A study published this week by The Lancet Digital Health compared the performance of deep learning—a form of artificial intelligence (AI)—in detecting diseases from medical imaging versus that of healthcare professionals, using a sample of studies carried out between 2012 and 2019.

The study found that, in the past few years, AI has become more accurate of identifying disease diagnosis in these images and has become a more viable source of diagnostic information. According to the researchers, out of 14 studies that compared deep learning models and healthcare professionals within the same sample, the diagnostic performances were found to be equivalent.

With advances in AI, deep learning may become even more efficient in identifying diagnosis in the next few years.

AI applications in the field of healthcare aren’t just limited to diagnosing a disease, they also include its possible treatment.

Pharmaceutical company Bayer has recently been working with tech companies to create software to help diagnose complex and rare conditions and help develop new drugs to treat these diseases. They have been working in partnership with hospitals and researchers to determine what the machine learning needs to analyze to learn how to diagnose a patient’s medical condition. The information that the AI is absorbing comes from a number of factors from symptom data, disease causes, test results, medical images, doctor reports and more.

“We can model how it will behave in a cell in combination with other drugs the patients might be taking. We’re looking at how we can identify the right patients and sites to run our clinical trials. We would be able to run shorter studies and show where the medication is the right one for those patients earlier,” Angeli Moeller, who heads artificial intelligence projects at Bayer, explained to the Associated Press.

The machine learning systems are not to replace doctors or make absolute decisions in a patient’s treatment. According to Moeller, they still want the patient to have control over their treatments and want to use the artificial intelligence to support decisions and make recommendations based on the findings.

Bayer is not the only company making waves in healthcare with AI. There are many other startup companies that are tackling AI treatment options for disease. According to BenchSci’s latest report ,there are currently 148 startups using artificial intelligence in drug discovery.

One of those startups, Atomwise, just partnered with Jiangsu Hansoh Pharmaceutical Group in a $1.5 billion dollar joint-venture operation to collaborate on designing new drugs for cancer treatments.

The partnership combines Atomwise’s artificial intelligence technology with Hansoh Pharma’s manufacturing capabilities in order to work together to design new ways to predict how a small molecule will bind to a target protein and hopefully lead to new advancements in medical treatments. These joint-ventures are promising as it combines two essential elements for advancements in both machine learning and medical device innovation.

A Canadian biotech company, Deep Genomics, has been experimenting with machine learning and drug development for the past 5 years. Specifically they have been testing different treatments for a rare genetic disorder named Wilson Disease that currently has no treatments on the market. The disease prevents the body from removing copper that eventually builds up in the organs and can cause life-threatening organ damage and sometimes failure.

Deep Genomic’s artificial intelligence system discovered that the mutation changes an amino acid in ATP7B, a copper-binding protein that is absent in Wilson patients, and causes a disruption in the genome that causes that protein not to be produced. They are currently testing their drug on their first candidate in the study and hopeful this will be successful in treating the disease.

As of today, there are not any drug treatments on the market that were created by AI, but many companies are working hard to see that happen soon. The collection of patient data and testing will continue to drive advancements forward, and while these are great strides in the advancements of artificial intelligence working with medical professionals to save lives, it is far from being mainstream.

“It’s probably going to take two years before it really hits mainstream medical practice. Getting the technology to the patient is still the hard part,” Moeller to the AP.

Source : https://www.forbes.com/sites/nicolemartin1/2019/09/30/artificial-intelligence-is-being-used-to-diagnose-disease-and-design-new-drugs/?ss=ai#251191944db5