Calling existing case data "retrospective and incomplete," the company said the map identifies populations likely to experience severe outcomes once infected.
In an effort to help flatten the curve in the coronavirus pandemic, clinical AI startup Jvion has launched the COVID Community Vulnerability Map, a free, publicly available tool that identifies populations—down to the census block level—that are likely to experience severe outcomes requiring hospitalization if they contract the virus.
The map integrates the findings of the data analysis project Jvion conducted during the last week of March, which focused on a representative sample of two million patients to understand the social and clinical risk drivers that make populations more vulnerable to viral infections like COVID-19.
The map also identifies the social determinants of health (SDOH) that drive risk for the community in question. In previous pandemics such as H1N1 in 2009, SDOH contributed to worse outcomes among socioeconomically disadvantaged populations, Jvion said.
The COVID Community Vulnerability Map was built on Microsoft Azure maps. It aims to arm healthcare providers and community leaders with insights to reduce disparities driven by SDOH and prevent severe cases of COVID-19 by more effectively allocating resources and deploying interventions, the company said.
"The interactive map identifies populations down to the census block level that are at risk for severe outcomes upon contracting a virus like COVID," Jvion said in a statement. "Severe outcomes" include hospitalization, organ failure, and mortality, the company said.
"Additionally, the map surfaces the socioeconomic and environmental factors, such as lack of access to transportation or nutritious food, that put patients at greater risk," the company said. "The map is also overlaid with points of interest, such as hospitals, food sources and transportation, in relation to the at-risk communities."
These insights can help inform providers, public health organizations and community support agencies as they look to deploy interventions, outreach, and other services to keep individuals from contracting the virus and, once infected, manage their care towards a positive outcome, Jvion said.
With more than 10,000 cases in the United States, there is a growing concern that healthcare systems could soon be overwhelmed, underscoring the need for proactive action to ensure the most vulnerable patients have access to care, the company said.
"However, the existing COVID case data is retrospective and incomplete, minimizing the value for public health officials, healthcare providers and other community organizations hoping to stem the outbreak and prioritize care for the most vulnerable patients," according to the company.
While there is not yet enough data from the pandemic for a COVID-specific risk calculation, Jvion said officials were able to leverage the health data of 30 million patients already accounted for in its AI core. Using such a large dataset minimizes the risk of bias, the company asserted. The data does not reveal personal information.
Of this data, Jvion looked at a representative sample to understand the risk drivers for similar viruses that can lead to acute respiratory illness and organ failure, such as influenza. The analysis identified disparities in risk between different patient populations, as well as the socioeconomic and environmental factors driving that risk, Jvion said. These insights have been applied to the COVID Community Vulnerability Map, the company said.
The map can quickly help local health departments prioritize their limited resources for response planning and adapt their tactics to the needs of neighborhoods and communities, Jvion said. By understanding the differentiated needs within their population, health systems can more adequately plan for healthcare utilization, deploy preventive or mitigating care resources, and anticipate the short-, mid- and long-term impacts of public health decisions, such as school and business closures, according to Jvion.
"We are tremendously grateful for the thousands of healthcare workers on the frontlines of the battle against COVID," said Shantanu Nigam, CEO and founder of Jvion, in a statement. "Their courage and rapid mobilization in the face of the greatest public health threat of our time has been incredibly inspiring. We are working around the clock to provide them with data-driven insights to help them protect the most vulnerable members of their communities."
- How to become a data scientist: A cheat sheet (TechRepublic)
- 60 ways to get the most value from your big data initiatives (free PDF) (TechRepublic download)
- Feature comparison: Data analytics software, and services (TechRepublic Premium)
- Volume, velocity, and variety: Understanding the three V's of big data (ZDNet)
- Best cloud services for small businesses (CNET)
- Big Data: More must-read coverage (TechRepublic on Flipboard)