Predictor Of Survival In Patients Research Articles

A Kernel Attention-based Transformer Model for Survival Prediction of Heart Disease Patients.

Survival analysis is employed to scrutinize time-to-event data, with emphasis on comprehending the duration until the occurrence of a specific event. In this article, we introduce two novel survival prediction models: CosAttnSurv and CosAttnSurv DyACT. CosAttnSurv model leverages transformer-based architecture and a softmax-free kernel attention mechanism for survival prediction. Our second model, CosAttnSurv DyACT, enhances CosAttnSurv with Dynamic Adaptive Computation Time (DyACT) control, optimizing computation efficiency. The proposed models are validated using two public clinical datasets related to heart disease patients. When compared to other state-of-the-art models, our models demonstrated an enhanced discriminative and calibration performance. Furthermore, in comparison to other transformer architecture-based models, our proposed models demonstrate comparable performance while exhibiting significant reduction in both time and memory requirements. Overall, our models offer significant advancements in the field of survival analysis and emphasize the importance of computationally effective time-based predictions, with promising implications for medical decision-making and patient care.

Deep learning-based diagnosis and survival prediction of patients with renal cell carcinoma from primary whole slide images

There is an urgent clinical demand to explore novel diagnostic and prognostic biomarkers for renal cell carcinoma (RCC). We proposed deep learning-based artificial intelligence strategies. The study included 1752 whole slide images from multiple centres. Based on the pixel-level of RCC segmentation, the diagnosis diagnostic model achieved an area under the receiver operating characteristic curve (AUC) of 0.977 (95% CI 0.969-0.984) in the external validation cohort. In addition, our diagnostic model exhibited excellent performance in the differential diagnosis of RCC from renal oncocytoma, which achieved an AUC of 0.951 (0.922-0.972). The graderisk for the recognition of high-grade tumour achieved AUCs of 0.840 (0.805-0.871) in the Cancer Genome Atlas (TCGA) cohort, 0.857 (0.813-0.894) in the Shanghai General Hospital (General) cohort, and 0.894 (0.842-0.933) in the Clinical Proteomic Tumor Analysis Consortium (CPTAC) cohort, for the recognition of high-grade tumour. The OSrisk for predicting 5-year survival status achieved an AUC of 0.784 (0.746-0.819) in the TCGA cohort, which was further verified in the independent general cohort and the CPTAC cohort, with AUCs of 0.774 (0.723-0.820) and 0.702 (0.632-0.765), respectively. Moreover, the competing-risk nomogram (CRN) showed its potential to be a prognostic indicator, with a hazard ratio (HR) of 5.664 (3.893-8.239, p<0.0001), outperforming other traditional clinical prognostic indicators. Kaplan-Meier survival analysis further illustrated that our CRN could significantly distinguish patients with high survival risk. Deep learning-based artificial intelligence could be a useful tool for clinicians to diagnose and predict the prognosis of RCC patients, thus improving the process of individualised treatment.

Comprehensive assessment of postoperative recurrence and survival in patients with cervical cancer

BackgroundThe prediction of postoperative recurrence and survival in cervical cancer patients has been a major clinical challenge. The combination of clinical parameters, inflammatory markers, intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI), and MRI-derived radiomics is expected to support the prediction of recurrence-free survival (RFS), disease-free survival (DFS), tumor-specific survival (CSS), and overall survival (OS) of cervical cancer patients after surgery. MethodsA retrospective analysis of 181 cervical cancer patients with continuous follow-up was completed. The parameters of IVIM-DWI and radiomics were measured, analyzed, and screened. The LASSO regularization was used to calculate the radiomics score (Rad-score). Multivariate Cox regression analysis was used to construct nomogram models for predicting postoperative RFS, DFS, CSS, and OS in cervical cancer patients, with internal and external validation. ResultsClinical stage, parametrial infiltration, internal irradiation, D-value, and Rad-score were independent prognostic factors for RFS; Squamous cell carcinoma antigen, internal irradiation, D-value, f-value and Rad-score were independent prognostic factors for DFS; Maximum tumor diameter, lymph node metastasis, platelets, D-value and Rad-score were independent prognostic factors for CSS; Lymph node metastasis, systemic inflammation response index, D-value and Rad-score were independent prognostic factors for OS. The AUCs of each model predicting RFS, DFS, CSS, and OS at 1, 3, and 5 years were 0.985, 0.929, 0.910 and 0.833, 0.818, 0.816 and 0.832, 0.863, 0.891 and 0.804, 0.812, 0.870, respectively. ConclusionsNomograms based on clinical and imaging parameters showed high clinical value in predicting postoperative RFS, DFS, CSS, and OS of cervical cancer patients and can be used as prognostic markers.

