ATR-FTIR Spectroscopy Integrated with Machine Learning: A New Method for Classification of Two Similar Gynecological Disorders

Imon Mitra, Abhijit Saha, Pratip Chakraborty, Sunita Sharma, Koel Chaudhury
In: 2025 1st IEEE Uttar Pradesh Section Women in Engineering International Conference on Electrical Electronics and Computer Engineering (UPWIECON) · 2025 · pp. 595–600 · doi:10.1109/upwiecon67212.2025.11390468 · W7131083743
article OA: closed CC0
View on OpenAlex View at publisher
⚙ AI-generated summary by claude@2026-06, 2026-06-08 ⓘ

Attenuated total reflectance Fourier transform infrared (ATR-FTIR) spectroscopy combined with a support vector machine model achieved 90.3% accuracy in distinguishing adenomyosis from endometriosis.

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

Abstract

Adenomyosis and endometriosis are two similar benign uterine diseases exhibiting symptoms of chronic pain, heavy menstrual bleeding and infertility. Both these conditions are common in the Indian population and affect the quality of life in women considerably. Adenomyosis remains under-explored as compared to endometriosis; yet this condition is associated with poor fertility outcome. We hypothesize that Fourier transform infrared (FTIR) spectral peaks corresponding to the biochemical signatures of adenomyosis and endometriosis may be used to generate a robust classification model for distinguishing between the two diseases. Herein, we have applied multivariate statistical methods and machine learning algorithms on FTIR spectroscopic data generated from endometrial tissue of adenomyosis, endometriosis along with controls. The supervised multivariate model, principal component analysis - linear discriminant analysis (PCA-LDA) showed good separation between the groups. Further, Support Vector Machine (SVM) demonstrated the best performance and outperformed other models in discriminating between adenomyosis and endometriosis with 90.3% accuracy and area under the curve (AUC) value of 0.96.

My notes (saved in your browser only)

Condition tags

endometriosisadenomyosisinfertility

Citation neighborhood (sparse)

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

Cites (3)

References (14)

Source provenance

openalex
last seen: 2026-06-04T00:00:01.174412+00:00
License: CC0 · commercial use OK