Description:
The current state of the art:
Healthcare-associated infection (HAI) places a significant burden on the patients and the health care system. It is estimated that 3% of hospitalized patients had one or more HAI in 2015. It accounts for about 1.7 million infections and 99,000 death per year. On the other hand, the Centers for Medicare and Medicaid Services no longer provide reimbursement for care required for several types of HAI. Therefore the timely detection of HAI is needed to improve patient care and reduce healthcare costs.
The problems with the current art
HAI can be detected via culture/histopathology and molecular testing. Blood and tissue culture and histopathology remain the established practice for diagnosing HAI. However, the long turnaround time, 2-3 days, can delay the timely treatment for infected patients. Molecular tests have quicker turnaround time as short as 2-3 hours, but the low sensitivity has limited the clinical use.
Therefore, it is critical to develop a system to quickly detect the HAI and reduce morbidity and mortality rate.
The advantages of our invention
Scientists at AU developed a hybrid model using live data to instantaneously detect fungal infection in hospitalized patients. The model gathers live data using blockchain technology and functions simultaneously on expert doctor opinion and mathematical principles. As a result, the model enables the timely determination of high-risk factors that can cause certain fungal infections, which will allow physicians to initiate pre-emptive treatment before the infection is developed. The model can be a promising tool to predict the HAI to reduce hospital costs and to initiate timely treatment to reduce morbidity and mortality rates in hospital-based patients.
AURI # 2019-010