A nomogram for risk stratification of central cervical lymph node metastasis in patients with papillary thyroid carcinoma.

Background: Whether to perform prophylactic central lymph node dissection for cN0 papillary thyroid carcinoma (PTC) patients is still controversial. This retrospective study aimed to develop and validate a nomogram based on ultrasound and dual-energy computed tomography (DECT) for the risk stratification of central lymph node metastasis (CLNM) in patients with PTC. Methods: A total of 525 patients from 2017 to 2019 [Tianjin First Central Hospital (Hospital A)] were retrospectively analyzed to form the training cohort and to conduct internal validation. Another group of 204 patients in 2020 (Hospital A) formed the temporal validation cohort. A total of 107 patients in 2020 [Binzhou Medical University Hospital (Hospital B)] formed the geographic validation cohort, which was a retrospective cohort study. The area under the curve (AUC), calibration curve, and decision curve were used to evaluate the performance of the nomogram. The locally weighted regression curve was used for risk stratification. Results: Diameter, taller-than-wide, calcification, capsular invasion, and iodine concentration in the arterial and venous phases were independent risk predictors of CLNM. The AUC of the nomogram was 0.922 (95% confidence interval: 0.895-0.943) in the training cohort. Two external validation cohorts demonstrated the good performance of the nomogram in predicting CLNM, with AUCs of 0.912 and 0.861. The significantly improved net reclassification index and integrated discriminatory improvement index indicated that DECT was a powerful supplement to ultrasound for predicting CLNM. The risk stratification system divided all patients into low-risk (0-50 points), intermediate-risk (51-100 points), and high-risk groups (>100 points). Conclusions: The nomogram and risk stratification system estimated the utility of CLNM to guide individualized treatment of patients with PTC.

Research trends in functionalized Fe3O4 composites based on affinity recognition systems for targeted extraction of natural products.

In recent years, target-specific affinity recognition systems based on Fe3O4-based composites have proven to be an effective method for screening natural products. Herbal medicines contain a wide range of natural products and are considered to be a major source for the development of novel drugs. However, the process of isolating and obtaining these bioactive components for the production of novel drugs is complex. Meanwhile, the complexity and diversity of herbal constituents have posed a great challenge to the screening studies of herbal active ingredients. Currently, traditional extraction and screening studies of active ingredients in herbal medicine include extraction and chromatographic separation technology development, serum medicinal chemistry, metabolomics and computerized virtual screening. In order to achieve integrated targeting of Fe3O4 for extraction and separation of natural products from herbs, various Fe3O4-based composites need to be synthesized so that the composites can be further functionalized and modified. Composites such as Fe3O4@SiO2, Fe3O4-based magnetic graphene oxide and Fe3O4-based magnetic carbon nanotubes were used to achieve targeted extraction and isolation of natural products from herbal medicines. The main extraction techniques involved based on these Fe3O4-based composites are molecularly imprinted techniques, immobilized ligand fishing techniques, and cell membrane-coated bionanotechnology methods. This article will present recent advances in the synthesis and modification of Fe3O4 composites and their applications for the extraction of natural products in conjunction with molecular imprinting, immobilization-targeted fishing, and cell-membrane-coated biomimetic techniques, as well as the future goals and challenges of functionalized modification of Fe3O4 composites for the targeted extraction of natural products, like protein overexpression modification, doping of fluorescent substances and genetic engineering development. A deeper understanding of the multi-level, multidisciplinary, and applied studies in materials science and phytochemistry will be provided by this article.

Influence of health education based on the transtheoretical model on kinesiophobia levels and rehabilitation outcomes in elderly patients undergoing total knee arthroplasty.

Objective: In this study, we evaluated the effectiveness of health education based on the transtheoretical model in reducing symptoms of kinesiophobia and enhancing rehabilitation outcomes among elderly patients post-total knee arthroplasty. Methods: Elderly patients post-knee replacement surgery were randomly divided into a control group, which received standard health education, and an experimental group, which received transtheoretical model-based health education. The intervention commenced on the day after surgery and continued for a duration of six months. Assessments of kinesiophobia scores, rehabilitation self-efficacy, and knee function were conducted before the intervention, and then at one, three, and six months postoperatively. Results: Between January 2022 and December 2022, 130 elderly patients who met the eligibility criteria were enrolled and subsequently randomly assigned into two groups of equal size. Comparable baseline characteristics were observed between the two groups The experimental group demonstrated lower kinesiophobia scores and higher scores in rehabilitation self-efficacy and knee function at one, three, and six months following surgery, compared to the control group. Conclusion: Health education based on a transtheoretical model reduces the symptoms of kinesiophobia and enhances rehabilitation self-efficacy and knee functions in elderly patients after knee replacement surgery.

