Oral squamous cell carcinoma (OSCC) is a common head and neck malignancy. Approximately 50% to 60% of patients with OSCC are diagnosed at a locally advanced stage (clinical staging III-IVa). Even with comprehensive and sequential treatment primarily based on surgery, the 5-year overall survival rate remains below 50%, and patients often suffer from postoperative functional impairments such as difficulties with speaking and swallowing. Programmed death receptor-1 (PD-1) inhibitors are increasingly used in the neoadjuvant treatment of locally advanced OSCC and have shown encouraging efficacy. However, clinical practice still faces key challenges, including the definition of indications, optimization of combination regimens, and standards for efficacy evaluation. Based on the latest research advances worldwide and the clinical experience of the expert group, this expert consensus systematically evaluates the application of PD-1 inhibitors in the neoadjuvant treatment of locally advanced OSCC, covering combination strategies, treatment cycles and surgical timing, efficacy assessment, use of biomarkers, management of special populations and immune related adverse events, principles for immunotherapy rechallenge, and function preservation strategies. After multiple rounds of panel discussion and through anonymous voting using the Delphi method, the following consensus statements have been formulated: 1) Neoadjuvant therapy with PD-1 inhibitors can be used preoperatively in patients with locally advanced OSCC. The preferred regimen is a PD-1 inhibitor combined with platinum based chemotherapy, administered for 2-3 cycles. 2) During the efficacy evaluation of neoadjuvant therapy, radiographic assessment should follow the dual criteria of Response Evaluation Criteria in Solid Tumors (RECIST) version 1.1 and immune RECIST (iRECIST). After surgery, systematic pathological evaluation of both the primary lesion and regional lymph nodes is required. For combination chemotherapy regimens, PD-L1 expression and combined positive score need not be used as mandatory inclusion or exclusion criteria. 3) For special populations such as the elderly (≥ 70 years), individuals with stable HIV viral load, and carriers of chronic HBV/HCV, PD-1 inhibitors may be used cautiously under the guidance of a multidisciplinary team (MDT), with close monitoring for adverse events. 4) For patients with a poor response to neoadjuvant therapy, continuation of the original treatment regimen is not recommended; the subsequent treatment plan should be adjusted promptly after MDT assessment. Organ transplant recipients and patients with active autoimmune diseases are not recommended to receive neoadjuvant PD-1 inhibitor therapy due to the high risk of immune related activation. Rechallenge is generally not advised for patients who have experienced high risk immune related adverse events such as immune mediated myocarditis, neurotoxicity, or pneumonitis. 5) For patients with a good pathological response, individualized de escalation surgery and function preservation strategies can be explored. This consensus aims to promote the standardized, safe, and precise application of neoadjuvant PD-1 inhibitor strategies in the management of locally advanced OSCC patients.

OBJECTIVE To explore and establish a full-cycle management model for drug traceability codes that aligns with national policy requirements and the practical needs of healthcare institutions， thereby enhancing the refinement of drug management and the level of medication safety. METHODS A tripartite strategy integrating “hardware deployment， system transformation， and process re-engineering” was adopted. This involved the introduction of intelligent identification devices （personal digital assistant， high-definition industrial reader）， the modification of the hospital information system interface， and the re-engineering of workflows （drug warehousing， dispensing and distribution， drug withdrawal， uploading to the insurance platform） to achieve comprehensive， informatized collection and association of drug traceability codes throughout all stages. RESULTS A full-cycle management model for drug traceability codes was successfully established， realizing the goals of making drugs “traceable to their source， trackable in their distribution， and accountable in their responsibility”. The patient waiting time for medication dispensing before and after the implementation was [3.08（1.67，5.58）] min and [3.28（1.77，5.98）] min， respectively. Among them， the patient waiting time under the pre-preparation mode was [3.60（2.13，6.35）] min and [3.50（2.03，6.30）] min， respectively； the patient waiting time under the real-time mode was [2.05（0.83，4.03）] min and [2.78（1.18，5.38）] min， respectively； the number of dispensing errors was 3， 0， respectively； the staffing of relevant positions had not been increased. CONCLUSIONS The drug traceability code management model constructed from a full-cycle perspective effectively meets national policy requirements. It provides data support for refined hospital management and offers solid technical and procedural safeguards for ensuring patient medication safety and strengthening medical insurance fund supervision， demonstrating practical value.

