Advances in telehealth and AI, along with increased acceptance by physicians, can lead to breakthroughs in virtual health care.
Telehealth is not a new concept; in fact, home-based health care dates back more than a century. In 1879, an article in Lancet suggested that the telephone could be used as a tool to reduce in-office visits. Thanks to ever-evolving technology, telehealth options have grown exponentially in recent years. Now, televisits conducted by video and email have become common, and advancements in artificial intelligence (AI) are rapidly changing the landscape of medicine.
Yet many physicians have not yet fully embraced the idea of telehealth. In a survey conducted by the American Medical Association (AMA) in 2016 and again in 2019, the number of physicians using telehealth visits and remote monitoring had doubled, yet still only 28% of physicians had adopted these practices.
However, the COVID-19 pandemic has drastically changed these statistics and opened the door further to the future of telehealth. Meg Barron, Vice President of Digital Innovation for the AMA, estimates that up to 90% of physicians are now using some sort of telehealth service, with many of them trying it for the first time.
The pandemic has also illustrated the innate need for virtual healthcare options in circumstances when the health of patients and providers is at risk. The good news is that with more physicians taking advantage of telehealth services, the door is opening to a future where the benefits of telehealth augmented by AI can have a lasting impact on the healthcare system.
AI, of course, takes telehealth a step further by automating some decision-making capabilities (such as when an EMR suggests a list of tests a patient might need) or adding data support to a physician’s deliberations (as in software-assisted diagnostic tools).
In a 2020 JAMIA Open article titled “Evaluating Artificial Intelligence in Medicine: Phases of Clinical Research,” researchers define AI in health care as “AI-based software that informs or influences clinical or administrative decisions and can affect health or healthcare delivery.” In effect, AI can impact everything from taking a patient’s health history to diagnosing diseases and monitoring and managing chronic health conditions.
AI technology can simplify the process of taking a patient’s health history, which can in turn assist a physician in making a definitive diagnosis, according to an article in the 2019 Yearbook of Medical Informatics.
“AI can make history taking easier by providing prompts to the process and clues to the diagnosis, and also asking the right next set of questions based on the answer, saving the clinician time,” the authors note. “For example, a person suffering long-term with chronic, dull aching pain in the upper abdomen without interference with sleep is likely suffering from gastritis. A summary of such questions being asked in sequence can be delivered as part of a telehealth application and may be implemented efficiently using mobile ICT [information and communication technology].”
These systems can also help patients make decisions when it’s not possible to speak to a physician. “Benefits from such questions and conclusions thereof can be availed of directly by the patient with the assistance of a local nurse practitioner. Such questioning can be assisted by easy-to-use symbols within the user interface which all can understand.”
AI has already begun to play an important role in the diagnosis of some clinical conditions, including certain cancers.
“Considering the progress of diseases that could relate to the formation of cancers, different disease diagnosis patterns might reflect different chances of cancer risks,” note Craig Kuziemsky, et al in the Medical Informatics article. “Modeling disease progression and variants in disease trajectories helps in prediction.”
A particular area of promise for AI and telediagnosis lies in teledermatology. According to studies in 2017 and 2018, computer algorithms using convolutional neural networks (CNN) were able to accurately diagnose melanoma.
“The CNN achieves performance on par with all tested experts across tasks of identification of the most common cancers, and identification of malignant melanoma, the deadliest skin cancer, demonstrating an artificial intelligence capable of classifying skin cancer with a level of competence comparable to dermatologists,” Kuziemsky, et al write.
Research being done on telehealth for breast and cervical cancer patients also shows encouraging results.
Patient Monitoring and Disease Management
Telemonitoring has been utilized by physicians for many chronic health conditions and is rapidly becoming more advanced.
A report issued by the Agency for Healthcare Research and Quality notes that “the evidence-base for telehealth is strong, especially for the remote management of chronic health conditions.” The report continues by observing that research has demonstrated telehealth’s effectiveness at managing conditions, achieving cost savings, encouraging patient engagement and boosting outcomes for multiple chronic diseases, ranging from asthma to mental health conditions.
The benefits of telemonitoring are many, as AI-enabled devices can utilize and incorporate statistical evidence and data from tools like location finders, accelerometers, motion sensors and more, improving analysis and care delivery and relieving the burden of data collection for providers, according to Kuziemsky, et al.
While the future of AI and telehealth holds great potential, hurdles remain. In the study conducted by the AMA, many physicians cited lack of information and support, along with concerns about liability and payment, as reasons why they had not yet implemented telehealth services.
Additionally, AI-enhanced telehealth faces issues of accessibility, as it would ideally be available to everyone regardless of economic status or technological proficiency.
“We must ensure that AI applications do not increase the digital divide, but rather enhance our ability to provide quality patient-centered care delivery to all citizens,” note Kuziemsky, et al.
With continued research and outreach, these issues can be addressed and the potential of telehealth can continue to expand.