CLUSTER ANALYSIS OF THE PAP SMEAR SCREENING IN THE STATE OF PARANÁ IN 2010
Palavras-chave:
Cervical Cancer, Cluster Analysis, k-meansResumo
The Uterine Cervical Neoplasm is one of the main causes of morbidity and mortality among women in Brazil and all around the world. The objective of this paper was to identify the profile of the results of cytopathological exams (Pap smears) of women aged 25 to 59 years living in 399 municipalities of the State of Paraná, Brazil, during 2010. A database was assembled using data collected in SISCOLO (Information System Cervical Cancer), which provides online information, and the cluster analysis was performed by the K-means algorithm. The analysis made it possible to divide the state into three clusters with similar characteristics between members and define the degree of neoplastic tissue injury that defines the differences. Thus, it was also possible to identify failures in the diagnosis of neoplasms and records request cytopathological exam of cervix incomplete.