Identification of cancer-associated fibroblast-related Ectodysplasin-A as a novel indicator for prognosis and immune response in gastric cancer.

Studies have indicated cancer-associated fibroblasts (CAFs) could have a significant impact in gastric cancer (GC) progression and chemotherapy resistance. However, the gene related to cancer fibroblasts that can be used as biomarkers to judge the occurrence of gastric cancer has not been fully explored. Based on two Gene Expression Omnibus (GEO) datasets, we focus on differentially expressed genes which may act as CAFs markers related to GC. Through COX regression, LASSO regression and Kaplan-Meier survival analysis, we discovered three upregulated genes (GLT8D2, GNAS and EDA) associated with poor GC patients' survival. By single-cell analysis and nomogram, we found that EDA may affect fibroblast production and disease prognosis in GC patients. EDA expression showed a positive correlation with 5-Fluorouracil IC50 values. Immunohistochemistry (IHC) and real time PCR indicated elevated EDA levels in GC tissues and cells. Enrichment analysis revealed that EDA was closely linked to immune system regulation. IHC and single-cell analysis indicated that EDA gene was associated with cancer fibroblasts marker FGF12 and influence cell interferon-gamma response, which may play a role in regulating immune-related characteristics. In summary, we concluded that EDA may be used as a new therapeutic CAFs marker for GC.

Morphological characterization and distribution of antennal sensilla of Spodoptera frugiperda (Lepidoptera: Noctuidae) using scanning electron microscopy.

The fall armyworm (FAW), Spodoptera frugiperda (J. E. Smith) (Lepidoptera: Noctuidae), is a globally significant agricultural pest, causing severe damage to corn production in China. Chemical odor-based trapping is a major approach for FAW control, making it essential to understand the FAW antennal sensillum types to enhance development of effective chemical odor attractants. In this study, we comprehensively examined the antennal sensilla types of FAW, identifying eight types and two subtypes, including Böhm's bristles, sensilla trichoidea, sensilla chaetica (I and II), sensilla coeloconica, sensilla styloconica, sensilla squamiformia (I and II), sensilla auricillica, and sensilla basiconica. Sensilla chaetica II, and sensilla squamiformia II are reported for the first time for FAW in this study. Detailed low-voltage field emission scanning electron microscope (LVSEM) images and descriptions are provided for each sensillum type. This study provides the morphological information to aid in conducting antennal sensillum neurophysiological tests on FAW. RESEARCH HIGHLIGHTS: The types of sensilla of fall armyworm were examined, identifying eight types and two subtypes, including Böhm's bristles, sensilla trichoidea, sensilla chaetica (I and II), sensilla coeloconica, sensilla styloconica, sensilla squamiformia (I and II), sensilla auricillica, and sensilla basiconica. Detailed low-voltage field emission scanning electron microscope images and descriptions were provided for each sensillum type.

Remote levodopa challenge test in Parkinson's disease: Feasibility, reliability, validity and economic value.

BACKGROUND AND PURPOSE: The aim was to demonstrate the feasibility, reliability and validity of an in-home remote levodopa challenge test (LCT), as delivered through an online platform, for patients with Parkinson's disease (PwPD). METHODS: Patients with Parkinson's disease eligible for deep brain stimulation surgery screening were enrolled. Participants sequentially received an in-home remote LCT and an in-hospital standard LCT (separated by 2.71 weeks). A modified Movement Disorder Society Unified Parkinson's Disease Rating Scale Part III omitting rigidity and postural stability items was used in the remote LCT. The reliability of the remote LCT was evaluated using the intraclass correlation coefficient and the concurrent validity was evaluated using the Pearson's correlation coefficient r between the levodopa responsiveness of the remote and standard LCT. RESULTS: Out of 106 PwPD screened, 80 (75.5%) completed both the remote and standard LCT. There was a good reliability (intraclass correlation coefficient 0.81, 95% confidence interval 0.69-0.88) and a strong correlation (r = 0.84, 95% confidence interval 0.77-0.90) between the levodopa responsiveness of the remote and standard LCT. The mean cost for PwPD was estimated to be reduced by 91% by using the remote LCT. CONCLUSION: The remote LCT is feasible, reliable and valid and may reduce healthcare-related costs for PwPD and their caregivers.

Novel progressive deep learning algorithm for uncovering multiple single nucleotide polymorphism interactions to predict paclitaxel clearance in patients with nonsmall cell lung cancer.

