Development and validation of a nomogram predictive model for cognitive impairment in cerebral small vessel disease: a comprehensive retrospective analysis.

Background: Cerebral small vessel disease (CSVD) is a common neurodegenerative condition in the elderly, closely associated with cognitive impairment. Early identification of individuals with CSVD who are at a higher risk of developing cognitive impairment is crucial for timely intervention and improving patient outcomes. Objective: The aim of this study is to construct a predictive model utilizing LASSO regression and binary logistic regression, with the objective of precisely forecasting the risk of cognitive impairment in patients with CSVD. Methods: The study utilized LASSO regression for feature selection and logistic regression for model construction in a cohort of CSVD patients. The model's validity was assessed through calibration curves and decision curve analysis (DCA). Results: A nomogram was developed to predict cognitive impairment, incorporating hypertension, CSVD burden, apolipoprotein A1 (ApoA1) levels, and age. The model exhibited high accuracy with AUC values of 0.866 and 0.852 for the training and validation sets, respectively. Calibration curves confirmed the model's reliability, and DCA highlighted its clinical utility. The model's sensitivity and specificity were 75.3 and 79.7% for the training set, and 76.9 and 74.0% for the validation set. Conclusion: This study successfully demonstrates the application of machine learning in developing a reliable predictive model for cognitive impairment in CSVD. The model's high accuracy and robust predictive capability provide a crucial tool for the early detection and intervention of cognitive impairment in patients with CSVD, potentially improving outcomes for this specific condition.

LASSO-Based Machine Learning Algorithm for Prediction of PICS Associated with Sepsis.

Introduction: This study aims to establish a comprehensive, multi-level approach for tackling tropical diseases by proactively anticipating and managing Persistent Inflammation, Immunosuppression, and Catabolism Syndrome (PICS) within the initial 14 days of Intensive Care Unit (ICU) admission. The primary objective is to amalgamate a diverse array of indicators and pathogenic microbial data to pinpoint pivotal predictive variables, enabling effective intervention specifically tailored to the context of tropical diseases. Methods: A focused analysis was conducted on 1733 patients admitted to the ICU between December 2016 and July 2019. Utilizing the Least Absolute Shrinkage and Selection Operator (LASSO) regression, disease severity and laboratory indices were scrutinized. The identified variables served as the foundation for constructing a predictive model designed to forecast the occurrence of PICS. Results: Among the subjects, 13.79% met the diagnostic criteria for PICS, correlating with a mortality rate of 38.08%. Key variables, including red-cell distribution width coefficient of variation (RDW-CV), hemofiltration (HF), mechanical ventilation (MV), Norepinephrine (NE), lactic acidosis, and multiple-drug resistant bacteria (MDR) infection, were identified through LASSO regression. The resulting predictive model exhibited a robust performance with an Area Under the Curve (AUC) of 0.828, an accuracy of 0.862, and a specificity of 0.977. Subsequent validation in an independent cohort yielded an AUC of 0.848. Discussion: The acquisition of RDW-CV, HF requirement, MV requirement, NE requirement, lactic acidosis, and MDR upon ICU admission emerges as a pivotal factor for prognosticating PICS onset in the context of tropical diseases. This study highlights the potential for significant improvements in clinical outcomes through the implementation of timely and targeted interventions tailored specifically to the challenges posed by tropical diseases.

Population-Specific gene expression profiles in prostate cancer: insights from Weighted Gene Co-expression Network Analysis (WGCNA).

This study investigates the genetic factors contributing to the disparity in prostate cancer incidence and progression among African American men (AAM) compared to European American men (EAM). The research focuses on employing Weighted Gene Co-expression Network Analysis (WGCNA) on public microarray data obtained from prostate cancer patients. The study employed WGCNA to identify clusters of genes with correlated expression patterns, which were then analyzed for their connection to population backgrounds. Additionally, pathway enrichment analysis was conducted to understand the significance of the identified gene modules in prostate cancer pathways. The Least Absolute Shrinkage and Selection Operator (LASSO) and Correlation-based Feature Selection (CFS) methods were utilized for selection of biomarker genes. The results revealed 353 differentially expressed genes (DEGs) between AAM and EAM. Six significant gene expression modules were identified through WGCNA, showing varying degrees of correlation with prostate cancer. LASSO and CFS methods pinpointed critical genes, as well as six common genes between both approaches, which are indicative of their vital role in the disease. The XGBoost classifier validated these findings, achieving satisfactory prediction accuracy. Genes such as APRT, CCL2, BEX2, MGC26963, and PLAU were identified as key genes significantly associated with cancer progression. In conclusion, the research underlines the importance of incorporating AAM and EAM population diversity in genomic studies, particularly in cancer research. In addition, the study highlights the effectiveness of integrating machine learning techniques with gene expression analysis as a robust methodology for identifying critical genes in cancer research.

Estimating risk of loneliness in adulthood using survey-based prediction models: A cohort study.

It is widely accepted that loneliness is associated with health problems, but less is known about the predictors of loneliness. In this study, we constructed a model to predict individual risk of loneliness during adulthood. Data were from the prospective population-based FinHealth cohort study with 3444 participants (mean age 55.5 years, 53.4% women) who responded to a 81-item self-administered questionnaire and reported not to be lonely at baseline in 2017. The outcome was self-reported loneliness at follow-up in 2020. Predictive models were constructed using bootstrap enhanced LASSO regression (bolasso). The C-index from the final model including 11 predictors from the best bolasso -models varied between 0.65 (95% CI 0.61 to 0.70) and 0.71 (95% CI 0.67 to 0.75) the pooled C -index being 0.68 (95% CI 0.61 to 0.75). Although survey-based individualised prediction models for loneliness achieved a reasonable C-index, their predictive value was limited. High detection rates were associated with high false positive rates, while lower false positive rates were associated with low detection rates. These findings suggest that incident loneliness during adulthood. may be difficult to predict with standard survey data.

SpliceAPP: an interactive web server to predict splicing errors arising from human mutations.

BACKGROUND: Splicing variants are a major class of pathogenic mutations, with their severity equivalent to nonsense mutations. However, redundant and degenerate splicing signals hinder functional assessments of sequence variations within introns, particularly at branch sites. We have established a massively parallel splicing assay to assess the impact on splicing of 11,191 disease-relevant variants. Based on the experimental results, we then applied regression-based methods to identify factors determining splicing decisions and their respective weights. RESULTS: Our statistical modeling is highly sensitive, accurately annotating the splicing defects of near-exon intronic variants, outperforming state-of-the-art predictive tools. We have incorporated the algorithm and branchpoint information into a web-based tool, SpliceAPP, to provide an interactive application. This user-friendly website allows users to upload any genetic variants with genome coordinates (e.g., chr15 74,687,208 A G), and the tool will output predictions for splicing error scores and evaluate the impact on nearby splice sites. Additionally, users can query branch site information within the region of interest. CONCLUSIONS: In summary, SpliceAPP represents a pioneering approach to screening pathogenic intronic variants, contributing to the development of precision medicine. It also facilitates the annotation of splicing motifs. SpliceAPP is freely accessible using the link https://bc.imb.sinica.edu.tw/SpliceAPP . Source code can be downloaded at https://github.com/hsinnan75/SpliceAPP .

Intestinal mRNA expression profiles associated with mucosal healing in ustekinumab-treated Crohn's disease patients: bioinformatics analysis and prospective cohort validation.

