Logistic LASSO Regression for Dietary Intakes and Breast Cancer

High expression of 3-hydroxy-3-methylglutaryl-CoA synthase 2 (HMGCS2) associated with Diquat-induced damage

Diquat (DQ) is a commonly used bipyridine herbicide known for its toxic properties and adverse effects on individuals. However, the mechanism underlying DQ-induced damage remain elusive. Our research aimed to uncover the regulatory network involved in DQ-induced damage. We analyzed publicly accessible gene expression patterns and performed research using a DQ-induced damage animal model. The GSE153959 dataset from the Gene Expression Omnibus collection and the animal model of DQ-induced kidney injury were used to identify differentially expressed genes (DEGs). Pathways including the regulation of DNA-templated transcription in response to stress, RNA polymerase II transcription regulator complex and transcription coregulatory activity were shown to be enriched in 21 DEGs. We used least absolute shrinkage and selection operator (LASSO) regression analysis to find possible diagnostic biomarkers for DQ-induced damage. Then, we used an HK-2 cell model to confirm these results. Additionally, we confirmed that 3-hydroxy-3-methylglutaryl-CoA synthase 2 (HMGCS2) was the major gene associated with DQ-induced damage using multi-omics screening. The sample validation strongly suggested that HMGCS2 has promise as a diagnostic marker and may provide new targets for therapy in the context of DQ-induced damage.

PET-based radiomic feature based on the cross-combination method for predicting the mid-term efficacy and prognosis in high-risk diffuse large B-cell lymphoma patients

Objectives

This study aims to develop 7×7 machine-learning cross-combinatorial methods for selecting and classifying radiomic features used to construct Radiomics Score (RadScore) of predicting the mid-term efficacy and prognosis in high-risk patients with diffuse large B-cell lymphoma (DLBCL).

Methods

Retrospectively, we recruited 177 high-risk DLBCL patients from two medical centers between October 2012 and September 2022 and randomly divided them into a training cohort (n=123) and a validation cohort (n=54). We finally extracted 110 radiomic features along with SUVmax, MTV, and TLG from the baseline PET. The 49 features selection-classification pairs were used to obtain the optimal LASSO-LASSO model with 11 key radiomic features for RadScore. Logistic regression was employed to identify independent RadScore, clinical and PET factors. These models were evaluated using receiver operating characteristic (ROC) curves and calibration curves. Decision curve analysis (DCA) was conducted to assess the predictive power of the models. The prognostic power of RadScore was assessed using cox regression (COX) and Kaplan-Meier plots (KM).

Results

177 patients (mean age, 63 ± 13 years,129 men) were evaluated. Multivariate analyses showed that gender (OR,2.760; 95%CI:1.196,6.368); p=0.017), B symptoms (OR,4.065; 95%CI:1.837,8.955; p=0.001), SUVmax (OR,2.619; 95%CI:1.107,6.194; p=0.028), and RadScore (OR,7.167; 95%CI:2.815,18.248; p<0.001) independently contributed to the risk factors for predicting mid-term outcome. The AUC values of the combined models in the training and validation groups were 0.846 and 0.724 respectively, outperformed the clinical model (0.714;0.556), PET based model (0.664; 0.589), NCCN-IPI model (0.523;0.406) and IPI model (0.510;0.412) in predicting mid-term treatment outcome. DCA showed that the combined model incorporating RadScore, clinical risk factors, and PET metabolic metrics has optimal net clinical benefit. COX indicated that the high RadScore group had worse prognosis and survival in progression-free survival (PFS) (HR, 2.1737,95%CI: 1.2983, 3.6392) and overall survival (OS) (HR,2.1356,95%CI: 1.2561, 3.6309) compared to the low RadScore group. KM survival analysis also showed the same prognosis prediction as Cox results.

Conclusion

The combined model incorporating RadScore, sex, B symptoms and SUVmax demonstrates a significant enhancement in predicting medium-term efficacy and prognosis in high-risk DLBCL patients. RadScore using 7×7 machine learning cross-combinatorial methods for selection and classification holds promise as a potential method for evaluating medium-term treatment outcome and prognosis in high-risk DLBCL patients.

Individualized radiology screening for newly diagnosed nasopharyngeal carcinoma

OBJECTIVES

Current guidelines recommend universal PET/CT screening for metastases staging in newly diagnosed nasopharyngeal carcinoma (NPC) despite the low rate of synchronous distant metastasis (SDM). The study aims to achieve individualized screening recommendations of NPC based on the risk of SDM.

METHODS AND MATERIALS

18 pre-treatment peripheral blood indicators was retrospectively collected from 2271 primary NPC patients. A peripheral blood risk score (PBRS) was constructed by indicators associated with SDM on least absolute shrinkage and selection operator (LASSO) regression. The PBRS-based distant metastases (PBDM) model was developed from features selected by logistic regression analyses in the training cohort and then validated in the validation cohort. Receiver operator characteristic curve analysis, calibration curves, and decision curve analysis were applied to evaluate PBDM model performance.

RESULTS

Pre-treatment Epstein-Barr viral DNA copy number, percentage of total lymphocytes, serum lactate dehydrogenase level, and monocyte-to-lymphocyte ratio were most strongly associated with SDM in NPC and used to construct the PBRS. Sex (male), T stage (T3-4), N stage (N2-3), and PBRS (≥1.076) were identified as independent risk factors for SDM and applied in the PBDM model, which showed good performance. Through the model, patients in the training cohort were stratified into low-, medium-, and high-risk groups. Individualized screening recommendations were then developed for patients with differing risk levels.

CONCLUSION

The PBDM model offers individualized recommendations for applying PET/CT for metastases staging in NPC, allowing more targeted screening of patients with greater risk of SDM compared with current recommendations.

The Association between Dietary Nutrient Intake and Acceleration of Aging: Evidence from NHANES

The acceleration of aging is a risk factor for numerous diseases, and diet has been identified as an especially effective anti-aging method. Currently, research on the relationship between dietary nutrient intake and accelerated aging remains limited, with existing studies focusing on the intake of a small number of individual dietary nutrients. Comprehensive research on the single and mixed anti-aging effects of dietary nutrients has not been conducted. This study aimed to comprehensively explore the effects of numerous dietary nutrient intakes, both singly and in combination, on the acceleration of aging. Data for this study were extracted from the 2015-2018 National Health and Nutrition Examination Surveys (NHANES). The acceleration of aging was measured by phenotypic age acceleration. Linear regression (linear), restricted cubic spline (RCS) (nonlinear), and weighted quantile sum (WQS) (mixed effect) models were used to explore the association between dietary nutrient intake and accelerated aging. A total of 4692 participants aged ≥ 20 were included in this study. In fully adjusted models, intakes of 16 nutrients were negatively associated with accelerated aging (protein, vitamin E, vitamin A, beta-carotene, vitamin B1, vitamin B2, vitamin B6, vitamin K, phosphorus, magnesium, iron, zinc, copper, potassium, dietary fiber, and alcohol). Intakes of total sugars, vitamin C, vitamin K, caffeine, and alcohol showed significant nonlinear associations with accelerated aging. Additionally, mixed dietary nutrient intakes were negatively associated with accelerated aging. Single dietary nutrients as well as mixed nutrient intake may mitigate accelerated aging. Moderately increasing the intake of specific dietary nutrients and maintaining dietary balance may be key strategies to prevent accelerated aging.

Prediction of anticancer drug sensitivity using an interpretable model guided by deep learning

BACKGROUND

The prediction of drug sensitivity plays a crucial role in improving the therapeutic effect of drugs. However, testing the effectiveness of drugs is challenging due to the complex mechanism of drug reactions and the lack of interpretability in most machine learning and deep learning methods. Therefore, it is imperative to establish an interpretable model that receives various cell line and drug feature data to learn drug response mechanisms and achieve stable predictions between available datasets.

RESULTS

This study proposes a new and interpretable deep learning model, DrugGene, which integrates gene expression, gene mutation, gene copy number variation of cancer cells, and chemical characteristics of anticancer drugs to predict their sensitivity. This model comprises two different branches of neural networks, where the first involves a hierarchical structure of biological subsystems that uses the biological processes of human cells to form a visual neural network (VNN) and an interpretable deep neural network for human cancer cells. DrugGene receives genotype input from the cell line and detects changes in the subsystem states. We also employ a traditional artificial neural network (ANN) to capture the chemical structural features of drugs. DrugGene generates final drug response predictions by combining VNN and ANN and integrating their outputs into a fully connected layer. The experimental results using drug sensitivity data extracted from the Cancer Drug Sensitivity Genome Database and the Cancer Treatment Response Portal v2 reveal that the proposed model is better than existing prediction methods. Therefore, our model achieves higher accuracy, learns the reaction mechanisms between anticancer drugs and cell lines from various features, and interprets the model's predicted results.

CONCLUSIONS

Our method utilizes biological pathways to construct neural networks, which can use genotypes to monitor changes in the state of network subsystems, thereby interpreting the prediction results in the model and achieving satisfactory prediction accuracy. This will help explore new directions in cancer treatment. More available code resources can be downloaded for free from GitHub ( https://github.com/pangweixiong/DrugGene ).

Bioinformatics and Machine Learning Methods Identified MGST1 and QPCT as Novel Biomarkers for Severe Acute Pancreatitis

Severe acute pancreatitis (SAP) is a life-threatening gastrointestinal emergency. The study aimed to identify biomarkers and investigate molecular mechanisms of SAP. The GSE194331 dataset from GEO database was analyzed using bioinformatics. Differentially expressed genes (DEGs) associated with SAP were identified, and a protein-protein interaction network (PPI) was constructed. Machine learning algorithms were used to determine potential biomarkers. Gene set enrichment analysis (GSEA) explored molecular mechanisms. Immune cell infiltration were analyzed, and correlation between biomarker expression and immune cell infiltration was calculated. A competing endogenous RNA network (ceRNA) was constructed, and biomarker expression levels were quantified in clinical samples using RT-PCR. 1101 DEGs were found, with two modules most relevant to SAP. Potential biomarkers in peripheral blood samples were identified as glutathione S-transferase 1 (MGST1) and glutamyl peptidyltransferase (QPCT). GSEA revealed their association with immunoglobulin regulation, with QPCT potentially linked to pancreatic cancer development. Correlation between biomarkers and immune cell infiltration was demonstrated. A ceRNA network consisting of 39 nodes and 41 edges was constructed. Elevated expression levels of MGST1 and QPCT were verified in clinical samples. In conclusion, peripheral blood MGST1 and QPCT show promise as SAP biomarkers for diagnosis, providing targets for therapeutic intervention and contributing to SAP understanding.

A machine learning screening model for identifying the risk of high-frequency hearing impairment in a general population

BACKGROUND

Hearing impairment (HI) has become a major public health issue in China. Currently, due to the limitations of primary health care, the gold standard for HI diagnosis (pure-tone hearing test) is not suitable for large-scale use in community settings. Therefore, the purpose of this study was to develop a cost-effective HI screening model for the general population using machine learning (ML) methods and data gathered from community-based scenarios, aiming to help improve the hearing-related health outcomes of community residents.

METHODS

This study recruited 3371 community residents from 7 health centres in Zhejiang, China. Sixty-eight indicators derived from questionnaire surveys and routine haematological tests were delivered and used for modelling. Seven commonly used ML models (the naive Bayes (NB), K-nearest neighbours (KNN), support vector machine (SVM), random forest (RF), eXtreme Gradient Boosting (XGBoost), boosting, and least absolute shrinkage and selection operator (LASSO regression)) were adopted and compared to develop the final high-frequency hearing impairment (HFHI) screening model for community residents. The model was constructed with a nomogram to obtain the risk score of the probability of individuals suffering from HFHI. According to the risk score, the population was divided into three risk stratifications (low, medium and high) and the risk factor characteristics of each dimension under different risk stratifications were identified.

RESULTS

Among all the algorithms used, the LASSO-based model achieved the best performance on the validation set by attaining an area under the curve (AUC) of 0.868 (95% confidence interval (CI): 0.847-0.889) and reaching precision, specificity and F-score values all greater than 80%. Five demographic indicators, 7 disease-related features, 5 behavioural factors, 2 environmental exposures, 2 hearing cognitive factors, and 13 blood test indicators were identified in the final screening model. A total of 91.42% (1235/1129) of the subjects in the high-risk group were confirmed to have HI by audiometry, which was 3.99 times greater than that in the low-risk group (22.91%, 301/1314). The high-risk population was mainly characterized as older, low-income and low-educated males, especially those with multiple chronic conditions, noise exposure, poor lifestyle, abnormal blood indices (e.g., red cell distribution width (RDW) and platelet distribution width (PDW)) and liver function indicators (e.g., triglyceride (TG), indirect bilirubin (IBIL), aspartate aminotransferase (AST) and low-density lipoprotein (LDL)). An HFHI nomogram was further generated to improve the operability of the screening model for community applications.

CONCLUSIONS

The HFHI risk screening model developed based on ML algorithms can more accurately identify residents with HFHI by categorizing them into the high-risk groups, which can further help to identify modifiable and immutable risk factors for residents at high risk of HI and promote their personalized HI prevention or intervention.

Integrative analysis and validation of necroptosis-related molecular signature for evaluating diagnosis and immune features in Rheumatoid arthritis

OBJECTIVES

Rheumatoid arthritis (RA) is a chronic autoimmune inflammatory disease that is characterized by persistent morning stiffness, joint pain, and swelling. However, there is a lack of reliable diagnostic markers and therapeutic targets that are both effective and trustworthy.

METHODS

In this study, gene expression profiles (GSE89408, GSE55235, GSE55457, and GSE77298) were obtained from the Gene Expression Omnibus database. Differentially expressed necroptosis-related genes were attained from intersection of necroptosis-related gene set, differentially expressed genes, and weighted gene co-expression network analysis. The LASSO, random forest, and SVM-RFE machine learning algorithms were utilized to further screen potential diagnostic genes for RA. Immune cell infiltration was analyzed using the CIBERSORT method. The expressions of diagnostic genes were validated through quantitative real-time PCR, western blotting, immunohistochemistry, and immunofluorescence staining in synovial tissues collected from three trauma controls and three RA patients.

RESULTS

Five core necroptosis-related genes (FAS, CYBB, TNFSF10, EIF2AK2, and BIRC2) were identified as potential biomarkers for RA. Two different necroptosis patterns based on these five genes were confirmed to significantly correlated with immune cells (especially macrophages). In vitro experiments showed significantly higher mRNA and protein expression levels of CYBB and EIF2AK2 in RA patients compared to normal controls, consistent with the bioinformatics analysis results.

CONCLUSION

Our study identified a novel necroptosis-related subtype and five diagnostic biomarkers of RA, revealed vital roles in the development and occurrence of RA, and offered potential targets for clinical diagnosis and immunotherapy.

Association of macronutrient consumption quality, food source and timing with depression among US adults: A cross-sectional study

BACKGROUND

Growing evidence suggests that meal timing may influence dietary choices and mental health. Thus, this study examined the association between macronutrient consumption quality, food source, meal timing, and depression prevalence in Americans.

METHODS

23,313 National Health and Nutrition Survey participants from 2007 to 2016 were included in this cross-sectional study. Macronutrient intake was calculated for all day, dinner, and breakfast and subtypes into 4 classes. Based on the Patient Health Questionnaire, depression was defined as a 9-item score ≥ 10 on the PHQ-9. The correlation between macronutrients and depression prevalence was estimated with multivariable logistic regression models and isocaloric substitution effects.

RESULTS

Low-quality carbohydrates (OR = 1.54, 95 % CI: 1.11, 2.12) were positively linked to depression compared with the lowest quartile, after adjusting for age and other covariates. In contrast, total high-quality carbohydrate (OR = 0.52, 95 % CI: 0.40, 0.66), total animal protein (OR = 0.60, 95 % CI: 0.45, 0.80), and total vegetable protein (OR = 0.61, 95 % CI: 0.43, 0.85) were negatively associated with depression was negatively associated. Replacing low-quality carbohydrates with high-quality carbohydrates throughout the day reduced the risk of depression by approximately 15 %.

LIMITATIONS

Cross-sectional data.

CONCLUSION

All in all, diet plays a crucial role in the prevention and treatment of depression. Especially in terms of macronutrient intake, high-quality, moderate intake can reduce the risk of depression. However, different subtypes of macronutrient consumption may have different effects on depression, so it becomes crucial to carefully consider the selection and combination of macronutrients.

Identification and validation of aging-related genes in heart failure based on multiple machine learning algorithms

Background

In the face of continued growth in the elderly population, the need to understand and combat age-related cardiac decline becomes even more urgent, requiring us to uncover new pathological and cardioprotective pathways.

Methods

We obtained the aging-related genes of heart failure through WGCNA and CellAge database. We elucidated the biological functions and signaling pathways involved in heart failure and aging through GO and KEGG enrichment analysis. We used three machine learning algorithms: LASSO, RF and SVM-RFE to further screen the aging-related genes of heart failure, and fitted and verified them through a variety of machine learning algorithms. We searched for drugs to treat age-related heart failure through the DSigDB database. Finally, We use CIBERSORT to complete immune infiltration analysis of aging samples.

Results

We obtained 57 up-regulated and 195 down-regulated aging-related genes in heart failure through WGCNA and CellAge databases. GO and KEGG enrichment analysis showed that aging-related genes are mainly involved in mechanisms such as Cellular senescence and Cell cycle. We further screened aging-related genes through machine learning and obtained 14 key genes. We verified the results on the test set and 2 external validation sets using 15 machine learning algorithm models and 207 combinations, and the highest accuracy was 0.911. Through screening of the DSigDB database, we believe that rimonabant and lovastatin have the potential to delay aging and protect the heart. The results of immune infiltration analysis showed that there were significant differences between Macrophages M2 and T cells CD8 in aging myocardium.

Conclusion

We identified aging signature genes and potential therapeutic drugs for heart failure through bioinformatics and multiple machine learning algorithms, providing new ideas for studying the mechanism and treatment of age-related cardiac decline.

Optimizing early neurological deterioration prediction in acute ischemic stroke patients following intravenous thrombolysis: a LASSO regression model approach

Background

Acute ischemic stroke (AIS) remains a leading cause of disability and mortality globally among adults. Despite Intravenous Thrombolysis (IVT) with recombinant tissue plasminogen activator (rt-PA) emerging as the standard treatment for AIS, approximately 6-40% of patients undergoing IVT experience Early Neurological Deterioration (END), significantly impacting treatment efficacy and patient prognosis.

Objective

This study aimed to develop and validate a predictive model for END in AIS patients post rt-PA administration using the Least Absolute Shrinkage and Selection Operator (LASSO) regression approach.

Methods

In this retrospective cohort study, data from 531 AIS patients treated with intravenous alteplase across two hospitals were analyzed. LASSO regression was employed to identify significant predictors of END, leading to the construction of a multivariate predictive model.

Results

Six key predictors significantly associated with END were identified through LASSO regression analysis: previous stroke history, Body Mass Index (BMI), age, Onset to Treatment Time (OTT), lymphocyte count, and glucose levels. A predictive nomogram incorporating these factors was developed, effectively estimating the probability of END post-IVT. The model demonstrated robust predictive performance, with an Area Under the Curve (AUC) of 0.867 in the training set and 0.880 in the validation set.

Conclusion

The LASSO regression-based predictive model accurately identifies critical risk factors leading to END in AIS patients following IVT. This model facilitates timely identification of high-risk patients by clinicians, enabling more personalized treatment strategies and optimizing patient management and outcomes.

Identification of Y‒linked biomarkers and exploration of immune infiltration of normal-appearing gray matter in multiple sclerosis by bioinformatic analysis

Background

The knowledge of normal‒appearing cortical gray matter (NAGM) in multiple sclerosis (MS) remains unclear. In this study, we aimed to identify diagnostic biomarkers and explore the immune infiltration characteristics of NAGM in MS through bioinformatic analysis and validation in vivo.

Methods

Differentially expressed genes (DEGs) were analyzed. Subsequently, the functional pathways of the DEGs were determined. After screening the overlapping DEGs of MS with two machine learning methods, the biomarkers' efficacy and the expression levels of overlapping DEGs were calculated. Quantitative reverse transcription polymerase chain reaction (qRT‒PCR) identified the robust diagnostic biomarkers. Additionally, infiltrating immune cell populations were estimated and correlated with the biomarkers. Finally, the characteristics of immune infiltration of NAGM from MS were evaluated.

Results

A total of 98 DEGs were identified. They participated in sensory transduction of the olfactory system, synaptic signaling, and immune responses. Nine overlapping genes were screened by machine learning methods. After verified by ROC curve, four genes, namely HLA‒DRB1, RPS4Y1, EIF1AY and USP9Y, were screened as candidate biomarkers. The mRNA expression of RPS4Y1 and USP9Y was significantly lower in MS patients than that in the controls. They were selected as the robust diagnostic biomarkers for male MS patients. RPS4Y1 and USP9Y were both positively correlated with memory B cells. Moreover, naive CD4+ T cells and monocytes were increased in the NAGM of MS patients compared with those in controls.

Conclusions

Low expressed Y‒linked genes, RPS4Y1 and USP9Y, were identified as diagnostic biomarkers for MS in male patients. The inhomogeneity of immune cells in NAGM might exacerbate intricate interplay between the CNS and the immune system in the MS.

Machine learning-based nomogram to predict poor response to overnight orthokeratology in Chinese myopic children: A multicentre, retrospective study

PURPOSE

To develop and validate an effective nomogram for predicting poor response to orthokeratology.

