December 25, 2024

Ferrum College : Iron Blade Online

Complete Canadian News World

A Manhattan high school student creates an amazingly accurate AI algorithm that predicts the resources needed for 911 calls.

A Manhattan high school student creates an amazingly accurate AI algorithm that predicts the resources needed for 911 calls.

subway

Exclusive

A Manhattan high school student designed an artificial intelligence algorithm to help 911 callers get the help they actually need, which in turn will reduce response times and ultimately save cities millions, he told The Post.

Pierce Wright, a 17-year-old senior at Browning School in Manhattan, said his sophisticated model could help emergency dispatchers, for example, by predicting when a caller is having a mental health episode.

“If the algorithm says, ‘I think this is a mental health call,’ you can send a psychiatrist or mental health professional with EMS staff to assist the patient and provide the most appropriate care” — rather than just rushing police to the scene. Wright said in an interview Wednesday.

Pierce Wright, 17, has created an artificial intelligence model that correctly predicts the type of resources required on a given 911 call. Gabriella Bass

“It saves time for the patient, but also for the city,” he said. “It is also able to free the ambulance much faster.”

To design the algorithm, Wright combined his experience as an EMS worker with his prowess in data science.

He spent the past year coding the AI, then training it using nearly two decades of statistics drawn from New York City's massive online database of about 24 million emergency calls.

His work has paid off, he says, because his model can predict what resources will be needed based solely on factors such as the zip code of the incoming call, the time of day, the police district, and the initial risk level.

Kicker? He said the model had an impressive success rate of 94.5%, 2.2% higher than its human counterparts.

Wright has already won several awards for this model, which he says is correct 94.5% of the time. Gabriella Bass
He said the model could ultimately improve responses and save millions from cities. Gabriella Bass

“You need very little input from the actual caller,” Wright said as he sat at a table in his family's Upper East Side dining room, which overlooks Park Avenue.

“You can really say, ‘This is what it looks like.’ And the 911 operator has the zip code, the police district, the time of day, etc. They put it all in there, and in a few seconds, the model spits out what it thinks the call will be at.” The accuracy range is approximately 94%.

“It basically predicts…what it thinks the call is going to be,” the teen said. “Accordingly, you can send the appropriate response.”

The model is 2.2% more accurate than human senders, Wright said. Gabriella Bass

Wright said he was inspired to create the program after receiving calls on his own shifts as a volunteer EMS worker in Westport, Connecticut.

Too often, he said, crews were sent to respond to what turned out to be a mental health or substance abuse call — not the true medical emergencies for which they were trained.

It's also not helpful to the patient, who is often brought to the local emergency room and left to suffer.

“This does not save care for the patient, and it wastes city resources,” he said, adding that his model would help eliminate patients “waiting in the hospital just to be let out.”

Wright is also a volunteer emergency medical responder in Westport, Connecticut. Gabriella Bass
The adaptable model could be used for mental health calls or a variety of other things, he said. Gabriella Bass

Wright's mother, Melanie, marveled at her son's ability to put in the enormous amount of work needed to create the model.

“I was like, ‘I just hope it works out,’” she said, laughing. “Because I would hate for him to feel like he spent all this time on something and it didn’t work out!”

“But it was so exciting — seeing those lightbulb moments where he was going to have a breakthrough,” she added. “This would take it to the next stage.”

Wright said his software could also be used for other types of emergency calls — for example, if the model believes the victim has suffered trauma, it can prepare to send a paramedic instead of just EMTs.

However, the program's creator was quick to say that the program is intended to help senders, not replace them.

But one day — by making it more customizable and accessible to the average person — the model could save cities millions of dollars and dramatically reduce response times.

Wright at the TerraNYC STEM Fair, where he won first place for his project in medicine and health sciences. Wright family

The impressive project — which took about 200 hours to complete — has earned the hard-working teen several accolades, including a first-place award at the TerraNYC STEM Fair at NYU's Tandon School of Engineering on April 7 and a second-place award at the New York State Science and Engineering Fair in Queens .

It could be linked to his future career – although he's not sure what that will be yet.

Wright said he would eventually like to work in either public health, computer science, or a combination of both.

“Whatever I decide to do, I'm really looking forward to being able to create something that can help people,” he said.

“That's definitely my goal.”

filed under

911
,

artificial intelligence
,

computer science
,

Data
,

emergency
,

ems
,

Exclusive
,

Manhattan
,

students
,

Upper East Side
,
04/17/24

Load more…




https://nypost.com/2024/04/17/us-news/manhattan-high-schooler-creates-astoundingly-accurate-ai-algorithm-that-predicts-resources-needed-for-911-calls/?utm_source =url_sitebuttons&utm_medium=site%20buttons&utm_campaign=site%20buttons

Copy the share URL