BACKGROUND: Variations exist in the response of patients with Crohn's disease (CD) to ustekinumab (UST) treatment, but the underlying cause remains unknown. Our objective was to investigate the involvement of immune cells and identify potential biomarkers that could predict the response to interleukin (IL) 12/23 inhibitors in patients with CD. METHODS: The GSE207022 dataset, which consisted of 54 non-responders and 9 responders to UST in a CD cohort, was analyzed. Differentially expressed genes (DEGs) were identified and subjected to Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analyses. Least absolute shrinkage and selection operator (LASSO) regression was used to screen the most powerful hub genes. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the predictive performances of these genes. Single-sample Gene Set Enrichment Analysis (ssGSEA) was used to estimate the proportions of immune cell types. These significantly altered genes were subjected to cluster analysis into immune cell-related infiltration. To validate the reliability of the candidates, patients prescribed UST as a first-line biologic in a prospective cohort were included as an independent validation dataset. RESULTS: A total of 99 DEGs were identified in the integrated dataset. GO and KEGG analyses revealed significant enrichment of immune response pathways in patients with CD. Thirteen genes (SOCS3, CD55, KDM5D, IGFBP5, LCN2, SLC15A1, XPNPEP2, HLA-DQA2, HMGCS2, DDX3Y, ITGB2, CDKN2B and HLA-DQA1), which were primarily associated with the response versus nonresponse patients, were identified and included in the LASSO analysis. These genes accurately predicted treatment response, with an area under the curve (AUC) of 0.938. T helper cell type 1 (Th1) cell polarization was comparatively strong in nonresponse individuals. Positive connections were observed between Th1 cells and the LCN2 and KDM5D genes. Furthermore, we employed an independent validation dataset and early experimental verification to validate the LCN2 and KDM5D genes as effective predictive markers. CONCLUSIONS: Th1 cell polarization is an important cause of nonresponse to UST therapy in patients with CD. LCN2 and KDM5D can be used as predictive markers to effectively identify nonresponse patients. TRIAL REGISTRATION: Trial registration number: NCT05542459; Date of registration: 2022-09-14; URL: https://www. CLINICALTRIALS: gov .

A novel nomogram to predict the recurrence of hepatocellular carcinoma after liver transplantation using extended selection criteria.

BACKGROUND: Liver transplantations (LTs) with extended criteria have produced surgical results comparable to those obtained with traditional standards. However, it is not sufficient to predict hepatocellular carcinoma (HCC) recurrence after LT according to morphological criteria alone. The present study aimed to construct a nomogram for predicting HCC recurrence after LT using extended selection criteria. METHODS: Retrospective data on patients with HCC, including pathology, serological markers and follow-up data, were collected from January 2015 to April 2020 at Huashan Hospital, Fudan University, Shanghai, China. Logistic least absolute shrinkage and selection operator (LASSO) regression and multivariate Cox regression analyses were performed to identify and construct the prognostic nomogram. Receiver operating characteristic (ROC) curves, Kaplan-Meier curves, decision curve analyses (DCAs), calibration diagrams, net reclassification indices (NRIs) and integrated discrimination improvement (IDI) values were used to assess the prognostic capacity of the nomogram. RESULTS: A total of 301 patients with HCC who underwent LT were enrolled in the study. The nomogram was constructed, and the ROC curve showed good performance in predicting survival in both the development set (2/3) and the validation set (1/3) (the area under the curve reached 0.748 and 0.716, respectively). According to the median value of the risk score, the patients were categorized into the high- and low-risk groups, which had significantly different recurrence-free survival (RFS) rates (P < 0.01). Compared with the Milan criteria and University of California San Francisco (UCSF) criteria, DCA revealed that the new nomogram model had the best net benefit in predicting 1-, 3- and 5-year RFS. The nomogram performed well for calibration, NRI and IDI improvement. CONCLUSIONS: The nomogram, based on the Milan criteria and serological markers, showed good accuracy in predicting the recurrence of HCC after LT using extended selection criteria.

Development and validation of a LASSO prediction model for cisplatin induced nephrotoxicity: a case-control study in China.

BACKGROUND: Early identification of high-risk individuals with cisplatin-induced nephrotoxicity (CIN) is crucial for avoiding CIN and improving prognosis. In this study, we developed and validated a CIN prediction model based on general clinical data, laboratory indications, and genetic features of lung cancer patients before chemotherapy. METHODS: We retrospectively included 696 lung cancer patients using platinum chemotherapy regimens from June 2019 to June 2021 as the traing set to construct a predictive model using Absolute shrinkage and selection operator (LASSO) regression, cross validation, and Akaike's information criterion (AIC) to select important variables. We prospectively selected 283 independent lung cancer patients from July 2021 to December 2022 as the test set to evaluate the model's performance. RESULTS: The prediction model showed good discrimination and calibration, with AUCs of 0.9217 and 0.8288, sensitivity of 79.89% and 45.07%, specificity of 94.48% and 94.81%, in the training and test sets respectively. Clinical decision curve analysis suggested that the model has value for clinical use when the risk threshold ranges between 0.1 and 0.9. Precision-Recall (PR) curve shown in recall interval from 0.5 to 0.75: precision gradually declines with increasing Recall, up to 0.9. CONCLUSIONS: Predictive models based on laboratory and demographic variables can serve as a beneficial complementary tool for identifying high-risk populations with CIN.

