By Samantha McGrail
February 09, 2021 – CLEW Medical recently announced that FDA granted clearance and authorization for the use of its artificial intelligence-based ICU solution, used to predict hemodynamic instability in adult patients.
The solution, CLEWICU, continuously monitors and categorizes patient risk levels. This information provides clinicians with physiological insight into a patient’s likelihood of future hemodynamic instability.
The clearance follows FDA’s emergency use authorization for CLEWICU’s respiratory deterioration model granted in June 2020. The solution has been used for the predictive screening of COVID-19 and other ICU patients.
“We are proud to have received this landmark FDA clearance and deliver a first-of-its-kind product for the industry, giving healthcare providers the critical data that they need to prevent life-threatening situations,” Gal Salomon, CLEW CEO, said in the announcement.
Many hospitals are reaching or have reached ICU capacity because of the COVID-19 pandemic, enhancing the need for quick and accurate decision-making. Effective risk evaluation is crucial to improving patient identification and care plans.
But these initiatives require advanced tools that provide comprehensive, predictive data to help medical professionals identify patients whose health conditions are likely to deteriorate as well as those whose conditions are unlikely to deteriorate.
Therefore, CLEWICU notifies caregivers of clinical deterioration nearly eight hours in advance, which allows for early evaluation and intervention. The system also identifies low-risk patients, enabling better ICU resource management and optimization.
“CLEW’s AI-based solution is a huge leap forward in ICU patient care, providing preemptive and potentially life-saving information that enables early intervention, reduces alarm fatigue and can potentially significantly improve clinical outcomes,” said Craig Lilly, vice chair of critical care operations and professor at the University of Massachusetts Medical School.
CLEWICU uses artificial intelligence-based algorithms and machine learning models trained to identify the likelihood of significant clinical events occurring in patients in the ICU.
The system receives patient data from sources such as electronic health records (EHR) and medical device data. Experts then analyze and evaluate the data in real-time to present insights for artificial intelligence models and provide overall unit status.
“AI can be a powerful force for change in healthcare, enabling assessment of time-critical patient information and predictive warning of deterioration that could enable better informed clinical decisions and improved outcomes in the ICU,” said David Bates, MD, medical director of clinical and quality analysis in information systems at Mass General Brigham healthcare system and CLEW advisory board member.
A January study from Epic Health Research Network found that by early December 2020, over 100,000 patients were hospitalized with COVID-19 in the US. The two top challenges that health systems faced were staff and ICU bed availability.
Researchers found that out of 809 hospitals in metro, suburban, and rural settings, there was a 90 percent increase in the number at capacity in their respective ICUs from July 2020 to December 2020.
Additionally, from July to early October, the largest groups of rural ICUs in the study only had zero percent to 20 percent occupancy. But by December, ICU capacity was at 90 percent to 100 percent.
When ICUs face overcapacity, patients have a 92 percent increased risk of death from COVID-19.
Artificial intelligence and machine learning can help to address care challenges during the pandemic, but experts have also tapped inpatient telehealth platforms to combat over-capacity in ICUs, reducing workload stresses for care providers and improving care outcomes.
New Haven, CT-based health systems, with sites in Connecticut and Rhode Island, treated nearly 4,300 COVID-19 patients over a five-month span, including more than 700 needing ICU care, a 2020 Applied Clinical Informatics study found.
Specifically, health system administrators took advantage of telemedicine platforms already in place for telestroke, tele-ICU, and teleconsultation services.