Ponte, Oscar Ponce

Abstract Context Incidental thyroid findings (ITFs) are increasingly detected on imaging performed for non-thyroid indications. Their prevalence, features, and consequences remain undefined. Objective To develop, validate, and deploy a natural language processing (NLP) pipeline to identify ITFs in radiology reports and assess their prevalence, features, and clinical outcomes. Design Retrospective cohort study. Setting Mayo Clinic sites (Rochester, Arizona, Florida, Mayo Clinic Health System). Participants Adults without prior thyroid disease undergoing thyroid-capturing imaging from July 1, 2017, to September 30, 2023. A transformer-based NLP pipeline identified ITFs and extracted nodule characteristics from image reports from multiple modalities and body regions. Outcomes ITF prevalence, downstream thyroid ultrasound, biopsy, thyroidectomy, and cancer diagnosis. Logistic regression identified demographic and imaging-related factors. Results Among 115 683 patients (mean age, 56.8 [SD 17.2]; 52.9% women), 9077 (7.8%) had an ITF (92.9% nodular). ITFs were more likely in women, older adults, higher BMI, and in imaging ordered by specialties different from Emergency Medicine. Compared with chest CT, ITFs were more likely via neck CT, PET, and nuclear medicine scans. Nodule characteristics were poorly documented, with size reported in 44% and other features in fewer than 15%. Compared with patients without ITFs, those with ITFs had higher odds of thyroid nodule diagnosis (OR 45, 95%CI 41.1-49.3), biopsy (OR 46.8, 95%CI 39.0-56.2) thyroidectomy (OR 55.8, 95%CI 31.3-99.3), and thyroid cancer diagnosis (OR 61.7, 95%CI 38.6-98.5). Most cancers were papillary (88.5%) and larger when detected after ITFs (2 cm SD 1.4) vs no ITF (1.3 cm SD 0.8). Conclusion ITFs were common and strongly associated with cascades leading to the detection of small, low-risk cancers, highlighting their role in overdiagnosis and the need for standardized reporting and more selective follow-up.

Background: Preparation for radioiodine (RAI) therapy in differentiated thyroid cancer (DTC) often requires thyroid hormone withdrawal (THW) to achieve thyrotropin (TSH) stimulation. Current guidelines recommend TSH ≥30 mIU/L, a target that prolongs hypothyroidism and worsens quality of life, yet rests on limited evidence. Objective: To evaluate the association between pre-RAI TSH levels and oncologic outcomes in adults with DTC prepared by THW. Methods: We conducted a systematic review and meta-analysis of studies comparing outcomes across pre-RAI TSH thresholds (<30 vs. ≥30, <60 vs. ≥60, and <90 vs. ≥90 mIU/L) in adults with DTC prepared by THW. Primary outcomes included disease-specific mortality, recurrence, and response to therapy. Searches in MEDLINE, Embase, Cochrane, and Scopus (inception to March 2025) identified eligible studies. Risk of bias was assessed using the CLARITY tool and certainty of evidence using GRADE. Pooled relative risks (RRs) were calculated using random-effects models. This systematic review was registered in PROSPERO (CRD42020158354). Results: This meta-analysis included eight retrospective cohort studies comprising a total of 4651 DTC patients, predominantly women (68.5%) with a mean age of 46 years. All patients underwent THW before RAI. Across all TSH thresholds examined (<30, <60, and <90 mIU/L), higher pre-RAI TSH levels were not associated with better treatment response, lower recurrence, or reduced mortality. Specifically, patients with higher pre-RAI TSH levels (≥30 mIU/L) did not have better oncologic outcomes compared with those with lower levels (<30 mIU/L). At 2- and 3-year follow-up, no significant differences were observed in excellent (pooled RR = 0.87; confidence interval [CI] 0.68–1.11) or indeterminate (RR = 1.28; CI 0.72–2.27) response rates. Similarly, recurrence rates did not differ (RR = 1.45; CI 0.83–2.55), and no study demonstrated a difference in disease-specific mortality across follow-up periods extending up to 10 years. The certainty of evidence for all outcomes was rated very low due to risk of bias, heterogeneity, and imprecision. Conclusions: The current evidence base is insufficient to support or refute the routine use of a specific TSH threshold before RAI administration. These findings question the recommendation to achieve TSH ≥30 mIU/L before RAI and highlight the need for trials to define the minimal effective level of TSH stimulation.