Construction and validation of a clinical risk model based on machine learning for screening characteristic factors of lymphovascular space invasion in endometrial cancer.

This study aimed to identify factors that affect lymphovascular space invasion (LVSI) in endometrial cancer (EC) using machine learning technology, and to build a clinical risk assessment model based on these factors. Samples were collected from May 2017 to March 2022, including 312 EC patients who received treatment at Xuzhou Medical University Affiliated Hospital of Lianyungang. Of these, 219 cases were collected for the training group and 93 for the validation group. Clinical data and laboratory indicators were analyzed. Logistic regression and least absolute shrinkage and selection operator (LASSO) regression were used to analyze risk factors and construct risk models. The LVSI and non-LVSI groups showed statistical significance in clinical data and laboratory indicators (P < 0.05). Multivariable logistic regression analysis identified independent risk factors for LVSI in EC, which were myometrial infiltration depth, cervical stromal invasion, lymphocyte count (LYM), monocyte count (MONO), albumin (ALB), and fibrinogen (FIB) (P < 0.05). LASSO regression identified 19 key feature factors for model construction. In the training and validation groups, the risk scores for the logistic and LASSO models were significantly higher in the LVSI group compared with that in the non-LVSI group (P < 0.001). The model was built based on machine learning and can effectively predict LVSI in EC and enhance preoperative decision-making. The reliability of the model was demonstrated by the significant difference in risk scores between LVSI and non-LVSI patients in both the training and validation groups.

Elucidating the multifaceted roles of GPR146 in non-specific orbital inflammation: a concerted analytical approach through the prisms of bioinformatics and machine learning.

Background: Non-specific Orbital Inflammation (NSOI) is a chronic idiopathic condition marked by extensive polymorphic lymphoid infiltration in the orbital area. The integration of metabolic and immune pathways suggests potential therapeutic roles for C-peptide and G protein-coupled receptor 146 (GPR146) in diabetes and its sequelae. However, the specific mechanisms through which GPR146 modulates immune responses remain poorly understood. Furthermore, the utility of GPR146 as a diagnostic or prognostic marker for NSOI has not been conclusively demonstrated. Methods: We adopted a comprehensive analytical strategy, merging differentially expressed genes (DEGs) from the Gene Expression Omnibus (GEO) datasets GSE58331 and GSE105149 with immune-related genes from the ImmPort database. Our methodology combined LASSO regression and support vector machine-recursive feature elimination (SVM-RFE) for feature selection, followed by Gene Set Enrichment Analysis (GSEA) and Gene Set Variation Analysis (GSVA) to explore gene sets co-expressed with GPR146, identifying a significant enrichment in immune-related pathways. The tumor microenvironment's immune composition was quantified using the CIBERSORT algorithm and the ESTIMATE method, which confirmed a positive correlation between GPR146 expression and immune cell infiltration. Validation of GPR146 expression was performed using the GSE58331 dataset. Results: Analysis identified 113 DEGs associated with GPR146, with a significant subset showing distinct expression patterns. Using LASSO and SVM-RFE, we pinpointed 15 key hub genes. Functionally, these genes and GPR146 were predominantly linked to receptor ligand activity, immune receptor activity, and cytokine-mediated signaling. Specific immune cells, such as memory B cells, M2 macrophages, resting mast cells, monocytes, activated NK cells, plasma cells, and CD8+ T cells, were positively associated with GPR146 expression. In contrast, M0 macrophages, naive B cells, M1 macrophages, activated mast cells, activated memory CD4+ T cells, naive CD4+ T cells, and gamma delta T cells showed inverse correlations. Notably, our findings underscore the potential diagnostic relevance of GPR146 in distinguishing NSOI. Conclusion: Our study elucidates the immunological signatures associated with GPR146 in the context of NSOI, highlighting its prognostic and diagnostic potential. These insights pave the way for GPR146 to be a novel biomarker for monitoring the progression of NSOI, providing a foundation for future therapeutic strategies targeting immune-metabolic pathways.

The roles of IRF8 in nonspecific orbital inflammation: an integrated analysis by bioinformatics and machine learning.

