For novice medical learners, do the benefits of correct AI explanations outweigh the risks of plausible misinformation? In a randomized trial with 111 students, we found they do not. Our results reveal a significant and problematic asymmetry: misleading AI explanations significantly degraded diagnostic accuracy, while correct explanations offered no significant improvement over a no-explanation control. Misleading explanations reduced diagnostic accuracy and showed no evidence of confidence calibration, such that confidence did not reliably distinguish correct from incorrect responses. This study provides crucial empirical evidence that, without proper safeguards, the harm caused by AI-generated falsehoods in this population and task is more potent and robust than the benefit derived from correct guidance. This finding highlights a fundamental safety challenge for AI in medical education, demanding a strategic pivot towards building learners’ critical appraisal skills. Trial registration: Chinese Clinical Trial Registry (ChiCTR), ChiCTR2500111932, registered on 7 November 2025.

Pretherapeutic serological parameters play a predictive role in pathologic risk factors (PRF), which correlate with treatment and prognosis in cervical cancer (CC). However, the method of pre-operative prediction to PRF is limited and the clinical availability of machine learning methods remains unknown in CC. Overall, 1260 early-stage CC patients treated with radical hysterectomy (RH) were randomly split into training and test cohorts. Six machine learning classifiers, including Gradient Boosting Machine, Support Vector Machine with Gaussian kernel, Random Forest, Conditional Random Forest, Naive Bayes, and Elastic Net, were used to derive diagnostic information from nine clinical factors and 75 parameters readily available from pretreatment peripheral blood tests. The best results were obtained by RF in deep stromal infiltration prediction with an accuracy of 70.8% and AUC of 0.767. The highest accuracy and AUC for predicting lymphatic metastasis with Cforest were 64.3% and 0.620, respectively. The highest accuracy of prediction for lymphavascular space invasion with EN was 59.7% and the AUC was 0.628. Blood markers, including D-dimer and uric acid, were associated with PRF. Machine learning methods can provide critical diagnostic prediction on PRF in CC before surgical intervention. The use of predictive algorithms may facilitate individualized treatment options through diagnostic stratification.

Background: We aimed to build a common terminology in the domain of cervical cancer, named Cervical Cancer Common Terminology (CCCT), that will facilitate clinical data exchange, ensure quality of data and support large scale data analysis. Methods: The standard concepts and relations of CCCT were collected from ICD-10-CM Chinese Version, ICD-9-PC Chinese Version, officially issued commonly used Chinese clinical terms, Chinese guidelines for diagnosis and treatment of cervical cancer and Chinese medical book Lin Qiaozhi Gynecologic Oncology. 2062 cervical cancer electronic medical records (EMRs) from 16 hospitals, belong to different regions and hospital tiers, were collected for terminology enrichment and building common terms and relations. Concepts hierarchies, terms and relationships were built using Protégé. The performance of natural language processing results was evaluated by average precision, recall, and F1-score. The usability of CCCT were evaluated by terminology coverage. Results: A total of 880 standard concepts, 1182 common terms, 16 relations and 6 attributes were defined in CCCT, which organized in 6 levels and 11 classes. Initial evaluation of the natural language processing results demonstrated average precision, recall, and F1-score percentages of 96%, 72.6%, and 88.5%. The average terminology coverage for three classes of terms, clinical manifestation, treatment, and pathology, were 87.22%, 92.63%, and 89.85%, respectively. Flexible Chinese expressions exist between regions, traditions, cultures, and language habits within the country, linguistic variations in different settings and diverse translation of introduced western language terms are the main reasons of uncovered terms. Conclusions: Our study demonstrated the initial results of CCCT construction. This study is an ongoing work, with the update of medical knowledge, more standard clinical concepts will be added in, and with more EMRs to be collected and analyzed, the term coverage will be continuing improved. In the future, CCCT will effectively support clinical data analysis in large scale.

Purpose This study aimed to investigate the factors associated with chemoresistance to neoadjuvant chemotherapy (NACT) followed by radical hysterectomy (RH) and construct a nomogram to predict the chemoresistance in patients with locally advanced cervical squamous carcinoma (LACSC).Materials and Methods This retrospective study included 516 patients with International Federation of Gynecology and Obstetrics (2003) stage IB2 and IIA2 cervical cancer treated with NACT and RH between 2007 and 2017. Clinicopathologic data were collected, and patients were assigned to training (n=381) and validation (n=135) sets. Univariate and multivariate analyses were performed to analyze factors associated with chemoresistance to NACT. A nomogram was built using the multivariate logistic regression analysis results. We evaluated the discriminative ability and accuracy of the model using a concordance index and a calibration curve. The predictive probability of chemoresistance to NACT was defined as > 34%.Results Multivariate analysis confirmed menopausal status, clinical tumor diameter, serum squamous cell carcinoma antigen level, and parametrial invasion on magnetic resonance imaging before treatment as independent prognostic factors associated with chemoresistance to NACT. The concordance indices of the nomogram for training and validation sets were 0.861 (95% confidence interval [CI], 0.822 to 0.900) and 0.807 (95% CI, 0.807 to 0.888), respectively. Calibration plots revealed a good fit between the modelpredicted probabilities and actual probabilities (Hosmer-Lemeshow test, p=0.597). Furthermore, grouping based on the nomogram was associated with progression-free survival.Conclusion We developed a nomogram for predicting chemoresistance in LACSC patients treated with RH. This nomogram can help physicians make clinical decisions regarding primary management and postoperative follow-up of the patients.

Objectives: Women with ovarian cancer (OC) have experienced unprecedented challenges since the novel coronavirus disease-2019 (COVID-19) outbreak in China. We aim to evaluate the experience of psychological status, physical symptoms and quality of life (QoL) and investigate the impact of COVID-19 pandemic on OC patients receiving olaparib.Methods: The survey was conducted online from April 22 to May 12 in 2020. Demographic and clinical questions were listed to collect general information. The degree of insomnia, depression, anxiety, stress symptoms and QoL were assessed by the Chinese versions of the Insomnia Severity Index, the Patient Health Questionnaire-9, the Generalized Anxiety Disorder-7, the Impact of Event Scale-Revised, and the General Functional Assessment of Cancer Therapy, respectively. Multivariate logistic regression analysis was conducted to analyze the risk factors for mental distress and QoL.Results: A total of 56 respondents coming from 15 various provinces in China participated in the survey. The prevalence of insomnia, depressive, anxiety, stress symptoms and reduced QoL were 37.5, 51.8, 37.5, 30.4, and 51.8%, respectively. Unfavorable disease status, shorter period of olaparib administration, adverse events of olaparib and delay in cancer care were correlated with mental health problems. Reduced QoL was also significantly associated with psychological distress.Conclusions: This study emphasized that mental health problems and reduced QoL should gain more attention in women with OC who are receiving oral olaparib at home. Appropriate psychological healthcare strategies are necessary for OC patients during the COVID-19 pandemic.