Subway
Exclusive
A Manhattan high school student has developed an artificial intelligence algorithm to help emergency callers get the help they actually need, reducing response times and ultimately saving cities millions, he told The Post.
Pierce Wright, a 17-year-old graduate of Manhattan’s Browning School, said his sophisticated model could help emergency responders by, for example, predicting when a caller is having a psychotic attack.
“If the algorithm says, ‘I believe this is a mental health call,’ you can send a psychiatrist or mental health professional along with emergency medical personnel to help the patient and provide the best possible care” — instead of sending the police to the crime scene. Wright said in an interview on Wednesday.
“It saves time for the patient, but also for the city,” he said. “It makes it possible to release the ambulance more quickly.”
To design the algorithm, Wright combined his experience as an emergency responder with his expertise in data science.
He spent the last year programming the AI ​​and then training it using nearly two decades of data culled from a massive New York City online database of nearly 24 million emergency calls.
His work was valuable, he says, because his model could predict what resources would be needed based only on factors such as an incoming call’s zip code, time of day, police district and initial risk level.
kicker? He said the model had an impressive 94.5% success rate, 2.2% higher than its human counterpart.
“You need very little input from the actual caller,” says Wright, sitting at a table in his family’s Upper East Side dining room overlooking 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. You put everything in there and within seconds the model spits out what it thinks the call is going to be.” Accuracy is about 94%.
“It basically predicts what he thinks the call is going to be,” Kishore said “Accordingly, you can send the appropriate response.”
Wright said she was inspired to create the program after receiving a call during her shift as an emergency medical services volunteer in Westport, Connecticut.
Often, he said, emergency responders were dispatched to respond to mental health or substance abuse calls — rather than the actual medical emergencies they were trained to handle.
It’s also not helpful to the patient, who is often rushed to the local emergency room and left to suffer.
“It doesn’t keep the patient out of care and doesn’t waste the city’s resources,” he said, adding that his model would help eliminate patients “waiting in the hospital to be discharged.”
Wright’s mother, Melanie, marveled at her son’s ability to put in so much work to create models.
“I was like, ‘I hope it works,'” he said with a laugh. “Because I’d hate for him to spend all this time trying to do something and it didn’t work out!”
“But it was exciting to see those aha moments where he would make a breakthrough,” he added. “This will take it to the next level.”
Wright said his software could also be used for other types of emergency calls — for example, if the model believes a victim is suffering from trauma, it can prepare to send a paramedic instead of just emergency responders.
However, the program’s creator is quick to explain that the program is intended to help senders, not replace them.
But one day the model could save cities millions of dollars and dramatically reduce response times by making it more customizable and accessible to the average citizen.
The impressive project — which took nearly 200 hours to complete — earned the hard-working teenager several awards, including a first-place trophy and a second-place trophy at the TerraNYC STEM Fair on April 7 at NYU’s Tandon School of Engineering. New York State Fair for Science and Engineering in Queens.
It could be related to his future career – although he’s not sure what that will be yet.
Wright said she eventually wants to work in public health, computer science or a combination of the two.
“Whatever I decide to do, I’m really excited to create something that can help people,” he said.
“That’s definitely my goal.”