Smart Cushions with Machine Learning-Enhanced Force Sensors for Pressure Injury Risk Assessment.

Prolonged sitting can easily result in pressure injury (PI) for certain people who have had strokes or spinal cord injuries. There are not many methods available for tracking contact surface pressure and shear force to evaluate the PI risk. Here, we propose a smart cushion that uses two-dimensional force sensors (2D-FSs) to measure the pressure and shear force in the buttocks. A machine learning algorithm is then used to compute the shear stresses in the gluteal muscles, which helps to determine the PI risk. The 2D-FS consists of a ferroelectret coaxial sensor (FCS) unit placed atop a ferroelectret film sensor (FFS) unit, allowing it to detect both vertical and horizontal forces simultaneously. To characterize and calibrate, two experimental approaches are applied: one involves simultaneously applying two perpendicular forces, and one involves applying a single force. To separate the two forces, the 2D-FS is decoupled using a deep neural network technique. Multiple FCSs are embedded to form a smart cushion, and a genetic algorithm-optimized backpropagation neural network is proposed and trained to predict the shear strain in the buttocks to prevent PI. By tracking the danger of PI, the smart cushion based on 2D-FSs may be further connected with home-based intelligent care platforms to increase patient equality for spinal cord injury patients and lower the expense of nursing or rehabilitation care.

Silicone oil migrating into the conjunctival space and orbit after surgery for an eye-penetrating injury: A case report.

BACKGROUND: We report a case of eye-penetrating injury in which a massive silicone oil migration into the patient's subconjunctival space and orbit occurred after vitrectomy. CASE SUMMARY: A 30-year-old male patient sought medical attention at Ganzhou People's Hospital after experiencing pain and vision loss in his left eye due to a nail wound on December 9, 2023. Diagnosis of penetrating injury caused by magnetic foreign body retention in the left eye and hospitalization for treatment. On December 9, 2023, pars plana vitrectomy was performed on the left eye for intraocular foreign body removal, abnormal crystal extraction, retinal photocoagulation. Owing to the discovery of retinal detachment at the posterior pole during surgery, silicone oil was injected to fill the vitreous body, following which upper conjunctival bubble-like swelling was observed. Postoperative orbital computed tomography (CT) review indicated migration of silicone oil to the subconjunctival space and orbit through a self-permeable outlet. On December 18, 2023, the patient sought treatment at the First Affiliated Hospital of Nanchang University, China. The patient presented with a pronounced foreign body sensation following left eye surgery. On December 20, 2023, the foreign body was removed from the left eye frame and an intraocular examination was conducted. The posterior scleral tear had closed, leading to termination of the surgical procedure following supplementary laser treatment around the tear. The patient reported a significant reduction in ocular surface symptoms just one day after surgery. Furthermore, a notable decrease in the migration of silicone oil was observed in orbital CT scans. CONCLUSION: The timing of silicone oil injection for an eye-penetrating injury should be carefully evaluated to avoid the possibility of silicone oil migration.

Anisotropic Effects in Local Anodic Oxidation Nanolithography on Silicon Surfaces: Insights from ReaxFF Molecular Dynamics.

Fully understanding the anisotropic effect of silicon surface orientations in local anodic oxidation (LAO) nanolithography processes is critical to the precise control of oxide quality and rate. This study used ReaxFF MD simulations to reveal the surface anisotropic effects in the LAO through the analysis of adsorbed species, atomic charge, and oxide growth. Our results show that the LAO behaves differently on silicon (100), (110), and (111) surfaces. Specifically, the application of an electric field significantly increases the quantity of surface-adsorbed -OH2 while reducing -OH on the (111) surface, and results in a higher charge on a greater number of Si atoms on the (100) surface. Moreover, the quantity of surface-adsorbed -OH plays a pivotal role in influencing the oxidation rate, as it directly correlates with an increased formation rate of Si-O-Si bonds. During bias-induced oxidation, the (111) surface appears with a high initial oxidation rate among three surfaces, while the (110) surface underwent increased oxidation at higher electric field strengths. This conclusion is based on the analysis of the evolution of Si-O-Si bond number, surface elevation, and oxide thickness. Our findings align well with prior theoretical and experimental studies, providing deeper insights and clear guidance for the fabrication of high-performance nanoinsulator gates using LAO nanolithography.

The nuclear matrix protein HNRNPU restricts hepatitis B virus transcription by promoting OAS3-based activation of host innate immunity.

Heterogeneous nuclear protein U (HNRNPU) plays a pivotal role in innate immunity by facilitating chromatin opening to activate immune genes during host defense against viral infection. However, the mechanism by which HNRNPU is involved in Hepatitis B virus (HBV) transcription regulation through mediating antiviral immunity remains unknown. Our study revealed a significant decrease in HNRNPU levels during HBV transcription, which depends on HBx-DDB1-mediated degradation. Overexpression of HNRNPU suppressed HBV transcription, while its knockdown effectively promoted viral transcription, indicating HNRNPU as a novel host restriction factor for HBV transcription. Mechanistically, HNRNPU inhibits HBV transcription by activating innate immunity through primarily the positive regulation of the interferon-stimulating factor 2'-5'-oligoadenylate synthetase 3, which mediates an ribonuclease L-dependent mechanism to enhance innate immune responses. This study offers new insights into the host immune regulation of HBV transcription and proposes potential targets for therapeutic intervention against HBV infection.

Preparation and Performance Study of Boron Adsorbent from Plasma-Grafted Polypropylene Melt-Blown Fibers.

In this study, the plasma graft polymerization technique was used to graft glycidyl methacrylate (GMA) onto polypropylene (PP) melt-blown fibers, which were subsequently aminated with N-methyl-D-glucamine (NMDG) by a ring-opening reaction, resulting in the formation of a boron adsorbent denoted as PP-g-GMA-NMDG. The optimal conditions for GMA concentration, grafting time, grafting temperature, and the quantity of NMDG were determined using both single factor testing and orthogonal testing. These experiments determined the optimal process conditions to achieve a high boron adsorption capacity of PP-g-GMA-NMDG. Fourier-transform infrared spectroscopy (FT-IR), scanning electron microscopy (SEM), energy dispersion spectrum analysis (EDS), and water contact angle measurements were performed to characterize the prepared adsorbent. Boron adsorption experiments were carried out to investigate the effects of pH, time, temperature, and boron concentration on the boron adsorption capacity of PP-g-GMA-NMDG. The adsorption isotherms and kinetics of PP-g-GMA-NMDG for boron were also studied. The results demonstrated that the adsorption process followed a pseudo-second-order kinetic model and a Langmuir isothermal model. At a pH of 6, the maximum saturation adsorption capacity of PP-g-GMA-NMDG for boron was 18.03 ± 1 mg/g. In addition, PP-g-GMA-NMDG also showed excellent selectivity for the adsorption of boron in the presence of other cations, such as Na+, Mg2+, and Ca2+, PP-g-GMA-NMDG, and exhibited excellent selectivity towards boron adsorption. These results indicated that the technique of preparing PP-g-GMA-NMDG is both viable and environmentally benign. The PP-g-GMA-NMDG that was made has better qualities than other similar adsorbents. It has a high adsorption capacity, great selectivity, reliable repeatability, and easy recovery. These advantages indicated that the adsorbents have significant potential for widespread application in the separation of boron in water.

The protective effects and potential mechanisms of fulvic acid against ethanol-induced gastric mucosal injury in mice.

Fulvic acid (FA) is a kind of natural organic acids extracted from lignite, which is the active ingredient in Wujin oral liquid, a proprietary Chinese medicine used to treat gastric and duodenal ulcers. However, our understanding of the mechanisms of FA remains limited. Currently, the protection of FA and its mechanism were explored using the ethanol-induced gastric mucosal injury mouse model. The histopathological examinations showed FAs at three doses effectively reduced gastric congestion, oedema caused by ethanol, and prevented gastric epithelial cell fall-off. When compared to the model group, FAs reduced IL-1ß and IL-6 levels in serum, as well as IL-1ß, IL-6, TNF-α, and COX-2 expression levels in tissue. Furthermore, FAs significantly inhibited p65, P38 MAPK, and Erk1/2 phosphorylation in damaged gastric tissue. It was indicated FA has good protection against ethanol-induced gastric mucosa injuries in mice and this effect was related to NF-κB and MAPK signalling pathways.

Develop a bone mineral density T-score distribution nomograms based on osteoporosis risk factors for middle-aged and older adults.