METHODS

Myopic children (aged 8-15 years) treated with orthokeratology between February 2018 and January 2022 were screened in four hospitals of different tiers (i.e. municipal and provincial) in China. Potential predictors included 32 baseline clinical variables. Nomogram for the outcome (1-year axial elongation ≥0.20 mm: poor response; <0.20 mm: good response) was computed from a logistic regression model with the least absolute shrinkage and selection operator. The data from the First Affiliated Hospital of Chengdu Medical College were randomly assigned (7:3) to the training and validation cohorts. An external cohort from three independent multicentre was used for the model test. Model performance was assessed by discrimination (the area under curve, AUC), calibration (calibration plots) and utility (decision curve analysis).

RESULTS

Between January 2022 and March 2023, 1183 eligible subjects were screened from the First Affiliated Hospital of Chengdu Medical College, then randomly divided into training (n = 831) and validation (n = 352) cohorts. A total of 405 eligible subjects were screened in the external cohort. Predictors included in the nomogram were baseline age, spherical equivalent, axial length, pupil diameter, surface asymmetry index and parental myopia (p < 0.05). This nomogram demonstrated excellent calibration, clinical net benefit and discrimination, with the AUC of 0.871 (95% CI 0.847-0.894), 0.863 (0.826-0.901) and 0.817 (0.777-0.857) in the training, validation and external cohorts, respectively. An online calculator was generated for free access (http://39.96.75.172:8182/#/nomogram).

CONCLUSION

The nomogram provides accurate individual prediction of poor response to overnight orthokeratology in Chinese myopic children.

Novel polymorphisms in CYP4A22 associated with susceptibility to coronary heart disease

BACKGROUND

Coronary heart disease (CHD) has become a worldwide public health problem. Genetic factors are considered important risk factors for CHD. The aim of this study was to explore the correlation between CYP4A22 gene polymorphism and CHD susceptibility in the Chinese Han population.

METHODS

We used SNPStats online software to complete the association analysis among 962 volunteers. False-positive report probability analysis was used to confirm whether a positive result is noteworthy. Haploview software and SNPStats were used for haplotype analysis and linkage disequilibrium. Multi-factor dimensionality reduction was applied to evaluate the interaction between candidate SNPs.

RESULTS

In overall and some stratified analyses (male, age ≤ 60 years or CHD patients complicated with hypertension), CYP4A22-rs12564525 (overall, OR = 0.83, p-value is 0.042) and CYP4A22-rs2056900 (overall, OR = 1.22, p-value is 0.032) were associated with the risk of CHD. CYP4A22-4926581 was associated with increased CHD risk only in some stratified analyses. FPRP indicated that all positive results in our study are noteworthy findings. In addition, MDR showed that the single-locus model composed of rs2056900 is the best model for predicting susceptibility to CHD.

CONCLUSION

There are significant associations between susceptibility to CHD and CYP4A22 rs12564525, and rs2056900.

Comprehensive Analysis Based on the TCGA Database Identified SCIN as a Key DNA Methylation-Driver Gene in Epstein-Barr Virus-Associated Gastric Cancer

An important feature of EBV-associated gastric cancer (EBVaGC) is extensive methylation of viral and host genomes. This study aims to analyze DNA methylation-driven genes (DMDG) in EBVaGC through bioinformatics methods, providing an important bioinformatics basis for the differential diagnosis and treatment of potential methylation biomarkers in EBVaGC. We downloaded the mRNA expression profiles and methylation datasets of EBVaGC and EBV-negative gastric cancer (EBVnGC) through the TCGA database to screen methylated-differentially expressed genes (MDEGs). DNA methylation-driver genes were identified based on MethylMix algorithm and key genes were further identified by LASSO regression and Random Forest algorithm. Then, we performed gene enrichment analysis for key genes and validated them by GEO database. Gene expression differences in EBVaGC and EBVnGC cell lines was determined by quantitative real-time PCR (qRT-PCR) and western blotting and in GT38 cell and SNU719 cell which all treated by 5-Aza-CdR. Finally, the effect of key gene on the migration and proliferation capacity of EBVaGC cells was determined by Transwells assay and Cell counting Kit-8 (CCK-8) assay. We obtained a total of 687 hypermethylation-low expression genes (Hyper-LGs) and further obtained 53 DNA methylation-driver genes based on the MethylMix algorithm. A total of six key genes (SCIN, ETNK2, PCDH20, PPP1R3C, MATN2, and HOXA5) were identified by LASSO regression and Random Forest algorithm. Among them, SCIN expression was significantly lower in EBVaGC cell lines than in EBVnGC cell lines, and its expression was significantly recovered in EBVaGC cell lines treated with 5-Aza-CdR. Overexpression of SCIN can promote the proliferation and migration capacity of EBVaGC cells. Our study will provide some bioinformatics basis for the study of EBVaGC-related methylation. SCIN may be used as potential methylation biomarkers for the diagnosis and treatment of EBVaGC.

Machine learning-based prediction model for distant metastasis of breast cancer

BACKGROUND

Breast cancer is the most prevalent malignancy in women. Advanced breast cancer can develop distant metastases, posing a severe threat to the life of patients. Because the clinical warning signs of distant metastasis are manifested in the late stage of the disease, there is a need for better methods of predicting metastasis.

METHODS

First, we screened breast cancer distant metastasis target genes by performing difference analysis and weighted gene co-expression network analysis (WGCNA) on the selected datasets, and performed analyses such as GO enrichment analysis on these target genes. Secondly, we screened breast cancer distant metastasis target genes by LASSO regression analysis and performed correlation analysis and other analyses on these biomarkers. Finally, we constructed several breast cancer distant metastasis prediction models based on Logistic Regression (LR) model, Random Forest (RF) model, Support Vector Machine (SVM) model, Gradient Boosting Decision Tree (GBDT) model and eXtreme Gradient Boosting (XGBoost) model, and selected the optimal model from them.

RESULTS

Several 21-gene breast cancer distant metastasis prediction models were constructed, with the best performance of the model constructed based on the random forest model. This model accurately predicted the emergence of distant metastases from breast cancer, with an accuracy of 93.6 %, an F1-score of 88.9 % and an AUC value of 91.3 % on the validation set.

CONCLUSION

Our findings have the potential to be translated into a point-of-care prognostic analysis to reduce breast cancer mortality.

Exploring factors influencing farmers' health self-assessment in China based on the LASSO method

As the main force and practice subject of rural revitalisation, farmers' health is intricately linked to agricultural production and the rural economy. This study utilizes open data from the 2015 China Nutrition and Health Survey and employs the Least Absolute Shrinkage and Selection Operator (LASSO) method to explore the factors influencing farmers' self-assessment of health. The findings reveal that education level, proactive nutrition knowledge seeking, healthy dietary preferences and habits, and the use of clean cooking fuel positively impact farmers' health self-assessment. Conversely, age, history of illness or injury, and participation in medical insurance negatively affect their self-assessment. Furthermore, factors influencing farmers' health self-assessment exhibit heterogeneity across regions. Our findings suggest that promoting health education, disseminating nutritional dietary knowledge, and enhancing rural household infrastructure play an important role in improving farmers' self-evaluation of health. Therefore, policymakers should design more targeted health interventions and infrastructure improvement plans based on farmers' self-assessment of health and the level of regional economic development.

Effect of lipid composition on RNA-Lipid nanoparticle properties and their sensitivity to thin-film freezing and drying

A library of 16 lipid nanoparticle (LNP) formulations with orthogonally varying lipid molar ratios was designed and synthesized, using polyadenylic acid [poly(A)] as a model for mRNA, to explore the effect of lipid composition in LNPs on (i) the initial size of the resultant LNPs and encapsulation efficiency of RNA and (ii) the sensitivity of the LNPs to various conditions including cold storage, freezing (slow vs. rapid) and thawing, and drying. Least Absolute Shrinkage and Selection Operator (LASSO) regression was employed to identify the optimal lipid molar ratios and interactions that favorably affect the physical properties of the LNPs and enhance their stability in various stress conditions. LNPs exhibited distinct responses under each stress condition, highlighting the effect of lipid molar ratios and lipid interactions on the LNP physical properties and stability. It was then demonstrated that it is feasible to use thin-film freeze-drying to convert poly(A)-LNPs from liquid dispersions to dry powders while maintaining the integrity of the LNPs. Importantly, the residual moisture content in LNP dry powders significantly affected the LNP integrity.Residual moisture content of ≤ 0.5% or > 3-3.5% w/w negatively affected the LNP size and/or RNA encapsulation efficiency, depending on the LNP composition. Finally, it was shown that the thin-film freeze-dried LNP powders have desirable aerosol properties for potential pulmonary delivery. It was concluded that Design of Experiments can be applied to identify mRNA-LNP formulations with the desired physical properties and stability profiles. Additionally, optimizing the residual moisture content in mRNA-LNP dry powders during (thin-film) freeze-drying is crucial to maintain the physical properties of the LNPs.

Identification of Senescence-Associated Biomarkers in Diabetic Glomerulopathy Using Integrated Bioinformatics Analysis

Background

Cellular senescence is thought to play a significant role in the onset and development of diabetic nephropathy. The goal of this study was to explore potential biomarkers associated with diabetic glomerulopathy from the perspective of senescence.

Methods

Datasets about human glomerular biopsy samples related to diabetic nephropathy were systematically obtained from the Gene Expression Omnibus database. Hub senescence-associated genes were investigated by differential gene analysis and Least Absolute Shrinkage and Selection Operator analysis. Cluster analysis was employed to identify senescence molecular subtypes. A single-cell dataset was used to validate the above findings and further evaluate the senescence environment. The relationship between these genes and the glomerular filtration rate was explored based on the Nephroseq database. These gene expressions have also been explored in various kidney diseases.

Results

Twelve representative senescence-associated genes (VEGFA, IQGAP2, JUN, PLAT, ETS2, ANG, MMP14, VEGFC, SERPINE2, CXCR2, PTGES, and EGF) were finally identified. Biological changes in immune inflammatory response, cell cycle regulation, metabolic regulation, and immune microenvironment have been observed across different molecular subtypes. The above results were also validated based on single-cell analysis. Additionally, we also identified several significantly altered cell communication pathways, including COLLAGEN, PTN, LAMININ, SPP1, and VEGF. Finally, almost all these genes could well predict the occurrence of diabetic glomerulopathy based on receiver operating characteristic analysis and are associated with the glomerular filtration rate. These genes are differently expressed in various kidney diseases.

Conclusion

The present study identified potential senescence-associated biomarkers and further explored the heterogeneity of diabetic glomerulopathy that might provide new insights into the diagnosis, assessment, management, and personalized treatment of DN.

Machine learning identifies the risk of complications after laparoscopic radical gastrectomy for gastric cancer

BACKGROUND

Laparoscopic radical gastrectomy is widely used, and perioperative complications have become a highly concerned issue.

