Artificial intelligence is making waves in healthcare. More than 40 percent of healthcare executives consider it the technology that will have the greatest impact on their organizations within the next three years, Accenture reports.
Some health systems are already using it to address a growing number of issues, from staff efficiencies to predicting patient outcomes that transform the delivery of care. Now, recipients of care are starting to leverage the functionality of AI as well.
Consider Froedtert Health and the Medical College of Wisconsin Health Network, which is using Buoy — an interactive digital tool that allows users to enter their symptoms and receive a personalized analysis and recommendations for care options in real time. Buoy uses an algorithm to listen to and calculate input, and it gets smarter as more people use the tool.
But is it a good idea for patients to use such a tool before contacting a doctor?
Despite concerns around education and privacy, AI might be well-suited for patient care, writes Christopher Mims, a technology columnist for The Wall Street Journal. And the rapidly evolving technology can’t be overlooked: Worldwide spending on AI is expected to exceed $35 billion by the end of the year.
Here’s a look at how patient-centered AI tools are being used for diagnosis and determining whether a doctor visit is necessary.
Chatbots Helps Patients Get the Care They Need Now
An increasing number of healthcare organizations are adopting AI chatbots to triage patients and guide them to the appropriate help. Generally seen as a more accurate and reliable alternative to patient-driven online searches concerning symptoms, chatbots are helping patients who might otherwise not know where best to receive care.
“It is really difficult for people to understand whether to go to the ER, the urgent care center, the retail clinic, telemedicine, the nurse call line — any of those,” Dr. Andrew Le, CEO and co-founder of Buoy Health, tells MobiHealthNews. “It’s hard for people to know which of those options are appropriate because, at the end of the day, people didn’t get trained medically to triage their cough.”
These chatbots operate by first collecting basic information from patients. Then, based on input, the chatbots can provide patients with more information about their conditions and suggest next steps.
Some might worry that such bots will eventually replace receiving primary care; however, that’s not the case, Pascal Zuta, CEO of virtual care solutions company GYANT, tells MobiHealthNews.
AI chatbots are intended to support clinical teams by lightening heavy daily caseloads. Some bots, after analyzing patient data, are able suggest a discussion with a clinician rather than an in-office visit, routing the patient’s case to a live provider via video call.
“We want to use AI to improve a provider’s ability to diagnose consistently and accurately, see more patients and, most importantly, help their patients get the care they need,” Zuta tells MobiHealthNews.
Partnerships between AI chatbot companies and healthcare organizations are already underway, with major hospitals such as Boston Children’s Hospital hoping to improve algorithms when it comes to pediatric expertise. These types are partnerships are intended to help the products specialize across different areas of care.
AI Tools and Wearables Bridge the Data Gap
Where chatbots fall short in data collection, wearables thrive. Combined with AI, these devices enable the remote measurement and analysis of patient data in real time, helping to improve quality of life for patients.
A team of researchers from the University of Waterloo in Ontario, Canada, applied AI to data gathered from wearable technology with the intent of predicting failing patient health. The study, which monitored healthy men via a smart shirt fitted with heart rate, breathing and acceleration sensors, concluded that it is possible to “accurately predict health-related benchmarks during daily activities using only the smart shirt.”
"This multi-disciplinary research is a great example of how artificial intelligence can be a potential game-changer for healthcare by turning data into predictive knowledge to help healthcare professionals better understand an individual's health," co-author Alexander Wong tells ScienceDaily. "It can have a significant impact on improving quality of life and well-being."
Effective wearables can be simple. Devices such as the Apple Watch and the Fitbit play an equally critical role for patients hoping to take elements of care into their own hands.
With the recent addition of electrocardiogram functionality to the Apple Watch and Fitbit’s integration with Cardiogram (an app that uses deep neural network technology), wearers can continuously monitor to detect various heart conditions.
“Cardiogram has shown that optical heart rate sensors, when combined with a deep neural network, can accurately detect multiple major health conditions including diabetes, hypertension, sleep apnea and atrial fibrillation,” Brandon Ballinger, the app’s CEO and co-founder, tells MobiHealthNews.
“With the accurate 24/7 heart rate data from Fitbit wearables, Cardiogram can make its algorithm more accurate and potentially save lives, by helping users at elevated risk of certain health conditions and guiding them to condition management,” he says.