Borras-Osorio, Mariana

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.

Abstract Background Patients living with diabetes and chronic conditions may face significant burden managing their health. Many of these patients use digital medicine tools such as continuous glucose monitoring systems. Although measures exist to assess treatment burden from tasks such as managing medications and attending healthcare visits, there is no patient-reported measure that captures the burden of digital care. Therefore, the purpose of this study is to validate the Treatment Burden Questionnaire Plus Digital (TBQ + D), a patient-reported measure of treatment burden that includes using digital tools for adults with diabetes. Methods Adult patients with type 1 or type 2 diabetes mellitus completed the 25-item TBQ + D (scored 0 [none] to 10 [maximum] per item; total score range 0–250). We evaluated ease of administration, internal consistency, and tested hypotheses about the relationship between TBQ + D scores and treatment complexity, digital tool use intensity, social risk factors, and digital comfort to assess TBQ + D’s validity. Results Of 324 patients approached, 300 (93%) consented and completed the TBQ + D (mean age 57 [SD 17]; 50% female; 50% with type 2). The mean TBQ + D score was 53.7 (SD 41.6). Internal consistency was excellent (Cronbach’s α = 0.94). As hypothesized, higher TBQ + D scores were reported by patients with type 1 vs. type 2 diabetes mellitus (61.7 vs. 45.7; p = .0008), maximal/moderate vs. minimal to no digital tool use (56.5/60.7 vs. 41.3; p = .001), those on intensive insulin therapy vs. other treatments (61.4 vs. 38.0; p < .0001), and those with greater social vulnerability (p < .0106). TBQ + D scores were not significantly higher in patients with HbA1c ≥ 8% (p = .055) or less comfortable with digital technology (p = .08). Conclusions TBQ + D is a novel and valid measure of treatment burden in patients living with diabetes, inclusive of digital burden, that can play a role in fostering minimally disruptive care for patients with diabetes.