PURPOSE: This study aimed to understand how age, health status, and lifestyle impact bone mineral density (BMD) in middle-aged and older adults, focusing on predicting osteoporosis risk. METHODS: This study included 2836 participants aged 50-88 from the Health Improvement Program of Bone (HOPE) conducted from 2021 to 2023. We used logistic regression to make a prediction tool. Then checked its accuracy and reliability using receiver operating characteristic (ROC) and calibration curves. RESULTS: Factors like age, body weight, prior fractures, and smoking were independently found to affect BMD T-score distribution in men. In women, age and body weight were identified as independent factors influencing BMD T-score distribution. A nomogram was created to visually illustrate these predictive relationships. CONCLUSIONS: The nomogram proved highly accurate in identifying men aged 50 and above and postmenopausal women based on their BMD T-score distribution, improving clinical decision-making and patient care in osteoporosis evaluation and treatment.

Transcription factor EB reprograms branched-chain amino acid metabolism and promotes pancreatic cancer progression via transcriptional regulation of BCAT1.

Pancreatic cancer cells have a much higher metabolic demand than that of normal cells. However, the abundant interstitium and lack of blood supply determine the lack of nutrients in the tumour microenvironment. Although pancreatic cancer has been reported to supply extra metabolic demand for proliferation through autophagy and other means, the specific regulatory mechanisms have not yet been elucidated. In this study, we focused on transcription factor EB (TFEB), a key factor in the regulation of autophagy, to explore its effect on the phenotype and role in the unique amino acid utilisation pattern of pancreatic cancer cells (PCCs). The results showed that TFEB, which is generally highly expressed in pancreatic cancer, promoted the proliferation and metastasis of PCCs. TFEB knockdown inhibited the proliferation and metastasis of PCCs by blocking the catabolism of branched-chain amino acids (BCAAs). Concerning the mechanism, we found that TFEB regulates the catabolism of BCAAs by regulating BCAT1, a key enzyme in BCAA metabolism. BCAA deprivation alone did not effectively inhibit PCC proliferation. However, BCAA deprivation combined with eltrombopag, a drug targeting TFEB, can play a two-pronged role in exogenous supply deprivation and endogenous utilisation blockade to inhibit the proliferation of pancreatic cancer to the greatest extent, providing a new therapeutic direction, such as targeted metabolic reprogramming of pancreatic cancer.

Establishment and validation of the prediction model for postoperative delirium risk factors in older patients after total knee arthroplasty: A retrospective study.

This study aimed to establish an effective predictive model for postoperative delirium (POD) risk assessment after total knee arthroplasty (TKA) in older patients. The clinical data of 446 older patients undergoing TKA in the Orthopedics Department of our University from January to December 2022 were retrospectively analyzed, and the POD risk prediction model of older patients after TKA was established. Finally, 446 patients were included, which were divided into training group (n = 313) and verification group (n = 133). Logistic regression method was used to select meaningful predictors. The prediction model was constructed with nomographs, and the model was evaluated with correction curve and receiver operating characteristic curve. The logistic regression analysis showed that age, educational level, American Society of Anesthesiologists grade, accompaniment of chronic obstructive pulmonary disease, accompaniment of cerebral stroke, postoperative hypoxemia, long operation time, and postoperative pain were independent risk factors for POD after TKA (P < .05). The nomogram prediction model established. The area under receiver operating characteristic curve of the model group and the validation group were 0.954 and 0.931, respectively. The calibration curve of the prediction model has a high consistency between the 2 groups. The occurrence of POD was associated with age, educational level, American Society of Anesthesiologists grade, accompaniment of chronic obstructive pulmonary disease, accompaniment of cerebral stroke, postoperative hypoxemia, long operation time, and postoperative pain in TKA patients.

Impact of must clarification treatments on chemical and sensory profiles of kiwifruit wine.

