David Toro-Tobon
Mayo Scholar
Research Interests
Make your next move.
Prepare your application
Review drafts before you send them.
Explore related searches
Articles (21)
Year:
2026
Year:
2026
Year:
2026
Graves’ disease (GD) is an autoimmune entity that had an unchanged treatment paradigm for more than half a century with radioactive iodine, antithyroid drugs (ATDs), and surgery representing the mainstay of therapy, with variation in their use over time and geographic location. Hypothyroidism has been an accepted tradeoff in many cases, though recently there are increased concerns about altered quality of life in these patients. Fortunately, the last decade has seen an intense pursuit of GD's immunological mechanisms and a recalibration of classic treatment modalities focusing on thyroid preservation, as reflected in the preference for ATD as primary therapy, including its use in long-term protocols. The immune targets currently explored aim to address this gap by intervening in the TRAb lifecycle: minimizing production (eg, B-cell targeting), enhancing clearance (eg, neonatal Fc receptor inhibitors), or neutralizing its target—the TSH receptor (eg, receptor blockade). While these approaches are going through the necessary clinical trials evaluation, we are starting to see the potential for technology and artificial intelligence to make an impact on how we identify, treat, and monitor patients with GD. The combination of these approaches will likely lead to a significant individualization of GD management that will take us from the goal of normalization of thyroid levels to that of inducing long-term remission and prevention of the associated autoimmune phenomena that GD is associated with. While time is needed for these aspects to mature, the future looks bright for our GD patients and maybe soon these lessons will open new doors for our patients with Hashimoto's thyroiditis as well.
Year:
2026
Year:
2026
Context Benign thyroid nodules (BTNs) are highly prevalent, and current treatment options are primarily invasive. There is a need for effective, noninvasive alternatives. Objective To systematically evaluate the efficacy of repurposed pharmacologic agents in reducing the size of BTNs. Data Sources MEDLINE, EMBASE, Cochrane databases, and Scopus were searched from inception to December 18, 2024. Study Selection We included preclinical and clinical studies evaluating repurposed drugs for BTNs in adults. Of 1499 records screened, 20 studies met inclusion criteria: 6 randomized controlled trials (RCTs), 6 prospective cohorts, 3 retrospective observational studies, 3 case reports, 1 cross-sectional study, and 1 preclinical study. Data Extraction Data were extracted independently in duplicate using a standardized form. Data Synthesis Narrative synthesis was conducted due to heterogeneity. Metformin was the most frequently evaluated agent (7 studies), with 5 studies (including 2 RCTs) reporting statistically significant reductions in dominant nodule volume. One prospective study demonstrated a reduction in the maximum nodule diameter, which was not statistically significant, and 1 RCT showed no changes in nodule size after intervention. Statins (4 studies) and somatostatin analogues (4 studies) showed mixed results. Myo-inositol with selenium, herbal formulations, and immune checkpoint inhibitors showed promise in single studies or case reports. Conclusion Metformin shows the most consistent potential for noninvasive reduction of BTN size, particularly in patients with metabolic comorbidities. However, current evidence is limited and heterogeneous. Further large-scale studies are needed to confirm efficacy and guide clinical use.
