Risk Score Model Research Articles

Seizure or syncope: Is the history-based scale feasible to use in an emergency department setting?

BackgroundThis study aimed to assess the efficacy of a screening questionnaire, based on historical criteria, in distinguishing between seizures and syncope in patients experiencing their first episode of transient loss of consciousness (TLOC) in a neurology emergency department. MethodsA prospective cohort of 159 patients with initial TLOC episodes underwent clinical observation and answered a nine-question screening questionnaire. The questionnaire's predictive ability was compared to final diagnoses determined through detailed neurology, electrophysiology, and cardiology assessments during a minimum 12-month follow-up. Logistic regression (LR) analysis was performed with final diagnosis as the outcome variable. The calibration and discrimination of the models were assessed. Resultsrevealed that the screening score accurately classified 72.33% of patients. Among those with positive screening scores, 65 (67.71%) had seizures compared to 31 (32.29%) with syncope. Introducing a novel risk-scoring model incorporating age and gender, in addition to the screening score, significantly improved performance achieving an accurate classification rate of 81.48%. Among patients with a positive prediction, 63 (80.77%) had seizure, whereas 15 (19.23%) had syncope. ConclusionsEmploying a structured questionnaire based on common historical criteria is a valuable tool for distinguishing between seizure and syncope in the dynamic setting of the emergency department.

Serum lipoprotein(a) and reclassification of coronary heart disease risk; application of prediction in a cross-sectional analysis of an ongoing Iranian cohort

IntroductionRecent studies have introduced elevated lipoprotein(a) (Lp(a)) as a risk factor for coronary heart disease (CHD). This study investigated whether the addition of Lp(a) as a novel biomarker to the Framingham Risk Score (FRS) model improves CHD risk prediction.MethodsThe study included 1101 Iranian subjects (443 non-diabetic and 658 diabetic patients) who were followed for 10 years (2003–2013). Lp(a) levels and CHD events were recorded for each participant.ResultsThe Net Reclassification Index (NRI) after adding Lp(a) to the FRS model was 19.57% and the discrimination slope was improved (0.160 vs. 0.173). The Akaike Information Criterion (AIC), a measure of model complexity, decreased significantly after adding Lp(a) to the FRS model (691.9 vs. 685.4, P value: 0.007).ConclusionsThe study concluded that adding Lp(a) to the FRS model improves CHD risk prediction in an Iranian population without making the model too complex. This could help clinicians to better identify individuals who are at risk of developing CHD and to implement appropriate preventive measures.

Novel molecular insights into pyroptosis in triple-negative breast cancer prognosis and immunotherapy.

Patients with triple-negative breast cancer (TNBC) often have a poor prognostic outcome. Current treatment strategies cannot benefit all TNBC patients. Previous findings suggested pyroptosis as a novel target for suppressing cancer development, although the relationship between TNBC and pyroptosis-related genes (PRGs) was still unclear. Gene expression data and clinical follow-up of TNBC patients were collected from the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) and Gene Expression Omnibus (GEO). PRGs were screened using weighted gene co-expression network analysis. Cox regression analysis and the least absolute shrinkage and selection operator (i.e. LASSO) technique were applied to construct a pyroptosis-related prognostic risk score (PPRS) model, which was further combined with the clinicopathological characteristics of TNBC patients to develop a survival decision tree and a nomogram. The model was used to calculate the PPRS, and then the overall survival, immune infiltration, immunotherapy response and drug sensitivity of TNBC patients were analyzed based on the PPRS. The PPRS model was closely related to clinicopathological features and can independently and accurately predict the prognosis of TNBC. According to normalized PPRS, patients in different cohorts were divided into two groups. Compared with the high-PPRS group, the low-PPRS group had significantly higher ESTIMATE (i.e. Estimation of STromal and Immune cells in MAlignantTumours using Expression data) score, immune score and stromal score, and it also had overexpressed immune checkpoints and significantly reduced Tumor Immune Dysfunction and Exclusion (TIDE) score, as well as higher sensitivity to paclitaxel, veliparib, olaparib and talazoparib. A decision tree and nomogram based on PPRS and clinical characteristics can improve the prognosis stratification and survival prediction for TNBC patients. A PPRS model was developed to predict TNBC patients' immune characteristics and response to immunotherapy, chemotherapy and targeted therapy, as well as their survival outcomes.

A model for predicting clinical prognosis based on brain metastasis-related genes in patients with breast cancer.

Brain metastasis (BM) is a clinically relevant cause of death in patients with breast cancer (BRCA). This study was designed to develop a clinical model capable of predicting BRCA patients' prognostic outcomes according to the expression of BM-related genes (BMRGs). The public Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA) databases served as data sources. BMRGs of BRCA were selected from previous literature. Differences among BRCA molecular subtypes were compared using R 'limma' package. The impact of BM-related differentially expressed genes (BM_DEGs) on BRCA patients' outcomes was explored with a risk score model, after which the relationship between these risk scores and immune cell infiltration was examined. Risk scores were also used to judge the predicted efficacy of immunotherapeutic interventions. The utility of risk scores in combination with clinicopathological characteristics was evaluated as a predictor of patient's survival through univariate and multivariate analyses. The R limma package was used to explore differential gene expression, after which 12 BM_DEGs were incorporated into a risk scoring model. The resultant risk scores were able to predict immunotherapeutic treatment efficacy. In addition, a nomogram incorporating risk scores, stage, and age was established. The nomogram was able to reliably predict the overall survival (OS) of BRCA patients, yielding predictive outcomes that aligned well with actual observations. In summary, a predictive clinical model for BRCA patients was successfully established in this study, providing a valuable tool that may be particularly helpful for the assessment of patients facing a risk of BM development.

Developing Integer‐based Risk Scores for Predicting the Risk of Incident Cognitive Impairment in Cognitively Normal Older Adults

AbstractBackgroundWe aimed to developed integer‐based risk scores for predicting incident cognitive impairment up to 10 years in initially cognitively normal older adults.MethodsParticipants were 479 older adults (aged 60 to 90) from longitudinal studies of aging and Alzheimer’s disease from the Knight ADRC at Washington University in St. Louis. The primary outcome was incident cognitive impairment, defined as conversion from Clinical Dementia Rating (CDR®) 0 to >0. The sample was divided into training (60%) and test (40%) sets. Feature‐sets were formed from combinations of four categories of variables: demographics (D), genetics (G), cognitive measures (C), and biomarkers (B) (Details in Figure 1 legend). Utilizing a modified version of the AutoScore‐Survival algorithm, variables were ranked based on variable importance using reduction in predictive accuracy due to replacement with a random permutation value in combination with Random Survival Forests. Variables were iteratively included in constructing risk score models based on coefficients of Cox regression models.ResultsFive risk score models were developed using five feature‐sets. All models retained age, APOE4 status, free recall from the Free and Cued Selective Reminding Test, hippocampal atrophy, and Tau positivity when included as potential variables in the feature‐sets. The risk score derived from the DGCB model had a Harrell’s concordance index (C‐index) of 0.754 and integrated Area Under the ROC Curve (iAUC) of 0.792. The best performing model without biomarkers used the DGC feature‐set and had a C‐index of 0.694 and iAUC of 0.699 while the risk score using the DG feature‐set only had a C‐index of 0.632 and iAUC of 0.647. Participants who had risk scores in the top quartile of the DGCB model risk score had an increased rate of conversion to CDR > 0.ConclusionsWe developed five risk score models for predicting incident cognitive impairment. Risk scores consisted of different sets of measures which differed in ease‐of‐access and costs. Using such simple risk scores that do not include biomakers as clinical decision support tools is practical in the clinical setting. Including biomarkers in risk scores provides slight improvement to classification accuracy, emphasizing their importance in research settings.

Electrocardiogram (ECG) risk score model in heart failure with reduced ejection fraction (HFrEF): Predictor of sudden cardiac death

Electrocardiogram (ECG) risk score model in heart failure with reduced ejection fraction (HFrEF): Predictor of sudden cardiac death

Predicting of β‐amyloid Positivity Using Integer‐based Risk Scores with Blood‐based Biomarkers

AbstractBackgroundβ‐amyloid (Aβ), a pathologic hallmark of Alzheimer’s disease (AD) is the target of recently FDA‐approved drugs. In trials and in practice, identifying individuals likely to be β‐amyloid positive (Aβ+) with accessible and affordable tests will be increasingly important. Blood‐based biomarkers (BBMs) have shown early promise in determining amyloid status. We aimed to develop machine learning‐based integer risk scores using BBMs and other accessible measures to predict Aβ positivity by PET in older, non‐demented (cognitively unimpaired or mild cognitive impairment) adults.MethodsWe used data from 722 individuals (72.1 ± 7.0 years old) from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) to develop integer risk scores for predicting Aβ positivity. The sample was divided into training (75%) and test (25%) sets. Variables were categorized as demographics (D: age, sex, and education), genetic information (G: APOE4 status), cognitive measures (C: ADAS‐Cog‐13 and MMSE), and plasma biomarkers of p‐Tau181(T) and neurofilament light (N: NfL). Feature‐sets were formed as hierarchically constructed combinations of these categorized variables (see Figure 1). Using the AutoScore algorithm, variables were ordered according to their Random Forest Gini Index and were iteratively included in the construction of logistic regression‐derived risk score models. Variables were included based on increases in Area Under the ROC Curves (AUCs).ResultsFour models were developed based on four feature‐sets. All models utilized age and APOE4 status and, when considered, all models retained ADAS‐Cog‐13, p‐Tau, and NfL. The best performing model corresponded to the DGCTN feature‐set with performance on the dedicated test set of AUC = 0.810 (C.I.: 0.745‐0.876). Using the DGCTN model on the test set, 97% of individuals with scores in the top quartile of possible risk score points were correctly identified as Aβ+.ConclusionsWe developed risk score models utilizing accessible and affordable measures to predict Aβ positivity. Plasma biomarkers improve performance of risk scores indicating their value. Applications include screening in clinical settings for therapeutic care and enrichment of clinical trials. These data can be used to optimize the efficient use of PET in determining eligibility for clinical trials and amyloid targeted therapies in practice.

Screening plasma metabolites as potential biomarkers for type B aortic dissection.

Aortic dissection (AD) is a serious aortic disease. Although current imaging methods can provide accurate diagnosis for AD, they do not include essential biological information. The aim of this study is to identify plasma metabolites for the risk and severity of type B AD (TBAD). In this cross-sectional study, we enrolled 16 hypertensive patients with TBAD and 7 hypertensive patients without TBAD in Jieyang People's Hospital between December 2021 and April 2022. After plasma metabolomics analysis, a metabolites risk score (MRS) model was conducted through logistic regression and least absolute shrinkage and selection operator (LASSO) regression to predict the risk of TBAD. Subsequently, TBAD group was divided into uncomplicated and complicated TBAD subgroups for further screening for metabolites related to the severity of TBAD. Three metabolites, including 1,5-anhydro-D-glucitol, D-(+)-sucrose and PC(O-16:0/0:0) were related to the risk of TBAD. Compared to hypertensive patients without TBAD, the abundance of 1,5-anhydro-D-glucitol and D-(+)-sucrose were significantly increased while PC(O-16:0/0:0) was significantly reduced in hypertensive patients with TBAD (P<0.001). We subsequently built an MRS model based on these three metabolites. Furthermore, we found that hydrocinnamic acid (r=0.741, P<0.001) was independently correlated with the TBAD severity, while glycine deoxycholic acid (r=-0.538, P=0.008) and glycochenodeoxycholic acid (r=-0.538, P=0.008) were inversely correlated with the TBAD severity independently. The present study screened out three plasma metabolites associated with the risk of TBAD, constructed an MRS model, and identified three metabolites that were independently associated with the severity of TBAD. These findings may serve to identify more TBAD-related biomarkers and shed light on exploring potential mechanisms of TBAD.

NetPRISBI‐AD: Network‐based Polygenic Risk Scoring model with Brain Imaging for Alzheimer’s Disease

AbstractBackgroundThe amount of gray matter can measure the structural characteristics of the brain, and the deterioration of brain function can be evaluated accordingly. In particular, the lower the amount of gray matter in areas involved in memory, the lower the cognitive function, eventually affecting the onset of dementia, such as Alzheimer’s disease (AD). Although there are various factors for changes in gray matter volume, genetic factors are also closely related. In addition, genetic factors are not only independently involved in biological activities, but also have complex interactions.MethodIn this study, we construct a SNP network that reflects interactions between SNPs and propose a model that can predict the risk score for AD and the gray matter volume of the brain by region from the SNP network. First, in the SNP network, interactions between SNPs are measured as similarities based on the linkage disequilibrium score. Then, the proposed method constructs a regression model to predict brain volume and risk scores for AD using feature propagation, which is conducted to refine existing genetic variant information.ResultThe proposed method was applied to data including both genetic and brain imaging information among UK Biobank (UKBB; 8,273 cases and 25,353 controls, total 33,626 participants) and Alzheimer’s Disease Neuroimaging Initiative (ADNI; 202 cases and 720 controls, total 922 participants) data. The results were cross‐validated from the two datasets and compared with other models including the conventional polygenic risk score with pruning and thresholding (PRS‐PT) model. Compared to the other methods, the proposed method showed outstanding performance and the discovery of genetic variants and brain regions affecting Alzheimer’s disease.ConclusionWe proposed the framework for predicting the volume of the brain with refined features of SNP that reflects the interactions between elements. The results revealed that genetic relations and inferring brain volumes are crucial for enhancing AD risk prediction. Furthermore, through the proposed method, it is expected that understanding and interpreting the phased mechanism of the onset of AD through brain lesions from genetic variants will be possible.

Improving dementia phenotype prediction with functional mapping of genetic data in non‐European ancestries

AbstractBackgroundMany common genetic variants have been associated with dementia, but their ability to predict dementia prospectively is unknown, especially in non‐European ancestral populations. We sought to optimize dementia risk prediction models with machine learning in individuals of diverse genetic ancestries.MethodSamples were selected from the University of California Los Angeles Health System with their electronic health records (EHRs) and linked genetic data. Dementia phenotype was defined using diagnosis codes and mapped phecodes. Polygenic risk scores (PRSs) were built using summary statistics of different population‐based genome‐wide association studies (GWASs). Independent significant and functionally mapped single nucleotide polymorphisms (SNPs) were identified using the FUMA tool. Logistic regression models were built with 1) APOE status, 2) a single PRS, or 3) multiple PRSs. The model with age and sex only was built as the baseline model. We trained LASSO models to determine dementia risk SNPs from weighted SNP‐level genetic data. We compared the predictive performance of these models after five‐fold cross‐validation with area under precision‐recall curve (AUPRC) and area under receiver operating characteristic (AUC). Finally, identified risk SNPs were mapped to genes for biological interpretation.ResultThere were 975 individuals included in the final Hispanic Latinx American ancestry sample, of which 9.44% (N = 92) were dementia cases. The model with LASSO‐selected functional mapped SNPs from multiple neurodegenerative diseases GWASs outperformed all other genetic risk score models (AUPRC: 0.39, AUROC: 0.87), resulting in a 19.6% increase in AUPRC from the best PRS model, and a 26.9% increase from the baseline model. The best‐performing LASSO model included nine SNPs, mostly located in the 19q13, 4p15, and 17q21 regions. Results of mapped genes not only revealed well‐known risk genes of dementia but identified risk genes from other neurodegenerative diseases.ConclusionWe demonstrated that building genetic risk scores with trans‐ancestry GWAS and selecting potential causal SNPs can be beneficial for dementia prediction in non‐European ancestry populations. Further training using machine learning methods with functionally mapped SNP‐level genetic data showed significant improvement in predictive power compared to PRS models. Genetic risks of multiple neurodegenerative diseases may contribute to the predisposition to dementia.

A prognostic signature for lung adenocarcinoma by five genes associated with chemotherapy in lung adenocarcinoma.

Lung adenocarcinoma (LUAD) is one of the most common subtypes of lung cancer. Finding prognostic biomarkers is helpful in stratifying LUAD patients with different prognosis. We explored the correlation of LUAD prognosis and genes associated with chemotherapy in LUAD and obtained data of LUAD patients from the Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases. Drug sensitivity data were acquired from the Genomics of Drug Sensitivity in Cancer (GDSC) database. Differential and enrichment analyses were used to screen the target genes utilizing limma and "clusterProfiler" packages. Then univariate and LASSO Cox analyses were used to select the prognosis-related genes. Survival analysis was used to estimate the overall survival (OS) of different groups. Twenty-three differentially expressed genes (DEGs) were screened between LUAD samples and healthy samples, and BTK, FGFR2, PIM2, CHEK1, and CDK1 were selected to construct a prognostic signature. The OS of patients in the high-risk group (risk score higher than 0.69) was worse than that in the low-risk group (risk score lower than 0.69). The risk score model constructed by five genes is a potential prognostic biomarker for LUAD patients.

Fatty Acid Metabolism-Related lncRNAs are Potential Biomarkers for Predicting Prognoses and Immune Responses in Patients with Skin Cutaneous Melanoma.

Skin cutaneous melanoma is becoming more dangerous since it has a poor prognosis and is resistant to treatment. Previous research has shown that lncRNAs and fatty acid metabolism are essential for numerous biological activities. There are no studies on the relationship between fatty acid metabolism-Related lncRNAs and skin cutaneous melanoma. In order to better understand the prognosis and survival of SKCM patients, we investigated the significance of lncRNAs related to fatty acid metabolism. In this work, we looked at the fatty acid metabolism genes and lncRNAs expression patterns. On the basis of lncRNAs associated with fatty acid metabolism, a nomogram and a prognosis prediction model were created. Based on the profile of lncRNAs associated with fatty acid metabolism, functional and pharmacological sensitivity investigations were also carried out. We also looked at the connection between immunotherapy and the immune response. The findings demonstrated that a risk score model based on 11 essential lncRNAs for fatty acid metabolism may discriminate between the clinical condition of SKCM and more accurately predict prognosis and survival. We conducted quantitative reverse transcription polymerase-chain reaction (RT-PCR) to verify the model. These important lncRNAs further showed a strong association with the tumor immune system, and these important lncRNAs also showed a connection between SKCM and chemotherapeutic treatment sensitivity. Our research strives to provide fresh viewpoints and innovative approaches to the treatment and administration of SKCM.

Construction of a prognostic risk score model based on the ARHGAP family to predict the survival of osteosarcoma

BackgroundOsteosarcoma (OS) is the most common primary malignancy of bone tumors. More and more ARHGAP family genes have been confirmed are to the occurrence, development, and invasion of tumors. However, its significance in osteosarcoma remains unclear. In this study, we aimed to identify the relationship between ARHGAP family genes and prognosis in patients with OS.MethodsOS samples were retrieved from the TCGA and GEO databases. We then performed LASSO regression analysis and multivariate COX regression analysis to select ARHGAP family genes to construct a risk prognosis model. We then validated this prognostic model. We utilized ESTIMATE and CIBERSORT algorithms to calculate the stroma and immune scores of samples, as well as the proportions of tumor infiltrating immune cells (TICs). Finally, we conducted in vivo and in vitro experiments to investigate the effect of ARHGAP28 on osteosarcoma.ResultsWe selected five genes to construct a risk prognosis model. Patients were divided into high- and low-risk groups and the survival time of the high-risk group was lower than that of the low-risk group. The high-risk group in the prognosis model constructed had relatively poor immune function. GSEA and ssGSEA showed that the low-risk group had abundant immune pathway infiltration. The overexpression of ARHGAP28 can inhibit the proliferation, migration, and invasion of osteosarcoma cells and tumor growth in mice, and IHC showed that overexpression of ARHGAP28 could inhibit the proliferation of tumor cells.ConclusionWe constructed a risk prognostic model based on five ARHGAP family genes, which can predict the overall survival of patients with osteosarcoma, to better assist us in clinical decision-making and individualized treatment.

M6A-related lncRNAs as potential biomarkers and the lncRNA ELFN1-AS1/miR-182-5p/BCL-2 regulatory axis in diffuse large B-cell lymphoma.

Diffuse large B-cell lymphoma (DLBCL) is the most common lymphoid subtype. However, unsatisfactory survival outcomes remain a major challenge, and the underlying mechanisms are poorly understood. N6-methyladenosine (m6A), the most common internal modification of eukaryotic mRNA, participates in cancer pathogenesis. In this study, m6A-associated long non-coding RNAs (lncRNA) were retrieved from publicly available databases. Univariate, LASSO, and multivariate Cox regression analyses were performed to establish an m6A-associated lncRNA model specific to DLBCL. Kaplan-Meier curves, principal component analysis, functional enrichment analyses and nomographs were used to study the risk model. The underlying clinicopathological characteristics and drug sensitivity predictions against the model were identified. Risk modelling based on the three m6A-associated lncRNAs was an independent prognostic factor. By regrouping patients using our model-based method, we could differentiate patients more accurately for their response to immunotherapy. In addition, prospective compounds that can target DLBCL subtypes have been identified. The m6A-associated lncRNA risk-scoring model developed herein holds implications for DLBCL prognosis and clinical response prediction to immunotherapy. In addition, we used bioinformatic tools to identify and verify the ceRNA of the m6A-associated lncRNA ELFN1-AS1/miR-182-5p/BCL-2 regulatory axis. ELFN1-AS1 was highly expressed in DLBCL and DLBCL cell lines. ELFN1-AS1 inhibition significantly reduced the proliferation of DLBCL cells and promoted apoptosis. ABT-263 inhibits proliferation and promotes apoptosis in DLBCL cells. Invitro and invivo studies have shown that ABT-263 combined with si-ELFN1-AS1 can inhibit DLBCL progression.

Diagnostic and prognostic value of ferroptosis-related genes in patients with Myelodysplastic neoplasms

ABSTRACT This study delves into the emerging role of ferroptosis in Myelodysplastic Neoplasms (MDS) and aims to identify a prognostic ferroptosis-related gene signature for MDS. Utilizing RNA-seq data and clinical information from the Gene Expression Omnibus database, the researchers extracted ferroptosis-related genes from the FerrDb website and conducted differential expression analysis using the 'limma' package in R. Hub ferroptosis-related genes in MDS were screened using the “RandomForest” and “carat” R packages. Kaplan -Meier and Cox regression analyses were employed to assess the prognostic role of three identified hub genes (BNIP3, MDM2, and RRM2). Receiver operator characteristic curve analysis confirmed the diagnostic efficacy of these genes. The study delved further into immune infiltration correlations, ncRNA-transcription factor coregulatory network analysis, and the identification of potential therapeutic drugs targeting hub ferroptosis-related genes in MDS. The researchers constructed a 3-gene signature-based risk score using datasets GSE58831 and GSE19429, demonstrating high accuracy (AUC > 0.75) in both datasets for survival prediction in MDS. A nomogram analysis reinforced the prognostic value of the risk-scoring model. Immunological analysis revealed an association between the risk score and immune infiltration. Quantitative reverse transcription polymerase chain reaction (qPCR) data indicated significant expression differences in MDM2, RRM2, and BNIP3 between MDS and healthy bone marrow samples. Notably, MDM2 and RRM2 showed decreased expression, while BNIP3 exhibited increased expression in MDS samples. This comprehensive study concludes that BNIP3, MDM2, and RRM2 hold diagnostic and prognostic significance in MDS and provide valuable insights into immune cell landscapes and potential therapeutic avenues for this condition.

