In crises, institutions are forced to act quickly and decisively in order to prevent the least possible damage. Even when the response is effective, the very nature of a crisis is to cause chaos, and that chaos results in bottlenecks down the road. The novel coronavirus has put healthcare systems across the globe in crisis mode for months, infecting more than 4.2 million and killing more than 287,000. Overcrowded and understaffed hospitals, a lack of medical supplies, and death have become the norm these past few months. Those issues won’t go away after the virus does—they’ll only get worse. But there are ways to mitigate the coming crisis, namely the utilization of artificial intelligence (AI).
Part of the strategy, for both fighting the pandemic and beyond, has to focus on understanding disease progression and enabling effective prioritization through that understanding. While most efforts to fight the COVID-19 pandemic to date have been on characterizing the virus, testing, and developing vaccinations or building immunity against it, there is very little to help the health system understand the potential for disease progression in patients—and therefore how to create the best care plan to fight it through effective prioritization of cases.
One of the greatest drivers of coronavirus-related mortality is the inability to detect potential severe cases early on and provide critical care to those who need it the most, which contributes to the capacity problem hospitals are facing globally, especially in countries that have been hit hardest by the pandemic, such as Italy and the U.S. That’s important for not only COVID-19 patients, but other patients as well. The novel coronavirus may seem like our only problem now, but unfortunately it is not.
Given the critical stage we are in, non-urgent cases and visits are being deferred to later, including procedures that are not urgent but extremely important—mammography screening, scanning for bone-health conditions, imaging for hip-replacement procedure planning, and post-operative follow-up scans are just a few examples. Critical non-COVID cases, too, are being delayed. In the UK, for example, more than 2,300 cancer cases are likely to be going undiagnosed across the UK every passing week, according to Cancer Research UK. Overall, the number of urgent referrals has dropped to around 25 percent of the usual number in the country.
A decline in cancer screenings due to the pandemic was even more striking in the U.S., as a recent study by Epic Health Research Network found that cancer screenings across the country dropped between 86-94 percent in March 2020, as compared with March 2019.
This will create substantial pressure further down the road, as the pent-up demand builds up and healthcare providers will struggle to process large imaging volumes in a very short time, for both urgent and non-urgent cases.
What is the effect of this? Obviously, we will have millions of patients waiting for the right time for their treatment while enduring the hardship brought on by their conditions, which are most likely worsening without proper care. The industry will need to be innovative to quickly provide these essential services as we overcome the peak of the COVID-19 crisis.
While AI can’t yet fight the coronavirus directly, it can play a central role in creating the efficiency needed for healthcare professionals to get to as many cases possible, especially post-COVID-19. AI can assist clinicians by prioritizing cases, allowing clinicians to focus on what matters most, and creating a safety net to ensure critical results and incidental findings are not missed.
AI-powered healthcare solutions offer concrete results, including reducing turnaround time for head CT scans and uncovering patients at risk of cardiovascular disease due to a build up of coronary calcium, as well as detect compression fractures that are impacting the patients’ quality of life. A whopping 70 percent of compression fractures go undiagnosed globally—a percentage, for example, that can be reduced with the assistance of AI technology’s ability to streamline processes.
The early detection of brain bleeds, too, regardless of the cause, as well as the early and accurate diagnosis of active bleeding is essential for the successful care of patients suffering from it. Intracranial hemorrhage is a devastating disease with a high 30-day mortality rate that ranges from 35 to 52 percent. It is estimated that about half of this mortality occurs within the first 24 hours, according to a National Institutes of Health study, emphasizing the importance of early detection and effective treatment in the emergency department.
As in any organization’s race to overcome a crisis, prioritization is key. It’s also crucial to prioritize and streamline processes after the pandemic ends, as health systems globally must learn from their mistakes and lack of preparedness for this one. We must prepare our last line of defense, our health systems, for the coming influx of cases, both COVID-related and not. An emphasis must be placed on early diagnoses so that prioritization is sorted out before the frontliners have to scramble to figure it out on their own.
About the Author
Ohad Arazi is Chief Executive Officer of Zebra Medical Vision. Ohad has 19 years of experience in general management and product development of solutions in Healthcare IT, Healthcare Services, and Medical Devices. Prior to joining Zebra, Ohad served as the Chief Strategy Officer for TELUS Health, the largest digital health company in Canada.
Sign up for the free insideAI News newsletter.
