Context: The impact of subclinical hypothyroidism (SCH) and of levothyroxine replacement in pregnant women with SCH is unclear. Objective: To assess (a) the impact of SCH during pregnancy on maternal and neonatal outcomes and (b) the effect of levothyroxine replacement therapy in these patients. Data Sources: Ovid MEDLINE In-Process & Other Non-Indexed Citations, Ovid MEDLINE, the Cochrane Controlled Trials Register, Ovid EMBASE, Web of Science, and Scopus were searched from inception to January 2015. Study selection: Randomized trials and cohort studies of pregnant women with SCH that examined adverse pregnancy and neonatal outcomes were included. Data extraction: Reviewers extracted data and assessed methodological quality in duplicate. Data synthesis: Eighteen cohort studies at low-to-moderate risk of bias were included. Compared to euthyroid pregnant women, pregnant women with SCH were at higher risk for pregnancy loss (RR 2.01, CI 1.66 to 2.44), placental abruption (RR 2.14, CI 1.23 to 3.70), premature rupture of membranes (RR 1.43, CI 1.04 to 1.95), and neonatal death (RR 2.58, CI 1.41 to 4.73). One study at high risk of bias compared pregnant women with SCH who received levothyroxine to those who did not and found no significant decrease in the rate of pregnancy loss, preterm delivery, gestational hypertension, low birth weight, or low Apgar score. Conclusions: SCH during pregnancy is associated with multiple adverse maternal and neonatal outcomes. The value of levothyroxine therapy in preventing these adverse outcomes remains uncertain.

Background: The use of artificial intelligence (AI) in health care has grown exponentially with the promise of facilitating biomedical research and enhancing diagnosis, treatment, monitoring, disease prevention, and health care delivery. We aim to examine the current state, limitations, and future directions of AI in thyroidology. Summary: AI has been explored in thyroidology since the 1990s, and currently, there is an increasing interest in applying AI to improve the care of patients with thyroid nodules (TNODs), thyroid cancer, and functional or autoimmune thyroid disease. These applications aim to automate processes, improve the accuracy and consistency of diagnosis, personalize treatment, decrease the burden for health care professionals, improve access to specialized care in areas lacking expertise, deepen the understanding of subtle pathophysiologic patterns, and accelerate the learning curve of less experienced clinicians. There are promising results for many of these applications. Yet, most are in the validation or early clinical evaluation stages. Only a few are currently adopted for risk stratification of TNODs by ultrasound and determination of the malignant nature of indeterminate TNODs by molecular testing. Challenges of the currently available AI applications include the lack of prospective and multicenter validations and utility studies, small and low diversity of training data sets, differences in data sources, lack of explainability, unclear clinical impact, inadequate stakeholder engagement, and inability to use outside of the research setting, which might limit the value of their future adoption. Conclusions: AI has the potential to improve many aspects of thyroidology; however, addressing the limitations affecting the suitability of AI interventions in thyroidology is a prerequisite to ensure that AI provides added value for patients with thyroid disease.

Background: Levothyroxine (LT4) is one of the most commonly prescribed medications. Although considered a life-long replacement therapy, LT4 therapy can be discontinued for some patients. This study aims at: (i) reviewing the evidence on clinical outcomes of patients undergoing thyroid hormone replacement discontinuation, (ii) identifying the predictors of successful discontinuation, and (iii) systematically appraising frameworks used for deprescribing thyroid hormone. Methods: We searched multiple bibliographic databases, including Ovid MEDLINE(R) and Epub Ahead of Print, In-Process & Other Non-Indexed Citations and Daily, Ovid Embase, Ovid Cochrane Central Register of Controlled Trials, Ovid Cochrane Database of Systematic Reviews, and Scopus, from inception to February 2020 for studies in which thyroid hormone replacement was discontinued. Clinical outcomes assessed included: proportion of patients that remained euthyroid or needed to restart thyroid hormone replacement after discontinuation and frequency of clinical symptoms of hypothyroidism and adverse effects. We also evaluated predictors for discontinuation and deprescribing frameworks. Reviewers (F.J.K.T., N.B., N.M.S.O., S.M.) evaluated studies for inclusion, extracted data, and assessed methodological quality independently and in duplicate. Results: Seventeen observational studies at moderate to high risk of bias met inclusion criteria, including a total of 1103 patients (86% women) with an age range of 2–81 years. Approximately a third of patients undergoing thyroid hormone discontinuation remained euthyroid at follow-up (37.2%, 95% confidence interval [CI 24.2–50.1%], I ² 97.5%). Subgroup analysis showed that patients with a previous diagnosis of overt hypothyroidism (OH) were less likely to remain euthyroid (11.8% [CI 0.4–23.2%], I ² 90.3%) than patients with a prior diagnosis of subclinical hypothyroidism (SCH) (35.6% [CI 8.2–62.9%], I ² 94.0%). No study followed a framework for systematically deprescribing LT4. Conclusions: Low-quality evidence suggests that up to a third of patients remained euthyroid after thyroid hormone discontinuation, with a higher proportion of patients with an initial diagnosis of SCH remaining euthyroid than patients with an initial diagnosis of OH. A deprescribing framework focusing on adequate selection of patients for deprescribing LT4 and a systematic process is warranted to guide clinicians in re-evaluating the need for LT4 in their patients.

