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.

Clinical Outcomes of Radioactive Iodine Redifferentiation Therapy in Previously Iodine Refractory Differentiated Thyroid Cancers.

Objective: Redifferentiation therapy (RDT) can restore radioactive iodine (RAI) uptake in differentiated thyroid cancer (DTC) cells to enable salvage 131I therapy for previously RAI refractory (RAIR) disease. This study evaluated the clinical outcomes of patients who underwent RDT and identified clinicopathologic characteristics predictive of RAI restoration following RDT. Methods: This is a retrospective case series of 33 patients with response evaluation criteria in solid tumors (RECIST)-progressive metastatic RAIR-DTC who underwent RDT between 2017 and 2022 at the Mayo Clinic (Rochester, MN). All patients underwent genomic profiling and received MEK, RET or ALK inhibitors alone, or combination BRAF-MEK inhibitors for 4 weeks. At week 3, those with increased RAI avidity in metastatic foci received high-dose 131I therapy. Baseline and clinicopathologic outcomes were comprehensively reviewed. Results: Of the 33 patients, 57.6% had restored RAI uptake following RDT (Redifferentiated subgroup). 42.1% (8/19) with papillary thyroid cancers (PTC), 100% (4/4) with invasive encapsulated follicular variant PTCs (IEFV-PTCs), and 100% (7/7) with follicular thyroid cancers (FTC) redifferentiated. All (11/11) RAS mutant tumors redifferentiated compared with 38.9% (7/18) with BRAF mutant disease (6 PTC and 1 IEFV-PTC). 76.5% (13/17) of redifferentiated and 66.7% (8/12) of non-redifferentiated patients achieved a best overall RECIST response of stable disease (SD) or non-complete response/non-progressive disease. Both subgroups had a median 12% tumor shrinkage at 3 weeks on drug(s) alone. The redifferentiated subgroup, following high-dose 131I therapy, achieved an additional median 20% tumor reduction at 6 months after RDT. There were no statistically significant differences between both groups in progression free survival (PFS), time to initiation of systemic therapy, and time to any additional therapy. Of the entire cohort, 6.1% (2/33) experienced histologic transformation to anaplastic thyroid cancer, 15.1% (5/33) died, and all had redifferentiated following RDT and received 131I therapy. Conclusion: RDT has the potential to restore RAI avidity and induce RECIST responses following 131I therapy in select patients with RAIR-DTC, particularly those with RAS-driven "follicular" phenotypes. In patients with PTC, none of the evaluated clinical outcomes differed statistically between the redifferentiated and non-redifferentiated subgroups. Further studies are needed to better characterize the long-term survival and/or safety outcomes of high-dose RAI following RDT, particularly whether it could be associated with histologic anaplastic transformation.

Physical Examination of the Thyroid: Accuracy in Detecting Thyroid Nodules and Frequency of Additional Findings.

OBJECTIVE: Thyroid palpation is a common clinical practice to detect thyroid abnormalities. However, its accuracy and potential for additional findings remain unclear. This study aimed to assess the diagnostic accuracy of physical exams in detecting thyroid nodules. METHODS: A retrospective observational study was conducted on a random sample of adult patients who underwent their first-time thyroid ultrasound between January 2015 and September 2017, following a documented thyroid physical exam. The study assessed the performance of thyroid palpation in detecting 1 or multiple thyroid nodules, as well as the proportion of additional findings on ultrasounds due to false positive thyroid palpation. RESULTS: We included 327 patients, mostly female (65.1%), white (84.1%), and treated in a primary care setting (54.4%) with a mean age of 50.8 years (SD 16.9). For solitary thyroid nodules, the physical exam had a sensitivity of 20.3%, specificity of 79.1%, an accuracy of 68.5%, negative predictive value of 81.8%, and positive predictive value of 17.6%. For detecting a multinodular goiter, physical exams demonstrated a sensitivity of 10.8%, specificity of 96.5%, accuracy of 55.4%, negative predictive value of 53.9, and positive predictive value of 73.9%. Among 154 cases with palpable nodules, 60% had additional nodules found in subsequent thyroid ultrasound. CONCLUSION: Thyroid physical exam has limited diagnostic performance and leads to additional findings when followed by a thyroid ultrasound. Future efforts should be directed at improving the accuracy of thyroid physical exams or re-evaluating its routine use.

Drivers of Thyroid Ultrasound Use: A Retrospective Observational Study.

OBJECTIVE: Excessive use of thyroid ultrasound (TUS) contributes to the overdiagnosis of thyroid nodules and thyroid cancer. In this study, we evaluated drivers of and clinical trajectories following TUS orders. METHODS: We conducted a retrospective review of 500 adult patients who underwent an initial TUS between 2015 and 2017 at Mayo Clinic in Rochester, MN. A framework was employed to classify the indication for TUS, and it was characterized as inappropriate when ordered without a guideline-based indication. Medical records were reviewed for up to 12 months following the TUS, and clinical outcomes were evaluated. RESULTS: The mean age mean age (SD) was 53.6 years (16.6), 63.8% female, and 86.6% white. TUS orders were triggered by incidental findings on unrelated imaging (31.6%), thyroid symptoms (20.4%), thyroid abnormalities on routine physical examination (17.2%), and thyroid dysfunction workup (11.8%). In females and males, the most common reason were incidental findings on imaging (female, 91/319, 28.5% and male, 67/181, 37.0%). In primary care practice, TUS orders were mostly triggered by symptoms (71/218, 32.5%), while thyroid dysfunction workup was the primary reason in endocrinology (28/100, 28.0%). We classified 11.2% (56/500) TUS orders as likely to have been ordered inappropriately based on current guidelines. Finally, 119 patients (119/500, 23.8%) had a thyroid biopsy with 11.8% had thyroid cancer (14/119. 11.8%). CONCLUSIONS: Incidental findings on imaging, symptoms, and routine physical exam findings in asymptomatic patients were the most prevalent drivers of TUS. Furthermore, 1 in 10 TUS were likely inappropriately ordered based on current practice guidelines.