Year:
2026
BACKGROUND Named Entity Recognition (NER), a key task in extracting structured information from unstructured text, such as names, dates, and locations. Traditional systems that apply NER to speech rely on a pipeline of Automatic Speech Recognition (ASR) and text-based NER, which can suffer from error propagation and performance degradation. There is a growing need to understand the capabilities of more advanced end-to-end (E2E) models that process speech directly, especially in the context of unscripted, human-to-human conversations relevant to clinical settings. OBJECTIVE To systematically evaluate the performance, architectures, data sources, and methodological innovations of E2E spoken NER models applied to unscripted, spontaneous human-to-human conversations. METHODS Following PRISMA 2020, we searched MEDLINE, Scopus, IEEE Xplore, arXiv, and other databases from inception, up to June 13, 2025. Studies were eligible if they applied E2E NER models to audio or audiovisual recordings of unscripted conversations between at least two people. Pipeline-only, text-only, scripted, and human–machine interaction studies were excluded. Data on conversational corpora, annotation schemas, model architectures, training strategies, and NER and ASR performance metrics were extracted and synthesized. RESULTS Of 1,094 records found, five studies met inclusion criteria. Four evaluated models on the SLUE-VoxPopuli benchmark, while one focused on spontaneous telephone and contact-center dialogues. All E2E approaches used self-supervised speech encoders (wav2vec 2.0, HuBERT, WavLM), and four studies employed the character-level Connectionist Temporal Classification (CTC) loss, and language-model–guided decoding. On SLUE-VoxPopuli, the strongest E2E systems achieved up to 77.2% NER F1 (ROVER ensemble) with 8.6% WER, surpassing competitive pipeline baselines. However, performance declined sharply on real-world conversational corpora, with F1 falling to 30.6% on noisy cross-domain telephone speech. E2E models required large amounts of external automatic speech recognition (ASR) and spoken language understanding (SLU) pretraining data to match or exceed pipelines, highlighting sensitivity to noise, domain shift, and limited in-domain labels. CONCLUSIONS E2E models leveraging state-of-the-art self-supervised learning encoders, contextual modeling, and semi-supervised learning represent the forefront of spoken NER. While they hold significant promise, their performance on noisy, real-world conversational data highlights a critical gap that must be addressed before they can be reliably deployed in challenging domains like healthcare. Future progress will depend on the development of domain-specific datasets and models robust to the complexities of spontaneous human interaction. Registration: PROSPERO (CRD42024627286).
Year:
2026
Purpose Overuse of thyroid ultrasound (TUS) has contributed to rising thyroid cancer diagnoses and is projected to increase US healthcare costs from $1.5 billion to $3.5 billion by 2030. This study evaluated the healthcare cost of inappropriately ordered TUS in a national multicenter academic system. Methods This is a secondary cost analysis of a retrospective cohort study across 4 Mayo Clinic sites (Rochester, MN; Jacksonville, FL; Scottsdale, AZ; and the Midwest Mayo Clinic Health System). Adult patients (≥18 years) undergoing their first TUS between January 1, 2017, and December 31, 2021, with at least 1 year of follow-up were included. TUS indications were classified as appropriate or inappropriate using a guideline-based natural language processing algorithm. The primary outcome was a comparison of adjusted 1-year all-cause healthcare costs. A secondary analysis calculated the direct procedural costs of the inappropriate TUS cascade. Results Among 6984 patients (mean age 56 [SD 16.4]; 76.2% female; 90.9% White), 546 (7.8%) underwent TUS for inappropriate indications. These patients were younger (mean age 53.0 vs 56.3 years, P < .0001) but otherwise demographically similar. Adjusted total healthcare costs over 90 days and 1 year were comparable: $4842 vs $5794 and $13 748 vs $14 257 for inappropriate vs appropriate TUS, respectively. The inappropriate TUS cascade, including an estimated 56 subsequent biopsies and 22 thyroidectomies, resulted in a minimum of $576 134 in direct procedural costs. Conclusion While adjusted total costs were similar, inappropriate TUS represents potentially avoidable spending and remains a viable target for cost-reduction strategies. Reducing low-value imaging remains a critical target for cost-saving interventions.
Year:
2025
Year:
2025
Year:
2025
Year:
2025
Year:
2025
Year:
2025
Year:
2025
Year:
2024
Year:
2024
Year:
2024
Year:
2024
Year:
2024
Year:
2024
Year:
2024
Collaborators (4)
Sheena Asthana
Director, Plymouth Centre for Health Technology
University of Plymouth
Juan P Brito
Mayo Clinic Minnesota
Javad Azadi
-
Sarah Mayson
Associate Professor of Medicine
University of Colorado Anschutz Medical Campus
Make your next move.
Prepare your application
Review drafts before you send them.