Artificial Intelligence has emerged as a powerful tool in the time to fight against Covid-19. The technology is used to train computers to leverage big data-enabled models for pattern recognition, interpretation, and prediction using Machine Learning, NLP and Computer Vision. These applications can be effective to diagnose, envision, and treat Covid-19 disease, and they can also assist in managing socio-economic impacts. Since the pandemic spreads quickly, there has been a rush to explore and deploy AI to cure and address the soaring demand of patient treatment infected by Coronavirus.
In this regard, Partners HealthCare, a Boston-based non-profit hospital and physician network, had conducted a chat through the hotline for patients, clinicians, and others with questions and concerns about Covid-19. The purpose behind this is to identify and reassure the people who don’t need additional care, as well as to direct people with less serious symptoms to germane information and virtual care options. The hospital also focused on directing the smaller number of high-risk and higher-acuity patients to the most appropriate resources, such as testing sites, newly created respiratory illness clinics, or emergency departments in certain cases.
However, as the hotline became overwhelmed, many callers couldn’t speak with the expert team of nurses staffing the hotline, and the hospital missed opportunities to facilitate pre-hospital triage to get the patient to the right care setting at the right time.
Led by Lee Schwamm, Haipeng (Mark) Zhang, and Adam Landman, the Partners HealthCare team started looking out technology options to address the growing need for patient self-triage, and turned to leverage interactive voice response systems and chatbots. The AI-powered technology has significantly delivered its potential, enabling patients with a series of questions based on content from the U.S. Centers for Disease Control and Prevention (CDC) and Partners HealthCare experts.
AI to Identify Covid-19 on Chest Scans
Besides, many companies around the world have now announced a number of AI-enabled systems to detect Covid-19 on chest CT or X-ray scans. These deep learning tools are already used in hospitals to screen mild cases, triage new infections, and keep an eye on advancing disease. In the analysis of chest scans, artificial intelligence has the ability to ease the overload from radiologists who review and prioritize a large number of patient chest scans on a daily basis. In the coming years, industry experts believe, the technology might assist in predicting the patients who are most likely to require medication.
While diagnosing Covid-19 from chest scans, RADLogics, a healthcare IT company providing a data analytics platform for medical imaging, reports up to 98 percent accuracy, which indicates that these AI tools will supersede standard nucleic acid tests as the primary diagnostic tool for coronavirus infection.
AI-Based Initiatives Across the Sector
There are many governments and hospital systems around the world using AI-driven sensors to support triage in sophisticated ways. In this way, Chinese technology giant Baidu has built a no-contact infrared sensor system that can quickly recognize individuals with a fever, even in crowds. In the same way, Tampa General Hospital in Florida has deployed an AI system, in association with Care.ai, at its entrances to capture individuals with potential symptoms of Covid-19. By positioning cameras at entrances, the technology escorts a facial thermal scan and distinguishes other symptoms, such as sweat and discoloration, to thwart visitors with fever.
Apart from this, China’s Zhongnan Hospital utilizes an AI-powered CT scan interpreter to identify Covid-19 when radiologists aren’t available. Moreover, Wuhan Wuchang Hospital in the country has also developed a smart field hospital staffed largely by robots, which deliver medicine and food to patients, limiting physician exposure to the virus.