Abstract

Chronic endometritis (CE) is one of the causes of impaired fertility, disorders of menstrual function, formation of pelvic pain, and for peri- and postmenopausal patients it serves as the background for the development of a number of proliferative diseases. Objective. Application of the method of cluster analysis of clinical data on patients with chronic endometritis. Patients and methods. The clinical data on 257 patients were analyzed according to a specially developed program. For feature clustering, distance measurement was performed by the Manhattan distance method (city-block distance) using Ward's algorithm. Results. The use of cluster analysis made it possible to group the clinical, anamnestic and laboratory features of CE and their distribution into homogeneous groups or clusters. Seven clusters were obtained. Conclusion. The widespread use of statistical analysis methods, in particular the use of clustering method, made it possible to demonstrate clinically significant combinations of disease features in a group of patients, the analysis of each cluster demonstrated a number of cause-effect relationships and allowed to evaluate the clinical and anamnestic data on CE patients from a different perspective. Key words: clustering, feature combinations, treatment, chronic endometritis

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call