Quality of life identification by unsupervised cluster analysis: A new approach to modelling the burden of endometriosis

Abstract

Background Symptoms frequently associated with endometriosis affect quality of life (QoL). Our aim investigated the hypothesis that cluster analysis can be used to identify homogeneous phenotyping subgroups of women according to the burden of the endometriosis for their QoL, and then to investigate the phenotype differences observed between these subgroups. Methods We developed an anonymous online survey, which received responses from 1,586 French women with endometriosis. K‐means, a major clustering algorithm, was performed to show structure in data and divide women into groups based on the burden of endometriosis. This was defined using 9 dimensions. Multivariable logistic regression was performed to highlight the association between QoL and several factors. Covariables were age, BMI, smoking, education, children, marital status and surgery. Results K‐means clustering was implemented with 8 clusters (optimal CCC value of 17.2162). In one cluster, women presented a high level of QoL and represented 234 women for 60% of women with a high level of QoL, and another with 410 women for 34% of women with worse QoL. Independent factors determining high QoL were age (over 45 years compared to below 25 years, OR = 0.17 [0.07–0.46], p<0.001), BMI (high vs low, OR = 0.47 [0.28–0.80], p = 0.005), having children (OR = 0.30 [0.18–0.48], p<0.001), having surgery for endometriosis (OR = 0.55 [0.32–0.94], p = 0.029), and education (high vs low, OR = 2.75 [1.75–4.31], p<0.001) Conclusion Cluster analysis identifies homogeneous women phenotypes for QoL with endometriosis. Implementing new methodological approaches improves QoL of endometriosis women and allows appropriate preventive strategies.