BACKGROUND: Nonspecific Orbital Inflammation (NSOI) represents a persistent and idiopathic proliferative inflammatory disorder, characterized by polymorphous lymphoid infiltration within the orbit. The transcription factor Interferon Regulatory Factor 8 (IRF8), integral to the IRF protein family, was initially identified as a pivotal element for the commitment and differentiation of myeloid cell lineage. Serving as a central regulator of innate immune receptor signaling, IRF8 orchestrates a myriad of functions in hematopoietic cell development. However, the intricate mechanisms underlying IRF8 production remain to be elucidated, and its potential role as a biomarker for NSOI is yet to be resolved. METHODS: IRF8 was extracted from the intersection analysis of common DEGs of GSE58331 and GSE105149 from the GEO and immune- related gene lists in the ImmPort database using The Lasso regression and SVM-RFE analysis. We performed GSEA and GSVA with gene sets coexpressed with IRF8, and observed that gene sets positively related to IRF8 were enriched in immune-related pathways. To further explore the correlation between IRF8 and immune-related biological process, the CIBERSORT algorithm and ESTIMATE method were employed to evaluate TME characteristics of each sample and confirmed that high IRF8 expression might give rise to high immune cell infiltration. Finally, the GSE58331 was utilized to confirm the levels of expression of IRF8. RESULTS: Among the 314 differentially expressed genes (DEGs), some DEGs were found to be significantly different. With LASSO and SVM-RFE algorithms, we obtained 15 hub genes. For biological function analysis in IRF8, leukocyte mediated immunity, leukocyte cell-cell adhesion, negative regulation of immune system process were emphasized. B cells naive, Macrophages M0, Macrophages M1, T cells CD4 memory activated, T cells CD4 memory resting, T cells CD4 naive, and T cells gamma delta were shown to be positively associated with IRF8. While, Mast cells resting, Monocytes, NK cells activated, Plasma cells, T cells CD8, and T cells regulatory (Tregs) were shown to be negatively linked with IRF8. The diagnostic ability of the IRF8 in differentiating NSOI exhibited a good value. CONCLUSIONS: This study discovered IRF8 that are linked to NSOI. IRF8 shed light on potential new biomarkers for NSOI and tracking its progression.

Unraveling the Predictors of Enlarged Perivascular Spaces: A Comprehensive Logistic Regression Approach in Cerebral Small Vessel Disease.

Background: This study addresses the predictive modeling of Enlarged Perivascular Spaces (EPVS) in neuroradiology and neurology, focusing on their impact on Cerebral Small Vessel Disease (CSVD) and neurodegenerative disorders. Methods: A retrospective analysis was conducted on 587 neurology inpatients, utilizing LASSO regression for variable selection and logistic regression for model development. The study included comprehensive demographic, medical history, and laboratory data analyses. Results: The model identified key predictors of EPVS, including Age, Hypertension, Stroke, Lipoprotein a, Platelet Large Cell Ratio, Uric Acid, and Albumin to Globulin Ratio. The predictive nomogram demonstrated strong efficacy in EPVS risk assessment, validated through ROC curve analysis, calibration plots, and Decision Curve Analysis. Conclusion: The study presents a novel, robust EPVS predictive model, providing deeper insights into EPVS mechanisms and risk factors. It underscores the potential for early diagnosis and improved management strategies in neuro-radiology and neurology, highlighting the need for future research in diverse populations and longitudinal settings.

Predicting ineffective thrombolysis in acute ischemic stroke with clinical and biochemical markers.

**Ischemic stroke remains a leading cause of morbidity and mortality globally. Despite the advances in thrombolytic therapy, notably recombinant tissue plasminogen activator (rtPA), patient outcomes are highly variable. This study aims to introduce a novel predictive model, the Acute Stroke Thrombolysis Non-Responder Prediction Model (ASTN-RPM), to identify patients unlikely to benefit from rtPA within the critical early recovery window. We conducted a retrospective cohort study at Baoding No.1 Central Hospital including 709 adult patients diagnosed with acute ischemic stroke and treated with intravenous alteplase within the therapeutic time window. The ASTN-RPM was developed using Least Absolute Shrinkage and Selection Operator (LASSO) regression technique, incorporating a wide range of biomarkers and clinical parameters. Model performance was evaluated using Receiver Operating Characteristic (ROC) curves, calibration plots, and Decision Curve Analysis (DCA). ASTN-RPM effectively identified patients at high risk of poor response to thrombolysis, with an AUC of 0.909 in the training set and 0.872 in the validation set, indicating high sensitivity and specificity. Key predictors included posterior circulation stroke, high admission NIHSS scores, extended door to needle time, and certain laboratory parameters like homocysteine levels. The ASTN-RPM stands as a potential tool for refining clinical decision-making in ischemic stroke management. By anticipating thrombolytic non-response, clinicians can personalize treatment strategies, possibly improving patient outcomes and reducing the burden of ineffective interventions. Future studies are needed for external validation and to explore the incorporation of emerging biomarkers and imaging data.

