ObjectiveTo develop and validate a nomogram for predicting overall survival among patients with breast apocrine carcinoma (BAC). MethodsThe patients diagnosed with BAC from 2010 to 2016 were selected from the Surveillance, Epidemiology, and End Results (SEER) database and then randomly divided into a training set and a validation set by a 7∶3 ratio. Additionally, external validation of the nomogram was conducted on BAC patients admitted to the Dongfeng Hospital Affiliated to Hubei Medical College from January 1, 2010 to December 31, 2018. The risk factors affecting the overall survival of BAC patients were determined by univariate and multivariate Cox regression analyses, which were used to develop the nomogram prediction model. The discriminative abilities of the nomogram for the 3- and 5-year overall survival rates were evaluated by the C-index and area under receiver operating characteristic curve (AUC), and the fit of actual data and nomogram-predicted data for calibrators should be evaluated. ResultsA total of 649 BAC patients who met the included criterion for this study were enrolled from the SEER database (including 454 in the training set and 195 in the internal validation set), and 21 BAC patients from the Dongfeng Hospital (external validation set) were included. The multivariate Cox regression analysis showed that the age, T stage, M stage, S stage, surgical method, and chemotherapy were the risk factors affecting the overall survival of BAC patients. The C-index values of the nomogram prediction model based on these risk factors was 0.76, 0.77, and 0.88 in the training set, internal validation set, and external validation set, respectively. The calibration curves of the actual 3- and 5-year overall survival rates and nomogram-predicted 3- and 5- year overall survival rates were close to the ideal curve. The AUCs (95%CI) of the nomogram prediction model for evaluating the 3-year and 5-year overall survival rates of BAC patients were 0.84 (0.78, 0.89) and 0.76 (0.71, 0.83) in the training set, 0.81 (0.73, 0.91) and 0.84 (0.77, 0.91) in the internal validation set, and 0.80 (0.70, 0.91) and 0.84 (0.76, 0.91) in the external validation set, respectively. ConclusionNomogram based on the SEER database to predict the overall survival of BAC patients has a good predictive effect for BAC patients.
Objective To systematically evaluate the consistency between large language models (LLMs) and human raters in the assessment of medical students’ knowledge examinations, clinical documentation, and behavioral performance. Methods PubMed, Web of Science, Embase, ERIC, China National Knowledge Infrastructure, and WanFang Data were searched for original research articles published between January 2020 and March 2026 regarding the agreement between LLMs and human scoring in medical student assessments. Meta-analysis was performed using R 5.3.0 software. Results A total of 16 studies were included, yielding 39 independent effect sizes, comprising 17 intraclass correlation coefficients (ICC) and 22 Cohen’s Kappa data points. The assessment tasks spanned three categories: knowledge examinations, clinical documentation, and behavioral assessment, involving various mainstream LLMs such as GPT-4. Meta-analysis revealed a pooled ICC of 0.74 [95% confidence interval (CI) (0.51, 0.87), P<0.001] and a pooled Cohen’s Kappa of 0.52 [95%CI (0.38, 0.64), P<0.001], indicating overall moderate-to-high consistency. Significant heterogeneity was observed among the included studies, primarily driven by task types and task difficulty. Conclusions Constrained by factors such as task difficulty, LLMs currently serve only as adjunctive tools to human evaluation, despite demonstrating a potential for consistency comparable to human scoring in medical education assessments. The future intelligent transformation of medical education evaluation must operate within a clinician-in-the-loop framework to achieve a balance between assessment efficiency and the rigor of medical logic.