As COVID-19 continues to spread across the country, hospitals are incorporating artificial intelligence into their daily operations.
Here are nine ways hospitals can use AI to fight COVID-19, according to Stat.
1. Screen people who may be infected: Cleveland Clinic has created its own chatbot that is designed to screen patients prior to their visit to determine if they may have been infected.
2. Identify high-risk patients for physicians to reach out to: Algorithms can be used based on existing patient data to proactively identity patients at the highest risk of contracting COVID-19.
3. Screen frontline workers: The University of California San Francisco has frontline providers wear rings that track vital signs.
4. Detect COVID-19 and distinguish from other respiratory illnesses: Because COVID-19 has symptoms similar to other respiratory illnesses, AI models can be built to identify COVID-19 based on chest images.
5. Predict which COVID-19 patients will deteriorate: Researchers at New York University, Columbia University and two hospitals in Wenzou, China, created an algorithm that predicts if patients will develop acute respiratory distress syndrome. Other AI models are being developed to identify patients who will need to be transferred to the intensive care unit.
6. Track hospital beds and supplies: In the wake of supply shortages, AI can be a great tool to determine when a hospital will run out of beds, ventilators and other resources.
7. Track patients outside the hospital: Rochester, Minn.-based Mayo Clinic and Pittsburgh-based UPMC are working with the maker of a digital stethoscope and mobile EKG technology. When patients are sent home, the technology can flag dangerous heart rhythm abnormalities and COVID-19 symptoms.
8. Detect high temperatures and prevent sick people from entering public spaces: Temperature monitors that are powered by AI can be leveraged to remotely detect patients with fevers. Tampa (Fla.) General Hospital is using thermal-screening face cameras to detect fevers, sweating and discoloration.
9. Gauge responses to experimental treatment: An AI model could be trained to analyze lung scans of patients enrolled in different COVID-19 clinical trials.