AIM

To develop a predictive model for complications in laparoscopic radical gastrectomy for gastric cancer to better predict the likelihood of complications in gastric cancer patients within 30 days after surgery, guide perioperative treatment strategies for gastric cancer patients, and prevent serious complications.

METHODS

In total, 998 patients who underwent laparoscopic radical gastrectomy for gastric cancer at 16 Chinese medical centers were included in the training group for the complication model, and 398 patients were included in the validation group. The clinicopathological data and 30-d postoperative complications of gastric cancer patients were collected. Three machine learning methods, lasso regression, random forest, and artificial neural networks, were used to construct postoperative complication prediction models for laparoscopic distal gastrectomy and laparoscopic total gastrectomy, and their prediction efficacy and accuracy were evaluated.

RESULTS

The constructed complication model, particularly the random forest model, could better predict serious complications in gastric cancer patients undergoing laparoscopic radical gastrectomy. It exhibited stable performance in external validation and is worthy of further promotion in more centers.

CONCLUSION

Using the risk factors identified in multicenter datasets, highly sensitive risk prediction models for complications following laparoscopic radical gastrectomy were established. We hope to facilitate the diagnosis and treatment of preoperative and postoperative decision-making by using these models.

Prediction of biomarkers associated with membranous nephropathy: Bioinformatic analysis and experimental validation

Membranous nephropathy (MN), the most prevalent form of nephrotic syndrome in non-diabetic adults globally, is currently the second most prevalent and fastest-increasing primary glomerular disease in China. Numerous renal disorders are developed partly due to ferroptosis. However, its relationship to the pathogenesis of MN has rarely been investigated in previous studies; actually, ferroptosis is closely linked to the immune microenvironment and inflammatory response, which might affect the entire process of MN development. In this study, we aimed to identify ferroptosis-related genes that are potentially related to immune cell infiltration, which can further contribute to MN pathogenesis. The microarray datasets were downloaded from the Gene Expression Omnibus (GEO) database. Ferroptosis-related differentially expressed genes (FDEGs) were identified, which were further used for functional enrichment analysis. The common genes identified using the Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression algorithm and the support vector machine recursive feature elimination (SVM-RFE) algorithm were used to identify the characteristic genes related to ferroptosis. The feasibility of the 7 genes as a distinguishing factor was assessed using the receiver operating characteristic (ROC) curve, with the area under the curve (AUC) score serving as the evaluation metric. Gene set enrichment analysis (GSEA) and correlation analysis of these genes were further performed. The correlation between the expression of these genes and immune cell infiltration inferred by single sample gene set enrichment analysis (ssGSEA) algorithm was explored. As a result, 7 genes, including NR1D1, YTHDC2, EGR1, ZFP36, RRM2, RELA and PDK4, which were most relevant to immune cell infiltration, were identified to be potential diagnostic genes in MN patients. Next, the signature genes were validated with other GEO datasets. In the subsequent steps, we conducted quantitative real-time fluorescence PCR (qRT-PCR) analysis and immunohistochemistry (IHC) method on the cationic bovine serum albumin (C-BSA) induced membranous nephropathy (MN) rat model and the passive Heymann nephritis (pHN) rat model to examine characteristic genes. Finally, we analysed the mRNA expression patterns of hub genes in MN patients and normal controls using the Nephroseq V5 online platform. In concise terms, our study successfully identified biomarkers specific to MN patients and delved into the potential interplay between these markers and immune cell infiltration. This knowledge bears significance for the diagnosis and prospective treatment strategies for individuals affected by MN.

Multiple machine-learning tools identifying prognostic biomarkers for acute Myeloid Leukemia

BACKGROUND

Acute Myeloid Leukemia (AML) generally has a relatively low survival rate after treatment. There is an urgent need to find new biomarkers that may improve the survival prognosis of patients. Machine-learning tools are more and more widely used in the screening of biomarkers.

METHODS

Least Absolute Shrinkage and Selection Operator (LASSO), Support Vector Machine-Recursive Feature Elimination (SVM-RFE), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), lrFuncs, IdaProfile, caretFuncs, and nbFuncs models were used to screen key genes closely associated with AML. Then, based on the Cancer Genome Atlas (TCGA), pan-cancer analysis was performed to determine the correlation between important genes and AML or other cancers. Finally, the diagnostic value of important genes for AML was verified in different data sets.

RESULTS

The survival analysis results of the training set showed 26 genes with survival differences. After the intersection of the results of each machine learning method, DNM1, MEIS1, and SUSD3 were selected as key genes for subsequent analysis. The results of the pan-cancer analysis showed that MEIS1 and DNM1 were significantly highly expressed in AML; MEIS1 and SUSD3 are potential risk factors for the prognosis of AML, and DNM1 is a potential protective factor. Three key genes were significantly associated with AML immune subtypes and multiple immune checkpoints in AML. The results of the verification analysis show that DNM1, MEIS1, and SUSD3 have potential diagnostic value for AML.

CONCLUSION

Multiple machine learning methods identified DNM1, MEIS1, and SUSD3 can be regarded as prognostic biomarkers for AML.

Identification of metabolite biomarkers in Salmonella enteritidis-contaminated chickens using UHPLC-QTRAP-MS-based targeted metabolomics

This study aimed to characterize the metabolic profile of Salmonella enteritidis (S. enteritidis) in chicken matrix and to identify metabolic biomarkers of S. enteritidis in chicken. The UHPLC-QTRAP-MS high-throughput targeted metabolomics approach was employed to analyze the metabolic profiles of contaminated and control group chickens. A total of 348 metabolites were quantified, and the application of deep learning least absolute shrinkage and selection operator (LASSO) modelling analysis obtained eight potential metabolite biomarkers for S. enteritidis. Metabolic abundance change analysis revealed significantly enriched abundances of anthranilic acid, l-pyroglutamic acid, 5-hydroxylysine, n,n-dimethylarginine, 4-hydroxybenzoic acid, and menatetrenone in contaminated chicken samples. The receiver operating characteristic (ROC) curve analysis demonstrated the strong ability of these six metabolites as biomarkers to distinguish S. enteritidis contaminated and fresh chicken samples. The findings presented in this study offer a theoretical foundation for developing an innovative approach to identify and detect foodborne contamination caused by S. enteritidis.

Comprehensive analysis reveals key genes and environmental toxin exposures underlying treatment response in ulcerative colitis based on in-silico analysis and Mendelian randomization

BACKGROUND

UC is increasingly prevalent worldwide and represents a significant global disease burden. Although medical therapeutics are employed, they often fall short of being optimal, leaving patients struggling with treatment non-responsiveness and many related complications.

MATERIALS AND METHODS

The study utilized gene microarray data and clinical information from GEO. Gene enrichment and differential expression analyses were conducted using Metascape and Limma, respectively. Lasso Regression Algorithm was constructed using glmnet and heat maps were generated using pheatmap. ROC curves were used to assess diagnostic parameter capability, while XSum was employed to screen for small-molecule drugs exacerbating UC. Molecular docking was carried out using Autodock Vina. The study also performed Mendelian randomization analysis based on TwoSampleMR and used CTD to investigate the relationship between exposure to environmental chemical toxicants and UC therapy responsiveness.

RESULTS

Six genes (ELL2, DAPP1, SAMD9L, CD38, IGSF6, and LYN) were found to be significantly overexpressed in UC patient samples that did not respond to multiple therapies. Lasso analysis identified ELL2 and DAPP1 as key genes influencing UC treatment response. Both genes accurately predicted intestinal inflammation in UC and impacted the immunological infiltration status. Clofibrate showed therapeutic potential for UC by binding to ELL2 and DAPP1 proteins. The study also reviews environmental toxins and drug exposures that could impact UC progression.

CONCLUSIONS

We used microarray technology to identify DAPP1 and ELL2 as key genes that impact UC treatment response and inflammatory progression. Clofibrate was identified as a promising UC treatment. Our review also highlights the impact of environmental toxins on UC treatment response, providing valuable insights for personalized clinical management.

Empirical assessment of carbon emissions in Guangdong Province within the framework of carbon peaking and carbon neutrality: a lasso-TPE-BP neural network approach

The escalating global greenhouse gas emission crisis necessitates a robust scientific carbon accounting framework and innovative development approaches. Achieving emission peaks remains the primary goal for emission reduction. Guangdong Province, a pivotal region in China, faces pressure to reduce carbon emissions. In this study, data was leveraged from the China Carbon Accounting Database (CEADS) and panel data from the "Guangdong Statistical Yearbook" spanning 1997 to 2022. Factors impacting carbon emissions were selected based on Guangdong Province's carbon reduction goals, macroeconomic development strategies, and economic-population dynamics. To address multicollinearity, lasso regression identified key factors, including population size, economic development level, energy intensity, and technology factors. A novel STIRPAT extended model, combined with the BP neural network optimized using the TPE algorithm, enhanced carbon emission predictions for Guangdong Province. Employing scenario analysis, five scenarios were generated in alignment with the planning policies of Guangdong Province, to forecast carbon emissions from 2020 to 2050. The results suggest that to achieve a win-win situation for both economic development and environmental protection, Guangdong Province should prioritize the energy-saving scenario (S2), which aligns with the "13th Five-Year Plan's" ecological and green development directives, to reach a projected carbon peak of 637.05Mt by 2030. In conclusion, recommendations for carbon reduction are proposed in the areas of low-carbon transformation for the population, sustainable economic development, and the development of low-carbon technologies.

Identification of important genes associated with acute myocardial infarction using multiple cell death patterns

Acute myocardial infarction (AMI) is a global health threat, and programmed cell death (PCD) plays a crucial role in its occurrence and development. In this study, integrated bioinformatics tools were used to explore new biomarkers and therapeutic targets in AMI. Thirteen types of PCD-related genes were identified through literature review, KEGG, and GSEA pathways. Gene expression matrices and clinical data from AMI patients and healthy controls were obtained from the GEO database. Statistical analysis in R identified 377 differentially expressed genes in AMI patients. Intersection analysis between the differentially expressed genes and PCD-related genes revealed 24 genes positively correlated with immune cells such as Neutrophils and Monocytes, while negatively correlated with T cells CD4 memory resting and Plasma cells. Unsupervised clustering analysis divided patients into two groups (C1 and C2) based on the expression levels of these 24 genes. GSVA analysis showed that C2 patients were more active in pathways related to maintaining normal cell morphology and promoting phagocytosis, suggesting a lower programmed cell death rate and a higher tendency to maintain cell survival. Two hub genes, TNFAIP3 and TP53INP2, were identified through LASSO regression analysis and SVM-RFE, and were validated using an external dataset and RT-qPCR、Western blot and ELISA analysis. These hub genes showed significantly higher expression and protein secretion levels in AMI patients compared to healthy individuals. Overall, regulating and controlling PCD, particularly through the identified hub genes, TNFAIP3 and TP53INP2, may provide new therapeutic strategies for improving the prognosis of AMI patients and preventing heart failure.

