Medha Gupta sometimes felt worried making the 20-minute walk from the corner where the school bus dropped her off to her home in Herndon, Virginia—especially during the colder months in winter.

Her mother, Divya Gupta had a ________: write an app. She was half-kidding, but Medha took the challenge ________. So she went to work.

The result was Safe Travel, an app ________ by Medha to help walkers feel more ________ when travelling alone. Using the iPhone, a person can programme it to send a warning to someone he or she trusts if he or she ________ to arrive at a destination within a certain time.

It was the first IOS app that Medha had created. While she didn’t think much would come from the project, her ________ caught the eye of judges for the annual Congressional App Challenge, who selected her as the winner for Virginia’s 10th District.

The App Challenge is designed to encourage ________ to consider careers in science, technology, engineering, and maths by ________ coding and computer science. Winning students are ________ to attend a reception on Capitol Hill in April and also received $ 250 in Amazon Web Service credits.

Medha said it took her about 40 hours to design, ________ and test the app. As for her next app, Medha’s not certain. She ________ has her app-development tasks on hold because she’s ________ teaching herself AI to help deal with improper words on Facebook. Yes, she knows that there are teams of ________ probably doing the same thing. But she ________ it can’t hurt her own part, too.

“If we see something ________ with the world, we should do something about it,” she said. “After all, the only one stopping us from doing something is ourselves.”

When Matthew Shifrin turned 13, he got a life-changing birthday present from his friend, Lilya Finkel.

It was an 843-piece Middle Easten _______ palace. And with it were instructions that Finkel made _______for it. Finkel invented a unique name for every piece in the palace set. Then she spent countless hours typing building _______ in Braille (盲文) that spelled out how to _______ them all together.

His mind was _______. As a blind person, he had never before been able to complete a Lego set on his own, Shifrin knew immediately that he had to help other blind children find the same _______.

Shifrin says, “For blind people, Lego sets act as small 3D_______ for real-life buildings instead of two-dimensional photographs. Lego bricks allow me to see things that are _______ to explore by touch.”

For years after that incredible Lego experience, he created similar instructions for about 45 other Lego sets, together with Finkel, all published on a website they created, “Lego for the _______”.

Shifrin began ________ to Lego several years ago to discuss his work, ________ it was in 2017, when Finkel died of cancer, that he finally connected with the right person.

His years-long devotion ________ when the Lego company released its first audio and Braille building instructions. The project is a high-tech version of what Shifrin and Finkel did for their ________.

It couldn’t have been completed without Shifrin’s ________ or without his determination.

He just wished Finkel had been here to see it. “I think she’d be very glad that we came this ________,” Shifrin said.

Face shape lets AI spot rare disorders

People with genetic syndromes (综合征) sometimes have revealing facial features, but using them to make a quick and cheap diagnosis can be _______given there are hundreds of possible conditions they may have. A new neural (神经系统) network that analyses photographs of faces can help doctors _______the possibilities.

Yaron Gurovich at biotechnology firm FDNA in Boston and his team built a neural network to look at the overall impression of faces and _______ a list of the 10 genetic syndromes a person is most likely to have.

They _______ the neural network, called DeepGestalt, on 17,000 images correctly labeled to match more than 200 genetic syndromes.The team then asked AI to _______potential genetic disorders from a further 502 photos of people with such conditions. It included the correct answer among its list of 10 responses 91 per cent of the time.

Gurovich and his team also_______the neural network's ability to distinguish between the different genetic mutations (父异) that can lead to the same syndrome.They used photographs of people with Noonan syndrome, which can result from mutations in any one of five genes.DeepGestalt correctly identified the genetic source of the physical appearance 64 per cent of the time. It’s clearly not _______, but it’s still much better than humans are at trying to do this.

As the system makes its assessments, the facial regions that are most helpful in the determination are_______and made available for doctors to view. This helps them to understand the relationships between genetic make-up and physical appearance.

The fact that the diagnosis is based on a simple photograph raises questions about_______. If faces can reveal details about genetics, then employers and insurance providers could, in principle,__________ use such techniques to__________ against people who have a high probability of having certain disorders.__________. Gurovich says the tool will only be __________for use by clinicians.

This technique could bring significant__________ for those who have genetic syndromes. The real value here is that for some of these ultra-rare diseases, the process of diagnosis can be many, many years. This kind of technology can help narrow down the search space and then be confirmed through checking genetic markers. For some diseases, it will cut down the time to diagnosis dramatically. For others, it could perhaps add means of finding other people with the disease and, __________, help find new treatments or cures.