Immune checkpoint inhibitors (ICIs) have revolutionized hepatocellular carcinoma (HCC) treatment, while immune-related adverse events (IRAEs) pose significant challenges. We report a 60-year-old male with unresectable HCC who developed Guillain-Barré syndrome (GBS), a rare but severe neurologic complication, after three cycles of sintilimab plus bevacizumab biosimilar and conventional transarterial chemoembolization (c-TACE). The patient presented with progressive ascending weakness, reaching symmetric quadriparesis with proximal muscle strength of 2/5 in upper limbs and 1/5 in lower limbs. Following sintilimab discontinuation, treatment with intravenous immunoglobulin (2 g/kg) and oral prednisone (30 mg/day) achieved complete neurological recovery within one month. Given the patient’s favorable initial tumor response and strong request, immunotherapy was cautiously reinstated using tislelizumab after thorough clinical evaluation. Following four cycles of treatment, significant tumor response enabled successful conversion surgery with major pathological response (necrosis rate >70%). With 26-month survival and no evidence of recurrence, this case demonstrates the potential feasibility of ICI rechallenge with an alternative PD-1 inhibitor following sintilimab-induced GBS. Our experience suggests that ICI-related neurological adverse events may be drug-specific rather than class-specific, potentially providing valuable treatment options for patients showing favorable tumor response despite experiencing severe IRAEs, though larger studies are needed for validation.

Background: Liver metastasis is the most common site of metastasis in pancreatic neuroendocrine tumors (PaNETs), significantly affecting patient prognosis. This study aims to develop machine learning algorithms to predict liver metastasis in PaNETs patients, assisting clinicians in the personalized clinical decision-making for treatment.Methods: We collected data on eligible PaNETs patients from the Surveillance, Epidemiology, and End Results (SEER) database for the period from 2010 to 2021. The Boruta algorithm and the Least Absolute Shrinkage and Selection Operator (LASSO) were used for feature selection. We applied 10 different machine learning algorithms to develop models for predicting the risk of liver metastasis in PaNETs patients. The model’s performance was assessed using a variety of metrics, including the area under the receiver operating characteristic curve (AUC), the area under the precision-recall curve (AUPRC), decision curve analysis (DCA), calibration curves, accuracy, sensitivity, specificity, F1 score, and Kappa score. The SHapley Additive exPlanations (SHAP) were employed to interpret models, and the best-performing model was used to develop a web-based calculator.Results: The study included a cohort of 7,463 PaNETs patients, of whom 1,356 (18.2%) were diagnosed with liver metastasis at the time of initial diagnosis. Through the combined use of the Boruta and LASSO methods, T-stage, N-stage, tumor size, grade, surgery, lymphadenectomy, chemotherapy, and bone metastasis were identified as independent risk factors for liver metastasis in PaNETs. Compared to other machine learning algorithms, the gradient boosting machine (GBM) model exhibited superior performance, achieving an AUC of 0.937 (95% CI: 0.931–0.943), an AUPRC of 0.94, and an accuracy of 0.87. DCA and calibration curve analyses demonstrate that the GBM model provides better clinical decision-making capabilities and predictive performance. Furthermore, the SHAP framework revealed that surgery, N-stage, and T-stage are the primary decision factors influencing the machine learning model’s predictions. Finally, based on the GBM algorithm, we developed an accessible web-based calculator to predict the risk of liver metastasis in PaNETs.Conclusion: The GBM model excels in predicting the risk of liver metastasis in PaNETs patients, outperforming other machine learning models and providing critical support for developing personalized medical strategies in clinical practice.