LASSO-based machine learning algorithm to predict the incidence of diabetes in different stages

BACKGROUND

Formal risk assessment is crucial for diabetes prevention. We aimed to establish a practical nomogram for predicting the risk incidence of prediabetes and prediabetes conversion to diabetes.

METHODS

A cohort of 1428 subjects was collected to develop prediction models. The LASSO was used to screen for important risk factors in prediabetes and diabetes and was compared with other algorithms (LR, RF, SVM, LDA, NB, and Treebag). Multivariate logistic regression analysis was used to construct the prediction model of prediabetes and diabetes, and drawn the predictive nomogram. The performance of the nomograms was evaluated by receiver-operating characteristic curve and calibration.

RESULTS

These findings revealed that the other six algorithms were not as good as LASSO in terms of diabetes risk prediction. The nomogram for individualized prediction of prediabetes included "Age," "FH," "Insulin_F," "hypertension," "Tgab," "HDL-C," "Proinsulin_F," and "TG" and the nomogram of prediabetes to diabetes included "Age," "FH," "Proinsulin_E," and "HDL-C". The results showed that the two models had certain discrimination, with the AUC of 0.78 and 0.70, respectively. The calibration curve of the two models also indicated good consistency.

CONCLUSIONS

We established early warning models for prediabetes and diabetes, which can help identify prediabetes and diabetes high-risk populations in advance.

Diet-Related Risk Factors for Cervical Cancer: Data from National Health and Nutrition Examination Survey 1999-2018

Diverse dietary constituents, encompassing both macro- and micronutrient intakes, have established connections with various cancers, though their specific roles in cervical cancer remain unclear. This study explores dietary intake correlations among women aged 30 yrs and above diagnosed with cervical cancer (n = 215), contrasted with women without (n = 860). These populations were selected from the 1999-2018 cycle of the National Health and Nutrition Examination Survey. The research implemented the univariate analysis and the least absolute shrinkage and selection operator (LASSO) regression to estimate the association of 29 variables with cervical cancer, subsequently identifying the most pertinent variables linked to cervical cancer. Six covariates emerged as significantly associated with cervical cancer in univariate analyses (age, race, fiber, magnesium, caffeine, vitamin C) (p < 0.05). In LASSO regression, with the escalating penalty factor (λ), it was discerned that specific covariates, including age, race, fiber, and Vitamin C, consistently remained in the model. Univariate analysis and logistic LASSO regression findings suggested that diets deficient in fiber and vitamin C were related to cervical cancer.

A Macrophage-Related Gene Signature for Identifying COPD Based on Bioinformatics and ex vivo Experiments

Background

This study aims to investigate the association between immune cells and the development of COPD, while providing a new method for the diagnosis of COPD according to the changes in immune microenvironment.

Methods

In this study, the "CIBERSORT" algorithm was used to estimate the tissue infiltration of 22 types of immune cells in GSE20257 and GSE10006. The "limma" package was used for differentially expressed analysis. The key modules associated with vital immune cells were identified using WGCNA. GO and KEGG enrichment analysis revealed the biological functions of the candidate genes. Ultimately, a novel diagnostic prediction model was constructed via machine learning methods and multivariate logistic regression analysis based on GSE20257. Furthermore, we examined the stability of the model on one internal test set (GSE10006), three external test sets (GSE8545, GSE57148 and GSE76925), one single-cell transcriptome dataset (GSE167295), macrophages (THP-M cells) and lung tissue from COPD patients.

Results

M0 macrophages (AUC > 0.7 in GSE20257 and GSE10006) were considered as the most important immune cells through exploring the immune microenvironment landscapes in COPD patients and healthy controls. The differentially expressed genes from GSE20257 and GSE10006 were divided into six and five modules via WGCNA, respectively. The green module in GSE20257 (cor = 0.41, P < 0.001) and the brown module in GSE10006 (cor = 0.67, P < 0.001) were highly correlated with M0 macrophages and were selected as key modules. Forty-one intersected genes obtained from two modules were primarily involved in regulation of cytokine production, regulation of innate immune response, specific granule, phagosome, lysosome, ferroptosis, and other biological processes. On the basis of the candidate genetic markers further characterized via the "Boruta" and "LASSO" algorithm for COPD, a diagnostic model comprising CLEC5A, FTL and SLC2A3 was constructed, which could accurately distinguish COPD patients from healthy controls in multiple datasets. GSE20257 as the training set has an AUC of 0.916. The AUCs of the internal test set and three external test sets were 0.873, 0.932, 0.675 and 0.688, respectively. Single-cell sequencing analysis suggested that CLEC5A, FTL and SLC2A3 were expressed in macrophages from COPD patients. The expressions of CLEC5A, FTL and SLC2A3 were up-regulated in THP-M cells and lung tissue from COPD patients.

Conclusion

According to the variations of immune microenvironment in COPD patients, we constructed and validated a novel macrophage M0-associated diagnostic model with satisfactory predictive value. CLEC5A, FTL and SLC2A3 are expected to be promising targets of immunotherapy in COPD.

Non-alcoholic fatty liver disease risk prediction model and health management strategies for older Chinese adults: a cross-sectional study

BACKGROUND

Non-alcoholic fatty liver disease (NAFLD) is a common chronic liver condition that affects a quarter of the global adult population. To date, only a few NAFLD risk prediction models have been developed for Chinese older adults aged ≥ 60 years. This study presented the development of a risk prediction model for NAFLD in Chinese individuals aged ≥ 60 years and proposed personalised health interventions based on key risk factors to reduce NAFLD incidence among the population.

METHODS

A cross-sectional survey was carried out among 9,041 community residents in Shanghai. Three NAFLD risk prediction models (I, II, and III) were constructed using multivariate logistic regression analysis based on the least absolute shrinkage and selection operator regression analysis, and random forest model to select individual characteristics, respectively. To determine the optimal model, the three models' discrimination, calibration, clinical application, and prediction capability were evaluated using the receiver operating characteristic (ROC) curve, calibration plot, decision curve analysis, and net reclassification index (NRI), respectively. To evaluate the optimal model's effectiveness, the previously published NAFLD risk prediction models (Hepatic steatosis index [HSI] and ZJU index) were evaluated using the following five indicators: accuracy, precision, recall, F1-score, and balanced accuracy. A dynamic nomogram was constructed for the optimal model, and a Bayesian network model for predicting NAFLD risk in older adults was visually displayed using Netica software.

RESULTS

The area under the ROC curve of Models I, II, and III in the training dataset was 0.810, 0.826, and 0.825, respectively, and that of the testing data was 0.777, 0.797, and 0.790, respectively. No significant difference was found in the accuracy or NRI between the models; therefore, Model III with the fewest variables was determined as the optimal model. Compared with the HSI and ZJU index, Model III had the highest accuracy (0.716), precision (0.808), recall (0.605), F1 score (0.692), and balanced accuracy (0.723). The risk threshold for Model III was 20%-80%. Model III included body mass index, alanine aminotransferase level, triglyceride level, and lymphocyte count.

CONCLUSIONS

A dynamic nomogram and Bayesian network model were developed to identify NAFLD risk in older Chinese adults, providing personalized health management strategies and reducing NAFLD incidence.

Identification of hub genes and their correlation with immune infiltrating cells in membranous nephropathy: an integrated bioinformatics analysis

BACKGROUND

Membranous nephropathy (MN) is a chronic glomerular disease that leads to nephrotic syndrome in adults. The aim of this study was to identify novel biomarkers and immune-related mechanisms in the progression of MN through an integrated bioinformatics approach.

METHODS

The microarray data were downloaded from the Gene Expression Omnibus (GEO) database. The differentially expressed genes (DEGs) between MN and normal samples were identified and analyzed by the Gene Ontology analysis, the Kyoto Encyclopedia of Genes and Genomes analysis and the Gene Set Enrichment Analysis (GSEA) enrichment. Hub The hub genes were screened and identified by the weighted gene co-expression network analysis (WGCNA) and the least absolute shrinkage and selection operator (LASSO) algorithm. The receiver operating characteristic (ROC) curves evaluated the diagnostic value of hub genes. The single-sample GSEA analyzed the infiltration degree of several immune cells and their correlation with the hub genes.

RESULTS

We identified a total of 574 DEGs. The enrichment analysis showed that metabolic and immune-related functions and pathways were significantly enriched. Four co-expression modules were obtained using WGCNA. The candidate signature genes were intersected with DEGs and then subjected to the LASSO analysis, obtaining a total of 6 hub genes. The ROC curves indicated that the hub genes were associated with a high diagnostic value. The CD4+ T cells, CD8+ T cells and B cells significantly infiltrated in MN samples and correlated with the hub genes.

CONCLUSIONS

We identified six hub genes (ZYX, CD151, N4BP2L2-IT2, TAPBP, FRAS1 and SCARNA9) as novel biomarkers for MN, providing potential targets for the diagnosis and treatment.

Associations between the chemical exposome and pregnancy induced hypertension

Exposure to environmental chemicals has been linked to an increased risk of pregnancy-induced hypertension (PIH). This prospective cohort study examined the associations between PIH and maternal chemical exposure to four classes of chemicals (i.e., phthalates, bisphenols, perfluoroalkyl acids, non-essential metals and trace minerals). Participants included 420 pregnant women from the Alberta Pregnancy Outcomes and Nutrition (APrON) cohort who had data available on diagnosed PIH and environmental chemical exposure. Twelve phthalate metabolites, two bisphenols, eight perfluoroalkyl acids and eleven non-essential metals or trace minerals were quantified in maternal urine or blood samples collected in the second trimester of pregnancy. Associations between the urinary and blood concentrations of these chemicals and PIH were assessed using multiple logistic and LASSO regression analyses in single- and multi-chemical exposure models, respectively. Thirty-five (8.3%) participants were diagnosed with PIH. In single chemical exposure models, two phthalate metabolites, mono-methyl phthalate (MMP) and monoethyl phthalate (MEP), three perfluoroalkyl acids, perfluoroheptanoic acid (PFHpA), perfluorononanoic acid (PFNA), and perfluorodecanoic acid (PFDA), and one metal, manganese, were associated with increased odds of PIH. The metabolites of di (2-ethylhexyl) phthalate (DEHP) and the molar sum of these metabolites, as well as antimony, displayed trend associations (p < 0.10). In multi-chemical exposure models using LASSO penalized regressions and double-LASSO regressions, MEP (AOR: 1.43, 95% CI: 1.09-1.88, p = 0.009) and PFNA (AOR: 2.03, 95% CI: 1.01-4.07, p = 0.04) were selected as the chemicals most highly associated with PIH. These findings suggest that maternal levels of phthalates and perfluoroalkyl acids may be associated with the diagnosis on PIH. Future research should consider both individual and multi-chemical exposures when examining predictors of PIH and other maternal cardiometabolic health disorders, such as preeclampsia, eclampsia, HELLP syndrome, and gestational diabetes.

