Thyroid Ultrasound Appropriateness Identification Through Natural Language Processing of Electronic Health Records.

Objective: To address thyroid cancer overdiagnosis, we aim to develop a natural language processing (NLP) algorithm to determine the appropriateness of thyroid ultrasounds (TUS). Patients and Methods: Between 2017 and 2021, we identified 18,000 TUS patients at Mayo Clinic and selected 628 for chart review to create a ground truth dataset based on consensus. We developed a rule-based NLP pipeline to identify TUS as appropriate TUS (aTUS) or inappropriate TUS (iTUS) using patients' clinical notes and additional meta information. In addition, we designed an abbreviated NLP pipeline (aNLP) solely focusing on labels from TUS order requisitions to facilitate deployment at other health care systems. Our dataset was split into a training set of 468 (75%) and a test set of 160 (25%), using the former for rule development and the latter for performance evaluation. Results: There were 449 (95.9%) patients identified as aTUS and 19 (4.06%) as iTUS in the training set; there are 155 (96.88%) patients identified as aTUS and 5 (3.12%) were iTUS in the test set. In the training set, the pipeline achieved a sensitivity of 0.99, specificity of 0.95, and positive predictive value of 1.0 for detecting aTUS. The testing cohort revealed a sensitivity of 0.96, specificity of 0.80, and positive predictive value of 0.99. Similar performance metrics were observed in the aNLP pipeline. Conclusion: The NLP models can accurately identify the appropriateness of a thyroid ultrasound from clinical documentation and order requisition information, a critical initial step toward evaluating the drivers and outcomes of TUS use and subsequent thyroid cancer overdiagnosis.

Social Determinants of Health and Disparities in Thyroid Care.

BACKGROUND: There have been documented racial and ethnic disparities in the care and clinical outcomes of patients with thyroid disease. CONTEXT: Key to improving disparities in thyroid care is understanding the context for racial and ethnic disparities, which includes acknowledging and addressing social determinants of health. Thyroid disease diagnosis, treatment, and survivorship care are impacted by patient- and system-level factors, including socioeconomic status and economic stability, language, education, health literacy, and health care systems and health policy. The relationship between these factors and downstream clinical outcomes is intricate and complex, underscoring the need for a multifaceted approach to mitigate these disparities. CONCLUSION: Understanding the factors that contribute to disparities in thyroid disease is critically important. There is a need for future targeted and multilevel interventions to address these disparities, while considering societal, health care, clinician, and patient perspectives.

Understanding diagnostic conversations in clinical practice: A systematic review.

OBJECTIVE: Summarize frameworks to understand diagnostic conversations and assessments of diagnostic conversations in practice. METHODS: We systematically searched MEDLINE, Scopus, Cochrane, and other databases from inception to July 2022 for reports of diagnostic conversations. Two authors independently reviewed studies for eligibility, assessed methodological quality with the mixed methods appraisal tool and extracted information related to study characteristics, frameworks and components evaluated in assessments of diagnostic conversations and results. RESULTS: Eight studies were included. One study reported an empiric framework of diagnostic conversations that included the following components: identifying the problem that requires diagnosis, obtaining information, and delivering the diagnosis and treatment plan. Thematic analyses highlighted communication between patients and clinicians as central in diagnostic conversations as it allows a) patient's presentation of their symptoms which guide subsequent diagnostic steps, b) negotiation of the significance of the patient's symptoms through conversation and c) introducing and resolving diagnostic uncertainty. CONCLUSION: Despite the importance of diagnostic conversation only one empiric framework described its components. Additionally, limited available evidence suggests patients can have an important role in the diagnostic process that expands beyond patients as an information source. PRACTICE IMPLICATIONS: Patients should be included as active partners in co-development of diagnostic plans of care.

Extracting Thyroid Nodules Characteristics from Ultrasound Reports Using Transformer-based Natural Language Processing Methods.

The ultrasound characteristics of thyroid nodules guide the evaluation of thyroid cancer in patients with thyroid nodules. However, the characteristics of thyroid nodules are often documented in clinical narratives such as ultrasound reports. Previous studies have examined natural language processing (NLP) methods in extracting a limited number of characteristics (<9) using rule-based NLP systems. In this study, a multidisciplinary team of NLP experts and thyroid specialists, identified thyroid nodule characteristics that are important for clinical care, composed annotation guidelines, developed a corpus, and compared 5 state-of-the-art transformer-based NLP methods, including BERT, RoBERTa, LongFormer, DeBERTa, and GatorTron, for extraction of thyroid nodule characteristics from ultrasound reports. Our GatorTron model, a transformer-based large language model trained using over 90 billion words of text, achieved the best strict and lenient F1-score of 0.8851 and 0.9495 for the extraction of a total number of 16 thyroid nodule characteristics, and 0.9321 for linking characteristics to nodules, outperforming other clinical transformer models. To the best of our knowledge, this is the first study to systematically categorize and apply transformer-based NLP models to extract a large number of clinical relevant thyroid nodule characteristics from ultrasound reports. This study lays ground for assessing the documentation quality of thyroid ultrasound reports and examining outcomes of patients with thyroid nodules using electronic health records.

