Explore the vast range of titles available.

IntroductionDifferentiated thyroid cancer (DTC) is the most common endocrine malignancy, with a high 5-year survival rate of approximately 98%. Despite advances in diagnosis and treatment, up to 20% of patients experience recurrence, adversely affecting their quality of life. Predictive models have been developed to assess recurrence risk and guide clinical decision-making, but these models often face limitations such as retrospective design, lack of diversity in study populations and absence of external validation. The primary aim is to externally validate existing predictive models for DTC recurrence using prospective data from a diverse Latin American cohort. The secondary aim is to explore opportunities for model recalibration to improve their performance in our population.Methods and analysisThe CaTaLiNA study is a multicentre prospective observational study conducted across 10 hospitals in five Latin American countries, including Ecuador, Peru, Uruguay and Mexico. Patients aged 18 years or older receiving treatment for DTC, such as the first thyroid surgery, active surveillance or radiofrequency ablation will be included. Recruitment will occur from November 2023 to June 2025, with follow-up extending until June 2028. Data collection will include baseline clinical, surgical and histological characteristics, treatment details and follow-up outcomes. Statistical analysis will follow the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis guidelines, using imputation strategies for missing data and evaluating calibration and discrimination of the prediction models. Calibration measures include the ratio of expected and observed events, calibration slope and calibration plot, while discrimination will be assessed using the C-index and area under the receiver operating characteristic curve.Ethics and disseminationThis study protocol was approved by Comité de Ética de Investigación en Seres Humanos de la Universidad San Francisco de Quito USFQ ‘CEISH-USFQ’ APO-010–2023-CEIHS-USFQ Oficio No. 161-2023-CA-23030M-CEISH-USFQ. Results will be disseminated via peer-reviewed publications.

The promise of artificial intelligence (AI) in medicine depends on its ability to learn from data that reflect what matters to patients and clinicians in the care process. Most existing models are trained on electronic health records (EHRs), which primarily capture biological measures but rarely the interactions and relationships between patients and clinicians. These relationships, central to how care is understood, negotiated, and delivered, unfold across multiple modalities, including voice, text, and video, yet remain largely absent from current datasets. As a result, AI systems trained solely on EHRs risk perpetuating a narrow biomedical view of medicine and overlooking the lived exchanges that define clinical encounters. This study aims to design, implement, and evaluate the feasibility of a longitudinal, multimodal system for capturing patient-clinician encounters, linking 360° video or audio recordings with postvisit surveys and EHR data, to create a foundational dataset for downstream AI research. This single-site study was conducted in an academic outpatient specialty clinic (Division of Endocrinology, Mayo Clinic, Rochester, Minnesota, United States). Adult patients attending in-person visits with participating clinicians were invited to enroll. Encounters were recorded using a 360° 2D monocular video camera and dual-channel audio. After each visit, patients completed a brief survey assessing relational empathy, satisfaction, visit pace, and treatment burden. Demographic and clinical data were extracted from the EHR. Feasibility was assessed using 5 prespecified end points: clinician consent, patient consent, recording success, survey completion, and data linkage across modalities. Recruitment began in January 2025. By August 2025, 35 of 36 (97%) eligible clinicians and 212 of 281 (75%) approached eligible patients had consented. Of the consented encounters, 162 (76%) resulted in a complete 360° video recording, and the postvisit surveys were completed for 204 of 212 (96%) consented encounters, reflecting 1 survey per encounter. Data collection is ongoing as of December 2025, and further analyses will be reported in subsequent publications. This protocol describes a longitudinal multimodal encounter capture system that links 360° audio or video with postvisit surveys and EHR data. The study specifies operational definitions, workflows, feasibility end points, and governance procedures to support implementation and replication in other clinical settings.

Shared decision-making (SDM) is necessary to achieve patient-centred care. Currently no methodology exists to automatically measure SDM at scale. This study aimed to develop an automated approach to measure SDM by using language modelling and the conversational alignment (CA) score. A total of 157 video-recorded patient-doctor conversations from a randomized multi-centre trial evaluating SDM decision aids for anticoagulation in atrial fibrillations were transcribed and segmented into 42,559 sentences. Context-response pairs and negative sampling were employed to train deep learning (DL) models and fine-tuned BERT models via the next sentence prediction (NSP) task. Each top-performing model was used to calculate four types of CA scores. A random-effects analysis by clinician, adjusting for age, sex, race, and trial arm, assessed the association between CA scores and SDM outcomes: the Decisional Conflict Scale (DCS) and the Observing Patient Involvement in Decision-Making 12 (OPTION12) scores. p-values were corrected for multiple comparisons with the Benjamini-Hochberg method. Among 157 patients (34% female, mean age 70 SD 10.8), clinicians on average spoke more words than patients (1911 vs 773). The DL model without the stylebook strategy achieved a recall@1 of 0.227, while the fine-tuned BERTbase (110M) achieved the highest recall@1 with 0.640. The AbsMax (18.36 SE7.74 p=0.025) and Max CA (21.02 SE7.63 p=0.012) scores generated with the DL without stylebook were associated with OPTION12. The Max CA score generated with the fine-tuned BERTbase (110M) was associated with the DCS score (-27.61 SE12.63 p=0.037). BERT model sizes did not have an impact the association between CA scores and SDM. This study introduces an automated, scalable methodology to measure SDM in patient-doctor conversations through explainable CA scores, with potential to evaluate SDM strategies at scale.

