Importance of thyroid-stimulating hormone levels in liver disease

Evaluation of MELD Scores and Thyroid Hormones as Prognostic Factors of Liver Cirrhosis

Background and Objectives: Hepatic cirrhosis is a disease with an increasing frequency globally, but its mechanisms of disease development are not yet completely known. The aim of this study was to evaluate the relationship between thyroid hormone levels (T3, fT4, and TSH) and survival in patients with chronic liver disease. Materials and Methods: A total of 419 patients diagnosed with liver cirrhosis were included in the study. The MELD score was computed, and TSH, T3, and fT4 were collected from each patient using the ELISA procedure. Signs and symptoms of liver failure and portal hypertension confirmed the clinical diagnosis of liver cirrhosis, and biological tests and imaging methods confirmed the diagnosis. Results: The MELD score was positively associated with TSH on admission and TSH on discharge and negatively associated with T3 at discharge. TSH levels were higher in non-survivors than in survivors. The values of T3 and fT4 present no significant changes to be considered as prognostic factors. Conclusions: Although the differences between the median TSH values of the patients who died and those who survived are not very large, the statistical significance of the data obtained demonstrates that there are changes in metabolism of the thyroid hormones during the progression of liver cirrhosis. It is possible that TSH is the one which maintains the normal balance of thyroid activity for patients with liver cirrhosis, so it can be considered as an important marker of evolution of these patients.

Analysis of epidemiological association patterns of serum thyrotropin by combining random forests and Bayesian networks

BACKGROUND

Approaching epidemiological data with flexible machine learning algorithms is of great value for understanding disease-specific association patterns. However, it can be difficult to correctly extract and understand those patterns due to the lack of model interpretability.

METHOD

We here propose a machine learning workflow that combines random forests with Bayesian network surrogate models to allow for a deeper level of interpretation of complex association patterns. We first evaluate the proposed workflow on synthetic data. We then apply it to data from the large population-based Study of Health in Pomerania (SHIP). Based on this combination, we discover and interpret broad patterns of individual serum TSH concentrations, an important marker of thyroid functionality.

RESULTS

Evaluations using simulated data show that feature associations can be correctly recovered by combining random forests and Bayesian networks. The presented model achieves predictive accuracy that is similar to state-of-the-art models (root mean square error of 0.66, mean absolute error of 0.55, coefficient of determination of R2 = 0.15). We identify 62 relevant features from the final random forest model, ranging from general health variables over dietary and genetic factors to physiological, hematological and hemostasis parameters. The Bayesian network model is used to put these features into context and make the black-box random forest model more understandable.

CONCLUSION

We demonstrate that the combination of random forest and Bayesian network analysis is helpful to reveal and interpret broad association patterns of individual TSH concentrations. The discovered patterns are in line with state-of-the-art literature. They may be useful for future thyroid research and improved dosing of therapeutics.

Non-Alcoholic Fatty Liver Disease and Hypothyroidism: Review of Clinical and Experimental Studies

Hypothyroidism is a widespread condition affecting people of different socio-economic background and geographical location. A lot of studies highlight the effect of hypothyroidism on the metabolic processes in various organs, including the liver. On the other hand, liver damage often results in the development of non-alcoholic fatty liver disease; however, the data on the impact of hypothyroidism on liver morphology, which can serve as a direct indicator and marker of liver condition and function, are limited and controversial. In this report, we reviewed the relationship between non-alcoholic fatty liver disease and hypothyroidism with an accent on morphological alteration of the liver discovered in clinical and experimental studies.