Moravian Academy junior is helping harness artificial intelligence to spot COVID-19 – lehighvalleylive.com

Moravian Academy junior is helping harness artificial intelligence to spot COVID-19 – lehighvalleylive.com

Mikail Jaffer is about to start his junior year at Moravian Academy, and isn’t yet sure what he wants to pursue after graduation.

But one thing that’s clear is he isn’t afraid to set his sights high.

Jaffer, 16 and from the Allentown area, is working with a Plano, Texas-based company called CovidScan.AI on harnessing the power of artificial intelligence to diagnose COVID-19, the illness caused by the novel coronavirus.

He grew up in the biopharmaceutical industry by way of his mother and father, Fatima and Gulam Jaffer, who own Yourway, “an integrated biopharmaceutical supply chain solutions provider” based in Upper Macungie Township.

A classmate introduced him to the CovidScan company, and he jumped at the opportunity.

“Basically I came in and helped come up with different ideas to help develop the program and make it more friendly to the user and give more data or insight to doctors or radiologists,” he told lehighvalleylive.com.

Moravian Academy junior is helping harness artificial intelligence to spot COVID-19

Mikail Jaffer, a rising junior at Moravian Academy, is inset against a file photo of a traditional method of analyzing chest X-rays. He is working with a company called CovidScan.AI to develop an artificial intelligence program for diagnosing COVID-19 based on chest X-ray images.Courtesy photo/NJ Advance Media file photo

The idea is to run chest X-ray images through the artificial intelligence program to quickly determine whether the patient has COVID-19 or some other lung disorder, or is normal. It’s trained on thousands of images and designed to be incorporated into traditional health care digital systems for widespread use, said Moksh Nirvaan, head of AI development for the company.

The program’s overall accuracy rate is running around 96%, which breaks down to near 99% for COVID-19 cases, 95% for non-coronavirus ailments and 92% for normal diagnoses, Nirvaan said in a telephone interview from Plano.

The effort won a cash prize for second place in a Facebook Hackathon earlier this year.

This type of technology shows promise, particularly for areas with too few physicians or radiologists, the National Institutes of Health said in a research publication focused on “Chest X-ray Analysis using Machine Intelligence Research for HIV/TB Screening.”

Advances in machine learning and artificial intelligence techniques offer a promise to supplement rapid, accurate, and reliable computer-assisted disease screening,” the NIH says. “Such techniques are particularly valuable in overburdened and/or resource constrained regions. These regions also tend to exhibit high prevalence of infectious diseases and report high mortality.”

CovidScan.ai has been in the works since April, when the founders realized the unprecedented strain COVID-19 was placing on the health care system, Nirvaan said.

Plans are to partner with five to 10 clinics to begin validating the program as early as September or October before bringing it to market, he said.

Jaffer has been helpful “from a business standpoint for scalability” and efforts to get the program into use, according to Nirvaan.

“My idea was, how could I help to advance this technology while also bringing it to market,” Jaffer said.

Globally, as of Friday, there have been 22,536,278 confirmed cases of COVID-19, including 789,197 deaths, reported to the World Health Organization. The United States from Jan. 20 to Friday has seen 5,477,305 confirmed cases of COVID-19 with 172,033 deaths, according to the WHO.

Our journalism needs your support. Please subscribe today to lehighvalleylive.com.

Kurt Bresswein may be reached at kbresswein@lehighvalleylive.com.

Source

Leave a Reply

%d bloggers like this: