Medical Software

5 Ways Artificial Intelligence Is Impacting Telehealth

Published by in Medical Software

Health delivery organizations (HDOs) are “on the threshold of a seismic change in how they will deliver clinical care.”

That’s according to Gartner’s latest “Hype Cycle for Telemedicine and Virtual Care,”* where analysts, Mike Jones and Thomas J. Handler, M.D. write that HDOs “now recognize the value of virtual care and telemedicine.”

So, what will this “seismic change” look like?

For one, it will likely include some form of artificial intelligence.

Artificial Intelligence Is Impacting Telehealth

Here, we’re looking at the latest news on telemedicine and the five ways it will get even better with the introduction of artificial intelligence (AI).

*Full content available to Gartner clients.

What’s the latest in telemedicine?

Telehealth is growing, and so is the demand for it. In the U.S. more than 6,500 locales have too few medical professionals to meet patients’ needs.

In Congress, senators and representatives have recently introduced four bipartisan bills aimed at expanding Medicare coverage of telehealth and remote monitoring services. Loosening the restrictions could save Medicare $1.8 billion on net over the next decade.

In 2016, Teladoc in partnership with Becker’s Healthcare surveyed 179 U.S. hospital and health system executives and other key telehealth stakeholders on the current consumer telehealth landscape.

They found that by December 2018, 76% of hospitals will have or will be implementing consumer telehealth.

Of the organizations that already have consumer telehealth in place, 69% plan to expand their programs. And 83% of respondents who work at organizations that plan to implement consumer telehealth rate it as a high-priority initiative.

Last year the National Business Group on Health surveyed 133 large companies employing 15 million Americans about their benefit practices. Respondents at 90% of companies said their employees will have access to at least some telemedicine services this year. Nearly all of them say they will by 2019.

Why AI and Telemedicine?

In many ways, telemedicine and AI are a match made in healthcare heaven. They are both aimed at cutting costs and diagnosing illnesses faster and more accurately.

Here are the five main ways AI is improving telemedicine.

1. Making better diagnoses

Clinicians can already diagnose, monitor, and treat diabetic retinopathy remotely via telemedicine. In fact, the Los Angeles County Department of Health Services recently reduced visits to specialty care professionals by more than 14,000 by implementing telemedicine screenings for diabetic retinopathy at its safety net clinics.

When you combine remote monitoring with machine learning, you get even better diagnoses with less speciality labor.

The machine learning algorithm that Google uses to label web images can diagnose diabetic retinopathy as well as a highly trained ophthalmologist. All it needs are retinal images, which can be obtained and analyzed remotely through telemedicine.

Similarly, FDNA is a startup which wants to train a machine learning algorithm to detect rare genetic diseases from photos of patients faces. Right now patients with rare genetic disorders must, on average, visit seven doctors before figuring out what they have. By sending pictures of their faces to an algorithm via telemedicine they can reduce that number to zero.

2. Recommending treatments

IBM Watson Health is recommending treatment plans to cancer patients using machine learning at a 327-bed hospital in Jupiter, Florida, through a partnership with Memorial Sloan Kettering Cancer Center, which provides clinical data reviewed and corrected by doctors.

Other partnerships with academic institutions include prominent biopharma companies such as Pfizer, Medtronic, and Johnson & Johnson.

Infusing telemedicine platforms with machine learning algorithms such as IBM Watson will mean better diagnoses with less human effort. For example, an algorithm should track every treatment for strep throat and then ask patients how long it took them to get better on average. The platform could then adapt and recommend treatments based on past success rates.

3. Solving logistical challenges

AI can also be used to reduce long hospital wait times and other administrative headaches.

GE Healthcare and the Johns Hopkins Hospital are using predictive analytics to reduce bottlenecks and improve patient flow. Today ambulances are dispatched to other facilities an hour faster on average thanks to the Judy Reitz Capacity Command Center. And emergency room patients get beds 30% faster than before.

While this is for in-person visits right now, predictive analytics will eventually help find doctors faster for telemedicine patients as well. For example, AI will be able to route questions to the doctor with the best outcomes for a patient’s symptoms instead of just sending them to the first doctor available.

4. Helping with eldercare

While we usually think of phones when we think of telehealth, at some point telehealth will come in the form of robots, and they will be essential in delivering home healthcare, according to Gartner’s “Hype Cycle for Telemedicine and Virtual Care, 2016” (full content available to clients).

Gartner analysts see smart machine robots growing in utility as the demand for home healthcare workers continues to outstrip supply. Smart machines will decrease the cost of delivering healthcare services while improving quality of life for patients.

One example of this tech is eldercare-assistive robots, which are smart machines that move semi-autonomously, perform tasks, and use sensors to understand their environments.

Already, the Japanese government funds research to develop robots that help elderly people by assisting with walking, waste disposal, bathing, and monitoring. A robot named IBA uses “smart rubber” sensors to detect an elderly person’s weight without lifting.

5. Preventing burnout

For some doctors, telemedicine combats burnout. And when you combine AI with telemedicine, it becomes even more powerful.

On a recent podcast, Rasu Shrestha, M.D., chief innovation officer at the University of Pittsburgh Medical Center (UPMC), spoke about using AI to help prevent physician burnout through a recently formed partnership with Microsoft.

“In some instances 40% or more of a clinician’s time is spent entering notes into an electronic medical record,” Shrestha says. “They’re interacting with the EMR as opposed to with the patients.”

The goal is to use AI to cut down on physicians’ screen time. Shrestha continues:

“We want to focus on what is really at the heart of better care, which is connecting with patients. Not connecting with clicks and screens and workflows related to clinical information systems, but with the story that’s unfolding in front of you with the patient and the disease we’re trying to treat.”

AI could also identify signals that often indicate imminent burnout to predict exactly how many patients a doctor can see before burning out.

Going forward

Telemedicine and AI are two great flavors that taste great together. To learn more about the future of medical technology, check out these articles too:

Looking for Medical Practice Management software? Check out Capterra's list of the best Medical Practice Management software solutions.

About the Author

Cathy Reisenwitz

Cathy Reisenwitz

Cathy Reisenwitz is a former Capterra analyst.


No comments yet. Be the first!

Comment on this article:

Comment Guidelines:
All comments are moderated before publication and must meet our guidelines. Comments must be substantive, professional, and avoid self promotion. Moderators use discretion when approving comments.

For example, comments may not:
• Contain personal information like phone numbers or email addresses
• Be self-promotional or link to other websites
• Contain hateful or disparaging language
• Use fake names or spam content
Your privacy is important to us. Check out our Privacy Policy.