Lasso Method Research Articles

A prognostic nomogram for patients with III-IV nasopharyngeal carcinoma based on dynamic changes in the inflammatory and nutrition index.

The purpose of the study was to explore the value of dynamic changes in inflammatory and nutritional index after comprehensive treatment in patients with stage III-IVA nasopharyngeal carcinoma (NPC). A prognostic model was also established and validated for progression-free survival (PFS) of patients. We retrospectively selected 279 NPC patients with stage III-IVA. Their general clinical data and hematological index were collected and then calculated the changes during treatment. X-tile software was used to determine the optimal cut-off value. COX regression, Lasso method, and Boruta method were used to variable selection and model establishment. Using the bootstrap internal validation method, concordance index (C-index), calibration plot, and Kaplan-Meier curves were used to evaluate the model. To test the prognostic value of the model, we have also evaluated the performance of the nomogram against a conventional tumor metastasis staging system (TNM). Multivariable COX regression analysis demonstrated that clinical staging, delta lymphocyte, delta monocyte, delta albumin, delta platelet-to-lymphocyte ratio and delta systemic immune inflammation index were related to the PFS of NPC patients. The C-index of the model was 0.712, and the calibration curve indicated that the model had good consistency. The C-index of the TNM staging system was 0.597, which was considerably lower compared to our model (P = 0.015). We demonstrated the predictive value of dynamic changes in inflammatory and nutritional indices for the prognosis of NPC by successfully establishing and validating a prognostic model for predicting 1- and 3-year PFS after comprehensive treatment in patients with stage III-IVA NPC.

Coexisting metabolic dysfunction-associated steatotic liver disease exacerbates in-hospital outcomes in patients with heat stroke

PurposeThis study aimed to investigate the impact of coexisting metabolic dysfunction-associated steatotic liver disease (MASLD) on in-hospital mortality and organ injury markers in patients with heat stroke (HS).ApproachHS patients were retrospectively identified between July 1, 2022 and September 30, 2023 at West China Hospital, Sichuan University. Baseline characteristics, such as demographics, initial vital signs, and organ functional indicators were collected. Outcome events included organ injury and in-hospital mortality. The Least Absolute Shrinkage and Selection Operator (Lasso) method was employed to identify the optimal predictors for in-hospital mortality in HS patients. Subsequently, multivariable logistic regression analysis was performed to assess the relationship between the presence of MASLD and in-hospital mortality as well as organ function indicators.FindingsA total of 112 patients were included in the study, in which 27 (24.1%) had coexisting MASLD. Compared to those without MASLD, patients with MASLD had higher levels of various organ injury markers such as aspartate aminotransferase, urea nitrogen, serum cystatin C, creatinine, uric acid, myoglobin, creatine kinase and its isoenzymes upon admission (P < 0.05). The multivariable Logistic regression analysis indicated that the presence of MASLD is an independent risk factor for in-hospital mortality in HS patients.ConclusionThis study firstly indicated that coexisting MASLD may exacerbate organ injury in HS patients and serve as an independent risk factor for in-hospital mortality.

BIOM-49. PATIENT-CENTRIC INTEGRATED GRAPH DATABASE REVEALS CRITICAL BIOMARKERS IN THE RECURRENCE OF IDH WILD-TYPE GLIOMA

Abstract BACKGROUND IDH wild-type glioblastoma (GBM) represents a formidable therapeutic challenge due to its consistent recurrence and progression despite standard treatments. Understanding the molecular and cellular mechanisms driving GBM recurrence through data integration is crucial. This study employs a novel graph database strategy to uncover insights into these tumors and identify functional biomarkers through graph algorithms-based pathway enrichment analysis. METHOD We developed a stand-alone graph database using Neo4j for primary-recurrent paired GBMs, integrating clinical and gene expression data from the Glioma Longitudinal AnalySiS (GLASS) Consortium and internal MD Anderson cohort. Based on log2 fold-change, we used hierarchical trees for differentially expressed genes to decompose the expression profile. Nodes in the database represent patients with considerable absolute log2 values determined by hierarchical trees, while shared patients define the edges. We applied graph algorithms such as degree centrality and community detection to identify potential biomarkers and supplemented these analyses with pathway identification to refine the biomarker list. Further, we divided the data set into 80% training and 20% testing sets. We evaluated the predictive performance of these biomarkers using machine learning models, including logistic regression, random forest, SVM, and neural networks. RESULTS DEG analysis revealed 33 down-regulated and 418 up-regulated genes in recurrent tumors. The top enriched pathways included neuroactive ligand-receptor interaction and GPCR ligand binding. Our database approach implicated 35 out of 451 genes as significant drivers of recurrence in IDH wild-type GBM. The prediction performance of these biomarkers was comparable to features selected through methods such as mRMR and logistic lasso and target identification methods like WGCNA. CONCLUSION Our innovative systems biology approach reveals that ligand-receptor interactions are crucial in driving recurrence in IDH wild-type GBM. This method also yielded promising mechanistic targets for recurrence, prompting focused and therapeutically relevant functional analyses. Moreover, this methodology is not limited to our study but can be applied in other multi-omics settings, offering a robust tool for biomarker discovery and validation.