Background: The rate at which the anticancer drug paclitaxel is cleared from the body markedly impacts its dosage and chemotherapy effectiveness. Importantly, paclitaxel clearance varies among individuals, primarily because of genetic polymorphisms. This metabolic variability arises from a nonlinear process that is influenced by multiple single nucleotide polymorphisms (SNPs). Conventional bioinformatics methods struggle to accurately analyze this complex process and, currently, there is no established efficient algorithm for investigating SNP interactions. Methods: We developed a novel machine-learning approach called GEP-CSIs data mining algorithm. This algorithm, an advanced version of GEP, uses linear algebra computations to handle discrete variables. The GEP-CSI algorithm calculates a fitness function score based on paclitaxel clearance data and genetic polymorphisms in patients with nonsmall cell lung cancer. The data were divided into a primary set and a validation set for the analysis. Results: We identified and validated 1184 three-SNP combinations that had the highest fitness function values. Notably, SERPINA1, ATF3 and EGF were found to indirectly influence paclitaxel clearance by coordinating the activity of genes previously reported to be significant in paclitaxel clearance. Particularly intriguing was the discovery of a combination of three SNPs in genes FLT1, EGF and MUC16. These SNPs-related proteins were confirmed to interact with each other in the protein-protein interaction network, which formed the basis for further exploration of their functional roles and mechanisms. Conclusion: We successfully developed an effective deep-learning algorithm tailored for the nuanced mining of SNP interactions, leveraging data on paclitaxel clearance and individual genetic polymorphisms.

Fine and combinatorial regulation of key metabolic pathway for enhanced ß-alanine biosynthesis with non-inducible Escherichia coli.

ß-Alanine is the only ß-amino acid in nature and one of the most important three-carbon chemicals. This work was aimed to construct a non-inducible ß-alanine producer with enhanced metabolic flux towards ß-alanine biosynthesis in Escherichia coli. First of all, the assembled E. coli endogenous promoters and 5'-untranslated regions (PUTR) were screened to finely regulate the combinatorial expression of genes panDBS and aspBCG for an optimal flux match between two key pathways. Subsequently, additional copies of key genes (panDBS K104S and ppc) were chromosomally introduced into the host A1. On these bases, dynamical regulation of the gene thrA was performed to reduce the carbon flux directed in the competitive pathway. Finally, the ß-alanine titer reached 10.25 g/L by strain A14-R15, 361.7% higher than that of the original strain. Under fed-batch fermentation in a 5-L fermentor, a titer of 57.13 g/L ß-alanine was achieved at 80 h. This is the highest titer of ß-alanine production ever reported using non-inducible engineered E. coli. This metabolic modification strategy for optimal carbon flux distribution developed in this work could also be used for the production of various metabolic products.

Strategies to improve the design of gapmer antisense oligonucleotide on allele-specific silencing.

Gapmer antisense oligonucleotides (ASOs) hold therapeutic promise for allele-specific silencing, but face challenges in distinguishing between mutant and wild-type transcripts. This study explores new design strategies to enhance ASO specificity, focusing on a common dominant mutation in COL6A3 gene associated with Ullrich congenital muscular dystrophy. Initial gapmer ASO design exhibited high efficiency but poor specificity for the mutant allele. We then adopted a mixmer design, incorporating additional RNA bases based on computational predictions of secondary structures for both mutant and wild-type alleles, aiming to enhance ASO accessibility to mutant transcripts. The mixmer ASO design demonstrated up to a 3-fold increase in specificity compared with the classical gapmer design. Further refinement involved introducing a nucleotide mismatch as a structural modification, resulting in a 10-fold enhancement in specificity compared with the gapmer design and a 3-fold over the mixmer design. Additionally, we identified for the first time a potential role of the RNA-induced silencing complex (RISC), alongside RNase H1, in gapmer-mediated silencing, in contrast with what was observed with mixmer ASOs, where only RNase H1 was involved. In conclusion, this study presents a novel design concept for allele-specific ASOs leveraging mRNA secondary structures and nucleotide mismatching and suggests a potential involvement of RISC in gapmer-mediated silencing.

Clickable tryptophan modification for late-stage diversification of native peptides.

As the least abundant residue in proteins, tryptophan widely exists in peptide drugs and bioactive natural products and contributes to drug-target interactions in multiple ways. We report here a clickable tryptophan modification for late-stage diversification of native peptides, via catalyst-free C2-sulfenylation with 8-quinoline thiosulfonate reagents in trifluoroacetic acid (TFA). A wide range of groups including trifluoromethylthio (SCF3), difluoromethylthio (SCF2H), (ethoxycarbonyl)difluoromethylthio (SCF2CO2Et), alkylthio, and arylthio were readily incorporated. The rapid reaction kinetics of Trp modification and full tolerance with other 19 proteinogenic amino acids, as well as the super dissolving capability of TFA, render this method suitable for all kinds of Trp-containing peptides without limitations from sequences, hydrophobicity, and aggregation propensity. The late-stage modification of 15 therapeutic peptides (1.0 to 7.6 kilodaltons) and the improved bioactivity and serum stability of SCF3- and SCF2H-modified melittin analogs illustrated the effectiveness of this method and its potential in pharmacokinetic property improvement.

Piperacillin/tazobactam treatment in children: evidence of subtherapeutic concentrations.

Objective: Piperacillin/tazobactam (PIP/TAZ) is used for the treatment of lower respiratory tract bacterial infections in children. This study was performed to evaluate if the current dosing regimen results in therapeutic drug concentrations. Patients and methods: Patients suspected or proven to have lower respiratory tract bacterial infection and administrated PIP/TAZ intravenously for a duration of no less than 0.5 h, q6h-q12h daily, were enrolled. Blood samples were collected, and PIP concentrations were determined by high-performance liquid chromatography. The individual predicted concentration of PIP was evaluated using the individual empirical Bayesian estimate method. The evaluated PK/PD targets included (1) 70% time when the predicted free drug concentration exceeds the minimum inhibitory concentration (fT > MIC) and (2) 50% fT > 4× MIC. Probability of target attainment (PTA) was assessed by the proportion of patients who reached the PK/PD targets. The PIP concentrations between different groups of patients were compared. Results: A total of 57 samples were collected from 57 patients with a median age of 2.26 years (0.17-12.58). For the PK/PD targets of 70% fT > MIC and 50% fT > 4× MIC for Pseudomonas aeruginosa and Klebsiella pneumoniae, the PTA was all 0. The median Cmin of PIP was significantly higher in infants than in children, and the median Cmin after administration in q8h was significantly higher than that after administration in q12h. Conclusion: The current dose regimen of PIP/TAZ leads to extremely low plasma concentrations in most children with lower respiratory tract bacterial infections. More optimized dosing regimens or better alternative therapies need to be further explored.

Trifluoroacetic Acid Mediated Additive-Free Late-Stage Native Peptide Cyclization to Form Disulfide Mimetics via Thioketalization with Ketones.

Peptide cyclization is often used to introduce conformational rigidity and to enhance the physiological stability of the peptide. This study presents a novel late-stage cyclization method for creating thioketal cyclic peptides from bis-cysteine peptides and drugs. Symmetrical cyclic ketones and acetone were found to react with bis-cysteine unprotected peptides efficiently to form thioketal linkages in trifluoroacetic acid (TFA) without any other additive. The attractive features of this method include high chemoselectivity, operational simplicity, and robustness. In addition, TFA as the reaction solvent can dissolve any unprotected peptide. As a showcase, the dimethyl thioketal versions of lanreotide and octreotide were prepared and evaluated, both of which showed much improved reductive stability and comparable activity.

Predictive modeling of lower extreme deep vein thrombosis following radical gastrectomy for gastric cancer: based on multiple machine learning methods.

