Time for a reassessment of the treatment of hypothyroidism

Abstract

Background: In the treatment for hypothyroidism, a historically symptom-orientated approach has given way to reliance on a single biochemical parameter, thyroid stimulating hormone (TSH).

Main body: The historical developments and motivation leading to that decision and its potential implications are explored from pathophysiological, clinical and statistical viewpoints. An increasing frequency of hypothyroid-like complaints is noted in patients in the wake of this directional shift, together with relaxation of treatment targets. Recent prospective and retrospective studies suggested a changing pattern in patient complaints associated with recent guideline-led low-dose policies. A resulting dramatic rise has ensued in patients, expressing in various ways dissatisfaction with the standard treatment. Contributing factors may include raised problem awareness, overlap of thyroid-related complaints with numerous non-specific symptoms, and apparent deficiencies in the diagnostic process itself. Assuming that maintaining TSH anywhere within its broad reference limits may achieve a satisfactory outcome is challenged. The interrelationship between TSH, free thyroxine (FT4) and free triiodothyronine (FT3) is patient specific and highly individual. Population-based statistical analysis is therefore subject to amalgamation problems (Simpson's paradox, collider stratification bias). This invalidates group-averaged and range-bound approaches, rather demanding a subject-related statistical approach. Randomised clinical trial (RCT) outcomes may be equally distorted by intra-class clustering. Analytical distinction between an averaged versus typical outcome becomes clinically relevant, because doctors and patients are more interested in the latter. It follows that population-based diagnostic cut-offs for TSH may not be an appropriate treatment target. Studies relating TSH and thyroid hormone concentrations to adverse effects such as osteoporosis and atrial fibrillation invite similar caveats, as measuring TSH within the euthyroid range cannot substitute for FT4 and FT3 concentrations in the risk assessment. Direct markers of thyroid tissue effects and thyroid-specific quality of life instruments are required, but need methodological improvement.

Conclusion: It appears that we are witnessing a consequential historic shift in the treatment of thyroid disease, driven by over-reliance on a single laboratory parameter TSH. The focus on biochemistry rather than patient symptom relief should be re-assessed. A joint consideration together with a more personalized approach may be required to address the recent surge in patient complaint rates.

Keywords: Diagnostic strategies; Free thyroxine; Free triiodothyronine; Statistical analysis; Thyroid stimulating hormone; Thyroxine therapy; Treatment protocols, Randomised clinical trials.

Fig. 1

Relative rates of hypothyroid versus hyperthyroid complaints reported by patients followed on LT4-treatment for differentiated thyroid carcinoma in two time periods. Trends in hypothyroid and hyperthyroid complaints have reversed over the last decade, in association with relaxation of TSH-suppression, marking an important change in the treatment strategy (see text). Data are from a retrospective study involving 2309 visits of 319 patients [50]

Fig. 2

Demonstration of correlation bias by combining dissimilar groups. In randomly sampled groups showing the same strong inverse correlation (blue and red regression line) but slightly shifted centres, a combined analysis (black regression line) - unlike the correct analysis by individual groups - weakens the correlation. Distinguishing between averaged and typical outcomes is particularly important for parameters with known high individuality such as thyroid hormones