Effects of exposure to multiple metallic elements in the first trimester of pregnancy on the risk of preterm birth.

Exposure to certain heavy metals has been demonstrated to be associated with a higher risk of preterm birth (PTB). However, studies focused on the effects of other metal mixtures were limited. A nested case‒control study enrolling 94 PTB cases and 282 controls was conducted. Metallic elements were detected in maternal plasma collected in the first trimester using inductively coupled plasma‒mass spectrometry. The effect of maternal exposure on the risk of PTB was investigated using logistic regression, least absolute shrinkage and selection operator, restricted cubic spline (RCS), quantile g computation (QGC) and Bayesian kernel machine regression (BKMR). Vanadium (V) and arsenic (As) were positively associated with PTB risk in the logistic model, and V remains positively associated in the multi-exposure logistic model. QGC analysis determined V (69.42%) and nickel (Ni) (70.30%) as the maximum positive and negative contributors to the PTB risk, respectively. BKMR models further demonstrated a positive relationship between the exposure levels of the mixtures and PTB risk, and V was identified as the most important independent variable among the elements. RCS analysis showed an inverted U-shape effect of V and gestational age, and plasma V more than 2.18 µg/L was considered a risk factor for shortened gestation length. Exposure to metallic elements mixtures consisting of V, As, cobalt, Ni, chromium and manganese in the first trimester was associated with an increased risk of PTB, and V was considered the most important factor in the mixtures in promoting the incidence of PTB.

Development and validation of a risk prediction model for physical frailty in older adults who are disabled.

Physical frailty is highly prevalent among the older adults who are disabled. The aim of this study was to explore the risk factors for physical frailty in older adults who are disabled and construct a nomogram prediction model. The data source was the China Health and Retirement Longitudinal Study (CHARLS). The prediction model was validated with a cohort of 1183 older adults who are disabled. The results showed that sleep quality, depression, fatigue, and chronic disease were the best predictive factors. These factors were used to construct the nomogram model, which showed good concordance and accuracy. The prediction model yielded an Area under the curve (AUC) value of 0.760. Calibration curves showed significant agreement between the nomogram model and actual observations. Receiver operating characteristic (ROC) and Decision curve analysis (DCA) showed that the nomogram had good predictive performance. The nomogram is contributed to the screening of specific populations by clinicians.

Lipoproteins and metabolites in diagnosing and predicting Alzheimer's disease using machine learning.

BACKGROUND: Alzheimer's disease (AD) is a chronic neurodegenerative disorder that poses a substantial economic burden. The Random forest algorithm is effective in predicting AD; however, the key factors influencing AD onset remain unclear. This study aimed to analyze the key lipoprotein and metabolite factors influencing AD onset using machine-learning methods. It provides new insights for researchers and medical personnel to understand AD and provides a reference for the early diagnosis, treatment, and early prevention of AD. METHODS: A total of 603 participants, including controls and patients with AD with complete lipoprotein and metabolite data from the Alzheimer's disease Neuroimaging Initiative (ADNI) database between 2005 and 2016, were enrolled. Random forest, Lasso regression, and CatBoost algorithms were employed to rank and filter 213 lipoprotein and metabolite variables. Variables with consistently high importance rankings from any two methods were incorporated into the models. Finally, the variables selected from the three methods, with the participants' age, sex, and marital status, were used to construct a random forest predictive model. RESULTS: Fourteen lipoprotein and metabolite variables were screened using the three methods, and 17 variables were included in the AD prediction model based on age, sex, and marital status of the participants. The optimal random forest modeling was constructed with "mtry" set to 3 and "ntree" set to 300. The model exhibited an accuracy of 71.01%, a sensitivity of 79.59%, a specificity of 65.28%, and an AUC (95%CI) of 0.724 (0.645-0.804). When Mean Decrease Accuracy and Gini were used to rank the proteins, age, phospholipids to total lipids ratio in intermediate-density lipoproteins (IDL_PL_PCT), and creatinine were among the top five variables. CONCLUSIONS: Age, IDL_PL_PCT, and creatinine levels play crucial roles in AD onset. Regular monitoring of lipoproteins and their metabolites in older individuals is significant for early AD diagnosis and prevention.