Predicting first-line VEGFR-TKI resistance and survival in metastatic clear cell renal cell carcinoma using a clinical-radiomic nomogram.

This study aims to construct predicting models using radiomic and clinical features in predicting first-line vascular endothelial growth factor receptor-tyrosine kinase inhibitor (VEGFR-TKI) early resistance in metastatic clear cell renal cell carcinoma (mccRCC) patients. We also aim to explore the correlation of predicting models with short and long-term survival of mccRCC patients. In this retrospective study, 110 mccRCC patients from 2009 to 2019 were included and assigned into training and test sets. Radiomic features were extracted from tumor 3D-ROI of baseline enhanced CT images. Radiomic features were selected by Lasso method to construct a radiomic score. A combined nomogram was established using the combination of radiomic score and clinical factors. The discriminative abilities of the radiomic, clinical and combined nomogram were quantified using ROC curve. Cox regression analysis was used to test the correlation of nomogram score with progression-free survival (PFS) and overall survival (OS). PFS and OS were compared between different risk groups by log-rank test. The radiomic, clinical and combined nomogram demonstrated AUCs of 0.81, 0.75, and 0.83 in training set; 0.79, 0.77, and 0.88 in test set. Nomogram score ≥ 1.18 was an independent prognostic factor of PFS (HR 0.22 (0.10, 0.47), p < 0.001) and OS (HR 0.38 (0.20, 0.71), p = 0.002), in training set. PFS in low-risk group were significantly longer than high-risk group in training (p < 0.001) and test (p < 0.001) set, respectively. OS in low-risk group were significantly longer than high-risk group in training (p = 0.003) and test (p = 0.009) set, respectively. A nomogram combining baseline radiomic signature and clinical factors helped detecting first-line VEGFR-TKI early resistance and predicting short and long-term prognosis in mccRCC patients.

Disentangling the gender-differentiated determinants of home-based self-employment choices in Nigeria

Abstract Understanding gender disparities in home-based self-employment (HBS) and their links to homeownership and socioeconomic factors is crucial for advancing sustainable development goals (SDGs) in Sub-Saharan Africa, especially Nigeria. This study uses data from the 2010/2011, 2012/13, 2015/16, and 2018/19 waves of the Nigerian General Household Survey (GHS). It employs random effect probit regression, the LASSO method for identifying predictors, and the Blinder–Oaxaca decomposition technique to analyse gender differences in nonlinear binary outcomes. The results show that female business owners are more likely to engage in HBS compared to males, highlighting the importance of gender equality (SDG 5) and decent work (SDG 8). While male entrepreneurs are mainly driven by profit, females prioritise balancing paid and unpaid work, reflecting motivations beyond profit within heterodox economics. Significant gender-differentiated impacts are observed in relation to monthly rent, post-secondary education, dwelling space, energy, and regional locations. Notably, the presence of children significantly increases female involvement in HBS, a trend not seen among males. Marriage also influences female participation, suggesting that marital circumstances and economic benefits play a role. These findings highlight the need for policies addressing gender-specific constraints, challenging traditional gender roles, and promoting inclusive human development within the SDG framework.

BIM investment decision model (BIDM): evaluation of features and proposal of a regression model based on the LASSO method

BIM investment decision model (BIDM): evaluation of features and proposal of a regression model based on the LASSO method

Are SNPs Linked to Somatic Cell Score Suitable Markers for the Susceptibility to Specific Mastitis Pathogens in Holstein Cows?

Mastitis in cattle is often caused by microorganism infections in the udder. The three most common pathogens are esculin-positive streptococci (SC+), coagulase-negative staphylococci (CNS), and Escherichia coli (E. coli). In a previous study, 10 SNPs were associated with somatic cell score and mastitis in diverse Holstein populations. We tested these SNPs for their effects on individual pathogen presence. Milk and pathogen samples of 3076 Holstein cows were collected from four farms. Samples were excluded if multiple pathogens were present at the same time. Records of the same pathogen within 14 days of each other were counted as one infection. This resulted in 1129 pathogen-positive samples. Cases and controls were in ratios of 20:80 for SC+, 8:92 for CNS, and 11:89 for E. coli. The lasso, backward, and forward methods were used to narrow down SNPs associated with pathogen presence. The suitability of the SNPs to separate the samples into cases or controls for each pathogen was indicated using ROC curves. The Cochran-Armitage (CAT) and the Jonckheere-Terpstra (JTT) tests evaluated the influence of the SNPs on pathogen presence. Finally, a generalised linear mixed model (GLMM) including fixed environmental effects and a random sire effect was fitted to the binary trait of pathogen presence to test for association. In total, six out of the 10 investigated SNPs showed associations with pathogen presence based on the forward method: Two SNPs each for SC+ (rs41588957, rs41257403) and CNS (rs109934030, rs109441194), and three for E. coli (rs109934030, rs41634110, rs41636878). The CAT and GTT tests linked four SNPs (rs41588957, rs41634110, rs109441194, rs41636878) to pathogen presence, two of which were confirmed with the GLMM (rs41634110, rs109441194), with effects on CNS and E. coli. The SNPs linked to CNS and those linked to E. coli explained 13.2% and 13.8% of the variance, compared to 19% and 18.4%, respectively, of the full model with all 10 SNPs. Half of the SNP genotypes previously linked to lower SCS also decreased the probability for pathogen presence and might therefore be targets not just for lower SCS but for a better pathogen resistance. Trial Registration: Not applicable, no new data were collected for this study.

Predictive modeling of bronchopulmonary dysplasia in premature infants: the impact of new diagnostic standards.

To provide a risk prediction for bronchopulmonary dysplasia (BPD) in premature infants under the new diagnostic criteria and establish a prediction model. In this study, we retrospectively collected case data on preterm infants admitted to the NICU from August 2015 to August 2018. A lasso analysis was performed to identify the risk factors associated with the development of BPD. A nomogram predictive model was constructed in accordance with the new diagnostic criteria for BPD. A total of 276 preterm infants were included in the study.The incidence of BPD under the 2018 diagnostic criteria was 11.2%. Mortality was significantly higher in the BPD group than the non-BPD group under the 2018 diagnostic criteria (P < 0.05). Fourteen possible variables were selected by the Lasso method, with a penalty coefficient λ=0.0154. The factors that eventually entered the logistic regression model included birth weight [BW, OR = 0.9945, 95% CI: 0.9904-0.9979], resuscitation way (OR = 4.8249, 95% CI: 1.3990-19.4752), intrauterine distress (OR = 8.0586, 95% CI: 1.7810-39.5696), score for SNAPPE-II (OR = 1.0880, 95% CI: 1.0210-1.1639), hematocrit (OR = 1.1554, 95% CI: 1.0469-1.2751) and apnea (OR = 7.6916, 95% CI: 1.4180-52.1236). The C-index after adjusting for fitting deviation was 0.894. This study made a preliminary exploration of the risk model for early prediction of BPD and indicated good discrimination and calibration in premature infants.

A network analysis of voice hearing, emotional distress and subjective recovery before and after cognitive behavioural interventions.