Postoperative venous thromboembolic events (VTEs), such as lower extremity deep vein thrombosis (DVT), are major risk factors for gastric cancer (GC) patients following radical gastrectomy. Accurately predicting and managing these risks is crucial for optimal patient care. This retrospective case‒control study involved 693 GC patients from our hospital who underwent radical gastrectomy. We collected plentiful and comprehensive clinical indicators including a total of 49 baseline, preoperative, surgical and pathological clinical data. Using univariate logistic regression, we identified potential risk factors, followed by feature selection through the Boruta algorithm. We then constructed the final predictive model using multivariate logistic regression and evaluated it using receiver operating characteristic (ROC) curve analysis, calibration plots, decision curve analysis, and other methods. Additionally, we applied various machine learning techniques, including decision trees and random forests, to assess our model's predictive strength. This retrospective case‒control study involved 693 GC patients from our hospital who underwent radical gastrectomy. We collected plentiful and comprehensive clinical indicators including a total of 49 baseline, preoperative, surgical and pathological clinical data. Using univariate logistic regression, we identified potential risk factors, followed by feature selection through the Boruta algorithm. We then constructed the final predictive model using multivariate logistic regression and evaluated it using receiver operating characteristic (ROC) curve analysis, calibration plots, decision curve analysis, and other methods. Additionally, we applied various machine learning techniques, including decision trees and random forests, to assess our model's predictive strength. Univariate logistic analysis revealed 14 risk factors associated with postoperative lower limb DVT. Based on the Boruta algorithm, six significant clinical factors were selected, namely, age, D-dimer (D-D) level, low-density lipoprotein, CA125, and calcium and chloride ion levels. A nomogram was developed using the outcomes from the multivariate logistic regression analysis. The predictive model showed high accuracy, with an area under the curve of 0.936 in the training set and 0.875 in the validation set. Various machine learning algorithms confirmed its strong predictive capacity. MR analysis revealed meaningful causal relationships between key clinical factors and DVT risk. Based on various machine learning methods, we developed an effective predictive diagnostic model for postoperative lower extremity DVT in GC patients. This model demonstrated excellent predictive value in both the training and validation sets. This novel model is a valuable tool for clinicians to use in identifying and managing thrombotic risks in this patient population.

Collaborative management of environmental pollution and carbon emissions drives local green growth: An analysis based on spatial effects.

Collaborative management of environmental pollution and carbon emissions (CMPC) has been a major policy instrument to promote Sustainable Development Goals (SDG) in recent years. However, the relationship between the benefits and drawbacks of this environmental management practice for green growth in and around a local area remains to be clarified. Using 30 provinces in China during 2001-2019 as the object of analysis, we assessed the efficiency of local CMPC practices using the nonradial directional distance function (NDDF) model, predicted local green growth using the frontier green complexity index (GCI), and empirically examined the spatial effects, locational heterogeneity, and threshold characteristics of the relationship using the spatial Durbin model and the panel threshold model. Our study finds that although efficient CMPC does drive local green growth, the promotion effect is nonlinear with decreasing marginal effect. This effect is particularly obvious in economically developed regions with higher CMPCs, which will absorb resources from neighboring regions and create a "siphoning" effect. It was found that local financial support and foreign direct investment (FDI) can radiate green growth to neighboring regions; therefore, CMPC practice needs to pay more attention to the effect of joint governance, supplemented by financial and foreign investment policy tools, to better promote the green transformation of local economy.

Impact of age-related gut microbiota dysbiosis and reduced short-chain fatty acids on the autonomic nervous system and atrial fibrillation in rats.

Objective: Aging is the most significant contributor to the increasing prevalence of atrial fibrillation (AF). Dysbiosis of gut microbiota has been implicated in age-related diseases, but its role in AF development remains unclear. This study aimed to investigate the correlations between changes in the autonomic nervous system, short-chain fatty acids (SCFAs), and alterations in gut microbiota in aged rats with AF. Methods: Electrophysiological experiments were conducted to assess AF induction rates and heart rate variability in rats. 16S rRNA gene sequences extracted from fecal samples were used to assess the gut microbial composition. Gas and liquid chromatography-mass spectroscopy was used to identify SCFAs in fecal samples. Results: The study found that aged rats exhibited a higher incidence of AF and reduced heart rate variability compared to young rats. Omics research revealed disrupted gut microbiota in aged rats, specifically a decreased Firmicutes to Bacteroidetes ratio. Additionally, fecal SCFA levels were significantly lower in aged rats. Importantly, correlation analysis indicated a significant association between decreased SCFAs and declining heart rate variability in aged rats. Conclusions: These findings suggest that SCFAs, as metabolites of gut microbiota, may play a regulatory role in autonomic nervous function and potentially influence the onset and progression of AF in aged rats. These results provide novel insights into the involvement of SCFAs and autonomic nervous system function in the pathogenesis of AF. These results provide novel insights into the involvement of SCFAs and autonomic nervous system function in the pathogenesis of AF.

Deciphering the lipid-cancer nexus: comprehensive Mendelian randomization analysis of the associations between lipid profiles and digestive system cancer susceptibility.

BACKGROUND: Digestive system cancers represent a significant global health challenge and are attributed to a combination of demographic and lifestyle changes. Lipidomics has emerged as a pivotal area in cancer research, suggesting that alterations in lipid metabolism are closely linked to cancer development. However, the causal relationship between specific lipid profiles and digestive system cancer risk remains unclear. METHODS: Using a two-sample Mendelian randomization (MR) approach, we elucidated the causal relationships between lipidomic profiles and the risk of five types of digestive system cancer: stomach, liver, esophageal, pancreatic, and colorectal cancers. The aim of this study was to investigate the effect impact of developing lipid profiles on the risk of digestive system cancers utilizing data from public databases such as the GWAS Catalog and the UK Biobank. The inverse‒variance weighted (IVW) method and other strict MR methods were used to evaluate the potential causal links. In addition, we performed sensitivity analyses and reverse MR analyses to ensure the robustness of the results. RESULTS: Significant causal relationships were identified between certain lipidomic traits and the risk of developing digestive system cancers. Elevated sphingomyelin (d40:1) levels were associated with a reduced risk of developing gastric cancer (odds ratio (OR) = 0.68, P < 0.001), while elevated levels of phosphatidylcholine (16:1_20:4) increased the risk of developing esophageal cancer (OR = 1.31, P = 0.02). Conversely, phosphatidylcholine (18:2_0:0) had a protective effect against colorectal cancer (OR = 0.86, P = 0.036). The bidirectional analysis did not suggest reverse causality between cancer risk and lipid levels. Strict MR methods demonstrated the robustness of the above causal relationships. CONCLUSION: Our findings underscore the significant causal relationships between specific lipidomic traits and the risk of developing various digestive system cancers, highlighting the potential of lipid profiles in informing cancer prevention and treatment strategies. These results reinforce the value of MR in unraveling complex lipid-cancer interactions, offering new avenues for research and clinical application.

Estimating the Heterogeneous Causal Effects of Parent-Child Relationships among Chinese Children with Oppositional Defiant Symptoms: A Machine Learning Approach.

Oppositional defiant symptoms are some of the most common developmental symptoms in children and adolescents with and without oppositional defiant disorder. Research has addressed the close association of the parent-child relationship (PCR) with oppositional defiant symptoms. However, it is necessary to further investigate the underlying mechanism for forming targeted intervention strategies. By using a machine learning-based causal forest (CF) model, we investigated the heterogeneous causal effects of the PCR on oppositional defiant symptoms in children in Chinese elementary schools. Based on the PCR improvement in two consecutive years, 423 children were divided into improved and control groups. The assessment of oppositional defiant symptoms (AODS) in the second year was set as the dependent variable. Additionally, several factors based on the multilevel family model and the baseline AODS in the first year were included as covariates. Consistent with expectations, the CF model showed a significant causal effect between the PCR and oppositional defiant symptoms in the samples. Moreover, the causality exhibited heterogeneity. The causal effect was greater in those children with higher baseline AODS, a worse family atmosphere, and lower emotion regulation abilities in themselves or their parents. Conversely, the parenting style played a positive role in causality. These findings enhance our understanding of how the PCR contributes to the development of oppositional defiant symptoms conditioned by factors from a multilevel family system. The heterogeneous causality in the observation data, established using the machine learning approach, could be helpful in forming personalized family-oriented intervention strategies for children with oppositional defiant symptoms.

Application of biomimetic nanovaccines in cancer immunotherapy: A useful strategy to help combat immunotherapy resistance.

Breakthroughs in actual clinical applications have begun through vaccine-based cancer immunotherapy, which uses the body's immune system, both humoral and cellular, to attack malignant cells and fight diseases. However, conventional vaccine approaches still face multiple challenges eliciting effective antigen-specific immune responses, resulting in immunotherapy resistance. In recent years, biomimetic nanovaccines have emerged as a promising alternative to conventional vaccine approaches by incorporating the natural structure of various biological entities, such as cells, viruses, and bacteria. Biomimetic nanovaccines offer the benefit of targeted antigen-presenting cell (APC) delivery, improved antigen/adjuvant loading, and biocompatibility, thereby improving the sensitivity of immunotherapy. This review presents a comprehensive overview of several kinds of biomimetic nanovaccines in anticancer immune response, including cell membrane-coated nanovaccines, self-assembling protein-based nanovaccines, extracellular vesicle-based nanovaccines, natural ligand-modified nanovaccines, artificial antigen-presenting cells-based nanovaccines and liposome-based nanovaccines. We also discuss the perspectives and challenges associated with the clinical translation of emerging biomimetic nanovaccine platforms for sensitizing cancer cells to immunotherapy.

Assessment Methods and Intervention Strategies for Cleft-Related Lateral Misarticulation in Chinese-Speaking Children.

The aim of this study was to analyze the characteristics and error speech features of cleft-related lateral misarticulation and provide a basis for clinical evaluation and rational intervention. Participants who were diagnosed with lateral misarticulation after cleft palate repairment were 126 children aged 4, 6 to 16, and 11, and they had complete palatopharyngeal closure, no abnormalities in their speech organs and occlusion, and no hearing or intellectual impairments. The Chinese standard pronunciation clarity word list, the American KAY CSL4500, the Beijing Yangchen YF-16 computer speech analysis workstation, soundproof rooms, Wechsler scales of intelligence-fourth edition, and audiometers were used to evaluate the cleft-related lateral misarticulation. Statistical analysis was performed on the age, gender, error rate, corner of the mouth deviation direction, comorbidity, duration of intervention, period of treatment, and therapeutic effect of concentrated or normal intervention group in different patients. Our results showed that 2 to 3 straight stripes were visible at the onset of consonants /ti:/ /t'i:/, and 3 clear straight lines were visible in /tʂ/, indicating that the lateralized sound had 2 or 3 bursts and lasted for 1 to 2 ms. The onset age of lateralized sound was mostly below 12 years old. Chinese lateralized sound mainly occurred in vowel /i:/, and the occurrence rate of consonants with tongue surface /tɕ]/ /tɕ'/ /ɕ/ was the highest. In addition, the corner of the mouth deviation was also an indicator of lateralization sound, and other types of speech disorders mostly accompanied it. There was a significant difference in the improvement of speech clarity between the concentrated intervention group and the normal group before and after treatment. The 2 groups' average duration and course of treatment were not significantly different. Still, the period of concentrated intervention was shortened considerably, and the speech clarity of both groups of children after treatment exceeded 96%, reaching a normal level.

Are there any differences in the quality of high-mountain green tea before and after the first new leaves unfold? A comprehensive study based on E-sensors, whole metabolomics and sensory evaluation.

High-mountain green tea, where the first new leaf hasn't yet unfurled, is prized for perceived superior quality, but this hasn't yet been verified by experimentation. Electronic sensors, whole metabolomics and sensory evaluation were employed to assess the quality of yymj (tea buds with a newly unfurled leaf) and qymj (tea buds without new leaves). The qymj proved to have significant advantages in aroma, color and shape, but still had some shortcomings in umami, bitterness and sourness. Differences in the content of volatile organic compounds (including alcohols, hydrocarbons and lipids) and nonvolatile organic compounds (flavonoids, amino acids, sugars, and phenolic acids) quality of high-mountain green teas with different maturity levels and provides well explained these quality differences. This study establishes a systematic approach to study the quality of high-mountain green tea at different maturity levels, and provides important reference information for consumers, governments and tea farmers.

Ultrasound-Based Predictive Model to Assess the Risk of Orbital Malignancies.

OBJECTIVE: Ultrasound (US) is widely used for evaluating various orbital conditions. However, accurately diagnosing malignant orbital masses using US remains challenging. We aimed to develop an ultrasonic feature-based model to predict the presence of malignant tumors in the orbit. METHODS: A total of 510 patients with orbital masses were enrolled between January 2017 and April 2023. They were divided into a development cohort and a validation cohort. In the development cohort (n = 408), the ultrasonic and clinical features with differential values were identified. Based on these features, a predictive model and nomogram were constructed. The diagnostic performance of the model was compared with that of MRI or observers, and further validated in the validation cohort (n = 102). RESULTS: The involvement of more than two quadrants, irregular shape, extremely low echo of the solid part, presence of echogenic foci, cast-like appearance, and two demographic characteristics (age and sex) were identified as independent features related to malignant tumors of the orbit. The predictive model constructed based on these features exhibited better performance in identifying malignant tumors compared to MRI (AUC = 0.78 [95% CI: 0.73, 0.82] vs. 0.69 [95% CI: 0.64, 0.74], p = 0.03) and observers (AUC = 0.93 [95% CI: 0.90, 0.95] vs. Observer 1, AUC = 0.80 [95% CI: 0.76, 0.84], p < 0.01; vs. Observer 2, AUC = 0.71 [95% CI: 0.66, 0.76], p < 0.01). In the validation cohort, the predictive model achieved an AUC of 0.88 (95% CI: 0.81, 0.94). CONCLUSION: The ultrasonic-clinical feature-based predictive model can accurately identify malignant orbital tumors, offering a convenient approach in clinical practice.