Machine learning-based prediction models for parathyroid carcinoma using pre-surgery cognitive function and clinical features

Patients with parathyroid carcinoma (PC) are often diagnosed postoperatively, due to incomplete resection during the initial surgery, resulting in poor outcomes. The aim of our study was to investigate the pre-surgery indicators of PC and try to develop a predictive model for PC utilizing machine learning. Evaluation of pre-surgery neuropsychological function and confirmation of pathology were carried out in 133 patients with primary hyperparathyroidism in Beijing Chaoyang Hospital from December 2019 to January 2023. Patients were randomly divided into a training cohort (n = 93) and a validating cohort (n = 40). Analysis of the clinical dataset, two machine learning including the extreme gradient boosting (XGBoost) and the least absolute shrinkage and selection operator (LASSO) regression were utilized to develop the prediction model for PC. Logistic regression analysis was also conducted for comparison. Significant differences in elevated parathyroid hormone and decreased serum phosphorus in PC compared to (BP). The lower score of MMSE and MOCA was observed in PC and a cutoff of MMSE < 24 was the optimal threshold to stratify PC from BP (area under the curve AUC 0.699 vs 0.625). The predicted probability of PC by machine learning was similar to the observed probability in the test set, whereas the logistic model tended to overpredict the possibility of PC. The XGBoost model attained a higher AUC than the logistic algorithms and LASSO models. (0.835 vs 0.683 vs 0.607). Preoperative cognitive function may be a probable predictor for PC. The cognitive function-based prediction model based on the XGBoost algorithm outperformed LASSO and logistic regression, providing valuable preoperative assistance to surgeons in clinical decision-making for patients suspected PC.

Survival nomogram for medulloblastoma and multi-center external validation cohort

Background: Medulloblastoma (MB) is a highly malignant neuroepithelial tumor occurring in the central nervous system. The objective of this study was to establish an effective prognostic nomogram to predict the overall survival (OS) of MB patients. Materials and methods: The nomogram was developed using data from a retrospective cohort of 280 medulloblastoma patients (aged 3-18 years) identified from Beijing Tiantan Hospital between 2016 and 2021 as the training cohort. To validate the performance of the nomogram, collaborations were formed with eight leading pediatric oncology centers across different regions of China. A total of 162 medulloblastoma patients meeting the inclusion criteria were enrolled from these collaborating centers. Cox regression analysis, best subsets regression, and Lasso regression were employed to select independent prognostic factors. The nomogram's prognostic effectiveness for overall survival was assessed using the concordance index, receiver operating characteristic curve, and calibration curve. Results: In the training cohort, the selected variables through COX regression, best subsets regression, and Lasso regression, along with their clinical significance, included age, molecular subtype, histological type, radiotherapy, chemotherapy, metastasis, and hydrocephalus. The internally and externally validated C-indexes were 0.907 and 0.793, respectively. Calibration curves demonstrated the precise prediction of 1-, 3-, and 5-year OS for MB patients using the nomogram. Conclusion: This study developed a nomogram that incorporates clinical and molecular factors to predict OS prognosis in medulloblastoma patients. The nomogram exhibited improved predictive accuracy compared to previous studies and demonstrated good performance in the external validation cohort. By considering multiple factors, clinicians can utilize this nomogram as a valuable tool for individualized prognosis prediction and treatment decision-making in medulloblastoma patients.

The impact of multiple metals exposure on the risk of developing proliferative diabetic retinopathy in Anhui, China: a case-control study

Through multiple different pathways, the environmental multiple metals make their ways to the human bodies, where they induce different levels of the oxidative stress response. This study further investigated the impact of multiple-metal exposure on the risk of developing proliferative diabetic retinopathy (PDR). We designed a case-control study with type 2 diabetic patients (T2D), in which the case group was the proliferative diabetic retinopathy group (PDR group), while the control group was the non-diabetic retinopathy group (NDR group). Graphite furnace atomic absorption spectrometry (GFAAS) and inductively coupled plasma optical emission spectrometry (ICP-OES) were used to detect the metal levels in our participants' urine samples. The least absolute shrinkage and selection operator (LASSO) regression approach was used to include these representative trace elements in a multiple exposure model. Following that, logistic regression models and Bayesian kernel machine regression (BKMR) models were used to describe the effect of different elements and also analyze their combined effect. In the single-element model, we discovered that lithium (Li), cadmium (Cd), and strontium (Sr) were all positively related to PDR. The multiple-exposure model revealed a positive relationship between Li and PDR risk, with a maximum quartile OR of 2.80 (95% CI: 1.10-7.16). The BKMR model also revealed that selenium (Se) might act as a protective agent, whereas magnesium (Mg), Li, and Cd may raise the risk of PDR. In conclusion, our study not only revealed an association between exposure to multiple metals and PDR risk but it also implied that urine samples might be a useful tool to assess PDR risk.

Association between number of medications and hip fractures in Japanese elderly using conditional logistic LASSO regression

To examine the association between hip fracture and associated factors, including polypharmacy, and develop an optimal predictive model, we conducted a population-based matched case-control study using the health insurance claims data on hip fracture among Japanese patients. We included 34,717 hospitalized Japanese patients aged ≥ 65 years with hip fracture and 34,717 age- and sex- matched controls who were matched 1:1. This study included 69,434 participants. Overall, 16 variable comorbidities and 60 variable concomitant medications were used as explanatory variables. The participants were added to early elderly and late elderly categories for further analysis. The odds ratio of hip fracture increased with the number of medications only in the early elderly. AUC was highest for early elderly (AUC, 0.74, 95% CI 0.72-0.76). Use of anti-Parkinson's drugs had the largest coefficient and was the most influential variable in many categories. This study confirmed the association between risk factors, including polypharmacy and hip fracture. The risk of hip fracture increased with an increase in medication number taken by the early elderly and showed good predictive accuracy, whereas there was no such association in the late elderly. Therefore, the early elderly in Japan should be an active target population for hip fracture prevention.

Development of a radiomic-clinical nomogram for prediction of survival in patients with diffuse large B-cell lymphoma treated with chimeric antigen receptor T cells

BACKGROUND

In our current work, an 18F-FDG PET/CT radiomics-based model was developed to assess the progression-free survival (PFS) and overall survival (OS) of patients with relapsed or refractory (R/R) diffuse large B-cell lymphoma (DLBCL) who received chimeric antigen receptor (CAR)-T cell therapy.

METHODS

A total of 61 DLBCL cases receiving 18F-FDG PET/CT before CAR-T cell infusion were included in the current analysis, and these patients were randomly assigned to a training cohort (n = 42) and a validation cohort (n = 19). Radiomic features from PET and CT images were obtained using LIFEx software, and radiomics signatures (R-signatures) were then constructed by choosing the optimal parameters according to their PFS and OS. Subsequently, the radiomics model and clinical model were constructed and validated.

RESULTS

The radiomics model that integrated R-signatures and clinical risk factors showed superior prognostic performance compared with the clinical models in terms of both PFS (C-index: 0.710 vs. 0.716; AUC: 0.776 vs. 0.712) and OS (C-index: 0.780 vs. 0.762; AUC: 0.828 vs. 0.728). For validation, the C-index of the two approaches was 0.640 vs. 0.619 and 0.676 vs. 0.699 for predicting PFS and OS, respectively. Moreover, the AUC was 0.886 vs. 0.635 and 0.778 vs. 0.705, respectively. The calibration curves indicated good agreement, and the decision curve analysis suggested that the net benefit of radiomics models was higher than that of clinical models.

CONCLUSIONS

PET/CT-derived R-signature could be a potential prognostic biomarker for R/R DLBCL patients undergoing CAR-T cell therapy. Moreover, the risk stratification could be further enhanced when the PET/CT-derived R-signature was combined with clinical factors.

A combined clinical and specific genes' model to predict live birth for in vitro fertilization and embryo transfer patients

BACKGROUND

We aimed to develop an accurate model to predict live birth for patients receiving in vitro fertilization and embryo transfer (IVF-ET) treatment.

METHODS

This is a prospective nested case-control study. Women aged between 18 and 38 years, whose body mass index (BMI) were between the range of 18.5-24 kg/m2, who had an endometrium of ≥ 8 mm at the thickest were enrolled from 2018/9 to 2020/8. All patients received IVF-ET treatment and were followed up until Jan. 2022 when they had reproductive outcomes. Endometrial samples during the window of implantation (LH + 6 to 9 days) were subjected to analyze specific endometrial receptivity genes' expression using real-time PCR (RT-PCR). Patients were divided into live birth group and non-live birth group based on IVF-ET outcomes. Clinical signatures relevant to live birth were collected, analyzed, and used to establish a predictive model for live birth by univariate analysis (clinical model). Specific endometrial receptivity genes' expression was analyzed, selected, and used to construct a predictive model for live birth by The Least Absolute Shrinkage and Selection Operator (LASSO) analysis (gene model). Finally, significant clinical factors and genes were used to construct a combined model for predicting live birth using multivariate logistical regression (combined model). Different models' Area Under Curve (AUC) were compared to identify the most predictive model.

RESULTS

Thirty-nine patients were enrolled in the study, twenty-four patients had live births, fifteen did not. In univariate analysis, the odds of live birth for women with ovulation dysfunction was 4 times higher than that for women with other IVF-ET indications (OR = 4.0, 95% CI: 1.125 - 8.910, P = 0.018). Age, body mass index, duration of infertility, primary infertility, repeated implantation failure, antral follicle counting, ovarian sensitivity index, anti-Mullerian hormone, controlled ovarian hyperstimulation protocol and duration, total dose of FSH/hMG, number of oocytes retrieved, regiment of endometrial preparation, endometrium thickness before embryo transfer, type of embryo transferred were not associated with live birth (P > 0.05). Only ovulation dysfunction was used to construct the clinical model and its AUC was 0.688. In lasso analysis, GAST, GPX3, THBS2 were found to promote the risk of live birth. AUCs for GAST, GPX3, THBS2 reached to 0.736, 0.672, and 0.678, respectively. The gene model was established based on these three genes and its AUC was 0.772. Ovulation dysfunction, GAST, GPX3, and THBS2 were finally used to construct the combined model, reaching the highest AUC (AUC = 0.842).

CONCLUSIONS

Compared to the single model, the combined model of clinical (Ovulation dysfunction) and specific genes (GAST, GPX3, THBS2) was more accurate to predict live birth for IVF-ET patients.