There is a need to identify and to better understand key processes involved in voice hearing, which can inform the targeting and development of psychological interventions for distressing voices. The current study aimed to examine interrelations between the negative impact of voices, voice characteristics, emotional distress and recovery before and after cognitive behavioural interventions for voices (Coping Strategy Enhancement, guided self-help Cognitive Behavioural Therapy, Relating Therapy and Person-Based Cognitive Therapy). The sample consisted of 172 participants from the Sussex Voices Clinic who completed pre- and post-treatment assessments. The negative impact of voices, voice characteristics, emotional distress and recovery were used to estimate two networks, before and after cognitive behavioural interventions, using the graphical lasso method with the extended Bayesian information criterion. Centrality indices were also computed, and the two networks were compared on connectivity, structure and individual edge weights. Depression, anxiety and the negative impact of voices were identified as key central symptoms and acted as bridge symptoms in pre- and post-treatment networks. There were no significant differences in network structure (M = 0.155, p = .57), global strength (S = 0.188, p = .07) and centralities (C = -0.318, p = -.06) between the two networks. Our findings suggest that anxiety and depression are promising treatment targets, that can lead to reductions in voice-related distress, whereas the characteristics of voices and subjective recovery play little role in the network structure. Limitations include the lack of a control group and the lack of diversity within the sample.

Estimating probability of default via delinquencies? Evidence from European P2P lending market

The unprecedented growth of the financial sector's digital transformation opens wide areas to the scaling up of finance in innovative and knowledge-based projects. Improving risk management takes centre stage in the acceleration of this process. This study uses loan-book data from the peer-to-peer (P2P) lending market to empirically investigate the determinants of default risk. Using the loan-book database covering the period from 2014 to 2020, we examine multiple factors related to the default risk of loans issued by P2P lending platforms. The results indicate that a higher interest rate and higher stock market returns increase the probability of default in the P2P lending market. Results are robust to additional tests based on endogeneity correction, the LASSO method and sampling bias. The severity of the impact of market returns and interest rates is found to be significantly different based on the levels of financial technology (FinTech) adoption and banking sector distress. Increases in the market interest rate are found to boost the sensitivity of P2P loan defaults to stock market volatility. This study contributes to existing literature on risk management models with its consideration of country-specific factors, paving the way to future best practices in the market.

Evaluation and Influencing Factors of Regional Green Innovation Efficiency Based on the Lasso Method

Regional green innovation efficiency is affected by multiple factors. Based on the undesirable output of 11 provinces in the Yangtze River Economic Belt from 2012–2021, this paper uses the Super-SBM model containing undesirable outputs to measure and analyze the regional green innovation efficiency and tests the variables affecting regional green innovation efficiency through lasso regression. Stepwise regression and least squares estimation are used to prove the rationality of the lasso regression model. The results show that the regional green innovation efficiency of the Yangtze River Economic Belt during 2012–2021 among different regions has differences that manifest as the efficiency of the lower, middle, and upper reaches decreases successively, and the differences decrease gradually over time. All the variables affecting the regional green innovation efficiency pass the lasso regression variable screening test, and most of the influencing factors positively promote the regional green innovation efficiency and are more explanatory than the stepwise regression and the least squares proof model.

Development of a prediction model for the incidence of type 2 diabetic kidney disease and its application based on a regional health data platform

Objective: To construct a risk prediction model for diabetes kidney disease (DKD). Methods: Patients newly diagnosed with type 2 diabetes mellitus (T2DM) between January 1, 2015, and December 31, 2022, were selected as study subjects from the Yinzhou Regional Health Information Platform in Ningbo City. The Lasso method was used to screen the risk factors, and the DKD risk prediction model was established using Cox proportional hazard regression models. Bootstrap 500 resampling was applied for internal validation. Results: The study included 49 706 subjects, with an median (Q1, Q3) age of 60.00 (50.00, 68.00) years old, and 55% were male. A total of 4 405 subjects eventually developed DKD. Age at first diagnosis of T2DM, BMI, education level, fasting plasma glucose, glycated hemoglobin A1c, urinary albumin, past medical history (hyperuricemia, rheumatic diseases), triglycerides, and estimated glomerular filtration rate were included in the final model. The final model's C-index was 0.653, with an average of 0.654 after Bootstrap correction. The final model's area under the receiver operating characteristic curve for predicting 4-year, 5-year, and 6-year was 0.657, 0.659, and 0.664, respectively. The calibration curve was closely aligned with the ideal curve. Conclusions: This study constructed a DKD risk prediction model for newly diagnosed T2DM patients based on real-world data that is simple, easy to use, and highly practical. It provides a reliable basis for screening high-risk groups for DKD.

Feature selection with annealing for forecasting financial time series

Stock market and cryptocurrency forecasting is very important to investors as they aspire to achieve even the slightest improvement to their buy-or-hold strategies so that they may increase profitability. However, obtaining accurate and reliable predictions is challenging, noting that accuracy does not equate to reliability, especially when financial time-series forecasting is applied owing to its complex and chaotic tendencies. To mitigate this complexity, this study provides a comprehensive method for forecasting financial time series based on tactical input–output feature mapping techniques using machine learning (ML) models. During the prediction process, selecting the relevant indicators is vital to obtaining the desired results. In the financial field, limited attention has been paid to this problem with ML solutions. We investigate the use of feature selection with annealing (FSA) for the first time in this field, and we apply the least absolute shrinkage and selection operator (Lasso) method to select the features from more than 1000 candidates obtained from 26 technical classifiers with different periods and lags. Boruta (BOR) feature selection, a wrapper method, is used as a baseline for comparison. Logistic regression (LR), extreme gradient boosting (XGBoost), and long short-term memory are then applied to the selected features for forecasting purposes using 10 different financial datasets containing cryptocurrencies and stocks. The dependent variables consisted of daily logarithmic returns and trends. The mean-squared error for regression, area under the receiver operating characteristic curve, and classification accuracy were used to evaluate model performance, and the statistical significance of the forecasting results was tested using paired t-tests. Experiments indicate that the FSA algorithm increased the performance of ML models, regardless of problem type. The FSA hybrid models showed better performance and outperformed the other BOR models on seven of the 10 datasets for regression and classification. FSA-based models also outperformed Lasso-based models on six of the 10 datasets for regression and four of the 10 datasets for classification. None of the hybrid BOR models outperformed the hybrid FSA models. Lasso-based models, excluding the LR type, were comparable to the best models for six of the 10 datasets for classification. Detailed experimental analysis indicates that the proposed methodology can forecast returns and their movements efficiently and accurately, providing the field with a useful tool for investors.

The Global and Local Patterns of Reading-Related Cognitive and Ecological Variables in Chinese First-Grade Children: A Cross-Sectional Network Analysis.

In the current study, we tested a network model of reading difficulty by using state-of-the-art psychological network analysis. Four hundred and fifty-three Chinese first-grade children (about 38% female, mean age = 7.00, SD = 0.41) were divided into good (n = 154), competent (n = 147), and struggling readers (n = 152) based on their scores of Chinese character reading. The Extended Bayesian Information Criterion graphical lasso (EBICglasso) method was applied to estimate cross-sectional networks for the three groups. Each network included four cognitive nodes (homophone awareness, morphological structure awareness, phonological awareness, and vocabulary) and two ecological nodes (family socioeconomic status and the number of books at home). Chronological age and nonverbal intelligence were also included in the estimated networks. The global (i.e., global structure and global connectivity) and local patterns (i.e., the most important edges and nodes) in each network were reported. The network comparison results showed that global connectivity was significantly lower among struggling readers than for good readers, implying that a holistic impairment of bidirectional connections among multiple variables relates to the difficulty in learning to read. The theoretical and empirical implications and the significance of applying the network approach to reading research are discussed.

A Sparse Beta Regression Model for Network Analysis

For statistical analysis of network data, the β -model has emerged as a useful tool, thanks to its flexibility in incorporating nodewise heterogeneity and theoretical tractability. To generalize the β -model, this paper proposes the Sparse β -Regression Model (S β RM) that unites two research themes developed recently in modelling homophily and sparsity. In particular, we employ differential heterogeneity that assigns weights only to important nodes and propose penalized likelihood with an ℓ 1 penalty for parameter estimation. While our estimation method is closely related to the LASSO method for logistic regression, we develop a new theory emphasizing the use of our model for dealing with a parameter regime that can handle sparse networks usually seen in practice. More interestingly, the resulting inference on the homophily parameter demands no debiasing normally employed in LASSO type estimation. We provide extensive simulation and data analysis to illustrate the use of the model. As a special case of our model, we extend the Erdős-Rényi model by including covariates and develop the associated statistical inference for sparse networks, which may be of independent interest.

Graphical model for mixed data types

With the development of data collection technologies, data types have become more diverse. Additionally, graphical models, as tools for describing variable network relationships, have become increasingly popular in recent years. Previous studies have focused on graphical models tailored to specific types of data. However, these existing methods fail to identify graphical models for mixed data types. The difficulty of constructing graphical models for mixed data types lies in the fact that each type of data has its own space, which challenges the estimation of network relationships in a graphical model when the data are combined. To address this issue, this study presents a novel method that utilizes a vectorization and alignment strategy developed particularly for mixed data types, including scalar, interval-valued, compositional, and functional data, to estimate a graphical model. By iteratively employing a block-sparse graphical lasso method on aligned data, the method can achieve satisfactory results, as shown by numerous simulation experiments. The results also validate the superiority of our proposed method over potential competing methods. Furthermore, this method was applied to an engine damage propagation network as an illustrative example. Our method provides a novel modeling approach for graphical models in the case of mixed data types.

Identifying the mitochondrial ribosomal protein MRPL13 as an oncogenic RBP that promotes proliferation, migration, and anti-apoptotic effects in esophageal cancer cells

PurposeThe correct transcription, processing and function of RNAs are the prerequisites of cell life. RNA-binding proteins (RBPs) are responsible for coordinating the biogenesis of RNA in cells and play a central role in the cellular processes of many diseases. Esophageal cancer (ESCA) is a high incidence of human malignant tumor with a complex molecular mechanism. The purpose of this study was to investigate the important role of RBPs in ESCA. MethodsTCGA-ESCA, IMvigor-210 and GSE53624 repositories were used to obtain esophageal cancer omics data and clinical information. Differential expression analysis, protein-protein interaction and LASSO methods were used to construct the risk signature. Kaplan-Meier and ROC methods were used to analyze the relationship between risk and prognostic. XCell, QUANRISEQ, MCPcounter, EPIC, CIBERSORT, ssGSEA and Estimate algorithm were used to evaluate the abundance of various components of the immune microenvironment. Gene enrichment variation analysis (GSVA) was performed to analyze molecular differences. EdU, transwell and flow cytometry assays were performed to detected proliferation, migration and apoptosis level of ESCA cell lines. ResultsWe visualized the core internal protein-protein interaction of 279 differential expression RBPs, and a 7-RBP risk signature was established. Riskscore was negative correlated with survival time. Meanwhile, high risk groups portend advanced stage, more macrophage and less CD4+ T/master cell infiltration enriched, hyperactive proliferation signal, and different therapeutic response. Finally, we found that RBP MRPL13 is upregulated in esophageal cancer, and its expression is associated with patients’ prognostic. MRPL13 is closely correlated with multiple signaling pathways, as well MRPL13 could promote cell proliferation, migration and anti-apoptosis. ConclusionRNA binding proteins are prognostic marker of esophageal cancer, which could provide clinical diagnosis and treatment strategies. RBP MRPL13 facilitated esophageal cancer progression.

Development of a predictive model for patients with bone metastases referred to palliative radiotherapy: Secondary analysis of a multicenter study (the PRAIS trial).

The decision to administer palliative radiotherapy (RT) to patients with bone metastases (BMs), as well as the selection of treatment protocols (dose, fractionation), requires an accurate assessment of survival expectancy. In this study, we aimed to develop three predictive models (PMs) to estimate short-, intermediate-, and long-term overall survival (OS) for patients in this clinical setting. This study constitutes a sub-analysis of the PRAIS trial, a longitudinal observational study collecting data from patients referred to participating centers to receive palliative RT for cancer-induced bone pain. Our analysis encompassed 567 patients from the PRAIS trial database. The primary objectives were to ascertain the correlation between clinical and laboratory parameters with the OS rates at three distinct time points (short: 3 weeks; intermediate: 24 weeks; prolonged: 52 weeks) and to construct PMs for prognosis. We employed machine learning techniques, comprising the following steps: (i) identification of reliable prognostic variables and training; (ii) validation and testing of the model using the selected variables. The selection of variables was accomplished using the LASSO method (Least Absolute Shrinkage and Selection Operator). The model performance was assessed using receiver operator characteristic curves (ROC) and the area under the curve (AUC). Our analysis demonstrated a significant impact of clinical parameters (primary tumor site, presence of non-bone metastases, steroids and opioid intake, food intake, and body mass index) and laboratory parameters (interleukin 8 [IL-8], chloride levels, C-reactive protein, white blood cell count, and lymphocyte count) on OS. Notably, different factors were associated with the different times for OS with only IL-8 included both in the PMs for short- and long-term OS. The AUC values for ROC curves for 3-week, 24-week, and 52-week OS were 0.901, 0.767, and 0.806, respectively. We successfully developed three PMs for OS based on easily accessible clinical and laboratory parameters for patients referred to palliative RT for painful BMs. While our findings are promising, it is important to recognize that this was an exploratory trial. The implementation of these tools into clinical practice warrants further investigation and confirmation through subsequent studies with separate databases.

Comprehensive evaluation of immunological attributes and immunotherapy responses of positive T cell function regulators in colorectal cancer

BackgroundPositive regulators of T-cell function (PTFRs), integral to T-cell proliferation and activation, have been identified as potential prognostic markers in colorectal cancer (CRC). Despite this, their role within the tumor microenvironment (TME) and their response to immunotherapy are not yet fully understood.MethodsThis study delved into PTFR-related CRC subtypes by analyzing four independent transcriptome datasets, emphasizing the most significant prognostic PTFRs. We identified differentially expressed genes (DEGs) between two subtypes and developed a PTFR risk model using LASSO and Cox regression methods. The model’s associations with survival time, clinical features, TME characteristics, tumor mutation profiles, microsatellite instability (MSI), cancer stem cell (CSC) index, and responses to chemotherapy, targeted therapy, and immunotherapy were subsequently explored.ResultsThe PTFR risk model demonstrated a strong predictive capacity for CRC. It facilitated the estimation of immune cell composition, HLA expression levels, immune checkpoint expression, mutation burden, CSC index features, and the effectiveness of immunotherapy.ConclusionsThis study enhances our understanding of the role of PTFRs in CRC progression and introduces an innovative assessment framework for CRC immunotherapy. This framework improves the prediction of treatment outcomes and aids in the customization of therapeutic strategies.

Risk stratification and overall survival prediction in extensive stage small cell lung cancer after chemotherapy with immunotherapy based on CT radiomics

The prognosis of extensive-stage small cell lung cancer is usually poor. In this study, a combined model based on pre-treatment CT radiomics and clinical features was constructed to predict the OS of extensive-stage small cell lung cancer after chemotherapy with immunotherapy.Clinical data of 111 patients with extensive stage small-cell lung cancer who received first-line immunotherapy combined with chemotherapy in our hospital from December 2019 to December 2021 were retrospectively collected. Finally, 93 patients were selected for inclusion in the study, and CT images were obtained through PACS system before treatment. All patients were randomly divided into a training set (n = 66) and a validation set (n = 27). Images were imported into ITK-SNAP to outline areas of interest, and Python software was used to extract radiomics features. A total of 1781 radiomics features were extracted from each patient’s images. The feature dimensions were reduced by MRMR and LASSO methods, and the radiomics features with the greatest predictive value were screened. The weight coefficient of radiomics features was calculated, and the linear combination of the feature parameters and the weight coefficient was used to calculate Radscore. Univariate cox regression analysis was used to screen out the factors significantly associated with prognosis from the radiomics and clinical features, and multivariate cox regression analysis was performed to establish the prognosis prediction model of extensive stage small cell lung cancer. The degree of metastases was selected as a significant clinical prognostic factor by univariate cox regression analysis. Seven radiomics features with significance were selected by LASSO-COX regression analysis, and the Radscore was calculated according to the coefficient of the radiomics features. An alignment diagram survival prediction model was constructed by combining Radscore with the number of metastatic lesions. The study population was stratified into those who survived less than 11 months, and those with a greater than 11 month survival. The C-index was 0.722 (se = 0.044) and 0.68(se = 0.074) in the training and the validation sets, respectively. The Log_rank test results of the combination model were as follows: training set: p < 0.0001, validation set: p = 0.00042. In this study, a combined model based on radiomics and clinical features could predict OS in patients with extensive stage small cell lung cancer after chemotherapy with immunotherapy, which could help guide clinical treatment strategies.