A machine-assisted framework for systematic error analysis in clinical concept extraction
Sunyang Fu, Qiuhao Lu, Jaerong Ahn, Fang Chen, Hanyun Yin, Julia Wen, Zhiyi Yue, Taylor Harrison, Jiang Jun, Xiaoyang Ruan, Ming Huang, Andrew Wen, Liwei Wang, Min Ji Kwak, Nahid Rianon, Yanshan Wang, Ruihong Huang, Hongfang Liu · 2026
Read A machine-assisted framework for systematic error analysis in clinical concept extraction by Sunyang Fu, Qiuhao Lu, Jaerong Ahn, Fang Chen, Hanyun Yin, Julia Wen, Zhiyi Yue, Taylor Harrison, Jiang Jun, Xiaoyang Ruan, Ming Huang, Andrew Wen, Liwei Wang, Min Ji Kwak, Nahid Rianon, Yanshan Wang, Ruihong Huang, Hongfang Liu (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-13612481.txt.
Description
Sunyang Fu and a large team of co-authors present a tool from 2026 for sorting errors made by software that pulls key facts from doctor notes. Such tools help research and care, but they fail in varied ways. Until now there was no shared, step by step way to study those failures.
Their tool, called MedError, pairs a tested list of error types with help from large language models and a clear human review flow. It was built from close to twelve hundred errors found in notes from three sites. Tests showed that machine sorting alone is not enough without human checks. Feedback from the tool also lifted fact pulling scores a lot over a plain work flow.
Catalog record
| CREATOR | Sunyang Fu, Qiuhao Lu, Jaerong Ahn, Fang Chen, Hanyun Yin, Julia Wen, Zhiyi Yue, Taylor Harrison, Jiang Jun, Xiaoyang Ruan, Ming Huang, Andrew Wen, Liwei Wang, Min Ji Kwak, Nahid Rianon, Yanshan Wang, Ruihong Huang, Hongfang Liu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 71 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |