression with up to 90% success rates in both English and Arabic. Depression has also been successfully detected early on from the emoticons we use.

Prediction of treatment responses

Several studies have shown that antidepressant treatment response can be predicted with more than 70 percent accuracy based on electronic health records alone. This could provide doctors with more accurate evidence when prescribing medication-based treatments.

By combining data from people in antidepressant trials, researchers have predicted whether taking the drugs will help certain patients go into remission from depression.

Artificial intelligence shows promise in the diagnosis and treatment of depression, but recent findings require validation before they can be trusted as a diagnostic tool. Until then, MRI scans, wearables and social media can help doctors diagnose and treat depression.

Sarah Hellewellresearcher, Faculty of Health Sciences, Curtin University and Perron Institute for Neurological and Translational Science, Curtin University

This article is republished from The Conversation under a Creative Commons license. Read the original article.

#future #depression #diagnosis #expert
Image Source : www.sciencealert.com

Leave a Comment