ObjectiveThis study aims to develop and validate a novel multimodal predictive model， termed criss-cross network（CCNet）-directed graph neural network（DGNN）（CGN）， for accurate assessment of pulmonary nodule progression in high-risk individuals for lung cancer， by integrating longitudinal chest computed tomography（CT） imaging with both traditional Chinese and western clinical evaluation data. MethodsA cohort of 4 432 patients with pulmonary nodules was retrospectively analyzed. A twin CCNet was employed to extract spatiotemporal representations from paired sequential CT scans. Structured clinical assessment and imaging-derived features were encoded via a multilayer perceptron， and a similarity-based alignment strategy was adopted to harmonize multimodal imaging features across temporal dimensions. Subsequently， a DGNN was constructed to integrate heterogeneous features， where nodes represented modality-specific embeddings and edges denoted inter-modal information flow. Finally， model optimization was performed using a joint loss function combining cross-entropy and cosine similarity loss， facilitating robust classification of nodule progression status. ResultsThe proposed CGN model demonstrated superior predictive performance on the held-out test set， achieving an area under the receiver operating characteristic curve（AUC） of 0.830， accuracy of 0.843， sensitivity of 0.657， specificity of 0.712， Cohen's Kappa of 0.417， and F₁ score of 0.544. Compared with unimodal baselines， the CGN model yielded a 36%-48% relative improvement in AUC. Ablation studies revealed a 2%-22% increase in AUC when compared to simplified architectures lacking key components， substantiating the efficacy of the proposed multimodal fusion strategy and modular design. Incorporation of traditional Chinese medicine （TCM）-specific symptomatology led to an additional 5% improvement in AUC， underscoring the complementary value of integrating TCM and western clinical data. Through gradient-weighted activation mapping visualization analysis， it was found that the model's attention predominantly focused on nodule regions and effectively captured dynamic associations between clinical data and imaging-derived features. ConclusionThe CGN model， by synergistically combining cross-attention encoding with directed graph-based feature integration， enables effective alignment and fusion of heterogeneous multimodal data. The incorporation of both TCM and western clinical information facilitates complementary feature enrichment， thereby enhancing predictive accuracy for pulmonary nodule progression. This approach holds significant potential for supporting intelligent risk stratification and personalized surveillance strategies in lung cancer prevention.

Objective:To establish a set of artificial intelligence (AI) verification rules for blood routine analysis.Methods:Blood routine analysis data of 18 474 hospitalized patients from the First Hospital of Jilin University during August 1st to 31st, 2019, were collected as training group for establishment of the AI verification rules,and the corresponding patient age, microscopic examination results, and clinical diagnosis information were collected. 92 laboratory parameters, including blood analysis report parameters, research parameters and alarm information, were used as candidate conditions for AI audit rules; manual verification combining microscopy was considered as standard, marked whether it was passed or blocked. Using decision tree algorithm, AI audit rules are initially established through high-intensity, multi-round and five-fold cross-validation and AI verification rules were optimized by setting important mandatory cases. The performance of AI verification rules was evaluated by comparing the false negative rate, precision rate, recall rate, F1 score, and pass rate with that of the current autoverification rules using Chi-square test. Another cohort of blood routine analysis data of 12 475 hospitalized patients in the First Hospital of Jilin University during November 1sr to 31st, 2023, were collected as validation group for validation of AI verification rules, which underwent simulated verification via the preliminary AI rules, thus performance of AI rules were analyzed by the above indicators. Results:AI verification rules consist of 15 rules and 17 parameters and do distinguish numeric and morphological abnormalities. Compared with auto-verification rules, the true positive rate, the false positive rate, the true negative rate, the false negative rate, the pass rate, the accuracy, the precision rate, the recall rate and F1 score of AI rules in training group were 22.7%, 1.6%, 74.5%, 1.3%, 75.7%, 97.2%, 93.5%, 94.7%, 94.1, respectively.All of them were better than auto-verification rules, and the difference was statistically significant ( P<0.001), and with no important case missed. In validation group, the true positive rate, the false positive rate, the true negative rate, the false negative rate, the pass rate, the accuracy, the precision rate, the recall rate and F1 score were 19.2%, 8.2%, 70.1%, 2.5%, 72.6%, 89.2%, 70.0%, 88.3%, 78.1, respectively, Compared with the auto-verification rules, The false negative rate was lower, the false positive rate and the recall rate were slightly higher, and the difference was statistically significant ( P<0.001). Conclusion:A set of the AI verification rules are established and verified by using decision tree algorithm of machine learning, which can identify, intercept and prompt abnormal results stably, and is moresimple, highly efficient and more accurate in the report of blood analysis test results compared with auto-vefication.