ObjectiveDiscriminating atypical hepatocellular carcinoma (HCC) from other malignancies in liver nodules classified as Liver Imaging Reporting and Data System category M (LR-M) remains a significant diagnostic challenge on conventional ultrasound examination. The LR-M category, originally intended to capture non-HCC malignancies, paradoxically contains up to 63% of atypical HCCs that deviate from classic enhancement patterns, leading to potential misdiagnosis and suboptimal treatment planning. While deep learning has shown promise in HCC diagnosis, most existing models rely exclusively on single-modality ultrasound, overlooking the diagnostic benefits of integrating complementary information from multiple imaging sources. To address this gap, we propose a novel attention-weighted tri-modal ultrasound network (TUS-Net) that integrates contrast-enhanced ultrasound (CEUS), B-mode ultrasound (BUS), and time-intensity curves (TICs) to improve diagnostic accuracy for these clinically challenging lesions. MethodsOur framework incorporates a three-dimensional convolutional neural network (C3D) backbone to extract spatiotemporal features from CEUS videos, capturing dynamic vascular patterns critical for lesion characterization. To effectively fuse complementary modalities, we introduce a dual-channel feature fusion module (DCFFM) that adaptively combines features from CEUS and BUS through channel-wise attention mechanisms, allowing the model to dynamically weigh the contribution of each modality based on diagnostic relevance. Additionally, we propose a temporal intensity feature fusion module (TIFFM) that leverages quantitative hemodynamic information from TICs to guide the model’s attention toward diagnostically critical temporal phases, such as arterial wash-in and portal venous washout. The model is further enhanced by automated lesion localization using YOLOX and class activation mapping for interpretability, ensuring that predictions align with clinically meaningful imaging features. ResultsEvaluated on a tri-modal ultrasound dataset comprising 161 patients with pathologically confirmed LR-M nodules (131 atypical HCC and 30 non-HCC malignancies), our model achieved an accuracy of 86.83%, a sensitivity of 92.50%, a specificity of 75.50%, and an AUC of 89.32% in screening atypical HCC. Compared to single-modality baselines, TUS-Net demonstrated superior specificity, a clinically critical metric given the higher risk associated with misclassifying non-HCC malignancies. Ablation studies confirmed the contribution of each module, with the full model outperforming both standard C3D and 3D ResNet backbones integrated with attention mechanisms. A reader study involving junior and senior radiologists further validated the clinical utility of AI assistance, showing consistent improvements in specificity and inter-reader consistency, particularly for less experienced clinicians. ConclusionThese results surpass existing benchmark models and demonstrate the potential of our approach to enhance diagnostic precision in clinically specific cases. By intelligently fusing multi-modal ultrasound data with attention-guided mechanisms, TUS-Net offers a reliable and interpretable tool that holds promise for improving the non-invasive diagnosis of atypical HCC in challenging LR-M liver nodules.