Background: Pancreatic adenocarcinoma (PAAD) is a lethal disease with a poor prognosis. Genes involved in acute pancreatitis (AP) or chronic pancreatitis (CP) might be important for PAAD development. This study sought to identify potential PAAD diagnosis markers and to establish a PAAD prognosis prediction model based on AP- and CP-related genes. Methods: The significantly differentially expressed genes in both AP or CP and PAAD were obtained by a bioinformatics analysis. A risk-score model for predicting survival was constructed based on The Cancer Genome Atlas (TCGA) data and validated using an International Cancer Genome Consortium (ICGC) cohort. Protein expression and the effects of the genes in the risk models were validated by immunohistochemistry, or Cell Counting Kit-8 (CCK-8) and transwell assays. The study sample data included six AP tissue samples and five normal pancreatic tissue samples, six CP tissue samples and six normal pancreatic tissue samples from the Gene Expression Omnibus (GEO) expression profiling microarrays GSE109227 and GSE41418 data sets, respectively, and fragments per kilobase per million mapped fragments (FPKM) data from four normal controls and 150 PAAD cases from TCGA database, and 182 cancer patient samples with complete survival prognostic data from the ICGC database. Results: In total, 508 significantly differentially expressed genes were found in both AP or CP and PAAD. Trefoil factor 2 (TFF2), tubulointerstitial nephritis antigen (TINAG), trefoil factor 1 (TFF1), aquaporin 5 (AQP5), SAM pointed domain containing ETS transcription factor (SPDEF), anterior gradient protein 2 (AGR2), apolipoprotein B messenger RNA editing enzyme catalytic subunit 1 (APOBEC1), kallikrein-related peptidase 6 (KLK6), dopa decarboxylase (DDC), mucin 13 (MUC13), claudin 18 (CLDN18), annexin A10 (ANXA10), and tetraspanin 1 (TSPAN1) were found to be present in PAAD and had the largest fold change. A risk-score model, comprising 19 genes, was constructed for prognostic prediction. A high-risk score indicated a poor prognosis. TINAG, DDC, SPDEF, and APOBEC1 proteins were increased in PAAD, while TINAG and DDC were correlated with the pathologic grade. Decreased TINAG, APOBEC1, transmembrane protein 94 (TMEM94), and kelch like family member 36 (KLHL36) expression inhibited PAAD cell proliferation, while decreased SPDEF, TMEM94, and KLHL36 expression significantly inhibited PAAD cell migration. Conclusions: The AP and CP co-related genes were significantly correlated with PAAD. TINAG, DDC, SPDEF, and APOBEC1 could serve as new PAAD predictors. The risk model developed in this study could be used to predict the prognosis of PAAD patients.

Background: As a commonly identified cancer in clinics, pancreatic cancer (PC) has poor prognostic outcomes. This work focused on clarifying the association between MIR‐766‐3P expression and PC development and progression, as well as the possible role as a biomarker in PC.Methods: MIR‐766‐3P expression within the human PC cells and samples was measured through miRNA RT‐PCR. The gene levels regulated by MIR‐766‐3P were analyzed through western blot (WB) and qRT‐PCR. To analyze whether MIR‐766‐3P was of certain significance in in vitro and in vivo PC cell proliferation, stemness, and cell cycle progression, the gain/loss‐of‐function assays were performed. Bioinformatics, RNA sequencing (RNA‐seq), and luciferase reporter assay were conducted for exploring regulatory role of MIR‐766‐3P/MAPK1/MAPK/ERK signal axis in PC.Result: In comparison with the normal controls, MIR‐766‐3P expression markedly decreased the tissues and cells of PC. Furthermore, MIR‐766‐3P could remarkably inhibit the proliferation, stemness, cell cycle progression, and development of PC. The analyses using RNA‐seq, and dual‐luciferase examination showed that MIR‐766‐3P could directly target mitogen‐activated protein kinase 1 (MAPK1). According to Gene Ontology (GO) as well as Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis, MIR‐766‐3P could affect PC malignant phenotype by MAPK1 and the regulation of the MAPK/ERK‐related pathway.Conclusion: MIR‐766‐3P has a certain impact on PC malignant phenotype through combining with MAPK1 while regulating MAPK/ERK‐related pathway in vitro and in vivo.