Effect of Plasma Epstein-Barr Virus Nucleic Acid Loads on the Clinical Features and Prognosis in Adult Secondary Hemophagocytic Lymphohistiocytosis

To investigate the effect of pre-treatment plasma Epstein-Barr virus (EBV) DNA copy number on the clinical features and prognosis of patients with adult secondary hemophagocytic lymphohistiocytosis(sHLH). The clinical characteristics, survival rate, and prognostic factors of 171 patients with adult sHLH treated at Jiangsu Province Hospital from June 2017 to January 2022 were retrospectively analyzed in this study. Patients were divided into three groups, including the EBV DNA-negative group(<5.0×102 copies/ml), lower EBV-DNA loads group(5.0×102-8.51×104 copies/ml), and higher EBV-DNA loads group(＞8.51×104 copies/ml), according to pre-treatment plasma EBV-DNA copy number. Cox regression model was established for screening prognostic factors. Adult sHLH survival prediction model was constructed and realized through the nomogram based on EBV-DNA load after adjusted the factors affecting survival of etiology and treatment strategy.Concordance index (C-index) and calibration curves were calculated to verify model predictive and discriminatory capacity. Among 171 adult sHLH patients, 84 patients were not infected with EBV (EBV DNA-negative group), and 87 with EBV (EBV DNA-positive group, 48 lower EBV-DNA loads group and 39 higher EBV-DNA loads group). Consistent elevations in the levels of liver enzymes (ALT and AST), LDH, TG, β 2-microglobulin and ferritin across the increasing of EBV-DNA load (all P <0.05), while the levels of fibrinogen decrease (P <0.001). The median follow-up time was 52 days (range 20-230 days), and 123 patients died. The overall survival (OS) rate of patients in EBV DNA-positive group was lower than that in EBV DNA-negative group (median OS: 40 days vs 118 days, P <0.001). Higher EBV-DNA loads had worse OS (median OS: 24 days vs 45 days vs 118 days, P <0.0001 for trend) compared to lower EBV-DNA loads and EBV DNA-negative group. Multivariate Cox analysis revealed that higher EBV-DNA loads (P =0.005), fibrinogen≤1.5 g/L (P ＝0.012), ferritin (P ＝0.041), associated lymphoma (P ＝0.002), and anti-tumor based strategy (P ＝0.001) were independent prognostic factors for OS. The C-indexes of 30 day, 90 days, 365 days survival rate were all greater than 0.8 of the nomogram model and calibration curves provided credibility to their predictive capability. Subgroup analysis showed that patients with higher EBV-DNA loads had a significantly worse prognosis in adult sHLH who were women, ferritin＞5 000 μg/L, β2-microglobulin＞7.4 mmol/L and regardless of age, etiologies, HScore points. The EBV-DNA load is a strong and independent predictor for survival in patients with sHLH. The prognostic nomogram based on EBV-DNA loads was dependable and provides a visual tool for evaluating the survival of adult sHLH.

Integrating a deep neural network and Transformer architecture for the automatic segmentation and survival prediction in cervical cancer.

Automated tumor segmentation and survival prediction are critical to clinical diagnosis and treatment. This study aimed to develop deep-learning models for automatic tumor segmentation and survival prediction in magnetic resonance imaging (MRI) of cervical cancer (CC) by combining deep neural networks and Transformer architecture. This study included 406 patients with CC, each with comprehensive clinical information and MRI scans. We randomly divided patients into training, validation, and independent test cohorts in a 6:2:2 ratio. During the model training, we employed two architecture types: one being a hybrid model combining convolutional neural network (CNN) and ransformer (CoTr) and one of pure CNNs. For survival prediction, the hybrid model combined tumor image features extracted by segmentation models with clinical information. The performance of the segmentation models was evaluated using the Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95). The performance of the survival models was assessed using the concordance index. The CoTr model performed well in both contrast-enhanced T1-weighted (ceT1W) and T2-weighted (T2W) imaging segmentation tasks, with average DSCs of 0.827 and 0.820, respectively, which outperformed other the CNN models such as U-Net (DSC: 0.807 and 0.808), attention U-Net (DSC: 0.814 and 0.811), and V-Net (DSC: 0.805 and 0.807). For survival prediction, the proposed deep-learning model significantly outperformed traditional methods, yielding a concordance index of 0.732. Moreover, it effectively divided patients into low-risk and high-risk groups for disease progression (P<0.001). Combining Transformer architecture with a CNN can improve MRI tumor segmentation, and this deep-learning model excelled in the survival prediction of patients with CC as compared to traditional methods.

