New COVID Local Risk Index Helps Cities Identify Neighborhoods at Highest Risk for COVID and Better Target Resources to Blunt Local Pandemic Impact

A new city-oriented COVID Local Risk Index will help municipal leaders identify cities and neighborhoods with populations at higher risk of COVID-19 infection and more severe COVID-19 illness by incorporating key risk factors of race and ethnicity, age, household crowding, poverty and underlying health conditions like diabetes and obesity.

Read more

Calibrated approach to AI and deep learning models could more reliably diagnose and treat disease

In a recent preprint (available through Cornell University’s open access website arXiv), a team led by a Lawrence Livermore National Laboratory computer scientist proposes a novel deep learning approach aimed at improving the reliability of classifier models designed for predicting disease types from diagnostic images, with an additional goal of enabling interpretability by a medical expert without sacrificing accuracy. The approach uses a concept called confidence calibration, which systematically adjusts the model’s predictions to match the human expert’s expectations in the real world.

Read more

FORECASTING URBANIZATION

A new global simulation model offers the first long-term look at how urbanization—the growth of cities and towns—will unfold in the coming decades. Using data science and machine learning, the research team projects the total amount of urban areas on Earth can grow anywhere from 1.8 to 5.9-fold by 2100, building approximately 618,000 square miles.

Read more

Researchers work on early warning system for COVID-19

To better understand early signs of coronavirus and the virus’ spread, physicians around the country and data scientists at UC San Diego are working together to use a wearable device to monitor more than 12,000 people, including thousands of healthcare workers. The effort has started at hospitals in the San Francisco Bay Area and at the University of West Virginia.

Read more