Story Search Results

Advanced Search

There are so many ways to search the solutions journalism stories in this database. Explore our searchable fields:

Search Results

You searched for: -

There are 73 results for your search. View and Refine Your Search Terms

Can We Build Less Biased Medical Bots?

Tolu Olasoji

April 11, 2022 |

Reasons to be Cheerful |

Text |

1500-3000 Words

Response Location: United States, Baltimore, Maryland

Melalogic is an app that provides skin health resources to people with dark skin. The uses crowdsourced imaging data to confront racial bias in diagnostic artificial intelligence. Users can access the Black Skin Resource Center with information on 14 issues that affect people with darker skin. The app also shares health posters that physicians use to share information with their patients and videos with dermatologic tips. In the works is Melalogic 2.0, an immersive telehealth experience.

Read More
Go to Original Story
The ‘AI-Powered Midwife' Helping Pregnant Nigerian Women and Newborns Stay Healthy

Innocent Eteng

January 24, 2022 |

Nigeria Health Watch |

Text |

800-1500 Words

Response Location: Nigeria, Lagos State

Encouraged by her own pregnancy experience, medical technology expert Abisola Oladapo worked with two of her colleagues to create Sister Agnes. It is an AI system that delivers periodic, timely information to pregnant women by calls and texts in local languages to empower them with information about their health. 79 percent of the women who used the service delivered in health centers, were four times more likely to survive the pregnancy, and the survival rate of their children was 33 percent higher than the national average.

Read More
Go to Original Story
How Social Media Fact-Checking Limits, But Can't Eliminate, Online Disinformation

William Newlin Fabian Munive Lora Yordanova Mack Brown

May 20, 2021 |

Grady Newsource |

Text |

800-1500 Words

Response Location: United States

Social media companies are using artificial intelligence to help identify misinformation. Once identified, human fact checkers will verify the posts. Facebook uses 60 partnered fact-checking organizations as well as SimSearchNet++ image-recognition system that can identify image manipulation and slight changes to misinformation. Hundreds of millions of posts are flagged every year and those that are identified as “false” or “altered” are labeled with warnings and distribution is reduced.

Read More
Go to Original Story
Treetop sensors help Indonesia eavesdrop on forests to cut logging

Harry Jacques

February 11, 2021 |

Thomson Reuters Foundation |

Text |

800-1500 Words

Response Location: Indonesia, Solok, West Sumatra

In Indonesia, there are 27 “Guardian” sensors eavesdropping on forests as a way to monitor them for cases of illegal logging. The organization Rainforest Connection uses artificial intelligence to analyze the audio from these sensors and if the system picks up the sound of a chainsaw, it sends a mobile alert to community patrols in the area. This technology can be scaled for other parts of the world and habitats. “We're basically building a nervous system for the natural world," says Topher White, founder of the nonprofit.

Read More
Go to Original Story
These Doctors Are Using AI to Screen for Breast Cancer

Will Knight

January 27, 2021 |

Wired |

Text |

800-1500 Words

Response Location: United States, Massachusetts

With many women skipping routine mammograms due to COVID-19 restrictions, doctors at Massachusetts General Hospital are using an artificial intelligence algorithm to identify those at risk for developing breast cancer. The approach has proved successful in multiple instances, with those flagged by the algorithm three times as likely to develop cancer. “What the AI tools are doing is they're extracting information that my eye and my brain can't,” a doctor using the tool explained.

Read More
Go to Original Story
An Algorithm Is Helping a Community Detect Lead Pipes

Sidney Fussell

January 14, 2021 |

Wired |

Text |

1500-3000 Words

Response Location: United States, Flint, Michigan

BlueConduit, an analytics startup, applies statistical models to identify neighborhoods and households that might have lead pipes. The models include dozens of factors, such as the age of the home and proximity of other homes where lead has been found, to help predict likely locations of lead pipes and create a ranking by likelihood that cities can use to prioritize which pipes to examine. In Flint, MI, about 70% of the homes identified using the models had lead pipes, compared to about 15% of homes where excavations did not use the model. The company is working with organizations in dozens of other cities.

Read More
Go to Original Story
The Newest Weapon Against Covid-19: AI That Speed-Reads Faxes

Tom Simonite

December 22, 2020 |

Wired |

Text |

800-1500 Words

Response Location: United States, Contra Costa County, California

Researchers from Stanford University have developed a software that uses machine-learning algorithms to identify and flag urgent faxes about COVID-19 cases. While the project doesn't have complete accuracy, it has helped overwhelmed and overburdened health care workers at the health department in Contra Costa County, California work more efficiently.

Read More
Go to Original Story
A Clever Strategy to Distribute Covid Aid—With Satellite Data

Tom Simonite

December 17, 2020 |

Wired |

Text |

1500-3000 Words

Response Location: Togo

To quickly distribute money to poverty-stricken areas in Togo during the coronavirus pandemic, the country's government turned to mobile cash payments. Working with a nonprofit and UC Berkeley’s Center for Effective Global Action, Togo established a system of mobile payments to reach 30,000 of Togo’s poorest people who were identified via satellite imagery and image analysis algorithms.

Read More
Go to Original Story
Can an Algorithm Prevent Suicide?

Benedict Carey

November 23, 2020 |

The New York Times |

Text |

1500-3000 Words

Response Location: United States

Veterans Affairs' Reach Vet program uses an algorithm weighing 61 factors to flag veterans deemed at highest risk of suicide. While its results have not been shown to affect the suicide rate, it has more than doubled high-risk veterans' uses of V.A. services and been associated with a lower overall mortality rate. Built on an analysis of thousands of previous suicides in the V.A.'s system, Reach Vet assesses scores of facts from medical records, including some that are not obvious to humans trying to spot problems. Doctors then intervene and ensure the veteran has a suicide safety plan in place.

Read More
Go to Original Story
How to prevent drowning

Claire Bates

September 22, 2020 |

BBC |

Podcast |

Over 15 Minutes

Response Location: Israel

Three projects show how effective national strategies can be to reduce accidental drownings, which kill an estimated 320,000 people worldwide each year. In Israel, artificial intelligence software processes video feeds from beaches to alert lifeguards to emergencies. The three African nations sharing Lake Victoria have invested in inexpensive weather forecasting gear and public information services to alert people who fish or traverse the lake. And Bangladesh's systems of daycare and swimming lessons are saving the lives of previously unsupervised children at highest risk of drowning.

Read More
Go to Original Story