Chemotherapy-induced mucositis, one of the most common complications of chemotherapy, can be subdivided in oral and gastrointestinal mucositis. The patients always suffer from oral pain and ulcers, nausea, vomiting, abdominal pain and diarrhea. 5-Fluorouracil- and irinotecan-based regimens are frequently associated with a higher risk and more severe grade of mucositis. The onset of mucositis is also influenced by the patient’s characteristics including age, sex, genetic polymorphisms, systemic comorbidities. At present, the diagnosis of chemotherapy-induced mucositis is mainly based on medical history, physical examination and gastroenteroscopy, lack of reliable biomarkers for early diagnosis. The principles of diagnosis and treatment mainly refer to the clinical practice guidelines issued. Therefore, this article will review the mechanism, diagnosis, latest preventive and treatment strategies of chemotherapy-induced mucositis for helping clinicians to further correctly understand and deal with the adverse reactions.
This study aims to investigate the value of pre-treatment computed tomography (CT) texture analysis in predicting therapeutic response of liver metastasis from colorectal cancer after combined targeting chemotherapy. A total of 82 patients with colorectal cancer liver metastases who underwent chemotherapy combined with targeted therapy (cetuximab) between March 2011 and October 2017 comprised this retrospective study population. According to the RECIST1.1, the best curative effect evaluation of patients was recorded. Complete response (CR) and partial response (PR) were assigned to the response group, and the stable disease (SD) and progressive disease (PD) were assigned to the non-response group. The CT texture analysis was based on the Omini-Kinetics software, and the three-dimensional (3D) texture analysis was performed on the marked lesion on portal phase. The differences of texture parameters between the response group and the non-response group were compared. The receiver operating characteristic (ROC) curves were depicted on the parameters which with statistically difference, to characterize value in predicting the response to target-combined chemotherapy. The differences of Entropy, Energy, Variance, std. Deviation, Quantile95 and sumEntropy between the two groups in pre-treatment lesions were significant (P < 0.05). And lesions with higher Entropy, lower Energy, higher Variance, higher std Deviation and higher sumEntropy seemed to indicate a better therapeutic response. When sumEntropy > 0.867, good diagnostic efficiency could be obtained, with sensitivity of 60.5% and specificity of 79.5%, respectively. In conclusion, texture parameters derived from baseline CT images of colorectal cancer liver metastasis have the potential value acting as imaging biomarkers in predicting tumor response to combined target chemotherapy.
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.