Novel machine-learning prediction tools for overall survival of patients with chondrosarcoma: Based on recursive partitioning analysis.

Chondrosarcoma (CHS), a bone malignancy, poses a significant challenge due to its heterogeneous nature and resistance to conventional treatments. There is a clear need for advanced prognostic instruments that can integrate multiple prognostic factors to deliver personalized survival predictions for individual patients. This study aimed to develop a novel prediction tool based on recursive partitioning analysis (RPA) to improve the estimation of overall survival for patients with CHS. Data from the Surveillance, Epidemiology, and End Results (SEER) database were analyzed, including demographic, clinical, and treatment details of patients diagnosed between 2000 and 2018. Using C5.0 algorithm, decision trees were created to predict survival probabilities at 12, 24, 60, and 120 months. The performance of the models was assessed through confusion scatter plot, accuracy rate, receiver operator characteristic (ROC) curve, and area under ROC curve (AUC). The study identified tumor histology, surgery, age, visceral (brain/liver/lung) metastasis, chemotherapy, tumor grade, and sex as critical predictors. Decision trees revealed distinct patterns for survival prediction at each time point. The models showed high accuracy (82.40%-89.09% in training group, and 82.16%-88.74% in test group) and discriminatory power (AUC: 0.806-0.894 in training group, and 0.808-0.882 in test group) in both training and testing datasets. An interactive web-based shiny APP (URL: https://yangxg1209.shinyapps.io/chondrosarcoma_survival_prediction/) was developed, simplifying the survival prediction process for clinicians. This study successfully employed RPA to develop a user-friendly tool for personalized survival predictions in CHS. The decision tree models demonstrated robust predictive capabilities, with the interactive application facilitating clinical decision-making. Future prospective studies are recommended to validate these findings and further refine the predictive model.

Systemic Inflammatory Markers Can Improve Survival Prediction of Patients with Diffuse Large B-Cell Lymphoma: Model Development and Evaluation

To establish a model to predict the overall survival (OS) rate of patients with diffuse large B-cell lymphoma (DLBCL) based on systemic inflammatory indicators, and study whether the new model combined with inflammatory related parameters is more effective than the conventional model using only clinical factors to predict the OS of patients with DLBCL. The clinical data of 213 patients with DLBCL were analyzed retrospectively. Backward stepwise Cox regression analysis was used to screen independent prognostic factors related to OS, and a nomogram for predicting OS was constructed based on these factors. Akaike information criterion (AIC) and Bayesian information criterion (BIC) were used to evaluate the fitting of the model, the consistency index (C-index), area under receiver operating characteristic (ROC) curve (AUC) and calibration curve were used to evaluate the prediction accuracy of nomogram, and decision curve analysis (DCA) and Kaplan Meier curve were used to evaluate the clinical practicability of nomogram. Multivariate analysis confirmed that age, ECOG PS score, serum lactate dehydrogenase (LDH) level, systemic immune inflammatory index (SII), and prognostic nutritional index (PNI) were used to construct the nomogram. The AIC and BIC of the nomogram were lower than the International Prognostic Index (IPI) and the National Comprehensive Cancer Network (NCCN)-IPI, indicating that the nomogram had better goodness of fit. The C-index and AUC of the nomogram were higher than IPI and NCCN-IPI, indicating that the prediction accuracy of the nomogram had been significantly improved, and the calibration curve showed that the prediction results were in good agreement with the actual survival results. DCA showed that the nomogram had better clinical net income. Kaplan Meier curve showed that patients could be well divided into low-risk, medium-risk and high-risk groups according to the nomogram score (P < 0.001). The nomogram combined with inflammatory indicators can accurately predict the individual survival probability of DLBCL patients.

