ABSTRACT
CONTEXT: Thyroid-stimulating hormone (TSH) trajectory classification represents a novel approach to defining the adequacy of levothyroxine (LT4) treatment for hypothyroidism over time. OBJECTIVE: This is a proof of principle study that uses longitudinal clinical data, including thyroid hormone levels from a large prospective study to define classes of TSH trajectories and examine changes in cardiovascular (CV) health markers over the study period. METHODS: Growth mixture modeling (GMM), including latent class growth analysis (LCGA), was used to classify LT4-treated individuals participating in the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil) based on serial TSH levels. Repeated measure analyses were then utilized to assess within-class changes in blood pressure, lipid levels, hemoglobin A1c, and CV-related medication utilization. RESULTS: From the 621 LT4-treated study participants, the best-fit GMM approach identified 4 TSH trajectory classes, as defined by their relationship to the normal TSH range: (1) high-high normal TSH, (2) normal TSH, (3) normal to low TSH, and (4) low to normal TSH. Notably, the average baseline LT4 dose was lowest in the high-high normal TSH group (77.7â µg, P < .001). There were no significant differences in CV health markers between the classes at baseline. At least 1 significant difference in CV markers occurred in all classes, highlighted by the low to normal class, in which total and high-density lipoprotein cholesterol, triglycerides, and A1c all increased significantly (P = .049, P < .001, P < .001, and P = .001, respectively). Utilization of antihypertensive, antihyperlipidemic, and antidiabetes medications increased in all classes. CONCLUSION: GMM/LCGA represents a viable approach to define and examine LT4 treatment by TSH trajectory. More comprehensive datasets should allow for more complex trajectory modeling and analysis of clinical outcome differences between trajectory classes.