Search research articles

Search research articles

Related Experiment Video

Updated: Jun 12, 2026

Platform for Quantitative Detection of Endometrial Immune Cells Based on Immunohistochemistry and Digital Image Analysis

Platform for Quantitative Detection of Endometrial Immune Cells Based on Immunohistochemistry and Digital Image Analysis

Published on: October 13, 2023

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

Saeed Anbari Moghadam¹, Elham Akhondzadeh Noughabi², Shahideh Jahanian Sadatmahalleh³

¹Department of Industrial and Systems Engineering, Tarbiat Modares University, Tehran, Iran.

BMC Medical Informatics and Decision Making

|June 11, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Adjunctive effects of apple cider vinegar on metabolic syndrome and insulin resistance in polycystic ovary syndrome patients receiving metformin: a randomized clinical trial.

Scientific reports·2026

Same author

The effect of hormonal contraceptives combined with vitamin D3 supplements on sexual dysfunction in women with polycystic ovary syndrome: a randomized double-blind placebo-controlled trial.

Archives of gynecology and obstetrics·2025

Same author

Efficacy of garlic (Allium sativum) on metabolic syndrome components in women with polycystic ovary syndrome: randomized controlled trial.

Journal of health, population, and nutrition·2025

Same author

The association between the follicular distribution pattern of polycystic ovaries and metabolic syndrome development in patients with polycystic ovary syndrome a prospective cohort study.

Scientific reports·2025

Same author

'The disease ruined my life': a qualitative study of the quality of life in women with uterine fibroids.

Quality of life research : an international journal of quality of life aspects of treatment, care and rehabilitation·2024

Same author

Psychological Predictors of Sexual Quality of Life Among Iranian Women With Vaginismus: A Cross-Sectional Study.

International journal of sexual health : official journal of the World Association for Sexual Health·2024

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

This study introduces a rule-based model to interpret endometriosis clinical data, offering clear diagnostic rules for better patient management. The model aids healthcare professionals in understanding and diagnosing endometriosis more effectively.

Area of Science:

Gynecology
Medical Informatics
Computational Biology

Background:

Endometriosis is a chronic gynecological disease with significant health impacts, yet current predictive models lack clinical interpretability.
Existing research often overlooks specific patient subsets or limited disease stages, creating knowledge gaps in comprehensive understanding.
Predictive modeling for endometriosis faces limitations due to complex, non-interpretable algorithms hindering clinical application.

Purpose of the Study:

To address limitations in current endometriosis predictive models by employing a rule-based approach.
To develop interpretable and actionable diagnostic rules for endometriosis using clinical data across all disease stages.
To empower healthcare professionals with enhanced understanding, diagnosis, and management strategies for endometriosis.

Keywords:

CN2 Endometriosis Interpretability Machine learning Rule-based model

More Related Videos

Establishment of an Experimental Mouse Model of Endometrioma to Study its Related Infertility

Establishment of an Experimental Mouse Model of Endometrioma to Study its Related Infertility

Published on: April 5, 2024

Related Experiment Videos

Last Updated: Jun 12, 2026

Platform for Quantitative Detection of Endometrial Immune Cells Based on Immunohistochemistry and Digital Image Analysis

Platform for Quantitative Detection of Endometrial Immune Cells Based on Immunohistochemistry and Digital Image Analysis

Published on: October 13, 2023

Establishment of an Experimental Mouse Model of Endometrioma to Study its Related Infertility

Establishment of an Experimental Mouse Model of Endometrioma to Study its Related Infertility

Published on: April 5, 2024

Main Methods:

A CN2 rule induction algorithm was applied to 1,489 patient records with 52 clinical variables.
Clinical data underwent preprocessing, including handling missing values, feature selection, and variable standardization.
Model performance was assessed using accuracy, F1-score, precision, recall, and AUC, with rules validated by clinical experts.

Main Results:

The CN2 model achieved 0.803 classification accuracy and an AUC of 0.906 for binary classification.
For multi-class classification of endometriosis stages, the model yielded an average AUC of 0.705.
Key predictive factors identified include pelvic pain, dysmenorrhea, dyspareunia, severe bleeding, tumor markers, age, and BMI.

Conclusions:

The CN2 rule induction model effectively bridges knowledge gaps by providing interpretable diagnostic rules for endometriosis.
Integrating this model into clinical practice can enhance diagnostic precision and reduce delays.
The interpretable rules offer potential strategies for improved endometriosis treatment and patient outcomes.