Artificial Intelligence in Thyroidology: A Narrative Review of the Current Applications, Associated Challenges, and Future Directions.

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.

Immunotherapy-Associated Hypothyroidism: Comparison of the Pre-Existing With De-Novo Hypothyroidism.

Background: Immunotherapy has revolutionized the treatment of solid malignancies, but is associated with endocrine-related adverse events. This study aims to dissect the natural course of immunotherapy-induced hypothyroidism and provide guidance regarding diagnosis and management in patients with and without pre-existing hypothyroidism. Methods: A retrospective analysis was conducted using patients who received immunotherapy between 2010-2019 within a multicenter hospital system. Participants were separated in three groups-those with pre-existing hypothyroidism, those who developed primary hypothyroidism and those with hypophysitis within a year of their first immunotherapy. Serial effects of immunotherapy on thyroid function tests (TFTs) and levothyroxine dosing were evaluated. Results: 822 patients were screened, with 85 determined to have pre-existing hypothyroidism, 48 de-novo primary hypothyroidism and 12 de-novo hypophysitis. All groups displayed fluctuations in TFTs around weeks 6-8 of treatment. In the pre-existing hypothyroidism group, the levothyroxine dose was higher at 54 weeks than at baseline with the difference showing a trend towards statistical significance (p=0.06). The observed mean levothyroxine dose was significantly lower than the mean calculated weight-based dose for all groups. This finding was most clinically significant for the de-novo hypophysitis group (mean difference: -58.3 mcg, p<0.0001). The mean 0.9 mcg/kg levothyroxine dose at week 54 for the de-novo hypophysitis group was statistically lower than the other groups (p=0.009). Conclusion: It is reasonable to screen with TFTs every 4 weeks, and space out TFTs surveillance to every 12 weeks after week 20. Our findings suggest a more conservative approach for levothyroxine dosing in those developing de-novo hypothyroidism, especially hypophysitis, such as initiating at 0.9-1.2 mcg/kg.

Thyroid storm as an early presentation of hCG-producing metastatic choriocarcinoma: a case report and review of the literature.

Human chorionic gonadotropin (hCG)-induced hyperthyroidism has been previously reported as a rare paraneoplastic syndrome in non-seminomatous germ cell tumours and usually presents with mild symptoms or subclinical thyrotoxicosis. We present a case of a young adult man who consulted with abdominal pain, nausea and emesis. On admission, he was found to be tachycardic, febrile, anxious and with icteric sclera and tenderness to palpation in the right upper abdomen. A right scrotal mass was also noted. Initial studies revealed transaminitis, hyperbilirubinaemia, suppressed thyroid-stimulating hormone and elevated free T4. Scrotal biopsy confirmed diagnosis of testicular choriocarcinoma with an elevated hCG level of 6074 mIU/mL, which was corrected to 6 760 713 mIU/mL when reassessed with dilution. The clinical scenario reflected hCG-induced thyrotoxicosis concerning for thyroid storm. Euthyroid state was restored after initiation of chemotherapy and a short course of methimazole. Unfortunately, the patient passed away due to progression of his malignant disease. This case suggests that when choriocarcinoma is suspected, the use of iodinated contrast agents should be limited to avoid precipitation of thyroid storm or worsening of hCG-induced hyperthyroidism. Moreover, if the clinical picture does not support a primary aetiology of hyperthyroidism and hCG is not concordantly elevated, reassessment of hCG by dilution should be considered as hCG assays are subject to prozone effect.

Chronic Myeloid Leukemia Associated Hypercalcemia: A Case Report and Literature Review.

BACKGROUND Hypercalcemia associated with chronic myeloid leukemia (CML) is an ominous sign. Although rare, several cases have been reported and multiple pathophysiologic mechanisms have been independently proposed. We present a patient case and a literature review of the clinical presentation and mechanisms of CML-associated hypercalcemia. CASE REPORT A 58-year-old male with a past medical history of CML diagnosed six years earlier, presented to the emergency department with one week of acute confusion, disorientation, polyuria, and polydipsia. On physical examination, we observed tachycardia, altered mental status, and dehydration. Blood analysis revealed leukocytosis, thrombocytosis, and marked hypercalcemia (18.6 mg/dL). His chest CT scan showed diffuse lytic lesions and bone destruction concerning for diffuse bone marrow involvement. The patient was diagnosed with hypercalcemia in the context of a CML blast phase. Treatment with hydration, calcitonin, and zoledronic acid lead to control of his symptoms and normalization of his serum calcium levels. After discharged, the patient was maintained on palliative treatment and zoledronic acid management without new episodes of hypercalcemia. However, eight months later, the patient died. CONCLUSIONS Evidence from the literature demonstrates a highly variable clinical presentation of CML-associated hypercalcemia, commonly occurring during an accelerated or a blast phase, and associated with poor survival. Multiple mechanisms could be involved and are not exclusive of each other. Better understanding of the pathophysiologic mechanisms involved in CML-associated hypercalcemia could lead to improvement in clinical and laboratory evaluation of these patients and be the foundation for the development of better management strategies and possibly target-directed therapy to positively improve prognosis.