ObjectiveDiscriminating atypical hepatocellular carcinoma (HCC) from other malignancies in liver nodules classified as Liver Imaging Reporting and Data System category M (LR-M) remains a significant diagnostic challenge on conventional ultrasound examination. The LR-M category, originally intended to capture non-HCC malignancies, paradoxically contains up to 63% of atypical HCCs that deviate from classic enhancement patterns, leading to potential misdiagnosis and suboptimal treatment planning. While deep learning has shown promise in HCC diagnosis, most existing models rely exclusively on single-modality ultrasound, overlooking the diagnostic benefits of integrating complementary information from multiple imaging sources. To address this gap, we propose a novel attention-weighted tri-modal ultrasound network (TUS-Net) that integrates contrast-enhanced ultrasound (CEUS), B-mode ultrasound (BUS), and time-intensity curves (TICs) to improve diagnostic accuracy for these clinically challenging lesions. MethodsOur framework incorporates a three-dimensional convolutional neural network (C3D) backbone to extract spatiotemporal features from CEUS videos, capturing dynamic vascular patterns critical for lesion characterization. To effectively fuse complementary modalities, we introduce a dual-channel feature fusion module (DCFFM) that adaptively combines features from CEUS and BUS through channel-wise attention mechanisms, allowing the model to dynamically weigh the contribution of each modality based on diagnostic relevance. Additionally, we propose a temporal intensity feature fusion module (TIFFM) that leverages quantitative hemodynamic information from TICs to guide the model’s attention toward diagnostically critical temporal phases, such as arterial wash-in and portal venous washout. The model is further enhanced by automated lesion localization using YOLOX and class activation mapping for interpretability, ensuring that predictions align with clinically meaningful imaging features. ResultsEvaluated on a tri-modal ultrasound dataset comprising 161 patients with pathologically confirmed LR-M nodules (131 atypical HCC and 30 non-HCC malignancies), our model achieved an accuracy of 86.83%, a sensitivity of 92.50%, a specificity of 75.50%, and an AUC of 89.32% in screening atypical HCC. Compared to single-modality baselines, TUS-Net demonstrated superior specificity, a clinically critical metric given the higher risk associated with misclassifying non-HCC malignancies. Ablation studies confirmed the contribution of each module, with the full model outperforming both standard C3D and 3D ResNet backbones integrated with attention mechanisms. A reader study involving junior and senior radiologists further validated the clinical utility of AI assistance, showing consistent improvements in specificity and inter-reader consistency, particularly for less experienced clinicians. ConclusionThese results surpass existing benchmark models and demonstrate the potential of our approach to enhance diagnostic precision in clinically specific cases. By intelligently fusing multi-modal ultrasound data with attention-guided mechanisms, TUS-Net offers a reliable and interpretable tool that holds promise for improving the non-invasive diagnosis of atypical HCC in challenging LR-M liver nodules.

To address the growing challenge of an increasing number of elderly lung cancer patients amidst China's aging population and to fill the gap in quality control standards for surgical treatment in this special population, this study aimed to develop a standardized surgical evaluation system for elderly lung cancer patients tailored to China's national conditions. The system was established through a literature review, integrated the pathophysiological characteristics of elderly patients, and was constructed following review, feedback, and revision by experts from multiple thoracic surgery centers. Employing a 100-point scoring system, it comprises three primary domains: physical infrastructure and geriatric adaptability foundational conditions (10 points); management level and perioperative care models (20 points); and technical proficiency and clinical outcomes (70 points). The system places a strong emphasis on geriatric adaptability, proposing specific, quantifiable indicators for age-friendly facility modifications, control of elderly-specific complications, multidisciplinary collaboration, and standardized perioperative management. It provides a convenient and measurable assessment tool for quality control in the surgical treatment of elderly lung cancer in China, which is expected to promote the standardization and homogenization of diagnosis and treatment.

Lung cancer constitutes the most prevalent and lethal malignant tumor in China. Approximately 85% of lung cancer diagnoses correspond to the non-small cell histological subtype [non-small cell lung cancer (NSCLC)]. Despite surgery being the mainstay for early-stage disease, postoperative recurrence remains high and adjuvant chemotherapy offers limited benefit. In recent years, targeted therapy has demonstrated substantial advantages in driver mutation-positive NSCLC. To this end, the Lung Cancer Medical Education Committee of the Chinese Medical Education Association developed guidelines based on a systematic review of evidence through November 2025, using the Grading of Recommendations, Assessment, Development and Evaluations (GRADE) approach and a modified Delphi method. Focusing on epidermal growth factor receptor (EGFR) and anaplastic lymphoma kinase (ALK), and addressing ROS proto-oncogene 1 (ROS1), B-Raf proto-oncogene serine/threonine kinase (BRAF) V600E mutation, and mesenchymal-epithelial transition factor (MET) exon 14 (METex14) skipping, the guideline covers molecular testing, neoadjuvant/adjuvant therapy, perioperative strategies, minimal residual disease monitoring, and postoperative surveillance. It defines testing requirements, specifies stage-directed and subtype-specific treatments, and standardizes minimal residual disease monitoring. These recommendations emphasize precision and feasibility to improve survival and quality of life.