The Future of Thyroid Nodule Risk Stratification.

Clinical evidence supports the association of ultrasound features with benign or malignant thyroid nodules and serves as the basis for sonographic stratification of thyroid nodules, according to an estimated thyroid cancer risk. Contemporary guidelines recommend management strategies according to thyroid cancer risk, thyroid nodule size, and the clinical scenario. Yet, reproducible and accurate thyroid nodule risk stratification requires expertise, time, and understanding of the weight different ultrasound features have on thyroid cancer risk. The application of artificial intelligence to overcome these limitations is promising and has the potential to improve the care of patients with thyroid nodules.

Treatment burden and perceptions of glucose-lowering therapy among people living with diabetes.

AIMS: Address treatment burden and general perceptions of pharmacological treatment in patients with diabetes. METHODS: We surveyed adult patients with diabetes cared for in a tertiary academic medical center about: i) knowledge about the impact of glucose-lowering medication use on diabetes control and complications, ii) common beliefs about natural medicine and insulin use, iii) attitudes towards glucose-lowering medications, iv) burden of treatment, v) general knowledge of diabetes pharmacological treatment, and vi) perceptions of shared decision-making. RESULTS: Two hundred-four participants completed the survey. While most (90%) agreed that adherence to medication would control diabetes and improve quality of life, 30-40% were not certain that it would translate to fewer disease complications. About one of three thought medications could be harmful (29.4%). Over 50% agreed or was unsure that natural remedies were as good/better than prescribed medications. About 30% acknowledged difficulties taking their diabetes medications and monitoring blood glucose, and over 50% were concerned about treatment costs. Nearly 30% denied receiving a detailed explanation from their clinician regarding their disease and is treatment. CONCLUSIONS: Our results highlight the importance of patient education regarding pharmacological treatment for diabetes, and eliciting sources of distress and treatment burden among patients with diabetes.

Potential Gains in Life Expectancy Associated With Achieving Treatment Goals in US Adults With Type 2 Diabetes.

Importance: Improvements in control of factors associated with diabetes risk in the US have stalled and remain suboptimal. The benefit of continually improving goal achievement has not been evaluated to date. Objective: To quantify potential gains in life expectancy (LE) among people with type 2 diabetes (T2D) associated with lowering glycated hemoglobin (HbA1c), systolic blood pressure (SBP), low-density lipoprotein cholesterol (LDL-C), and body mass index (BMI) toward optimal levels. Design, Setting, and Participants: In this decision analytical model, the Building, Relating, Assessing, and Validating Outcomes (BRAVO) diabetes microsimulation model was calibrated to a nationally representative sample of adults with T2D from the National Health and Nutrition Examination Survey (2015-2016) using their linked short-term mortality data from the National Death Index. The model was then used to conduct the simulation experiment on the study population over a lifetime. Data were analyzed from January to October 2021. Exposure: The study population was grouped into quartiles on the basis of levels of HbA1c, SBP, LDL-C, and BMI. LE gains associated with achieving better control were estimated by moving people with T2D from the current quartile of each biomarker to the lower quartiles. Main Outcomes and Measures: Life expectancy. Results: Among 421 individuals, 194 (46%) were women, and the mean (SD) age was 65.6 (8.9) years. Compared with a BMI of 41.4 (mean of the fourth quartile), lower BMIs of 24.3 (first), 28.6 (second), and 33.0 (third) were associated with 3.9, 2.9, and 2.0 additional life-years, respectively, in people with T2D. Compared with an SBP of 160.4 mm Hg (fourth), lower SBP levels of 114.1 mm Hg (first), 128.2 mm Hg (second), and 139.1 mm Hg (third) were associated with 1.9, 1.5, and 1.1 years gained in LE in people with T2D, respectively. A lower LDL-C level of 59 mg/dL (first), 84.0 mg/dL (second), and 107.0 mg/dL (third) were associated with 0.9, 0.7, and 0.5 years gain in LE, compared with LDL-C of 146.2 mg/dL (fourth). Reducing HbA1c from 9.9% (fourth) to 7.7% (third) was associated with 3.4 years gain in LE. However, a further reduction to 6.8% (second) was associated with only a mean of 0.5 years gain in LE, and from 6.8% to 5.9% (first) was not associated with LE benefit. Overall, reducing HbA1c from the fourth quartile to the first is associated with an LE gain of 3.8 years. Conclusions and Relevance: These findings can be used by clinicians to motivate patients in achieving the recommended treatment goals and to help prioritize interventions and programs to improve diabetes care in the US.

