[Thyroid dysfunction]

A class-imbalanced hybrid learning strategy based on Raman spectroscopy of serum samples for the diagnosis of hepatitis B, hepatitis A, and thyroid dysfunction

Computer-aided vibrational spectroscopy detection technology has achieved promising results in the field of early disease diagnosis. Yet limited by factors such as the number of actual samples and the cost of spectral acquisition in clinical medicine, the data available for model training are insufficient, and the amount of data varies greatly between different diseases, which constrain the performance optimization and enhancement of the diagnostic model. In this study, vibrational spectroscopy data of three common diseases are selected as research objects, and experimental research is conducted around the class imbalance situation that exists in medical data. When dealing with the challenge of class imbalance in medical vibrational spectroscopy research, it no longer relies on some kind of independent and single method, but considers the combined effect of multiple strategies. SVM, K-Nearest Neighbor (KNN), and Decision Tree (DT) are used as baseline comparison models on Raman spectroscopy medical datasets with different imbalance rates. The performance of the three strategies, Ensemble Learning, Feature Extraction, and Resampling, is verified on the class imbalance dataset by G-mean and AUC metrics, respectively. The results show that all the above three methods mitigate the negative impact caused by unbalanced learning. Based on this, we propose a hybrid ensemble classifier (HEC) that integrates resampling, feature extraction, and ensemble learning to verify the effectiveness of the hybrid learning strategy in solving the class imbalance problem. The G-mean and AUC values of the HEC method are 82.7 % and 83.12 % for the HBV dataset, is 2.02 % and 1.98 % higher than the optimal strategy; 83.62 % and 83.76 % for the HCV dataset, is 9.79 % and 8.47 % higher than the optimal strategy; while for the thyroid dysfunction dataset are 77.56 % and 77.85 %, is 6.92 % and 6.36 % higher than that of the optimal strategy, respectively. The experimental results show that the G-mean and AUC metrics of the HEC method are higher than those of the baseline classifier as well as the optimal combination using separate strategies. It can be seen that the HEC method can effectively counteract the unfavorable effects of imbalance learning and is expected to be applied to a wider range of imbalance scenarios.

The role of the thyroid in polycystic ovary syndrome

Polycystic ovary syndrome (PCOS) is the most common endocrine and metabolic disease in women of childbearing age and can cause metabolic disorder, infertility, and increased anxiety and depression; as a result, it can seriously affect the physical and mental health of fertile women. PCOS is a highly clinically heterogeneous disease with unclear etiology and pathogenesis, which increases the difficulty of treatment. The thyroid gland has complex regulatory effects on metabolism, reproduction, and emotion, and produces hormones that act on almost all cells of the human body. The clinical manifestations of PCOS are similar to some thyroid diseases. Furthermore, some thyroid diseases, such as subclinical hypothyroidism (SCH), not only increase the incidence rate of PCOS, but also exacerbate its associated metabolic abnormalities and reproductive disorders. Interestingly, PCOS also increases the incidence of some thyroid diseases. However, the role of the thyroid in PCOS remains unclear. This review is intended to thoroughly explore the critical role of the thyroid in PCOS by summarizing the comorbidity of PCOS and thyroid diseases and their combined role in metabolic disorders, related metabolic diseases, and reproductive disorders; and by analyzing the potential mechanism through which the thyroid influences the development and progression of PCOS and its symptoms. We hope this review will provide a valuable reference for the role of the thyroid in PCOS.

Hypothyroidism-Induced Nonalcoholic Fatty Liver Disease (HIN): Mechanisms and Emerging Therapeutic Options

Nonalcoholic fatty liver disease (NAFLD) is an emerging worldwide problem and its association with other metabolic pathologies has been one of the main research topics in the last decade. The aim of this review article is to provide an up-to-date correlation between hypothyroidism and NAFLD. We followed evidence regarding epidemiological impact, immunopathogenesis, thyroid hormone-liver axis, lipid and cholesterol metabolism, insulin resistance, oxidative stress, and inflammation. After evaluating the influence of thyroid hormone imbalance on liver structure and function, the latest studies have focused on developing new therapeutic strategies. Thyroid hormones (THs) along with their metabolites and thyroid hormone receptor β (THR-β) agonist are the main therapeutic targets. Other liver specific analogs and alternative treatments have been tested in the last few years as potential NAFLD therapy. Finally, we concluded that further research is necessary as well as the need for an extensive evaluation of thyroid function in NAFLD/NASH patients, aiming for better management and outcome.

Relationship between Hypothyroidism and Non-Alcoholic Fatty Liver Disease: A Systematic Review and Meta-analysis

BACKGROUND

Previous studies propose that hypothyroidism might play a crucial role in the pathogenesis of non-alcoholic fatty liver disease (NAFLD), but findings from published studies on the relationship between hypothyroidism and NAFLD are still controversial. Our study aimed to make a comprehensive evaluation of the relationship between hypothyroidism and NAFLD through a meta-analysis.

METHODS

PubMed, China Dissertation Database, and EMBASE databases were searched to find observational studies assessing the relationship between hypothyroidism and NAFLD. The pooled odds ratios (ORs) with 95% confidence intervals (95% CIs) were calculated to evaluate the strength of the relationship between hypothyroidism and NAFLD through meta-analysis.

RESULTS

Thirteen articles were ultimately included in our meta-analysis. Meta-analysis of the 13 studies found a high correlation between hypothyroidism and NAFLD (OR = 1.52, 95% CI 1.24-1.87, P < 0.001). Meta-analysis of 9 studies providing adjusted ORs found that hypothyroidism was independently correlated with NAFLD (OR = 1.72, 95% CI 1.32-2.23, P < 0.001). Subgroup analysis found that both overt hypothyroidism and subclinical hypothyroidism were significantly correlated with NAFLD, and the pooled ORs were 1.70 (95% CI 1.23-2.36, P = 0.002) and 1.40 (95% CI 1.10-1.77, P = 0.006), respectively. Besides, meta-analysis of studies providing adjusted ORs also found that both overt hypothyroidism and subclinical hypothyroidism were independently correlated with NAFLD, and the pooled ORs were 1.81 (95% CI 1.30-2.52, P < 0.001) and 1.63 (95% CI 1.19-2.24, P = 0.002), respectively.

CONCLUSION

The meta-analysis provides strong epidemiological evidence for the relationship between hypothyroidism and NAFLD. Both individuals with subclinical and overt hypothyroidism are at higher risk for NAFLD than euthyroid subjects.