This study examined the effect of various clarification treatments on the physicochemical properties, volatile compounds, and sensory attributes of kiwi wines produced from five different kiwifruit (Actinidia deliciosa) varieties. The degree of clarification had a minimal impact on physicochemical parameters, including the content of residual sugar, ethanol, volatile acid, titratable acidity (except for the kiwifruit variety 'Qinmei'), and the pH value. However, wines made from unclarified juices (muddy juice and pulp) displayed a higher glycerol content than those made from clarified juices. The cluster heat map and principal component analyses (PCA) demonstrated that kiwi wines produced from clarified kiwi juices possessed a higher ester content, whereas muddy juice and pulp wines contained elevated levels of higher alcohols. Quantitative descriptive analysis (QDA) indicated that clarified juice wines outperformed muddy juice and pulp wines in terms of purity, typicality, harmony, intensity, and freshness, with negligible differences in terms of palate acidity. Moreover, the clarified juice wines featured more characteristic kiwi wine aromas (kiwifruit, passionfruit, and pineapple) compared with that of the muddy juice and pulp wines, which exhibited an increased grassy flavour. Although the 100-NTU kiwifruit juice-fermented wine did not show an advantage in the cluster heat map and PCA, it presented better freshness, typicality, and intensity in the QDA, as well as a more passionfruit aroma. Based on the orthogonal partial least-squares discriminant analysis, A. deliciosa 'Xuxiang' was deemed to be the most suitable variety for vinification. This study provides crucial insights for enhancing the production of high-quality kiwi wine.

IQGAP1 overexpression attenuates chemosensitivity through YAP-mediated ferroptosis inhibition in esophageal squamous cell cancer cells.

Chemoresistance is one of the major hindrances to many cancer therapies, including esophageal squamous cell carcinoma (ESCC). Ferroptosis, a new programmed cell death, plays an essential role in chemoresistance. IQ-domain GTPase activating protein 1 (IQGAP1) is a scaffold protein and functions as an oncogene in various human malignancies. However, the underlying effect and molecular mechanisms of IQGAP1 on paclitaxel (PTX) resistance and ferroptosis in ESCC remain to be elucidated. In this study, we found that IQGAP1 was highly expressed in ESCC tissues and could as a potential biomarker for diagnosis and predicting the prognosis of ESCC. Functional studies revealed that IQGAP1 overexpression reduced the sensitivity of ESCC cells to PTX by enhancing ESCC cell viability and proliferation and inhibiting cell death, and protected ESCC cells from ferroptosis, whereas IQGAP1 knockdown exhibited contrary effects. Importantly, reductions of chemosensitivity and ferroptosis caused by IQGAP1 overexpression were reversed with ferroptosis inducer RSL3, while the increases of chemosensitivity and ferroptosis caused by IQGAP1 knockdown were reversed with ferroptosis inhibitor ferrostatin-1 (Fer-1) in ESCC cells, indicating that IQGAP1 played a key role in resistance to PTX through regulating ferroptosis. Mechanistically, we demonstrated that IQGAP1 overexpression upregulated the expression of Yes-associated protein (YAP), the central mediator of the Hippo pathway. YAP inhibitor Verteporfin (VP) could reverse the effects of IQGAP1 overexpression on ESCC chemoresistance and ferroptosis. Taken together, our findings suggest that IQGAP1 promotes chemoresistance by blocking ferroptosis through targeting YAP. IQGAP1 may be a novel therapeutic target for overcoming chemoresistance in ESCC.

Application of deep learning classification model for regional evaluation of roof pressure support evolution effects over time in coal mining face.

Hydraulic support leg pressure serves as a crucial indicator for assessing work face support quality. Current evaluation methods for support quality primarily concentrate on static analyses-like inadequate initial support force, pressure overrun, and uneven bracket force-while neglecting dynamic column pressure changes. This paper introduces a model for assessing hydraulic support quality using deep learning techniques. Real-time data is preprocessed into a spatio-temporal pressure sub-matrix sample, which is then inputted into the model. This process assesses the support quality type and characterizes its dynamic evolution within the area. The model facilitates the identification of dynamic support quality effects in the working face area, aiding operators in making targeted adjustments to hydraulic support status. Experimental results revealed that the optimized LeNet-5 network-adjusting parameters like convolutional layer count, kernel size, and ReLU activation function-achieved the highest classification accuracy of 85.25 % for support quality, surpassed other networks. Furthermore, the improved LeNet-5 network outperformed other networks in both F1 score and recall. Additionally, the improved LeNet-5 network achieved faster convergence to the optimal solution, accelerated training speed. This highlighted its advantages in evaluating the spatio-temporal support quality of hydraulic supports in smart mining operations.

Trends in the burden and determinants of HIV in the Asia-Pacific region (1990-2019): An age-period-cohort analysis of the 2019 Global Burden of Disease Study.