The Revised Trauma Score: A Better Early Predictor for Survival of Head Trauma Patients than the Glasgow Coma Scale-Age-Pressure Score

Purpose: Trauma is a common cause of death worldwide and head injury is the most common form of trauma presented at the Emergency Department. Physiological scores are better for predicting outcome than anatomical scores. To reduce mortality rates, this study compared the capacity of the revised trauma scores (RTS) and the Glasgow coma scale- age- pressure (GAP) scores to predict the survival of patients and effectively channel resources.Methods: An observational study of head trauma patients aged 12 to 80 years was performed at a tertiary care center (N = 500). We noted demographic information, RTS and GAP trauma scores, and outcomes in terms of mortality or survival at 24 hours, 48 hours, and 7 days.Results: Of the 500 patients who were enrolled, 414 (82.8%) survived 24 hours, 373 (74.6%) survived 48 hours, and 265 (53%) survived after 7 days. Using the Receiver Operating Characteristic curve, the RTS score was a significantly better predictor of survival in patients with head trauma than the GAP score at 24 hours (p = 0.044) and 48 hours (p = 0.049) of admission. The results were not significantly different at 7 days (p = 0.240). Mortality or survival outcomes were not significantly different between the RTS and GAP scores (p = 0.373).Conclusion: RTS appears to be a better early predictor for mortality (within 48 hours of admission) than the GAP score. The RTS was more effective in directing the triage of patients which improved survival rates in head trauma patients.

Hemoglobin, albumin, lymphocytes and platelets (HALP) score as a predictor of survival in patients with glioblastoma (GBM)

BackgroundWe aimed to investigate whether the HALP score was a predictor of survival in patients with Glioblastoma (GBM).MethodsA total of 84 Glioblastoma (GBM) patients followed in our clinic were included in the study. HALP scores were calculated using the preoperative hemoglobin, albumin, lymphocyte and platelet results of the patients. For the HALP score, a cut-off value was found by examining the area below the receiver operating characteristic (ROC) curve. Patients were divided into two groups as low and high according to this cut-off value. The relationships among the clinical, dermographic and laboratory parameters of the patients were examined using these two groups.ResultsMedian OS, PFS, HALP score, NLR, PLR were 15 months (1.0–78.0), 8 months (1.0–66.0), 37.39 ± 23.84 (min 6.00-max 132.31), 4.14, 145.07 respectively. A statistically significant correlation was found between HALP score and OS, PFS, NLR, PLR, ECOG-PS status using Spearman’s rho test (p = 0.001, p < 0.001, p < 0.001, p < 0.001, p = 0.026 respectively). For the HALP score, a cut-off value of = 37.39 (AUC = 0.698, 95% CI, p < 0.002) was found using ROC analysis. Median OS was 12 (6.99–17.01) months in the low HALP group and 21 (11.37–30.63) months in the high HALP group (p = 0.117). NLR and PLR were significantly lower in the HALP high group (p < 0.001, p < 0.001 respectively). The ratio of receiving treatment was significantly higher in the high HALP group (p < 0.05). In Multivariate analysis, significant results were found for treatment status and ECOG-PS status (p < 0.001, p = 0.038 respectively).ConclusionsThe HALP score measured at the beginning of treatment seems to have predictive importance in the prognosis of GBM patients. A HALP score of > 37.39 was associated with prolonged survival in high-grade brain tumors.

Ubiquitin-Specific Protease 52 as a Prognostic Biomarker Correlates with Tumor Microenvironment and Therapy Response in Colorectal Cancer

