Algorithmic fairness in AI-based fitness advice: evaluating socioeconomic bias in county-contextualized physical activity prescriptions
Hegui Bao, Tianle Yu, Junyue Wang, Han Yin, Yuan Gao, Yong Mao · 2026
Read Algorithmic fairness in AI-based fitness advice: evaluating socioeconomic bias in county-contextualized physical activity prescriptions by Hegui Bao, Tianle Yu, Junyue Wang, Han Yin, Yuan Gao, Yong Mao (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13553809.txt.
Description
Chatbots can give fitness advice to anyone, but their tips may quietly assume money, cars, or a nearby gym. Hegui Bao and co-authors audit that bias in a 2026 study. They pair fake patient profiles with county data on wealth and health, then grade the advice by its hidden access cost.
Prompts that flagged access cut the cost gap between rich and poor counties by more than half. Re-ranking answers kept that gain and matched activity guidelines better. Other weightings kept the same order of results. Each model in a three-model panel bent in its own way. The team offers the audit as a fair, open check for health bots.
Catalog record
| CREATOR | Hegui Bao, Tianle Yu, Junyue Wang, Han Yin, Yuan Gao, Yong Mao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 55 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |