Two logistic models for the prediction of hypothyroidism in pregnancy

Abstract

Abstract Background The mounting evidence linking hypothyroidism during pregnancy with poor pregnancy outcome underscores the need for screening and, therefore, a search for more reliable and cheaper screening methods. Methods The study was conducted in two phases. The phase one study comprised of healthy women in different stages of pregnancy who attended routine antenatal clinic at St Theresa's Maternity Hospital, Enugu, Nigeria from September 6 to October 18 1994. In this study the variables compared between the hypothyroid and non-hypothyroid pregnant women were maternal age, the number of the pregnancy or gravidity, gestational age, social class, body weight, height, the clinically assessed size of the thyroid gland, serum free thyroxin (FT4) and serum thyrotrophin (TSH). Based on the parameter differences between the two comparison groups of pregnant women two Logistic models, Model I and Model 11, were derived to differentiate the hypothyroid group from their non-hypothyroid counterparts. The two logistic models were then applied in a prospective validation study involving 197 pregnant women seen at presentation in Mother of Christ Specialist Hospital and Maternity, Ogui Road, Enugu from March 2002 to November 2007 Findings The findings were that 82 (50.3%) of the 163 pregnant women had thyroid gland enlargement while 60 (36.8%) had hypothyroidism as defined by FT4 values below and/or TSH above their laboratory reference ranges. The pregnant subjects with hypothyroidism, compared with their non-hypothyroid counterparts, were characterized by a higher gravidity (p < 0.01), a higher body weight (p < 0.01), a higher goiter prevalence rate (p < 0.01) and a more advanced gestational age (p < 0.0001). A significant, positive correlation was also found between body weight and gestational age (r = 0.5; p < 0.01) At the cut-off point for Model l (fitted with gravidity, thyroid size and gestational age) it had a sensitivity of 100%, a specificity of 72.8% and an overall predictive accuracy of 82.9%; whereas for Model II (fitted with gravidity, thyroid size and body weight) the sensitivity was 100%, the specificity was 59.2% and the overall accuracy of discrimination was 74.8%. In the prospective validation study both models showed a sensitivity of 100% each with specificities of 85.5% for Model I and 76.2% for Model II. Conclusion It is concluded that logistic models fitting gravidity, thyroid gland size and gestational age or body weight are useful alternatives in screening for hypothyroidism during pregnancy. There is, however, a need for further independent confirmation of these findings.