Introduction: As the primary members of the deubiquitinase family, ubiquitin-specific proteases can regulate the efficacy of immunotherapy and mediate immune evasion. However, further research is needed to explore the influence of USP52 on the prognosis of colorectal cancer (CRC), the tumor immune microenvironment, and therapeutic response. Methods: The differential expression of USP52 between CRC and normal tissues was analyzed using multiple public databases. The relationship between USP52 with the prognosis and clinicopathological characteristics of CRC patients was evaluated, and a nomogram was constructed to predict patient survival based on USP52 expression. Subsequently, gene set variation analysis (GSVA) was used to explore the potential biological functions of USP52 in CRC. The impact of USP52 on the tumor microenvironment (TME) was estimated. Moreover, the effect of USP52 on the response to immunotherapy and chemotherapeutic drugs in CRC was investigated. Finally, the correlation between tumor mutation burden (TMB)/microsatellite instability (MSI) status and USP52 was explored. Results: The expression of USP52 was markedly upregulated in CRC, correlating with a poor prognosis in patients. GSVA uncovered a strong association between high USP52 and immune suppression. Furthermore, high USP52 was found to be correlated with a non-inflamed TME, resulting in reduced immune cell infiltration levels. Additionally, it was observed that patients with high USP52 exhibited low sensitivity to both immunotherapy and chemotherapeutic drugs. Lastly, high USP52 was negatively associated with high TMB and MSI. Conclusion: This study revealed the significance of USP52 in TME, efficacy of therapy, and clinical prognosis in CRC, offering novel insights for the therapeutic advancements in CRC.

Minimum number of lymph nodes to maximize survival in non-metastatic appendiceal adenocarcinoma

IntroductionIn non-metastatic appendiceal adenocarcinoma, the relationship between the number of lymph nodes harvested and overall survival is unknown. The objective of this study was to determine whether the number of lymph nodes harvested impacts survival in patients with mucinous and non-mucinous appendiceal cancer. MethodsRetrospective cohort analysis was conducted in patients who underwent surgery for appendiceal adenocarcinoma in the SEER database from 2000–2019. Exclusion criteria included patients without the number of regional nodes harvested/node positivity, missing survival data, stage IV disease, and certain subtypes of appendiceal tumors. The primary outcome was 10-year overall survival. ResultsA total of 1651 patients were identified, 1101 with mucinous and 550 with non-mucinous cancer. The majority of patients were male (54 %) and between the ages of 50–74 (52 %). Mean ± SD number of lymph nodes harvested was 17.04 ± 10.41. The ten-year survival rates for patients with mucinous appendiceal cancer were 43–74 % and 25–68 % for non-mucinous cancer, depending on AJCC stage. Multivariate Cox-regression analysis displayed that the number of lymph nodes harvested was an independent predictor of survival (p < 0.0001). The optimal threshold predicted by Cox-regression for maximal survival benefit was harvest of a minimum of 15 nodes for mucinous and 12 for non-mucinous cancer. Additionally, for mucinous cancer, per each additional 3 nodes harvested past 15, the 10-year risk of mortality decreased by 7 % (HR 0.93 (0.88 to 0.98), p < 0.001). ConclusionsThe number of lymph nodes harvested is an independent predictor of survival for patients with appendiceal adenocarcinoma. To maximize this survival benefit, a minimum of 15 regional lymph nodes must be harvested for mucinous and 12 for non-mucinous cancer.

Investigating the effects of artificial intelligence on the personalization of breast cancer management: a systematic study

BackgroundProviding appropriate specialized treatment to the right patient at the right time is considered necessary in cancer management. Targeted therapy tailored to the genetic changes of each breast cancer patient is a desirable feature of precision oncology, which can not only reduce disease progression but also potentially increase patient survival. The use of artificial intelligence alongside precision oncology can help physicians by identifying and selecting more effective treatment factors for patients.MethodA systematic review was conducted using the PubMed, Embase, Scopus, and Web of Science databases in September 2023. We performed the search strategy with keywords, namely: Breast Cancer, Artificial intelligence, and precision Oncology along with their synonyms in the article titles. Descriptive, qualitative, review, and non-English studies were excluded. The quality assessment of the articles and evaluation of bias were determined based on the SJR journal and JBI indices, as well as the PRISMA2020 guideline.ResultsForty-six studies were selected that focused on personalized breast cancer management using artificial intelligence models. Seventeen studies using various deep learning methods achieved a satisfactory outcome in predicting treatment response and prognosis, contributing to personalized breast cancer management. Two studies utilizing neural networks and clustering provided acceptable indicators for predicting patient survival and categorizing breast tumors. One study employed transfer learning to predict treatment response. Twenty-six studies utilizing machine-learning methods demonstrated that these techniques can improve breast cancer classification, screening, diagnosis, and prognosis. The most frequent modeling techniques used were NB, SVM, RF, XGBoost, and Reinforcement Learning. The average area under the curve (AUC) for the models was 0.91. Moreover, the average values for accuracy, sensitivity, specificity, and precision were reported to be in the range of 90-96% for the models.ConclusionArtificial intelligence has proven to be effective in assisting physicians and researchers in managing breast cancer treatment by uncovering hidden patterns in complex omics and genetic data. Intelligent processing of omics data through protein and gene pattern classification and the utilization of deep neural patterns has the potential to significantly transform the field of complex disease management.