Objective Jejunal interposition is an important option for restoring gastrointestinal continuity in patients with complex esophageal cancer in whom the stomach is unavailable for reconstruction due to previous gastrectomy, tumor involvement, failed gastric conduit, or other constraints. Although the jejunum offers a caliber similar to the esophagus, a rich blood supply, and preserved peristaltic function, anatomical variations in mesenteric length and vascular arcades render long-segment and high-level reconstruction susceptible to excessive tension, mesenteric torsion, venous congestion, and inadequate distal perfusion. This consensus aims to provide standardized recommendations for the application of jejunal interposition in this specific patient population. Methods This consensus was developed in accordance with the WHO Handbook for Guideline Development and Chinese national guideline development standards, with reference to the Appraisal of Guidelines for Research & Evaluation Ⅱ(AGREE Ⅱ), Reporting Items for Practice Guidelines in Healthcare (RIGHT), and Scientific, Transparent and Applicable Rankings (STAR) checklists. The project was registered on the international practice guidelines registry platform (PREPARE-2026CN1384). The working group systematically searched Chinese and English evidence addressing 12 clinical questions. Evidence was graded using the Oxford Centre for Evidence-Based Medicine (OCEBM) 2009 system, with structured appraisal of risk of bias, inconsistency, indirectness, and imprecision. Recommendations were formulated through two rounds of Delphi surveys and a face-to-face consensus meeting, with an agreement threshold of ≥75%. Results The consensus generated 12 recommendations covering indications, selection between jejunum and colon, preoperative assessment, surgical approach and reconstruction route, pedicled jejunal interposition (PJI), supercharged pedicled jejunal interposition (SPJ), indocyanine green (ICG) perfusion assessment, perioperative nutrition, management of anastomotic leakage, long-term follow-up, and special treatment scenarios. Given that the available direct evidence is predominantly derived from single-center retrospective cohorts and case series, recommendations extrapolated from general esophagectomy or other gastrointestinal surgical evidence are deliberately phrased with caution. Conclusion Jejunal interposition is a safe and effective approach for digestive tract reconstruction in patients with complex esophageal cancer in whom the stomach is unavailable. This consensus emphasizes that clinical decision-making should be individualized based on the patient's prior treatment history, reconstruction height, vascular anatomy, technical availability, and institutional experience in the Chinese context.

The recombinant human thyroid-stimulating hormone (rhTSH) can be used for differentiated thyroid cancer (DTC) preparation before ¹³¹I therapy, and follow-up. Since its approval by the American Food and Drug Administration (FDA) in 1998, rhTSH has been clinically used in European countries, the United States, and other countries for nearly 30 years. In April 2024, China’s first independently developed rhTSH agent was approved. Based on clinical experience and evidence from domestic and international studies, an expert consensus on the application of rhTSH has been developed following thorough consultations among experts. The consensus offers evidence-based recommendations to guide the appropriate use of rhTSH in clinical practice.

OBJECTIVE To provide technical support for improving recognition rate of adverse drug events （ADEs） related to traditional Chinese medicine （TCM） formula granules and decoction pieces among inpatient patients. METHODS By referencing the global trigger tool （GTT） whitepaper， literature on adverse reactions to TCM， and expert review opinions， ADE trigger items for TCM formula granules and decoction pieces used in the inpatients were established. GTT was applied to analyze ADEs in inpatients who had used TCM formula granules and decoction pieces in our hospital from August 2013 to August 2023， utilizing the Chinese Hospital Pharmacovigilance System. The effectiveness of GTT and the characteristics of these ADEs were analyzed. RESULTS A total of forty-eight triggers were established， including thirty-two laboratory test indexes， thirteen clinical symptoms， and three antidotes. Among the 1 682 patients included， GTT identified 652 potential ADEs， 284 true positive ADEs，with a trigger rate of 38.76% and a positive predictive value of 43.56%. After review by the auditor， 278 cases of ADEs were finally confirmed， with an incidence rate of 16.53%， significantly higher than the number of spontaneously reported ADEs during the same period （0）. The 278 cases of ADEs were mostly grade 1 （223 cases）， mainly involving hepatobiliary system， gastrointestinal system， blood- lymphatic system， etc；a total of 219 types of TCMs are involved，and the top five suspected TCMs used at a frequency higher than 1% were Poria cocos， Codonopsis pilosula， Atractylodes macrocephala， fried Glycyrrhiza uralensis， and Scutellaria baicalensis. CONCLUSIONS The established GTT can improve the recognition rate of ADEs for hospitalized patients using traditional Chinese medicine formula granules and decoction pieces.