The promise of AI in medicine depends on learning from data that reflect what matters to patients and clinicians. Most existing models are trained on electronic health records (EHRs), which capture biological measures but rarely patient-clinician interactions. These relationships, central to care, unfold across voice, text, and video, yet remain absent from datasets. As a result, AI systems trained solely on EHRs risk perpetuating a narrow biomedical view of medicine and overlooking the lived exchanges that define clinical encounters. Our objective is to design, implement, and evaluate the feasibility of a longitudinal, multimodal system for capturing patient-clinician encounters, linking 360 degree video/audio recordings with surveys and EHR data to create a dataset for AI research. This single site study is in an academic outpatient endocrinology clinic at Mayo Clinic. Adult patients with in-person visits to participating clinicians are invited to enroll. Encounters are recorded with a 360 degree video camera. After each visit, patients complete a survey on empathy, satisfaction, pace, and treatment burden. Demographic and clinical data are extracted from the EHR. Feasibility is assessed using five endpoints: clinician consent, patient consent, recording success, survey completion, and data linkage across modalities. Recruitment began in January 2025. By August 2025, 35 of 36 eligible clinicians (97%) and 212 of 281 approached patients (75%) had consented. Of consented encounters, 162 (76%) had complete recordings and 204 (96%) completed the survey. This study aims to demonstrate the feasibility of a replicable framework for capturing the multimodal dynamics of patient-clinician encounters. By detailing workflows, endpoints, and ethical safeguards, it provides a template for longitudinal datasets and lays the foundation for AI models that incorporate the complexity of care.

Large Language Models (LLMs) are increasingly demonstrating the potential to reach human-level performance in generating clinical summaries from patient-clinician conversations. However, these summaries often focus on patients' biology rather than their preferences, values, wishes, and concerns. To achieve patient-centered care, we propose a new standard for Artificial Intelligence (AI) clinical summarization tasks: Patient-Centered Summaries (PCS). Our objective was to develop a framework to generate PCS that capture patient values and ensure clinical utility and to assess whether current open-source LLMs can achieve human-level performance in this task. We used a mixed-methods process. Two Patient and Public Involvement groups (10 patients and 8 clinicians) in the United Kingdom participated in semi-structured interviews exploring what personal and contextual information should be included in clinical summaries and how it should be structured for clinical use. Findings informed annotation guidelines used by eight clinicians to create gold-standard PCS from 88 atrial fibrillation consultations. Sixteen consultations were used to refine a prompt aligned with the guidelines. Five open-source LLMs (Llama-3.2-3B, Llama-3.1-8B, Mistral-8B, Gemma-3-4B, and Qwen3-8B) generated summaries for 72 consultations using zero-shot and few-shot prompting, evaluated with ROUGE-L, BERTScore, and qualitative metrics. Patients emphasized lifestyle routines, social support, recent stressors, and care values. Clinicians sought concise functional, psychosocial, and emotional context. The best zero-shot performance was achieved by Mistral-8B (ROUGE-L 0.189) and Llama-3.1-8B (BERTScore 0.673); the best few-shot by Llama-3.1-8B (ROUGE-L 0.206, BERTScore 0.683). Completeness and fluency were similar between experts and models, while correctness and patient-centeredness favored human PCS.

Importance Incidental thyroid findings (ITFs) are increasingly detected on imaging performed for non-thyroid indications. Their prevalence, features, and clinical 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, Setting, and Participants Retrospective cohort of adults without prior thyroid disease undergoing thyroid-capturing imaging at Mayo Clinic sites 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. Main Outcomes and Measures Prevalence of ITFs, downstream thyroid ultrasound, biopsy, thyroidectomy, and thyroid cancer diagnosis. Logistic regression identified demographic and imaging-related factors. Results Among 115,683 patients (mean age, 56.8 [SD 17.2] years; 52.9% women), 9,077 (7.8%) had an ITF, of which 92.9% were nodules. ITFs were more likely in women, older adults, those with higher BMI, and when imaging was ordered by oncology or internal 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% (e.g. calcifications). Compared with patients without ITFs, those with ITFs had higher odds of thyroid nodule diagnosis, biopsy, thyroidectomy and thyroid cancer diagnosis. Most cancers were papillary, and larger when detected after ITFs vs no ITF. Conclusions ITFs were common and strongly associated with cascades leading to the detection of small, low-risk cancers. These findings underscore the role of ITFs in thyroid cancer overdiagnosis and the need for standardized reporting and more selective follow-up.