A study predicting long-term survival capacity in postoperative advanced gastric cancer patients based on MAOA and subcutaneous muscle fat characteristics

BackgroundThe prognosis of advanced gastric cancer (AGC) is relatively poor, and long-term survival depends on timely intervention. Currently, predicting survival rates remains a hot topic. The application of radiomics and immunohistochemistry-related techniques in cancer research is increasingly widespread. However, their integration for predicting long-term survival in AGC patients has not been fully explored.MethodsWe Collected 150 patients diagnosed with AGC at the Affiliated Zhongshan Hospital of Dalian University who underwent radical surgery between 2015 and 2019. Following strict inclusion and exclusion criteria, 90 patients were included in the analysis. We Collected postoperative pathological specimens from enrolled patients, analyzed the expression levels of MAOA using immunohistochemical techniques, and quantified these levels as the MAOAHScore. Obtained plain abdominal CT images from patients, delineated the region of interest at the L3 vertebral body level, and extracted radiomics features. Lasso Cox regression was used to select significant features to establish a radionics risk score, convert it into a categorical variable named risk, and use Cox regression to identify independent predictive factors for constructing a clinical prediction model. ROC, DCA, and calibration curves validated the model’s performance.ResultsThe enrolled patients had an average age of 65.71 years, including 70 males and 20 females. Multivariate Cox regression analysis revealed that risk (P = 0.001, HR = 3.303), MAOAHScore (P = 0.043, HR = 2.055), and TNM stage (P = 0.047, HR = 2.273) emerged as independent prognostic risk factors for 3-year overall survival (OS) and The Similar results were found in the analysis of 3-year disease-specific survival (DSS). The nomogram developed could predict 3-year OS and DSS rates, with areas under the ROC curve (AUCs) of 0.81 and 0.797, respectively. Joint calibration and decision curve analyses (DCA) confirmed the nomogram’s good predictive performance and clinical utility.ConclusionIntegrating immunohistochemistry and muscle fat features provides a more accurate prediction of long-term survival in gastric cancer patients. This study offers new perspectives and methods for a deeper understanding of survival prediction in AGC.

MGPPI: multiscale graph neural networks for explainable protein-protein interaction prediction.

Protein-Protein Interactions (PPIs) involves in various biological processes, which are of significant importance in cancer diagnosis and drug development. Computational based PPI prediction methods are more preferred due to their low cost and high accuracy. However, existing protein structure based methods are insufficient in the extraction of protein structural information. Furthermore, most methods are less interpretable, which hinder their practical application in the biomedical field. In this paper, we propose MGPPI, which is a Multiscale graph convolutional neural network model for PPI prediction. By incorporating multiscale module into the Graph Neural Network (GNN) and constructing multi convolutional layers, MGPPI can effectively capture both local and global protein structure information. For model interpretability, we introduce a novel visual explanation method named Gradient Weighted interaction Activation Mapping (Grad-WAM), which can highlight key binding residue sites. We evaluate the performance of MGPPI by comparing with state-of-the-arts methods on various datasets. Results shows that MGPPI outperforms other methods significantly and exhibits strong generalization capabilities on the multi-species dataset. As a practical case study, we predicted the binding affinity between the spike (S) protein of SARS-COV-2 and the human ACE2 receptor protein, and successfully identified key binding sites with known binding functions. Key binding sites mutation in PPIs can affect cancer patient survival statues. Therefore, we further verified Grad-WAM highlighted residue sites in separating patients survival groups in several different cancer type datasets. According to our results, some of the highlighted residues can be used as biomarkers in predicting patients survival probability. All these results together demonstrate the high accuracy and practical application value of MGPPI. Our method not only addresses the limitations of existing approaches but also can assists researchers in identifying crucial drug targets and help guide personalized cancer treatment.

Skeletal Muscle Index-Based Cachexia Index as a Predictor of Prognosis in Patients With Cancer: A Meta-Analysis and Systematic Review.