Identification of dietary components in association with abdominal aortic calcification

The precise impact of dietary components on vascular health remains incompletely understood. To identify the dietary components and their associations with abdominal aortic calcification (AAC), the data from NHANES was employed in this cross-sectional study. The LASSO method and logistic regression were utilized to identify dietary components that exhibited the strongest association with AAC. Grouped WQS regression analysis was employed to evaluate the combined effects of dietary components on AAC. Furthermore, principal component analysis was employed to identify the primary dietary patterns in the study population. The present analysis included 1862 participants, from whom information on 35 dietary macro- and micronutrient components was obtained through 24-hour dietary recall interviews. The assessment of AAC was performed utilizing dual-energy X-ray absorptiometry. The LASSO method identified 10 dietary components that were associated with AAC. Total protein, total fiber, vitamin A, and β-cryptoxanthin exhibited a negative association with AAC. Compared to the first quartile, the adjusted odds ratios (95% CIs) for the highest quartile were 0.59 (0.38, 0.93), 0.63 (0.42, 0.93), 0.59 (0.41, 0.84), and 0.68 (0.48, 0.94), respectively. Grouped WQS regression demonstrated a positive association between the lipid group and AAC (aOR: 1.29; 95% CI: 1.12, 1.50), while the proteins and phytochemical group exhibited a negative association with AAC (aOR: 0.69; 95% CI: 0.58, 0.82). For the dietary pattern analysis, high adherence to the plant-based pattern (aOR: 0.62; 95% CI: 0.44, 0.88) was associated with a lower risk of AAC, whereas the caffeine and theobromine pattern (aOR: 1.73; 95% CI: 1.25, 2.41) was associated with a higher risk of AAC. The findings of this study indicate that adopting a dietary pattern characterized by high levels of protein and plant-based foods, as well as reduced levels of fat, may offers potential advantages for the prevention of AAC.

AP003352.1/miR-141-3p axis enhances the proliferation of osteosarcoma by LPAR3

Osteosarcoma (OS) is a highly malignant tumor with a poor prognosis and a growing incidence. LncRNAs and microRNAs control the occurrence and development process of osteosarcoma through ceRNA patterns. The LPAR3 gene is important in cancer cell proliferation, apoptosis and disease development. However, the regulatory mechanism of the ceRNA network through which LPAR3 participates in osteosarcoma has not been clarified. Herein, our study demonstrated that the AP003352.1/miR-141-3p axis drives LPAR3 expression to induce the malignant progression of osteosarcoma. First, the expression of LPAR3 is regulated by the changes in AP003352.1 and miR-141-3p. Similar to the ceRNA of miR-141-3p, AP003352.1 regulates the expression of LPAR3 through this mechanism. In addition, the regulation of AP003352.1 in malignant osteosarcoma progression depends to a certain degree on miR-141-3p. Importantly, the AP003352.1/miR-141-3p/LPAR3 axis can better serve as a multi-gene diagnostic marker for osteosarcoma. In conclusion, our research reveals a new ceRNA regulatory network, which provides a novel potential target for the diagnosis and treatment of osteosarcoma.

Identification and validation of novel biomarkers associated with immune infiltration for the diagnosis of osteosarcoma based on machine learning

Objectives: Osteosarcoma is the most common primary malignant tumor in children and adolescents, and the 5-year survival of osteosarcoma patients gained no substantial improvement over the past decades. Effective biomarkers in diagnosing osteosarcoma are warranted to be developed. This study aims to explore novel biomarkers correlated with immune cell infiltration in the development and diagnosis of osteosarcoma. Methods: Three datasets (GSE19276, GSE36001, GSE126209) comprising osteosarcoma samples were extracted from Gene Expression Omnibus (GEO) database and merged to obtain the gene expression. Then, differentially expressed genes (DEGs) were identified by limma and potential biological functions and downstream pathways enrichment analysis of DEGs was performed. The machine learning algorithms LASSO regression model and SVM-RFE (support vector machine-recursive feature elimination) analysis were employed to identify candidate hub genes for diagnosing patients with osteosarcoma. Receiver operating characteristic (ROC) curves were developed to evaluate the discriminatory abilities of these candidates in both training and test sets. Furthermore, the characteristics of immune cell infiltration in osteosarcoma, and the correlations between these potential genes and immune cell abundance were illustrated using CIBERSORT. qRT-PCR and western blots were conducted to validate the expression of diagnostic candidates. Results: GEO datasets were divided into the training (merged GSE19276, GSE36001) and test (GSE126209) groups. A total of 71 DEGs were screened out in the training set, including 10 upregulated genes and 61 downregulated genes. These DEGs were primarily enriched in immune-related biological functions and signaling pathways. After machine learning by SVM-RFE and LASSO regression model, four biomarkers were chosen for the diagnostic nomogram for osteosarcoma, including ASNS, CD70, SRGN, and TRIB3. These diagnostic biomarkers all possessed high diagnostic values (AUC ranging from 0.900 to 0.955). Furthermore, these genes were significantly correlated with the infiltration of several immune cells, such as monocytes, macrophages M0, and neutrophils. Conclusion: Four immune-related candidate hub genes (ASNS, CD70, SRGN, TRIB3) with high diagnostic value were confirmed for osteosarcoma patients. These diagnostic genes were significantly connected with the immune cell abundance, suggesting their critical roles in the osteosarcoma tumor immune microenvironment. Our study provides highlights on novel diagnostic candidate genes with high accuracy for diagnosing osteosarcoma patients.

Construction of a Matrix Cancer-Associated Fibroblast Signature Gene-Based Risk Prognostic Signature for Directing Immunotherapy in Patients with Breast Cancer Using Single-Cell Analysis and Machine Learning

Cancer-associated fibroblasts (CAFs) are heterogeneous constituents of the tumor microenvironment involved in the tumorigenesis, progression, and therapeutic responses of tumors. This study identified four distinct CAF subtypes of breast cancer (BRCA) using single-cell RNA sequencing (RNA-seq) data. Of these, matrix CAFs (mCAFs) were significantly associated with tumor matrix remodeling and strongly correlated with the transforming growth factor (TGF)-β signaling pathway. Consensus clustering of The Cancer Genome Atlas (TCGA) BRCA dataset using mCAF single-cell characteristic gene signatures segregated samples into high-fibrotic and low-fibrotic groups. Patients in the high-fibrotic group exhibited a significantly poor prognosis. A weighted gene co-expression network analysis and univariate Cox analysis of bulk RNA-seq data revealed 17 differential genes with prognostic values. The mCAF risk prognosis signature (mRPS) was developed using 10 machine learning algorithms. The clinical outcome predictive accuracy of the mRPS was higher than that of the conventional TNM staging system. mRPS was correlated with the infiltration level of anti-tumor effector immune cells. Based on consensus prognostic genes, BRCA samples were classified into the following two subtypes using six machine learning algorithms (accuracy > 90%): interferon (IFN)-γ-dominant (immune C2) and TGF-β-dominant (immune C6) subtypes. Patients with mRPS downregulation were associated with improved prognosis, suggesting that they can potentially benefit from immunotherapy. Thus, the mRPS model can stably predict BRCA prognosis, reflect the local immune status of the tumor, and aid clinical decisions on tumor immunotherapy.

Prognostic significance and mechanisms of CXCL genes in clear cell renal cell carcinoma

This study aimed to investigate the clinical significance, biological functions, and underlying mechanisms of CXCL genes in clear cell renal cell carcinoma (ccRcc) based on patient datasets and pan-cancer analysis. The interaction between CXCL genes in ccRcc and immune components, particularly in relation to neutrophil recruitment and polarization mechanisms, was also evaluated. Furthermore, a risk score was developed using a signature for neutrophil polarization. The role of CXCL2 was assessed through in vitro experiments. Results showed that five CXCL genes (CXCL 2, 5, 9, 10, and 11) were upregulated in renal cancer tissue, while seven genes (CXCL 1, 2, 3, 5, 8, 13, and 14) significantly impacted patient survival. Moreover, CXCL 1, 5, and 13 affected progression-free survival. Besides, differences in mRNA expression and immune components affected renal cancer outcomes. Furthermore, three pairs of CXCL gene-immune cell interactions (CXCL13-CD8+ T cells, CXCL9/10-M1 cells, CXCL1/2/3/8-neutrophils) were identified through single-cell and pan-cancer analysis. A TAN risk score with prognostic value for KIRC patients was constructed using 11 genes and a TAN signature. Neutrophil polarization significantly impacted survival. Notably, CXCL2 was involved in neutrophil recruitment and polarization, thus promoting ccRcc progression. In conclusion, seven prognostic CXCL genes (CXCL 1/2/3/5/8/13/14) for ccRcc patients and three pairs of CXCL gene-immune cell interactions were identified. Furthermore, results showed that CXCL 2 promotes ccRcc progression through neutrophil recruitment and polarization.

Nonsentinel Axillary Lymph Node Status in Clinically Node-Negative Early Breast Cancer After Primary Systemic Therapy and Positive Sentinel Lymph Node: A Predictive Model Proposal

BACKGROUND

In clinically node-negative (cN0) early stage breast cancer (EBC) undergoing primary systemic treatment (PST), post-treatment positive sentinel lymph node (SLN+) directs axillary lymph node dissection (ALND), with uncertain impacts on outcomes and increased morbidities.

PATIENTS AND METHODS

We conducted an observational study on imaging-confirmed cN0 EBC, who underwent PST and breast surgery that resulted in SLN+ and underwent ALND. The association among baseline/postsurgical clinic-pathological factors and positive nonsentinel additional axillary lymph nodes (non-SLN+) was analyzed with logistic regression. LASSO regression (LR) identified variables to include in a predictive score of non-SLN+ (ALND-predict). The accuracy and calibration were assessed, an optimal cut-point was then identified, and in silico validation with bootstrap was undertaken.

RESULTS

Non-SLN+ were detected in 22.2% cases after ALND. Only progesterone receptor (PR) levels and macrometastatic SLN+ were independently associated to non-SLN+. LR identified PR, Ki67, and type and number of SLN+ as the most efficient covariates. The ALND-predict score was built based on their LR coefficients, showing an area under the curve (AUC) of 0.83 and an optimal cut-off of 63, with a negative predictive value (NPV) of 0.925. Continuous and dichotomic scores had a good fit (p = 0.876 and p = 1.00, respectively) and were independently associated to non-SLN+ [adjusted odds ratio (aOR): 1.06, p = 0.002 and aOR: 23.77, p < 0.001, respectively]. After 5000 bootstrap-adjusted retesting, the estimated bias-corrected and accelerated 95%CI included the aOR.

CONCLUSIONS

In cN0 EBC with post-PST SLN+, non-SLN+ at ALND are infrequent (~22%) and independently associated to PR levels and macrometastatic SLN. ALND-predict multiparametric score accurately predicted absence of non-SLN involvement, identifying most patients who could be safely spared unnecessary ALND. Prospective validation is required.