ObjectivePrimary liver cancer, predominantly hepatocellular carcinoma (HCC), is a significant global health issue, ranking as the sixth most diagnosed cancer and the third leading cause of cancer-related mortality. Accurate and early diagnosis of HCC is crucial for effective treatment, as HCC and non-HCC malignancies like intrahepatic cholangiocarcinoma (ICC) exhibit different prognoses and treatment responses. Traditional diagnostic methods, including liver biopsy and contrast-enhanced ultrasound (CEUS), face limitations in applicability and objectivity. The primary objective of this study was to develop an advanced, light-weighted classification network capable of distinguishing HCC from other non-HCC malignancies by leveraging the automatic analysis of brightness changes in CEUS images. The ultimate goal was to create a user-friendly and cost-efficient computer-aided diagnostic tool that could assist radiologists in making more accurate and efficient clinical decisions. MethodsThis retrospective study encompassed a total of 161 patients, comprising 131 diagnosed with HCC and 30 with non-HCC malignancies. To achieve accurate tumor detection, the YOLOX network was employed to identify the region of interest (ROI) on both B-mode ultrasound and CEUS images. A custom-developed algorithm was then utilized to extract brightness change curves from the tumor and adjacent liver parenchyma regions within the CEUS images. These curves provided critical data for the subsequent analysis and classification process. To analyze the extracted brightness change curves and classify the malignancies, we developed and compared several models. These included one-dimensional convolutional neural networks (1D-ResNet, 1D-ConvNeXt, and 1D-CNN), as well as traditional machine-learning methods such as support vector machine (SVM), ensemble learning (EL), k-nearest neighbor (KNN), and decision tree (DT). The diagnostic performance of each method in distinguishing HCC from non-HCC malignancies was rigorously evaluated using four key metrics: area under the receiver operating characteristic (AUC), accuracy (ACC), sensitivity (SE), and specificity (SP). ResultsThe evaluation of the machine-learning methods revealed AUC values of 0.70 for SVM, 0.56 for ensemble learning, 0.63 for KNN, and 0.72 for the decision tree. These results indicated moderate to fair performance in classifying the malignancies based on the brightness change curves. In contrast, the deep learning models demonstrated significantly higher AUCs, with 1D-ResNet achieving an AUC of 0.72, 1D-ConvNeXt reaching 0.82, and 1D-CNN obtaining the highest AUC of 0.84. Moreover, under the five-fold cross-validation scheme, the 1D-CNN model outperformed other models in both accuracy and specificity. Specifically, it achieved accuracy improvements of 3.8% to 10.0% and specificity enhancements of 6.6% to 43.3% over competing approaches. The superior performance of the 1D-CNN model highlighted its potential as a powerful tool for accurate classification. ConclusionThe 1D-CNN model proved to be the most effective in differentiating HCC from non-HCC malignancies, surpassing both traditional machine-learning methods and other deep learning models. This study successfully developed a user-friendly and cost-efficient computer-aided diagnostic solution that would significantly enhances radiologists’ diagnostic capabilities. By improving the accuracy and efficiency of clinical decision-making, this tool has the potential to positively impact patient care and outcomes. Future work may focus on further refining the model and exploring its integration with multimodal ultrasound data to maximize its accuracy and applicability.