FairCareNLP: An AI-driven patient review analyzer for healthcare

Sayyed Mohammad Pourya Momtaz Esfahani, Davey Seeman, Christoffer Dharma, Mohammad Noaeen, Shion Guha, Zahra Shakeri · 2026

Read FairCareNLP: An AI-driven patient review analyzer for healthcare by Sayyed Mohammad Pourya Momtaz Esfahani, Davey Seeman, Christoffer Dharma, Mohammad Noaeen, Shion Guha, Zahra Shakeri (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/plos-pone-0337676.txt.

Description

Sayyed Mohammad Pourya Momtaz Esfahani and co-authors built FairCareNLP, a system that reads written patient reviews and sorts them by sentiment and theme while actively fighting bias. Hospitals mine such comments to improve care, but standard language models can treat patients unfairly depending on gender, ethnicity, or income. Their 2026 system pairs language models with three different debiasing techniques.

One popular method, adversarial training, actually hurt accuracy across the board. Two others, which scrub bias from word representations, improved fairness scores while keeping performance intact. The best configuration reached solid accuracy and fairer treatment of gender in particular. The authors note that ethnicity and income bias remain harder to remove.

Catalog record

CREATORSayyed Mohammad Pourya Momtaz Esfahani, Davey Seeman, Christoffer Dharma, Mohammad Noaeen, Shion Guha, Zahra Shakeri
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE82491
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0337676

Browse the full library · About the Tower of Babel