Comparative study of two models predicting the risk of deep vein thrombosis progression in spinal trauma patients after operation

ObjectivePatients with preoperative deep vein thrombosis (DVT) exhibit a notable incidence of postoperative deep vein thrombosis progression (DVTp), which bears a potential for silent, severe consequences. Consequently, the development of a predictive model for the risk of postoperative DVTp among spinal trauma patients is important. MethodsData of 161 spinal traumatic patients with preoperative DVT, who underwent spine surgery after admission, were collected from our hospital between January 2016 and December 2022. The least absolute shrinkage and selection operator (LASSO) combined with multivariable logistic regression analysis was applied to select variables for the development of the predictive logistic regression models. One logistic regression model was formulated simply with the Caprini risk score (Model A), while the other model incorporated not only the previously screened variables but also the age variable (Model B). The model’s capability was evaluated using sensitivity, specificity, positive predictive value, negative predictive value, accuracy, F1 score, and receiver operating characteristic (ROC) curve. Nomograms simplified and visually presented Model B for the clinicians and patients to understand the predictive model. The decision curve was used to analyze the clinical value of Model B. ResultsA total of 161 DVT patients were enrolled in this study. Postoperative DVTp occurred in 48 spinal trauma patients, accounting for 29.81% of the total patient enrolled. Model A inadequately predicted postoperative DVTp in spinal trauma patients, with ROC AUC values of 0.595 for the training dataset and 0.593 for the test dataset. Through the application of LASSO regression and multivariable logistic regression, a screening process was conducted for seven risk factors: D-dimer, blood platelet, hyperlipidemia, blood group, preoperative anticoagulant, spinal cord injury, lower extremity varicosities. Model B demonstrated superior and consistent predictive performance, with ROC AUC values of 0.809 for the training dataset and 0.773 for the test dataset. According to the calibration curves and decision curve analysis, Model B could accurately predict the probability of postoperative DVTp after spine surgery. The nomograms enhanced the interpretability of Model B in charts and graphs. ConclusionsIn summary, we established a logistic regression model for the accurate predicting of postoperative deep vein thrombosis progression in spinal trauma patients, utilizing D-dimer, blood platelet, hyperlipidemia, blood group, preoperative anticoagulant, spinal cord injury, lower extremity varicosities, and age as predictive factors. The proposed model outperformed a logistic regression model based simply on CRS. The proposed model has the potential to aid frontline clinicians and patients in identifying and intervening in postoperative DVTp among traumatic patients undergoing spinal surgery.

Identification and validation of candidate clinical signatures of apolipoprotein L isoforms in hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is a lethal malignancy worldwide with an increasing number of new cases each year. Apolipoprotein (APOL) isoforms have been explored for their associations with HCC.The GSE14520 cohort was used for training data; The Cancer Genome Atlas (TCGA) database was used for validated data. Diagnostic, prognostic significance and mechanisms were explored using these cohorts. Risk score models and nomograms were constructed using prognosis-related isoforms and clinical factors for survival prediction. Oncomine and HCCDB databases were further used for validation of diagnostic, prognostic significance. APOL1, 3, and 6 were differentially expressed in two cohorts (all P ≤ 0.05). APOL1 and APOL6 had diagnostic capacity whereas APOL3 and APOL6 had prognostic capacity in two cohorts (areas under curves [AUCs] > 0.7, P ≤ 0.05). Mechanism studies demonstrated that APOL3 and APOL6 might be involved in humoral chemokine signaling pathways (all P ≤ 0.05). Risk score models and nomograms were constructed and validated for survival prediction of HCC. Moreover, diagnostic values of APOL1 and weak APOL6 were validated in Oncomine database (AUC > 0.700, 0.694); prognostic values of APOL3 and APOL6 were validated in HCCDB database (all P < 0.05). Differentially expressed APOL1 and APOL6 might be diagnostic biomarkers; APOL3 and APOL6 might be prognostic biomarkers of RFS and OS for HCC via chemokine signaling pathways.

Risk factors for hyperglycemia in COVID-19 patients treated with remdesivir.

