Health groups and researchers in Peru and Argentina are using artificial intelligence to expand sexual and reproductive health information for young and marginalised people. Several projects aim to reduce barriers caused by language, stigma and limited services.
In Peru, obstetrician Ana Miluzka Baca Gamarra developed TeleNanu, a Quechua-language chatbot at the University of San Martín de Porres. TeleNanu uses generative AI and a five-step counselling model. Midwives trained the system with World Health Organization and Peru Ministry of Health guidelines, peer-reviewed literature and professional knowledge. The platform gives evidence-based answers and can recommend human counselling.
TeleNanu handled more than 88,000 queries in the last year in Quechua and Spanish. In October, the non-profit APROPO launched NOA on WhatsApp, the web and social media; it was trained with local and international data and aims to reach 100,000 adolescents by 2026. Public health data note rising HIV cases, many births to mothers aged ten to 19, and increasing adolescent maternal mortality. Experts warn about access, biased data and the need for oversight and coordination. Researchers in Argentina found stigmatising responses in large language models and are working to reduce bias and involve communities in design.
Difficult words
- reproductive — related to having children and body functions
- stigma — negative social attitudes or shame about something
- counselling — professional advice to help with personal problems
- oversight — official supervision to ensure rules are followed
- biased — showing unfair preference or a negative view
- adolescent — a young person between childhood and adulthoodadolescents
Tip: hover, focus or tap highlighted words in the article to see quick definitions while you read or listen.
Discussion questions
- Do you think chatbots can help young people ask about sexual health? Why or why not?
- What are possible problems if the data used to train AI are biased?
- How could communities be involved when researchers design health chatbots?
Related articles
People learn to use robotic leg prostheses but misjudge their gait
A four-day study found that people who practised with a robotic lower‑limb prosthesis improved their walking but misjudged their own movement. Researchers say better visual feedback could help users calibrate their body image and gait.
Forest loss in tropics raises local heat and deaths
A study using satellite data found that tropical deforestation from 2001–2020 exposed 345 million people to local warming and likely caused about 28,000 heat-related deaths per year, mainly in Africa, Southeast Asia and Latin America.
Yale reveals molecular structure of cholera flagella
Yale researchers imaged the molecular structure of Vibrio cholerae flagella in living bacteria. The study shows how flagella proteins sit inside a hydrophilic sheath and suggests the sheath helps the bacterium move and infect cells.