Background and Objectives: Thyroid nodules are lumps of solid or liquid-filled tumors that form inside the thyroid gland, which can be malignant or benign. Our aim was to test whether the described features of the Thyroid Imaging Reporting and Data System (TI-RADS) could improve radiologists’ decision making when integrated into a computer system. In this study, we developed a computer-aided diagnosis system integrated into multiple-instance learning (MIL) that would focus on benign–malignant classification. Data were available from the Universidad Nacional de Colombia. Materials and Methods: There were 99 cases (33 Benign and 66 malignant). In this study, the median filter and image binarization were used for image pre-processing and segmentation. The grey level co-occurrence matrix (GLCM) was used to extract seven ultrasound image features. These data were divided into 87% training and 13% validation sets. We compared the support vector machine (SVM) and artificial neural network (ANN) classification algorithms based on their accuracy score, sensitivity, and specificity. The outcome measure was whether the thyroid nodule was benign or malignant. We also developed a graphic user interface (GUI) to display the image features that would help radiologists with decision making. Results: ANN and SVM achieved an accuracy of 75% and 96% respectively. SVM outperformed all the other models on all performance metrics, achieving higher accuracy, sensitivity, and specificity score. Conclusions: Our study suggests promising results from MIL in thyroid cancer detection. Further testing with external data is required before our classification model can be employed in practice.

Background: Subclinical hypothyroidism (SCH) has been associated with increased risk of adverse pregnancy outcomes in some, but not all, studies. Uncertainty remains regarding the impact of levothyroxine (LT4) therapy on improving health outcomes in pregnant women with SCH. The objective of this study was to assess the potential benefits of LT4 therapy in pregnant women with SCH. Methods: The medical records were reviewed of pregnant women with SCH, defined as an elevated serum thyrotropin (TSH) of >2.5 mIU/L for the 1st trimester or >3 mIU/L for the 2nd and 3rd trimesters, but ≤10 mIU/L. Pregnant women were divided into two groups depending on whether they received LT4 (group A) or not (group B). Pregnancy loss and other pre-specified adverse outcomes were evaluated during follow-up. Results: There were 82 women in group A and 284 in group B. Group A had a higher body mass index ( p = 0.04) and a higher serum TSH level ( p < 0.0001) compared with group B. Group A had fewer pregnancies lost ( n = 5 [6.1%] vs. n = 25 [8.8%]; p = 0.12), low birth weight (LBW) offspring (1.3% vs. 10%; p < 0.001), and no neonates with a five-minute Apgar score ≤7 (0% vs. 7%; p < 0.001) compared with group B. Other pregnancy-related adverse outcomes were similar between the two groups. Inferences remained unchanged after considering different models to adjust for potential predictors of outcome. Conclusions: LT4 therapy is associated with a decreased risk of LBW and a low Apgar score among women with SCH. This association awaits confirmation in randomized trials before the widespread use of LT4 therapy in pregnant women with SCH.

Background: The best treatment option for patients with Graves' disease (GD) depends on each person's situation and how the differences between the treatment options matter to them in bringing resolution to their illness. The objective of this study was to develop and test an encounter decision tool (GD Choice) for patients and clinicians to engage in shared decision making about the treatment of GD. Methods: GD Choice was developed using an iterative process based on the principles of interaction design and participatory action research. To evaluate the impact of the tool, a controlled before–after study was conducted, assessing the use of GD Choice versus usual care (UC). Results: Sixty-eight patients were enrolled, 37 to UC and 31 to GD Choice. At baseline, the groups were similar. Treatment discussion length was similar in both arms. After their visit, patients in both groups had similar knowledge about the options, except for GD Choice patients knowing significantly more about the complications of treatment (correctly answered by 83% vs. 55%; p = 0.04). Compared with UC, patients in the GD Choice arm had greater involvement in decision making observed on video recordings of clinical encounters (mean OPTION scale score, 35% vs. 30%; p = 0.02), but reported similar levels of decisional comfort and participation in shared decision making. Conclusions: GD Choice increases engagement in the decision-making process and knowledge regarding intervention complications without increasing the length of consultation. These promising results support the conduct of a randomized trial of GD Choice versus UC in a large multicenter trial.