Cachexia is associated with poor survival rates. In the clinical setting, the diagnosis of cancer cachexia is challenging. The cachexia index (CXI), a new index for predicting survival time, is a promising tool for diagnosing cancer cachexia; however, its efficacy in predicting patient survival has not been validated. This meta-analysis and systematic review aimed to explore the CXI's prognostic value in patients with cancer. The PubMed, Embase, MEDLINE, and Cochrane Library databases were searched for relevant studies to determine the association between CXI findings and prognosis. The outcomes were overall survival (OS), progression-, disease-, and recurrence-free survival (PFS/DFS/RFS) rates, and the rate of complete response. The QUality In Prognostic Studies (QUIPS) tool was used to evaluate the quality of the included trials. This meta-analysis comprised 14 studies involving 2777 patients. A low CXI was associated with decreased OS (hazard ratio [HR] 2.34, 95% confidence interval [CI] 2.01-2.72; P < .001), PFS/DFS/RFS (HR 1.93, 95% CI 1.68-2.22; P < .001), and complete response (odds ratio [OR] 0.49, 95% CI 0.36-0.66; P < .001). Patients with a low CXI had a lower body mass index (mean difference [MD] -0.75, 95% CI -1.00 to 0.50; P < .001), skeletal muscle index (standardized MD -0.80, 95% CI -0.98 to -0.61; P < .001), and serum albumin level (MD -0.23, 95% CI -0.26 to -0.20; P < .001); and a higher neutrophil-lymphocyte ratio (MD 1.88, 95% CI 1.29-2.47; P < .001) and more advanced disease stages (OR 0.80, 95% CI 0.71-0.91; P = .001). A low CXI was found to be associated with poor survival in patients with cancer. While the CXI is a promising marker for predicting cancer cachexia, further studies are required to verify its usefulness.

Neutrophil PAD4 Expression and Its Pivotal Role in Assessment of Alcohol-Related Liver Disease.

Neutrophils release neutrophil extracellular traps (NETs) as a defense strategy in response to broad-spectrum infections and sterile triggers. NETs consist of a DNA scaffold decorated with antimicrobial peptides (AMPs) and enzymatically active proteases, including peptidyl arginine deiminase type 4 (PAD4). Susceptibility to infections and inflammatory dysregulation are hallmarks of alcohol-related liver disease (ALD). Sixty-two patients with ALD were prospectively recruited, and they were followed for 90 days. Twenty-four healthy volunteers served as the control group. PAD4 concentrations were quantified using immunoenzymatic ELISAs. Correlation coefficients between PAD4 blood concentrations and markers of systemic inflammation; liver dysfunction severity scores; and ALD complications were calculated. The receiver operating curves (ROCs) and their areas under the curve (AUCs) were checked in order to assess the accuracy of PAD4 expression in predicting the degree of liver failure and the development of ALD complications. Systemic concentrations of PAD4 were significantly increased in the patients with ALD in comparison with controls. PAD4 levels correlated with the standard markers of inflammation and revealed a good predictive AUC (0.76) for survival in the whole ALD group. PAD4 seems to be an inflammatory mediator and may be potentially applied as a predictor of patient survival in ALD.

The role of biomarkers and dosimetry parameters in overall and progression free survival prediction for patients treated with personalized 90Y glass microspheres SIRT: a preliminary machine learning study