Nomogram for predicting post-therapy recurrence in BCLC A/B hepatocellular carcinoma with Child-Pugh B cirrhosis.

Introduction: This study conducts a retrospective analysis on patients with BCLC stage A/B hepatocellular carcinoma (HCC) accompanied by Child-Pugh B cirrhosis, who underwent transarterial chemoembolization (TACE) in combination with local ablation therapy. Our goal was to uncover risk factors contributing to post-treatment recurrence and to develop and validate an innovative 1-, 3-, and 5-year recurrence free survival (RFS) nomogram. Methods: Data from 255 BCLC A/B HCC patients with Child-Pugh B cirrhosis treated at Beijing You'an Hospital (January 2014 - January 2020) were analyzed using random survival forest (RSF), LASSO regression, and multivariate Cox regression to identify independent risk factors for RFS. The prognostic nomogram was then constructed and validated, categorizing patients into low, intermediate, and high-risk groups, with RFS assessed using Kaplan-Meier curves. Results: The nomogram, integrating the albumin/globulin ratio, gender, tumor number, and size, showcased robust predictive performance. Harrell's concordance index (C-index) values for the training and validation cohorts were 0.744 (95% CI: 0.703-0.785) and 0.724 (95% CI: 0.644-0.804), respectively. The area under the curve (AUC) values for 1-, 3-, and 5-year RFS in the two cohorts were also promising. Calibration curves highlighted the nomogram's reliability and decision curve analysis (DCA) confirmed its practical clinical benefits. Through meticulous patient stratification, we also revealed the nomogram's efficacy in distinguishing varying recurrence risks. Conclusion: This study advances recurrence prediction in BCLC A/B HCC patients with Child-Pugh B cirrhosis following TACE combined with ablation. The established nomogram accurately predicts 1-, 3-, and 5-year RFS, facilitating timely identification of high-risk populations.

A multi-parametric prognostic model based on clinicopathologic features: vessels encapsulating tumor clusters and hepatic plates predict overall survival in hepatocellular carcinoma patients.

BACKGROUND: Vessels encapsulating tumor clusters (VETC) is a newly described vascular pattern that is distinct from microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC). Despite its importance, the current pathological diagnosis report does not include information on VETC and hepatic plates (HP). We aimed to evaluate the prognostic value of integrating VETC and HP (VETC-HP model) in the assessment of HCC. METHODS: A total of 1255 HCC patients who underwent radical surgery were classified into training (879 patients) and validation (376 patients) cohorts. Additionally, 37 patients treated with lenvatinib were studied, included 31 patients in high-risk group and 6 patients in low-risk group. Least absolute shrinkage and selection operator (LASSO) regression analysis was used to establish a prognostic model for the training set. Harrell's concordance index (C-index), time-dependent receiver operating characteristics curve (tdROC), and decision curve analysis were utilized to evaluate our model's performance by comparing it to traditional tumor node metastasis (TNM) staging for individualized prognosis. RESULTS: A prognostic model, VETC-HP model, based on risk scores for overall survival (OS) was established. The VETC-HP model demonstrated robust performance, with area under the curve (AUC) values of 0.832 and 0.780 for predicting 3- and 5-year OS in the training cohort, and 0.805 and 0.750 in the validation cohort, respectively. The model showed superior prediction accuracy and discrimination power compared to TNM staging, with C-index values of 0.753 and 0.672 for OS and disease-free survival (DFS) in the training cohort, and 0.728 and 0.615 in the validation cohort, respectively, compared to 0.626 and 0.573 for TNM staging in the training cohort, and 0.629 and 0.511 in the validation cohort. Thus, VETC-HP model had higher C-index than TNM stage system(p < 0.01).Furthermore, in the high-risk group, lenvatinib alone appeared to offer less clinical benefit but better disease-free survival time. CONCLUSIONS: The VETC-HP model enhances DFS and OS prediction in HCC compared to traditional TNM staging systems. This model enables personalized temporal survival estimation, potentially improving clinical decision-making in surveillance management and treatment strategies.

