Unlocking the True Value of Artificial Intelligence — The Medical Field

When I was first introduced to artificial intelligence, I was tasked to investigate how AI can help a financial institution determine the next best action for a potential customer. Using this information, the financial institution would display ads aimed towards turning views into clicks and curious viewers into customers. What started off as a data-driven exercise turned into a evolved project that is changing the way we market customers.

While that is one use case for AI, there are hundreds more that are being explored and have yet to truly be investigated. After all, why should we harness this power to make the rich richer when it can be used to help those in need? That’s the question that drove me to dive deeper into AI and to evaluate other ways that it can be used. What I found were areas that could thrive with artificial intelligence.

In this series, I look to give a brief glimpse into how AI is being used in different industries with the hope of create a renewed interest in others. Such technology can shape the way we tackle problems of today while creating opportunities for the future. It all starts with awareness.

The medical field is one area near and dear to me as I began to see how doctors and scientists were using artificial intelligence to better help their patients. We live in a time where medicines are used to treat symptoms, but not prevent and proper diagnose.

In my research, I’ve found that in more than half the cases of misdiagnosed sicknesses, the technology was not there to evaluate. If the technology is readily available and gives medical professionals the ability to be proactive as opposed to reactive, the number of misdiagnosed illnesses goes down and patients can receive proper treatment sooner.

Multiple sclerosis (MS) is an autoimmune disease that affects 2.3 million people globally with 200 cases being diagnosed each week. Over the last several years, the number of cases has increased and what is more troubling, researchers and neurologists cannot say with certainty what causes it. They only know that it comes with damage to myelin, nerve fibers, and neurons in the brain and spinal cord.

Until symptoms are manifest, patients won’t know they have it. Patients suffering from multiple sclerosis could have received the care needed earlier if they were properly diagnosed. One research group I’ve been reading up on has made this their purpose. Their name is AIMS — Artificial Intelligence for Multiple Sclerosis. While they are in the research phase, they are looking to solve a major problem. From their website:

“There is currently a significant lack of accurate diagnostic tools for MS due to gaps in knowledge regarding its etiology. In 2015, the MS Society found that 4 out of every 5 MS patients in the UK are misdiagnosed at least once, often waiting years between the onset of their symptoms and their diagnosis. Even worse, symptoms used to detect MS are found in other similar diseases such as myasthenia gravis and sarcoidosis, and change drastically in a patient over time. Accordingly, symptom patterns must be established to properly diagnose and monitor the progression of MS for optimized treatment.”

Continuing as to why their solution will solve the problem:

“While symptoms are one of the primary aspects of diagnosing MS, they are highly variable from patient to patient and can appear sporadically for years before visible disability sets in. AIMS would solve the mounting problem of misdiagnosis by establishing patterns of these symptoms in the beginning stages of MS through using a Bayesian network to mine data of consenting users. The network would aid neurologists by generating maps of patient data over time that could scale the probability of disease presence and alert users of potential conditions they might have with warning signals sent to their mobile devices.”

Using consumer-facing software such as mobile applications and cloud services and digital systems, they are looking to tackle this problem.

In 2014, the Ebola virus disease (EVD) struck Liberia and other countries in West Africa. Between December 2013 and January 2016, there was a reported 28,646 cases and 11,323 deaths. While the epidemic was no longer declared an emergency in March 2016, other outbreaks have continued with the most recent being in the Democratic Republic of Congo.

During this outbreak, a company named Atomwise partnered with the University of Toronto and IBM to develop a treatment for Ebola. Using AI, they were able to perform the necessary rapid testing to put the medication into production.

More recently, scientists were able to track Ebola to bat carriers using artificial intelligence. AI allowed them to perform their research and get the results faster. Scientists used machine learning algorithms to match the patterns within viral genomes to the animal they came from. With this information, they were able to perform the necessary research to trace it back to not only the animal, but the particular species. This information would allow professionals to better treat and test for Ebola.

According to Simon Anthony, D.Phil, assistant professor of Epidemiology in the Center for Infection and Immunity at the Columbia University Mailman School of Public Health, who led the laboratory discovery:

“There have been unanswered questions about the source of Ebola outbreaks. There was speculation that they may have originated from bats, but there was no direct evidence. A critical element in this discovery, was VirCapSeq-VERT, a tool invented at the CII that improves the sensitivity of next generation sequencing 1,000-fold. It is possible that there are also other bat species that carry Ebola. Going forward, we will be analyzing additional specimens to fill in the picture.”

MIT’s Computer Science and Artificial Intelligence Lab has recently developed a new deep learning-based AI prediction model that can anticipate the development of breast cancer up to five years in advance. What I found even more encouraging is that it worked equally well for white and black patients and it will allow for greater degree of accuracy. When medical professionals get their hands on this technology, treatment for breast cancer (and soon, other cancers) can be tracked and treated in earlier stages.

While we are still in the assessment phase of AI, its role in the medical field is absolutely secure. Properly diagnosing, rapid testing, refined tracing, and advanced tracking of diseases provides a value so desperately needed in a field that is often used to treat symptoms of diseases and not preventing them.

From my research, there many cases of how AI is being used in the medical field. Diseases and viruses such as HIV/AIDS, Alzheimer’s, and Parkinson’s are others that are being locked into. My hope is that artificial intelligence along with other emerging technology continues to grow into a force in the field of medicine.

Source link
Back to top button
Thanks !

Thanks for sharing this, you are awesome !

Pin It on Pinterest

Share This

Share this post with your friends!