AI has had some interesting use cases in recent years, such as researchers attempt to use it to optimize the flow of people through the emergency department of a hospital.  The researchers developed a model that translates predictions on the arrival of patients into the emergency room into a better process for dealing with those numbers.

At the moment, hospitals often use congestion data, with ambulances instructed to divert to another facility once an existing facility is too over-loaded.  The authors suggest that this can be improved significantly by using predictive data so that hospital staff can predict when that congestion might occur rather than reacting to it when it does.  By doing this, hospitals can divert patients before load becomes excessive, and thus reduce waiting times for patients.

“These delays can have significant, life-changing ramifications,” the authors explained. “These are the kinds of changes that potentially could affect all of us.”

Improving performance

New research from Cornell University attempts to perform a similar trick with food banks to improve the distribution and allocation of food among the facility’s patrons.

“In order to serve thousands of people and combat food insecurity, our algorithm helps food banks manage their food resources more efficiently – and patrons get more nutrition,” the researchers say.

The researchers gathered data from the Food Bank of the Southern Tier, which serves six counties in upstate New York.  It had distributed nearly 11 million meals during 2019, with around 21,700 people served each week.  Of these, roughly 19% are seniors, with 41% children.

They were able to distribute nearly 3 million pounds of fresh fruit in that time, with the help of 157 partner agencies, while also distributing 3.4 million pounds of food through local mobile pantries.

The algorithm was designed to determine how the food bank could allocate various different food categories efficiently based upon the needs of each pantry.  The algorithm was able to improve efficiency by 7.73%, with a 3% improvement in nutrition also achieved.

“We hope our research is used as a baseline model for food banks improving practices,” the researchers conclude. “And boosting nutrition and policies to help people at risk for hunger.”