Although the burden of the human immunodeficiency virus (HIV) in the Asia-Pacific region is increasingly severe, comprehensive evidence of the burden of HIV is scarce. We aimed to report the burden of HIV in people aged 15-79 years from 1990 to 2019 using data from the Global Burden of Disease Study (GBD) 2019. We analyzed rates of age-standardized disability-adjusted life years (ASDR), age-standardized mortality (ASMR), and age-standardized incidence (ASIR) in our age-period-cohort analysis by sociodemographic index (SDI). According to HIV reports in 2019 from 29 countries in the Asia-Pacific region, the low SDI group in Papua New Guinea had the highest ASDR, ASMR, and ASIR. From 1990 to 2019, the ASDR, ASIR, and ASMR of persons with acquired immune deficiency syndrome (AIDS) increased in 21 (72%) of the 29 countries in the Asia-Pacific region. During the same period, the disability-adjusted life years (DALYs) of AIDS patients in the low SDI group in the region grew the fastest, particularly in Nepal. The incidence of HIV among individuals aged 20-30 years in the low-middle SDI group was higher than that of those in the other age groups. In 2019, unsafe sex was the main cause of HIV-related ASDR in the region's 29 countries, followed by drug use. The severity of the burden of HIV/AIDS in the Asia-Pacific region is increasing, especially among low SDI groups. Specific public health policies should be formulated based on the socioeconomic development level of each country to alleviate the burden of HIV/AIDS.

Teach them how to fish or give them fish? The effect of collective narcissism on intergroup help.

Intergroup help contributes to the solution of global issues in particular. However, whether to teach an outgroup how to address their problem permanently, or to directly help them solve the current problem? Collective narcissism might play a crucial role in this process. Based on the core characteristics of collective narcissism, this research explored whether and how collective narcissism would affect people's willingness to give different types of intergroup help. Study 1 examined the correlation between collective narcissism and intergroup help. Studies 2 and 3 investigated the impacts of outgroup threat and ingroup image on the relationship between collective narcissism and intergroup help respectively. In Study 4, the interaction between outgroup threat and ingroup image was further examined. The results showed that collective narcissism reduced participants' willingness to offer intergroup help, especially autonomy-oriented help. For low-threat outgroups, collective narcissism increased participants' willingness to give dependency-oriented help. In contrast, collective narcissism increased participants' willingness to give autonomy-oriented help when refusal to intergroup help tarnished the ingroup image. For high-threat outgroups, collective narcissism did not predict participants' willingness to give intergroup help. These findings suggest that collective narcissists' preferences for intergroup help change with outgroup threat and ingroup image.

The predictive value of serum tumor markers for EGFR mutation in non-small cell lung cancer patients with non-stage IA.

Objective: The predictive value of serum tumor markers (STMs) in assessing epidermal growth factor receptor (EGFR) mutations among patients with non-small cell lung cancer (NSCLC), particularly those with non-stage IA, remains poorly understood. The objective of this study is to construct a predictive model comprising STMs and additional clinical characteristics, aiming to achieve precise prediction of EGFR mutations through noninvasive means. Materials and methods: We retrospectively collected 6711 NSCLC patients who underwent EGFR gene testing. Ultimately, 3221 stage IA patients and 1442 non-stage IA patients were analyzed to evaluate the potential predictive value of several clinical characteristics and STMs for EGFR mutations. Results: EGFR mutations were detected in 3866 patients (57.9 %) of all NSCLC patients. None of the STMs emerged as significant predictor for predicting EGFR mutations in stage IA patients. Patients with non-stage IA were divided into the study group (n = 1043) and validation group (n = 399). In the study group, univariate analysis revealed significant associations between EGFR mutations and the STMs (carcinoembryonic antigen (CEA), squamous cell carcinoma antigen (SCC), and cytokeratin-19 fragment (CYFRA21-1)). The nomogram incorporating CEA, CYFRA 21-1, pathology, gender, and smoking history for predicting EGFR mutations with non-stage IA was constructed using the results of multivariate analysis. The area under the curve (AUC = 0.780) and decision curve analysis demonstrated favorable predictive performance and clinical utility of nomogram. Additionally, the Random Forest model also demonstrated the highest average C-index of 0.793 among the eight machine learning algorithms, showcasing superior predictive efficiency. Conclusion: CYFRA21-1 and CEA have been identified as crucial factors for predicting EGFR mutations in non-stage IA NSCLC patients. The nomogram and 8 machine learning models that combined STMs with other clinical factors could effectively predict the probability of EGFR mutations.