AI in Healthcare: The Future of Patient Care and Health Management

With the extensive media coverage in recent months, you’ve probably heard about artificial intelligence (AI), a technology that allows computers to do things that would otherwise require a human brain. In other words, machines can be given access to large amounts of information and trained to solve problems, detect patterns, and make recommendations. Common examples of AI in everyday life are virtual assistants such as Alexa and Siri.

What you may not know is that AI has been and is being used for a variety of healthcare applications. Here’s a look at how AI can be useful in healthcare and what to watch for as it develops.

What can AI technology in healthcare do for me?

NMA report identified three potential benefits of AI in healthcare: improving outcomes for both patients and clinical teams, lowering healthcare costs, and promoting population health.

From preventive screenings to diagnosis and treatment, AI is being used across the continuum of care today. Here are two examples:

Preventive care

Cancer screenings that use radiology, such as mammography or lung cancer screening, can use AI to help deliver results faster.

For example, in polycystic kidney disease (PKD), researchers have found that kidney size — specifically an attribute known as total kidney volume — correlates with how quickly kidney function will decline in the future.

But assessing total kidney volume, while incredibly informative, involves analyzing dozens of kidney images, one slide after another—a laborious process that can take about 45 minutes per patient. With innovations developed at Mayo Clinic’s PKD Center, researchers now use artificial intelligence (AI) to automate the process, generating results in seconds.

Bradley J. Erickson, MD, Ph.D., director of Mayo Clinic’s Radiology Informatics Laboratory, says AI can do time-consuming or mundane work for radiology professionals, such as tracking tumors and structures or measuring amounts of fat and muscle. “If a computer can do that first pass, that could help us a lot,” says Dr. Erickson.

Risk Assessment

In a Mayo Clinic cardiology study, AI successfully identified people at risk for left ventricular dysfunction, which is the medical term for a weak heart pump, even though the individuals had no noticeable symptoms. And this is far from the only intersection of cardiology and AI.

“We already have an AI model that can randomly say, ‘Hey, you have a lot of calcium in your coronary artery and you’re at high risk for heart attack or stroke in five or 10 years,'” says Bhavik Patel, MD, MBA, chief artificial intelligence officer. intelligence at the Mayo Clinic in Arizona.

How can AI technology improve medicine and public health?

When it comes to maintaining the overall health of a population, AI can help people manage chronic diseases themselves — think asthma, diabetes, and high blood pressure — by connecting certain people with appropriate screening and therapy and reminding them to take steps in your care by taking medication.

AI can also help promote disease prevention information online, reaching large numbers of people quickly, and even analyze text on social media to predict outbreaks. With the example of a widespread public health crisis in mind, consider how these examples may have supported people during the early stages of COVID-19. For example, one study found that internet searches for terms related to COVID-19 were associated with actual cases of COVID-19. Here, artificial intelligence could be used to predict where an outbreak will occur and then help officials know how best to communicate and make decisions to help stop the spread.

How can AI solutions help deliver superior patient care?

You might think that health care from a computer is not equal to what a person can provide. This is true in many situations, but not always.

Studies show that in some situations AI can do a more accurate job than humans. For example, artificial intelligence has done a more accurate job than current pathology methods at predicting who will survive malignant mesothelioma, which is a type of cancer that affects internal organs. AI is being used to identify colon polyps and has been shown to improve the accuracy of colonoscopy and diagnose colorectal cancer as accurately as experienced endoscopists can.

In a survey of a social media forum, most people asking healthcare questions preferred answers from an AI-based chatbot over those from doctors, ranking the chatbot’s answers higher in quality and empathy. However, the researchers conducting this study stress that their results only suggest the value of such chatbots in answering patient questions, and recommend that it be followed up with more conclusive research.

How can doctors use AI and machine learning in healthcare?

One of the key things AI can do to help healthcare professionals is save them time. For example:

• Keep up with current progress. When physicians are actively involved in human care and other clinical duties, it can be challenging for them to keep up with the evolving technological advances that support care. AI can work with huge volumes of information – from medical journals to health records – and highlight the most relevant parts.
• Taking care of boring work. When a healthcare professional needs to complete tasks such as writing clinical notes or filling out forms, AI can potentially complete the task faster than traditional methods, even if revision is needed to refine the first pass the AI ​​makes.

Despite AI’s potential to save healthcare professionals time, AI is not intended to replace humans. The American Medical Association commonly refers to “augmented intelligence,” which emphasizes the importance of AI assisting, not replacing, healthcare professionals. In the case of current AI applications and technologies, healthcare professionals are still needed to provide:

• A clinical context for the algorithms that train AI.
• Accurate and relevant AI information for analysis.
• Translating AI findings to be meaningful to patients.

A useful comparison to reiterate the necessary nature of collaboration between AI and humans for healthcare is that in most cases a human pilot is still needed to fly an airplane. Although technology has enabled a fair amount of automation in flying today, humans are needed to make adjustments, interpret equipment data, and take over in an emergency.

What are the disadvantages of AI in healthcare?

Despite the many exciting opportunities for AI in healthcare, there are some risks that need to be considered:

• If not trained properly, AI can lead to bias and discrimination. For example, if an AI is trained on electronic health records, it is based only on people who have access to health care and maintains any human bias captured in the records.
• AI chatbots can generate medical advice that is misleading or incorrect, so there is a need to effectively regulate their use.

Where can AI solutions take the healthcare industry next?

As AI continues to develop and play an increasingly important role in healthcare, the need for effective regulation and use becomes increasingly critical. That’s why Mayo Clinic is a member of the Health AI Partnership, which focuses on helping healthcare organizations evaluate and implement AI effectively, fairly, and safely.

Regarding opportunities for healthcare professionals to further integrate AI, Dr. Mark D. Stegall, a transplant surgeon and researcher at the Mayo Clinic in Minnesota, says, “I predict that AI will also become an important tool for making solutions for doctors.’

The Mayo Clinic hopes that AI can help create new ways to diagnose, treat, predict, prevent and cure disease. This can be achieved by:

• Selection and matching of patients to the most promising clinical trials.
• Development and setup of remote health monitoring devices.
• Detection of currently unobservable states.
• Predicting disease risk years in advance.