A new extended belief rule base method based on neighborhood covering reduction for diabetes diagnosis
Shucheng Feng, Wei He, Li Jiang, Manlin Chen · 2026
Read A new extended belief rule base method based on neighborhood covering reduction for diabetes diagnosis by Shucheng Feng, Wei He, Li Jiang, Manlin Chen (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-0347303.txt.
Description
Shucheng Feng, Wei He, Li Jiang, and Manlin Chen built an explainable computer system for diagnosing diabetes. Doctors face patients who differ widely, and black-box algorithms that hide their reasoning are hard to trust at the bedside. Their 2026 model instead reasons through a library of belief rules, which state in plain form how combinations of symptoms point toward a diagnosis.
To keep the rule library lean, the team first ranked which measurements matter most, then pruned redundant rules using a neighbourhood method, and finally tuned the remaining parameters with an evolutionary search. The paper walks through this construction in detail, aiming at diagnoses that are both accurate and open to inspection.
Catalog record
| CREATOR | Shucheng Feng, Wei He, Li Jiang, Manlin Chen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 58351 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |