Cluster Analysis: A New Approach for Identification of Underlying Risk Factors and Demographic Features of First Trimester Pregnancy Women

Abstract

Thyroid pathology is reported internationally in 5–10% of all pregnancies. The overall aim of this research was to determine the prevalence of hypothyroidism and risk factors during the first trimester screening in a Mexican patients sample. We included the records of 306 patients who attended a prenatal control consultation between January 2016 and December 2017 at the Women’s Institute in Monterrey, Mexico. The studied sample had homogeneous demographic characteristics in terms of age, weight, height, BMI (body mass index) and number of pregnancies. The presence of at least one of the risk factors for thyroid disease was observed in 39.2% of the sample. Two and three clusters were identified, in which patients varied considerably among risk factors, symptoms and pregnancy complications. Compared to Cluster 0, one or more symptoms or signs of hypothyroidism occurred, while Cluster 1 was characterized by healthier patients. When three clusters were used, Cluster 2 had a higher TSH (thyroid stimulating hormone) value and pregnancy complications. There were no significant differences in perinatal variables. In addition, high TSH levels in first trimester pregnancy are characterized by pregnancy complications and decreased newborn weight. Our findings underline the high degree of disease heterogeneity with existing pregnant hypothyroid patients and the need to improve the phenotyping of the syndrome in the Mexican population.

Resultados de un registro prospectivo de pacientes con desórdenes hipertensivos del embarazo en un centro de la Ciudad de Buenos Aires

“…(16-18) Los métodos de screening actuales identifican pobremente a las mujeres con riesgo de padecer DHE; particularmente aquellas que desarrollarán PE tardía. Para la PEp el índice de detección es del 82%, y del 53% para la PEt (ecografía obstétrica con translucencia nucal plus) (17,18). En nuestro registro el 38,1% de las pacientes que desarrollaron un DHE tenían prescripta esta droga como profilaxis; solo el 33,3% de las mujeres que desarrollaron PEt, el 50% de las que desarrollaron PEp, y el 60% de las que desarrollaron PESI.…”

“…Se reconoce al hipotiroidismo como una patología frecuente en las mujeres, que puede presentarse entre un 0,3 a un 2,5% de las embarazadas. (19) En nuestro registro el 24,3% padecía hipotiroidismo, lo que permite suponer una relación entre ambas patologías, y una hipótesis a futuro para evaluar métodos de screening más precisos (17,18).…”

Introduction to Machine Learning in Obstetrics and Gynecology

“…In obstetrics and gynecology, cluster analysis was applied to a data set from a large trial of women in the first trimester of pregnancy to identify risk factors for thyroid profile phenotype. 6 Reinforcement learning is a type of machine learning that focuses on taking actions or making decisions through specific situations. The concept of "reinforcement" uses right actions to reward and wrong actions to penalize the algorithm, with the ultimate objective of achieving a certain goal without human intervention.…”

Study the Correlation between the Mother-To-Child Transmission Risk Factors in Chronic Hepatitis B Virus Infection Pregnant Women in Vietnam by HCA Method

“…The number of clusters must be determined ahead of time and submitted as a parameter to the k-means algorithm. 6 We use 20 methods to describe to clustering of these subclinical parameters. They measures the quality of a clustering.…”

“…We set up a Clustering study to find the possible link between HBV infection in pregnant women and cord blood in order to give a clinical reference marker for prenatal surveillance and postnatal management, as well as to enhance the prevention of HBV MTCT Clustering is a machine learning approach for identifying subgroups of homogeneous individuals who share characteristics with other groups or clusters 3,4 . Clustering is used in the medical field for image processing, document classification, and group building although it is required to handle the interaction of multiple variables 5,6 A single link between the subclinical index and pregnancy has been shown in several research. There are some of the categories discovered in the pregnancy-related literature, for example: Hypertension 7,8 , preeclampsia 9,10 , fetal growth restriction 11 , miscarriage 12 , the incidence of pregnancy termination linked to demographics 13 , nutritional and birth control related to mother education, cleanliness, and nutrients 14 .…”