Integrative analysis illustrates the role of PCDH7 in lung cancer development, cisplatin resistance, and immunotherapy resistance: an underlying target

Background: Cisplatin resistance is a common clinical problem in lung cancer. However, the underlying mechanisms have not yet been fully elucidated, highlighting the importance of searching for biological targets. Methods: Bioinformatics analysis is completed through downloaded public data (GSE21656, GSE108214, and TCGA) and specific R packages. The evaluation of cell proliferation ability is completed through CCK8 assay, colony formation, and EdU assay. The evaluation of cell invasion and migration ability is completed through transwell and wound-healing assays. In addition, we evaluated cell cisplatin sensitivity by calculating IC50. Results: Here, we found that PCDH7 may be involved in cisplatin resistance in lung cancer through public database analysis (GSE21656 and GSE108214). Then, a series of in vitro experiments was performed, which verified the cancer-promoting role of PCDH7 in NSCLC. Moreover, the results of IC50 detection showed that PCDH7 might be associated with cisplatin resistance of NSCLC. Next, we investigated the single-cell pattern, biological function, and immune analysis of PCDH7. Importantly, we noticed PCDH7 may regulate epithelial-mesenchymal transition activity, and the local infiltration of CD8+ T and activated NK cells. Furthermore, we noticed that patients with high PCDH7 expression might be more sensitive to bortezomib, docetaxel, and gemcitabine, and resistant to immunotherapy. Finally, a prognosis model based on three PCDH7-derived genes (GPX8, BCAR3, and TNS4) was constructed through a machine learning algorithm, which has good prediction ability on NSCLC patients' survival. Conclusion: Our research has improved the regulatory framework for cisplatin resistance in NSCLC and can provide direction for subsequent related research, especially regarding PCDH7.

Prognostic nutritional index combined with carcinoembryonic antigen and carbohydrate antigen 242 for early prediction of anastomotic leakage after radical gastrectomy for gastric cancer

OBJECTIVE

To observe the clinical value of prognostic nutritional index (PNI) combined with carcinoembryonic antigen (CEA) and carbohydrate antigen (CA) 242 in early prediction of anastomotic leakage after radical gastrectomy for gastric cancer.

METHODS

We retrospectively collected clinical data of 350 gastric cancer patients who underwent radical gastrectomy in Gansu Provincial Hospital of Traditional Chinese Medicine between January 2018 and May 2022. According to the occurrence of anastomotic leakage, patients were divided into an occurrence group (n=34) and a non-occurrence group (n=316). The clinical value of PNI combined with CEA and CA242 on the 3rd day after surgery in predicting anastomotic leakage was explored. Lasso regression analysis was used to screen predictive indicators of anastomotic leakage and establish a risk model.

RESULTS

In the 350 patients who underwent radical gastrectomy for gastric cancer, anastomotic leakage was observed in 34 cases, with an incidence rate of 9.7%. A higher proportion of patients in the occurrence group exhibited diabetes, hand-sewn anastomosis, advanced tumor node metastasis (TNM) staging, and intraoperative bleeding, when compared to those in the non-occurrence group (P<0.05). Moreover, on the 3rd postoperative day, patients in the occurrence group demonstrated a significantly lower PNI than those in the non-occurrence group, along with elevated levels of CEA and CA242 (P<0.05). The area under the curve (AUC) for PNI, CEA, and CA242 were 0.827, 0.601, and 0.504, respectively, while the AUC for the combination was 0.829. As per the LASSO regression analysis, history of diabetes and PNI were identified as key factors correlating with anastomotic leakage (P<0.05). Employing the risk score formula, we obtained individual risk scores for each sample. Notably, risk scores in the occurrence group significantly surpassed those in the non-occurrence group (P<0.0001). The AUC for the risk score in predicting patient lung infection was 0.854. The internal verification C-index emerged as 0.863 (0.806-0.920), indicating a good model fit. Furthermore, the DeLong test revealed a significantly greater AUC of the risk model, compared to the combination and PNI (P<0.05).

CONCLUSION

CEA and CA242 are not promising predictive indicators for anastomotic leakage after surgery in patients with gastric cancer, but the prediction model we established can improve the predictive efficiency of anastomotic leakage in these patients.

Establishment of a prognostic risk prediction modelfor non-small cell lung cancer patients with brainmetastases: a retrospective study

Background

Patients with non-small cell lung cancer (NSCLC) who develop brain metastases (BM) have a poor prognosis. This study aimed to construct a clinical prediction model to determine the overall survival (OS) of NSCLC patients with BM.

Methods

A total of 300 NSCLC patients with BM at the Yunnan Cancer Centre were retrospectively analysed. The prediction model was constructed using the least absolute shrinkage and selection operator-Cox regression. The bootstrap sampling method was employed for internal validation. The performance of our prediction model was compared using recursive partitioning analysis (RPA), graded prognostic assessment (GPA), the update of the graded prognostic assessment for lung cancer using molecular markers (Lung-molGPA), the basic score for BM (BSBM), and tumour-lymph node-metastasis (TNM) staging.

Results

The prediction models comprising 15 predictors were constructed. The area under the curve (AUC) values for the 1-year, 3-year, and 5-year time-dependent receiver operating characteristic (curves) were 0.746 (0.678-0.814), 0.819 (0.761-0.877), and 0.865 (0.774-0.957), respectively. The bootstrap-corrected AUC values and Brier scores for the prediction model were 0.811 (0.638-0.950) and 0.123 (0.066-0.188), respectively. The time-dependent C-index indicated that our model exhibited significantly greater discrimination compared with RPA, GPA, Lung-molGPA, BSBM, and TNM staging. Similarly, the decision curve analysis demonstrated that our model displayed the widest range of thresholds and yielded the highest net benefit. Furthermore, the net reclassification improvement and integrated discrimination improvement analyses confirmed the enhanced predictive power of our prediction model. Finally, the risk subgroups identified by our prognostic model exhibited superior differentiation of patients' OS.

Conclusion

The clinical prediction model constructed by us shows promise in predicting OS for NSCLC patients with BM. Its predictability is superior compared with RPA, GPA, Lung-molGPA, BSBM, and TNM staging.

Prediction of Diabetic Kidney Disease in Newly Diagnosed Type 2 Diabetes Mellitus

Background

Diabetic kidney disease (DKD), a common microvascular complication of diabetes mellitus (DM), is always asymptomatic until it develops to the advanced stage. Thus, we aim to develop a nomogram prediction model for progression to DKD in newly diagnosed type 2 diabetes mellitus (T2DM).

Methods

This was a single-center analysis of prospective data collected from 521 newly diagnosed patients with T2DM. All related clinical records were incorporated, including the triglyceride-glucose index (TyG index). The least absolute shrinkage and selection operator (LASSO) was used to build a prediction model. In addition, discrimination, calibration, and clinical practicality of the nomogram were evaluated.

Results

In this study, 156 participants were incorporated as the validation set, while the remaining 365 were incorporated into the training set. The predictive factors included in the individualized nomogram prediction model included 5 variables. The area under the curve (AUC) for the prediction model was 0.826 (95% CI 0.775 to 0.876), indicating excellent discrimination performance. The model performed exceptionally well in terms of predictive accuracy and clinical applicability, according to calibration curves and decision curve analysis.

Conclusion

The predictive nomogram for the risk of DKD in newly diagnosed T2DM patients had outstanding discrimination and calibration, which could help in clinical practice.

Identification of Novel Diagnostic and Prognostic Gene Signature Biomarkers for Breast Cancer Using Artificial Intelligence and Machine Learning Assisted Transcriptomics Analysis

BACKGROUND

Breast cancer (BC) is one of the most common female cancers. Clinical and histopathological information is collectively used for diagnosis, but is often not precise. We applied machine learning (ML) methods to identify the valuable gene signature model based on differentially expressed genes (DEGs) for BC diagnosis and prognosis.

METHODS

A cohort of 701 samples from 11 GEO BC microarray datasets was used for the identification of significant DEGs. Seven ML methods, including RFECV-LR, RFECV-SVM, LR-L1, SVC-L1, RF, and Extra-Trees were applied for gene reduction and the construction of a diagnostic model for cancer classification. Kaplan-Meier survival analysis was performed for prognostic signature construction. The potential biomarkers were confirmed via qRT-PCR and validated by another set of ML methods including GBDT, XGBoost, AdaBoost, KNN, and MLP.

RESULTS

We identified 355 DEGs and predicted BC-associated pathways, including kinetochore metaphase signaling, PTEN, senescence, and phagosome-formation pathways. A hub of 28 DEGs and a novel diagnostic nine-gene signature (COL10A, S100P, ADAMTS5, WISP1, COMP, CXCL10, LYVE1, COL11A1, and INHBA) were identified using stringent filter conditions. Similarly, a novel prognostic model consisting of eight-gene signatures (CCNE2, NUSAP1, TPX2, S100P, ITM2A, LIFR, TNXA, and ZBTB16) was also identified using disease-free survival and overall survival analysis. Gene signatures were validated by another set of ML methods. Finally, qRT-PCR results confirmed the expression of the identified gene signatures in BC.

CONCLUSION

The ML approach helped construct novel diagnostic and prognostic models based on the expression profiling of BC. The identified nine-gene signature and eight-gene signatures showed excellent potential in BC diagnosis and prognosis, respectively.

CT-based radiomics models may predict the early efficacy of microwave ablation in malignant lung tumors

PURPOSE

To establish and validate radiomics models for predicting the early efficacy (less than 3 months) of microwave ablation (MWA) in malignant lung tumors.

METHODS

The study enrolled 130 malignant lung tumor patients (72 in the training cohort, 32 in the testing cohort, and 26 in the validation cohort) treated with MWA. Post-operation CT images were analyzed. To evaluate the therapeutic effect of ablation, three models were constructed by least absolute shrinkage and selection operator and logistic regression: the tumoral radiomics (T-RO), peritumoral radiomics (P-RO), and tumoral-peritumoral radiomics (TP-RO) models. Univariate and multivariate analyses were performed to identify clinical variables and radiomics features associated with early efficacy, which were incorporated into the combined radiomics (C-RO) model. The performance of the C-RO model was evaluated by the area under the receiver operating characteristic (ROC) curve (AUC), calibration curve, and decision curve analysis (DCA). The C-RO model was used to derive the best cutoff value of ROC and to distinguish the high-risk group (Nomo-score of C-RO model below than cutoff value) from the low-risk group (Nomo-score of C-RO model higher than cutoff value) for survival analysis of patients.

RESULTS

Four radiomics features were selected from the region of interest of tumoral and peritumoral CT images, which showed good performance for evaluating prognosis and early efficacy in three cohorts. The C-RO model had the highest AUC value in all models, and the C-RO model was better than the P-RO model (AUC in training, 0.896 vs. 0.740; p = 0.036). The DCA confirmed the clinical benefit of the C-RO model. Survival analysis revealed that in the C-RO model, the low-risk group defined by best cutoff value had significantly better progression-free survival than the high-risk group (p<0.05).

CONCLUSIONS

CT-based radiomics models in malignant lung tumor patients after MWA could be useful for individualized risk classification and treatment.