Artificial Intelligence in the Diagnosis and Understanding of Primary Dysmenorrhea and Endometriosis: Emerging Insights and Clinical Implications

Prerana Sakharwade, Bibin Kurian, Amar Taksande, Bharat Rathi, Achita Sawarkar
In: 2025 3rd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry (IDICAIHEI) · 2025 · pp. 1–6 · doi:10.1109/idicaihei65991.2025.11379307 · W7131102071
article OA: closed CC0
View on OpenAlex View at publisher
⚙ AI-generated summary by gemini-2.5-flash-lite, 2026-07-09 ⓘ

AI, using models like SVM, XGBoost, and NLP, shows potential for improved diagnosis and understanding of endometriosis and primary dysmenorrhea, though challenges in data, interpretability, and clinical acceptance remain.

One-sentence paraphrase of the abstract; not a substitute for reading it. No clinical advice. How this works

Abstract

Menstrual illnesses, in particular, endometriosis and primary dysmenorrhea (PD) are highly prevalent yet largely ignored conditions that produce significant adverse productivity and quality of life changes. Traditional methods of diagnosis largely depend on the symptoms presented by the patient thus leading to underreporting, delay in diagnosis, and misdiagnosis. The recent advancements in the field of artificial intelligence (AI) have offered new opportunities to improve the accuracy of diagnosis and the understanding of the causes of the disease. One machine learning model that has demonstrated great performance in distinguishing between individuals with the Parkinson disease (PD) and healthy individuals is support vector machines (SVM) which is a model that uses neuroimaging to identify patterns of individuals brain competence. Like this, AI-based solutions, such as ensemble models such as extreme gradient boosting (XGBoost) and natural language processing (NLP) have been shown to have the potential to forecast the risk of endometriosis and discover therapeutically relevant data. Although these developments are promising with earlier and more accurate diagnosis, there are still problems with the heterogeneity of data, small sample sizes, model interpretability and acceptance in clinical settings. To ensure equal accessibility and the ability to apply in practice, the implementation of AI in gynecological care requires careful validation, interdisciplinary collaboration, and ethics.

My notes (saved in your browser only)

Condition tags

endometriosisdysmenorrhea

Citation neighborhood (sparse)

Too few in-corpus citations on either side for a chart; here are the lists.

Cites (3)

References (13)

Source provenance

openalex
last seen: 2026-06-10T17:14:06.276822+00:00
License: CC0 · commercial use OK