The primary objective of this study was to investigate the factors contributing to hyperglycemic adverse events (AEs) associated with the administration of remdesivir in hospitalized patients diagnosed with coronavirus disease 2019 (COVID-19). Furthermore, the study aimed to develop a risk score model employing various machine learning approaches. A total of 1262 patients were enrolled in this investigation. The relationship between covariates and hyperglycemic AEs was assessed through logistic regression analysis. Diverse machine learning algorithms were employed for the purpose of forecasting hyperglycemia-related complications. After adjusting for covariates, individuals with a body mass index ≥23 kg/m2 , those using proton pump inhibitors, cholinergic medications, or individuals with cardiovascular diseases exhibited approximately 2.41-, 2.73-, 2.65-, and 1.97-fold higher risks of experiencing hyperglycemic AEs (95% CI 1.271-4.577, 1.223-6.081, 1.168-5.989, and 1.119-3.472, respectively). Multivariate logistic regression, elastic net, and random forest models displayed area under the receiver operating characteristic curve values of 0.65, 0.66, and 0.60, respectively (95% CI 0.572-0.719, 0.640-0.671, and 0.583-0.611, respectively). This study comprehensively explored factors associated with hyperglycemic complications arising from remdesivir administration and, concurrently, leveraged a range of machine learning methodologies to construct a risk scoring model, thereby facilitating the tailoring of individualized remdesivir treatment regimens for patients with COVID-19.

Construction and validation of a risk-scoring model to predict lymph node metastasis in T1b-T2 esophageal cancer.

Lymph node status is an important factor in determining preoperative treatment strategies for stage T1b-T2 esophageal cancer (EC). Thus, the aim of this study was to investigate the risk factors for lymph node metastasis (LNM) in T1b-T2 EC and to establish and validate a risk-scoring model to guide the selection of optimal treatment options. Patients who underwent upfront surgery for pT1b-T2 EC between January 2016 and December 2022 were analyzed. On the basis of the independent risk factors determined by multivariate logistic regression analysis, a risk-scoring model for the prediction of LNM was constructed and then validated. The area under the receiver operating characteristic curve (AUC) was used to assess the discriminant ability of the model. The incidence of LNM was 33.5% (214/638) in our cohort, 33.4% (169/506) in the primary cohort and 34.1% (45/132) in the validation cohort. Multivariate analysis confirmed that primary site, tumor grade, tumor size, depth, and lymphovascular invasion were independent risk factors for LNM (all P < 0.05), and patients were grouped based on these factors. A 7-point risk-scoring model based on these variables had good predictive accuracy in both the primary cohort (AUC, 0.749; 95% confidence interval 0.709-0.786) and the validation cohort (AUC, 0.738; 95% confidence interval 0.655-0.811). A novel risk-scoring model for lymph node metastasis was established to guide the optimal treatment of patients with T1b-T2 EC.

Development and validation of a predictive model for persistent opioid use in new opioid analgesic users via a nationwide claims database.

Chronic opioid use is associated with problematic opioid use, such as opioid abuse. It is important to develop a prediction model for safe opioid use. In this study, we aimed to develop and validate a risk score model for chronic opioid use in opioid-naïve, noncancer patients, using data from a nationwide database. Data from the National Health Insurance Claims Database in the Republic of Korea from 2016 to 2018 were used, and adult, noncancer patients who were started on non-injectable opioid analgesics (NIOAs) were included. The risk score model was developed using the β coefficient of each variable in the multivariable logistic regression analysis. Overall, 676,676 noncancer patients were started on NIOAs, of which 65,877 (9.7%) were prescribed NIOAs chronically. Age, baseline healthcare utilization, comorbidities, co-medications, and pattern of first NIOA prescription were identified as risk factors for chronic opioid use. The c-static for the performance of our risk score model was 0.754 (95% confidence interval, 0.750-0.758). To our knowledge, this is the first tool that can predict chronic opioid use in the Korean population. The model can help physicians examine the risk of chronic opioid use by patients who are started on NIOA.