Engineered probiotics can serve as therapeutics based on their ability of produce recombinant immune-stimulating properties. In this study, we built the recombinant Bacillus subtilis WB800 expressing antimicrobial peptide KR32 (WB800-KR32) using genetic engineering methods and investigated its protective effects of nuclear factor-E2-related factor 2 (Nrf2)‍-Kelch-like ECH-associated protein 1 (Keap1) pathway activation in intestinal oxidative disturbance induced by enterotoxigenic Escherichia coli (ETEC) K88 in weaned piglets. Twenty-eight weaned piglets were randomly distributed into four treatment groups with seven replicates fed with a basal diet. The feed of the control group (CON) was infused with normal sterilized saline; meanwhile, the ETEC, ETEC+WB800, and ETEC+WB800-KR32 groups were orally administered normal sterilized saline, 5×10¹⁰ CFU (CFU: colony forming units) WB800, and 5×10¹⁰ CFU WB800-KR32, respectively, on Days 1‍‒‍14 and all infused with ETEC K88 1×10¹⁰ CFU on Days 15‍‒‍17. The results showed that pretreatment with WB800-KR32 attenuated ETEC-induced intestinal disturbance, improved the mucosal activity of antioxidant enzyme (catalase (CAT), superoxide dismutase (SOD), and glutathione peroxidase (GPx)) and decreased the content of malondialdehyde (MDA). More importantly, WB800-KR32 downregulated genes involved in antioxidant defense (GPx and SOD1). Interestingly, WB800-KR32 upregulated the protein expression of Nrf2 and downregulated the protein expression of Keap1 in the ileum. WB800-KR32 markedly changed the richness estimators (Ace and Chao) of gut microbiota and increased the abundance of Eubacterium_rectale_ATCC_33656 in the feces. The results suggested that WB800-KR32 may alleviate ETEC-induced intestinal oxidative injury through the Nrf2-Keap1 pathway, providing a new perspective for WB800-KR32 as potential therapeutics to regulate intestinal oxidative disturbance in ETEC K88 infection.
Animals ; Swine ; Enterotoxigenic Escherichia coli ; Kelch-Like ECH-Associated Protein 1 ; Bacillus subtilis ; NF-E2-Related Factor 2 ; Antioxidants ; Oxidative Stress

Objective:To explore the effect of preoperative video education in patients with coronary heart disease after percutaneous coronary intervention (PCI) .Methods:From July 2018 to October 2019, convenience sampling was used to select 110 patients with coronary heart disease who received PCI in the Second Department of Cardiology, the Second Hospital of Hebei Medical University as the research object. According to the random number table, the patients were divided into the control group and the observation group, 55 cases in each group. The control group received conventional preoperative education, while the observation group was given video education on the basis of conventional preoperative education. The mastery of education knowledge, heart rate, anxiety and depression were compared between the two groups.Results:After intervention, there was no significant difference in heart rate between the two groups ( P>0.05) . The mastery of education knowledge, anxiety and depression in the observation group were better than those in the control group, and the differences were statistically significant ( P<0.05) . Conclusions:Preoperative video education can relieve anxiety and depression in patients with coronary heart disease after PCI, improve the effect of health education, and is worthy of popularization and application.

Objective: To investigate the effect of 1q21 amplification (1q) on the therapeutic response and prognosis of bortezomib(Btz) in the treatment of newly diagnosed multiple myeloma (MM) patients. Methods: A total of 180 newly diagnosed MM were included for analyses of clinical characteristics, cytogenetics, objective response rate (ORR), progression-free survival (PFS) and overall survival (OS), retrospectively. Gene expression profiling (GEP) was analyzed using publicly available R2 platform. Results: ① In 180 patients, 1q was found in 51.1% cases. Of them, 174 patients had complete follow-up data, including 88 cases with 1q and 86 without 1q (non-1q). ②Incidence of 1q was positively associated with percentage of IGH rearrangement (72.2%, P=0.017) and 1p deletion (1p) (27.8%, P=0.040). ③ The median PFS was 15.0 and 20.3 months for the 1q group and non-1q group, and the median OS was 29.4 and 44.0 months, respectively. Both PFS and OS of 1q group was significantly shorter than those of the non-1q group (P=0.029 and 0.038, respectively). Multivariate analysis further revealed that 1q was an independent prognostic factor for both PFS (HR=1.910, 95% CI 1.105-3.303, P=0.020) and OS (HR=2.353, 95% CI 1.090-5.078, P=0.029). ④ In 91 evaluable cases with 1q, very good partial remission (VGPR) rate was higher after treatment with Btz than those without Btz (62.1% vs 40.0%, P=0.032). Of note, the patients with 1q who received auto-HSCT after induction with Btz had significantly longer PFS than those without auto-HSCT (19 months vs 13 months, P=0.048). ⑤GEP analysis revealed that 1q21 amplification predominantly up-regulated expression of >50% genes within 1q21 region, and also altered expression of 28% genes in chromosome 1 and 10% genes in whole genome, particularly related to DNA repair and cell cycle. Conclusions 1q is an independent adverse prognostic factor in patients with newly diagnosed MM. It is often associated with 1p deletion and IGH rearrangement. Patients with 1q respond well to Btz-based regimen, but they fail to gain long-term benefit from this treatment itself. However, auto-HSCT following Btz induction might improve survival of patients with 1q, suggesting a potential strategy to treat this high-risk subset of MM. GEP analysis warrants further attention in understanding the mechanisms underlying the high-risk of 1q.