Construction of oxidative phosphorylation-related prognostic risk score model in uveal melanoma.

BACKGROUND: Uveal melanoma (UVM) is a malignant intraocular tumor in adults. Targeting genes related to oxidative phosphorylation (OXPHOS) may play a role in anti-tumor therapy. However, the clinical significance of oxidative phosphorylation in UVM is unclear. METHOD: The 134 OXPHOS-related genes were obtained from the KEGG pathway, the TCGA UVM dataset contained 80 samples, served as the training set, while GSE22138 and GSE39717 was used as the validation set. LASSO regression was carried out to identify OXPHOS-related prognostic genes. The coefficients obtained from Cox multivariate regression analysis were used to calculate a risk score, which facilitated the construction of a prognostic model. Kaplan-Meier survival analysis, logrank test and ROC curve using the time "timeROC" package were conducted. The immune cell frequency in low- and high-risk group was analyzed through Cibersort tool. The specific genomic alterations were analyzed by "maftools" R package. The differential expressed genes between low- or high-risk group were analyzed and performed Gene Ontology (GO) and GSEA. Finally, we verified the function of CYC1 in UVM by gene silencing in vitro. RESULTS: A total of 9 OXPHOS-related prognostic genes were identified, including NDUFB1, NDUFB8, ATP12A, NDUFA3, CYC1, COX6B1, ATP6V1G2, ATP4B and NDUFB4. The UVM prognostic risk model was constructed based on the 9 OXPHOS-related prognostic genes. The prognosis of patients in the high-risk group was poorer than low-risk group. Besides, the ROC curve demonstrated that the area under the curve of the model for predicting the 1 to 5-year survival rate of UVM patients were all more than 0.88. External validation in GSE22138 and GSE39717 dataset revealed that these 9 genes could also be utilized to evaluate and predict the overall survival of patients with UVM. The risk score levels related to immune cell frequency and specific genomic alterations. The DEGs between the low- and high- risk group were enriched in tumor OXPHOS and immune related pathway. In vitro experiments, CYC1 silencing significantly inhibited UVM cell proliferation and invasion, induced cell apoptosis. CONCLUSION: In sum, a prognostic risk score model based on oxidative phosphorylation-related genes in UVM was developed to enhance understanding of the disease. This prognostic risk score model may help to find potential therapeutic targets for UVM patients. CYC1 acts as an oncogene role in UVM.

Risk assessment model based on nucleotide metabolism-related genes highlights SLC27A2 as a potential therapeutic target in breast cancer.

PURPOSE: Breast cancer (BC) is the most prevalent malignant tumor worldwide among women, with the highest incidence rate. The mechanisms underlying nucleotide metabolism on biological functions in BC remain incompletely elucidated. MATERIALS AND METHODS: We harnessed differentially expressed nucleotide metabolism-related genes from The Cancer Genome Atlas-BRCA, constructing a prognostic risk model through univariate Cox regression and LASSO regression analyses. A validation set and the GSE7390 dataset were used to validate the risk model. Clinical relevance, survival and prognosis, immune infiltration, functional enrichment, and drug sensitivity analyses were conducted. RESULTS: Our findings identified four signature genes (DCTPP1, IFNG, SLC27A2, and MYH3) as nucleotide metabolism-related prognostic genes. Subsequently, patients were stratified into high- and low-risk groups, revealing the risk model's independence as a prognostic factor. Nomogram calibration underscored superior prediction accuracy. Gene Set Variation Analysis (GSVA) uncovered activated pathways in low-risk cohorts and mobilized pathways in high-risk cohorts. Distinctions in immune cells were noted between risk cohorts. Subsequent experiments validated that reducing SLC27A2 expression in BC cell lines or using the SLC27A2 inhibitor, Lipofermata, effectively inhibited tumor growth. CONCLUSIONS: We pinpointed four nucleotide metabolism-related prognostic genes, demonstrating promising accuracy as a risk prediction tool for patients with BC. SLC27A2 appears to be a potential therapeutic target for BC among these genes.