AFP: New tool predicts risk of Covid hospitalisation, death

AFP:New tool predicts risk of Covid hospitalisation, death. “The five percent of people in Britain predicted by a new tool to be at highest risk from Covid-19 accounted for three-quarters of deaths during the first wave of the pandemic, researchers reported Wednesday. As countries worldwide grapple with a second wave of disease, the risk-assessment method — which also predicts the chances of hospitalisation — could help identify the small percentage of the population most in need of being shielded from the virus, they reported in BMJ, a medical journal.”

Penn State: Building a landslide prediction tool with Google and AI

Penn State: Building a landslide prediction tool with Google and AI. “Worldwide, landslides cause thousands of deaths and injuries and cost billions of dollars each year, according to the United States Geological Survey (USGS). The most frequent of these are induced by rainfall, often transforming into fast-moving debris flows like the Montecito, California mudslides in 2018.”

The Harvard Crimson: HMS Researchers Develop New Tool for Early Detection of Local-Level COVID-19 Outbreaks

The Harvard Crimson: HMS Researchers Develop New Tool for Early Detection of Local-Level COVID-19 Outbreaks. “The COVID-19 Outbreak Detection Tool — which was developed in partnership with researchers at Massachusetts General Hospital, Georgia Tech, and Boston Medical Center — includes an interactive map dashboard that color codes counties by predicted COVID-19 case count doubling time. The tool also includes a ‘data explorer’ table which can sort counties by a variety of relevant parameters, such as 14-day new case trends or average daily cases in the past week.”

Stony Brook Statesman: SBU researchers use social media to study unhealthy drinking habits

Stony Brook Statesman: SBU researchers use social media to study unhealthy drinking habits. “The study, in collaboration with professors from the University of Pennsylvania, is led by H. Andrew Schwartz, assistant professor of computer science at Stony Brook University. Schwartz’s team is trying to develop an artificial intelligence (AI) program that can scan social media data and use the recorded information to understand the users’ habits in order to predict their future behavior. In this case, the team is focusing on the ability to understand how mood and environment lead to unhealthy drinking behavior. Such behavior is defined as 14 drinks in a single week for a man, or seven drinks for a woman.”

CanIndia News: Google expands AI-driven flood forecast to all of India, Bangladesh

CanIndia News: Google expands AI-driven flood forecast to all of India, Bangladesh. “As floods wreak havoc in South Asian countries, Google on Tuesday said it is expanding its Artificial Intelligence (AI)-powered flood forecasting to all of India and Bangladesh that will provide greater details on timing and water depths in alerts in nine new local languages.”

New York Times: Can an Algorithm Predict the Pandemic’s Next Moves?

New York Times: Can an Algorithm Predict the Pandemic’s Next Moves?. “Judging when to tighten, or loosen, the local economy has become the world’s most consequential guessing game, and each policymaker has his or her own instincts and benchmarks. The point when hospitals reach 70 percent capacity is a red flag, for instance; so are upticks in coronavirus case counts and deaths. But as the governors of states like Florida, California and Texas have learned in recent days, such benchmarks make for a poor alarm system.”

EurekAlert: Researchers use machine learning to build COVID-19 predictions

EurekAlert: Researchers use machine learning to build COVID-19 predictions. ” As parts of the U.S. tentatively reopen amid the COVID-19 pandemic, the nation’s long-term health continues to depend on tracking the virus and predicting where it might surge next. Finding the right computer models can be tricky, but two researchers at Binghamton University, State University of New York believe they have an innovative way to solve those problems, and they are sharing their work online. Using data collected from around the world by Johns Hopkins University, Arti Ramesh and Anand Seetharam — both assistant professors in the Department of Computer Science — have built several prediction models that take advantage of artificial intelligence. Assisting the research is PhD student Raushan Raj.”

Twitter Blog: Using data from the conversation on Twitter to help detect wildfires

Twitter Blog: Using data from the conversation on Twitter to help detect wildfires. “This wildfire season, Mayday.ai is set to combine data from the unfolding conversation on Twitter with its proprietary incident detection system, which is based on satellite sensors, an array of 35,000 traffic cameras, and IP911 to power a comprehensive detection and a highly targeted notification tracker. Mayday.ai has developed a comprehensive dispatch platform and a mobile app which will provide first responders and civilians unprecedented access to real-time incident information — and has so far had much success in detecting wildfires using its proprietary platform and is being used as a template for other disasters in Mayday’s roadmap.”

EurekAlert: New COVID-19 tool warns relaxing rules may increase deaths

EurekAlert: New COVID-19 tool warns relaxing rules may increase deaths. “A new tool designed to help state and local officials estimate the effects of social distancing and other public health interventions used to combat the COVID-19 pandemic has been released by the nonprofit, nonpartisan RAND Corporation. The free tool combines information from both epidemiological and economic models to estimate the effects of five different disease-fighting portfolios on public health metrics such as disease transmission and economic consequences such as gross state income.”

Cornell Chronicle: Weill Cornell doctor creates epidemic modeling tool

Cornell Chronicle: Weill Cornell doctor creates epidemic modeling tool. “Using a tool he created called the Cornell COVID Caseload Calculator C5V, Dr. Nathaniel Hupert, associate professor of population health sciences and of medicine at Weill Cornell Medicine, has been making forecasts of the potential impact of COVID-19 on local and regional health care systems. The data helps state and city leaders answer questions related to when cases of the disease will peak in hospitals and what resources will be needed to successfully care for those patients.”

Sydney Morning Herald: New database to predict which Sydney suburbs could have restrictions eased

Sydney Morning Herald: New database to predict which Sydney suburbs could have restrictions eased. “A new database could be the key to determining in which suburbs the NSW government could relax its social distancing measures and where to exercise greater control to curb the spread of the coronavirus. The interactive dashboard created by University of Sydney researchers combines NSW Health and ABS data to identify the neighbourhoods most vulnerable to outbreaks: postcodes with a high proportion of people

WAVY: ODU center launches COVID-19 prediction tool online

WAVY: ODU center launches COVID-19 prediction tool online. This is for Virginia only. “The Virginia Modeling, Analysis and Simulation Center produced the tool to give predictions about the virus’ spread and give a daily tally of COVID-19 symptom tweets. The online tool also includes age ranges and hospitalization outcomes forecasts, other COVID-19 modeling resources, and more.”

Washington Post: A leading model now estimates tens of thousands fewer covid-19 deaths by summer

Washington Post: A leading model now estimates tens of thousands fewer covid-19 deaths by summer. “The Post reported last week that Washington, D.C., is relying on a separate model offering a starkly different picture for how the virus will affect the district. At the time, IHME saw the peak number of deaths arriving in mid-April. The D.C. model, developed by Penn Medicine, estimates the peak will come in late June. That variance is a function of the difficulty of modeling the pandemic, something FiveThirtyEight explored last month. Models should get more accurate as the actual peak approaches — though identifying when the peak has arrived is itself tricky, predictive models aside.”

EurekAlert: Arkansas researchers developing prediction models for coronavirus

EurekAlert: Arkansas researchers developing prediction models for coronavirus. “Data science professor Justin Zhan is collaborating with University of Arkansas for Medical Sciences professors David Ussery and Xuming Zhang to develop accurate predictions of genomic variation trends of coronavirus.”

EurekAlert: New tool exploring different paths the corona pandemic may take

EurekAlert: New tool exploring different paths the corona pandemic may take. “Umeå University in Sweden is leading a team of researchers across Europe in the development of a coronavirus simulation framework that can support decision makers to experiment and evaluate possible interventions and their combined effects, in a simulated controlled world.”