De-implementing low-value care in endocrinology.

Low-value care exposes patients to ineffective, costly, and potentially harmful care. In endocrinology, low-value care practices are common in the care of patients with highly prevalent conditions. There is an urgent need to move past the identification of these practices to an active process of de-implementation. However, clinicians, researchers, and other stakeholders might lack familiarity with the frameworks and processes that can help guide successful de-implementation. To address this gap and support the de-implementation of low-value care, we provide a summary of low-value care practices in endocrinology and a primer on the fundamentals of de-implementation science. Our goal is to increase awareness of low-value care within endocrinology and suggest a path forward for addressing low-value care using principles of de-implementation science.

Thyroid Nodule Evaluation and Management in Older Adults: A Review of Practical Considerations for Clinical Endocrinologists.

OBJECTIVE: Contextualizing the evaluation of older adults with thyroid nodules is necessary to fully understand which management strategy is the most appropriate. Our goal was to summarize available clinical evidence to provide guidance in the care of older adults with thyroid nodules and highlight special considerations for thyroid nodule evaluation and management in this population. METHODS: We conducted a literature search of PubMed and Ovid MEDLINE from January 2000 to November 2020 to identify relevant peer-reviewed articles published in English. References from the included articles as well as articles identified by the authors were also reviewed. RESULTS: The prevalence of thyroid nodules increases with age. Although thyroid nodules in older adults have a lower risk of malignancy, identified cancers are more likely to be of high-risk histology. The goals of thyroid nodule evaluation and the tools used for diagnosis are similar for older and younger patients with thyroid nodules. However, limited evidence exists regarding thyroid nodule evaluation and management to guide personalized decision making in the geriatric population. CONCLUSION: Considering patient context is significant in the diagnosis and management of thyroid nodules in older adults. When making management decisions in this population, it is essential to carefully weigh the risks and benefits of thyroid nodule diagnosis and treatment, in view of older adults' higher prevalence of high-risk thyroid cancer as well as increased risk for multimorbidity, functional and cognitive decline, and treatment complications.

Clinical features and prognosis of thymic neuroendocrine tumours associated with multiple endocrine neoplasia type 1: A single-centre study, systematic review and meta-analysis.

OBJECTIVE: Thymic neuroendocrine tumour (TH-NET) accounts for almost 20% of multiple endocrine neoplasia type 1 (MEN1)-associated mortality. Identifying risk factors for the development of these rare tumours and prognostic factors for clinical outcomes will be helpful in clinical practice. DESIGN AND PATIENTS: We performed a retrospective analysis of patients treated for TH-NET associated with MEN1 in a single institution and meta-analysis of literature reports. We used a fixed effect model to pool results across studies to evaluate the prevalence, clinical features and prognosis. RESULTS: TH-NET was detected in 9 (7.4%) of 121 patients with MEN1 seen in our institution, and 5 (55.6%) were women. Seven additional studies were identified through a systematic review of the literature. The pool estimate of TH-NET prevalence was 3.7% (n = 99) in MEN1 (n = 2710), sex ratio was 79:20 (male vs female), and the median age at diagnosis was 43.0 years (range, 16.0-72.0 years). Forty-three patients died with a median survival time of 8.4 years. Older age at diagnosis (HR = 1.4, 95% CI = 1.0-1.8, P = .03), maximum tumour diameter (HR = 1.5, 95% CI = 1.0-2.3, P = .04) and presence of metastasis (HR = 1.6, 95% CI = 1.0-2.5, P = .04) were associated with worse outcome. A male predominance (91.9% vs 59.5%, P < .001) and history of smoking (59.0% vs 23.5%, P = .015) were more common in American/European series compared to Asian reports. CONCLUSION: TH-NET is a rare but fatal component of MEN1. Earlier detection of TH-NET in patients with MEN1 may be recommended which should theoretically result in better outcomes. Different genetic backgrounds (race) appear to result in clinical difference.

Clinical Features of a Family with Multiple Endocrine Neoplasia Type 2A Caused by the D631Y RET Mutation.

