Interpretable machine learning for endometriosis classification: a rule-based approach

Saeed Anbari Moghadam, Elham Akhondzadeh Noughabi, Shahideh Jahanian Sadatmahalleh · 2026

Read Interpretable machine learning for endometriosis classification: a rule-based approach by Saeed Anbari Moghadam, Elham Akhondzadeh Noughabi, Shahideh Jahanian Sadatmahalleh (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/PMC13479425.txt.

Description

Saeed Anbari Moghadam, Elham Akhondzadeh Noughabi, and Shahideh Jahanian Sadatmahalleh present a 2026 study building a rule-based model that doctors can read, for sorting endometriosis cases. Endometriosis, where womb-like tissue grows outside the uterus, causes pelvic pain and trouble having children, yet naming it is slow. Earlier forecast models relied on opaque math that doctors cannot inspect or use at the bedside.

The team instead built plain rules from patient data, sorted by disease stage. Rules state their terms in plain if-then form, so a doctor can see exactly which findings drive each call. The authors argue this openness matters more than small gains in hit rate, because doctors must explain decisions to patients. Stage-by-stage rules also fit how the illness looks at each phase.

Catalog record

CREATORSaeed Anbari Moghadam, Elham Akhondzadeh Noughabi, Shahideh Jahanian Sadatmahalleh
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE73156
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13479425

Browse the full library · About the Tower of Babel