We describe a family with multiple endocrine neoplasia type 2A (MEN2A) caused by the D631Y RET mutation resulting in an atypical phenotype. The index case was a 24-year-old man with history of recurrent anaplastic ependymoma incidentally found to have the D631Y RET mutation. At first assessment, four family members had evidence of large pheochromocytomas. One patient was found to have micromedullary thyroid cancer at 79 years of age. None of the patients had primary hyperparathyroidism. Patients with MEN2A caused by a D631Y RET mutation most commonly present with pheochromocytomas. Medullary thyroid cancer is a less common part of the syndrome when compared with other RET mutations.

IMAGE-GUIDED THERMAL ABLATION OF ADRENAL METASTASES: HEMODYNAMIC AND ENDOCRINE OUTCOMES.

OBJECTIVE: Image-guided thermal ablation of adrenal metastases has been increasingly used for local tumor control. This procedure has been associated with hypertensive urgency; however, endocrine complications have not been clearly described. Our objective was to assess the hemodynamic behavior and risk for adrenal insufficiency related to adrenal ablation. Additionally, we sought to understand the utility of preprocedural α-blockade to prevent periprocedural hemodynamic complications. METHODS: This was a retrospective study of patients undergoing image-guided ablation of adrenal metastases between 2003 and 2015 at our institution. We reviewed electronic medical records to obtain clinical information, including α-blockade preparation, periprocedural hemodynamic parameters, interventions, and postablation adrenal function. RESULTS: Thermal ablation was performed in 58 patients (46 men [79%]; median age, 66 years) with 60 adrenal metastases ablated in 62 sessions. Alpha-blockade was used pre-ablation in 49 (79%) sessions; it was associated with less hypertensive urgency (23 [47%] for α-blockade vs. 10 [77%] for no α-blockade; P = .048) but higher need for vasopressors (22 [45%] for α-blockade vs. 1 [8%] for no α-blockade; P = .02) during ablation. Adrenal insufficiency occurred in 13 (22%) patients, of whom 10 had history of contralateral adrenalectomy or metastases, and only 3 of 13 had a normal-appearing contralateral adrenal gland. CONCLUSION: Hemodynamic changes during ablation of adrenal metastases are common. Pre-ablation α-blockade decreases the severity of the hypertensive episode, at the expense of higher need for vasopressors periprocedurally. Adrenal function should be assessed after adrenal metastasis ablation, as adrenal insufficiency may occur after such treatment. ABBREVIATIONS: ACTH = adrenocorticotropic hormone BP = blood pressure CT = computed tomography DBP = diastolic blood pressure HR = heart rate IQR = interquartile range IV = intravenous MAP = mean arterial pressure MWA = microwave ablation RFA = radiofrequency ablation SBP = systolic blood pressure.

Shared decision making in endocrinology: present and future directions.

In medicine and endocrinology, there are few clinical circumstances in which clinicians can accurately predict what is best for their patients. As a result, patients and clinicians frequently have to make decisions about which there is uncertainty. Uncertainty results from limitations in the research evidence, unclear patient preferences, or an inability to predict how treatments will fit into patients' daily lives. The work that patients and clinicians do together to address the patient's situation and engage in a deliberative dialogue about reasonable treatment options is often called shared decision making. Decision aids are evidence-based tools that facilitate this process. Shared decision making is a patient-centred approach in which clinicians share information about the benefits, harms, and burden of different reasonable diagnostic and treatment options, and patients explain what matters to them in view of their particular values, preferences, and personal context. Beyond the ethical argument in support of this approach, decision aids have been shown to improve patients' knowledge about the available options, accuracy of risk estimates, and decisional comfort. Decision aids also promote patient participation in the decision-making process. Despite accumulating evidence from clinical trials, policy support, and expert recommendations in endocrinology practice guidelines, shared decision making is still not routinely implemented in endocrine practice. Additional work is needed to enrich the number of available tools and to implement them in practice workflows. Also, although the evidence from randomised controlled trials favours the use of this shared decision making in other settings, populations, and illnesses, the effect of this approach has been studied in a few endocrine disorders. Future pragmatic trials are needed to explore the effect and feasibility of shared decision making implementation into routine endocrinology and primary care practice. With the available evidence, however, endocrinologists can now start to practice shared decision making, partner with their patients, and use their expertise to formulate treatment plans that reflect patient preferences and are more likely to fit into the context of patients' lives. In this Personal View, we describe shared decision making, the evidence behind the approach, and why and how both endocrinologists and their patients could benefit from this approach.