BackgroundOverall Survival (OS) and Progression-Free Survival (PFS) analyses are crucial metrics for evaluating the efficacy and impact of treatment. This study evaluated the role of clinical biomarkers and dosimetry parameters on survival outcomes of patients undergoing 90Y selective internal radiation therapy (SIRT).Materials/MethodsThis preliminary and retrospective analysis included 17 patients with hepatocellular carcinoma (HCC) treated with 90Y SIRT. The patients underwent personalized treatment planning and voxel-wise dosimetry. After the procedure, the OS and PFS were evaluated. Three structures were delineated including tumoral liver (TL), normal perfused liver (NPL), and whole normal liver (WNL). 289 dose-volume constraints (DVCs) were extracted from dose-volume histograms of physical and biological effective dose (BED) maps calculated on 99mTc-MAA and 90Y SPECT/CT images. Subsequently, the DVCs and 16 clinical biomarkers were used as features for univariate and multivariate analysis. Cox proportional hazard ratio (HR) was employed for univariate analysis. HR and the concordance index (C-Index) were calculated for each feature. Using eight different strategies, a cross-combination of various models and feature selection (FS) methods was applied for multivariate analysis. The performance of each model was assessed using an averaged C-Index on a three-fold nested cross-validation framework. The Kaplan-Meier (KM) curve was employed for univariate and machine learning (ML) model performance assessment.ResultsThe median OS was 11 months [95% CI: 8.5, 13.09], whereas the PFS was seven months [95% CI: 5.6, 10.98]. Univariate analysis demonstrated the presence of Ascites (HR: 9.2[1.8,47]) and the aim of SIRT (segmentectomy, lobectomy, palliative) (HR: 0.066 [0.0057, 0.78]), Aspartate aminotransferase (AST) level (HR:0.1 [0.012–0.86]), and MAA-Dose-V205(%)-TL (HR:8.5[1,72]) as predictors for OS. 90Y-derived parameters were associated with PFS but not with OS. MAA-Dose-V205(%)-WNL, MAA-BED-V400(%)-WNL with (HR:13 [1.5–120]) and 90Y-Dose-mean-TL, 90Y-D50-TL-Gy, 90Y-Dose-V205(%)-TL, 90Y-Dose- D50-TL-Gy, and 90Y-BED-V400(%)-TL (HR:15 [1.8–120]) were highly associated with PFS among dosimetry parameters. The highest C-index observed in multivariate analysis using ML was 0.94 ± 0.13 obtained from Variable Hunting-variable-importance (VH.VIMP) FS and Cox Proportional Hazard model predicting OS, using clinical features. However, the combination of VH. VIMP FS method with a Generalized Linear Model Network model predicting OS using Therapy strategy features outperformed the other models in terms of both C-index and stratification of KM curves (C-Index: 0.93 ± 0.14 and log-rank p-value of 0.023 for KM curve stratification).ConclusionThis preliminary study confirmed the role played by baseline clinical biomarkers and dosimetry parameters in predicting the treatment outcome, paving the way for the establishment of a dose-effect relationship. In addition, the feasibility of using ML along with these features was demonstrated as a helpful tool in the clinical management of patients, both prior to and following 90Y-SIRT.

Predictive modeling of gene mutations for the survival outcomes of epithelial ovarian cancer patients.

Epithelial ovarian cancer (EOC) has a low overall survival rate, largely due to frequent recurrence and acquiring resistance to platinum-based chemotherapy. EOC with homologous recombination (HR) deficiency has increased sensitivity to platinum-based chemotherapy because platinum-induced DNA damage cannot be repaired. Mutations in genes involved in the HR pathway are thought to be strongly correlated with favorable response to treatment. Patients with these mutations have better prognosis and an improved survival rate. On the other hand, mutations in non-HR genes in EOC are associated with increased chemoresistance and poorer prognosis. For this reason, accurate predictions in response to treatment and overall survival remain challenging. Thus, analyses of 360 EOC cases on NCI's The Cancer Genome Atlas (TCGA) program were conducted to identify novel gene mutation signatures that were strongly correlated with overall survival. We found that a considerable portion of EOC cases exhibited multiple and overlapping mutations in a panel of 31 genes. Using logistical regression modeling on mutational profiles and patient survival data from TCGA, we determined whether specific sets of deleterious gene mutations in EOC patients had impacts on patient survival. Our results showed that six genes that were strongly correlated with an increased survival time are BRCA1, NBN, BRIP1, RAD50, PTEN, and PMS2. In addition, our analysis shows that six genes that were strongly correlated with a decreased survival time are FANCE, FOXM1, KRAS, FANCD2, TTN, and CSMD3. Furthermore, Kaplan-Meier survival analysis of 360 patients stratified by these positive and negative gene mutation signatures corroborated that our regression model outperformed the conventional HR genes-based classification and prediction of survival outcomes. Collectively, our findings suggest that EOC exhibits unique mutation signatures beyond HR gene mutations. Our approach can identify a novel panel of gene mutations that helps improve the prediction of treatment outcomes and overall survival for EOC patients.

A comprehensive meta-analysis of tissue resident memory T cells and their roles in shaping immune microenvironment and patient prognosis in non-small cell lung cancer.

Tissue-resident memory T cells (TRM) are a specialized subset of long-lived memory T cells that reside in peripheral tissues. However, the impact of TRM-related immunosurveillance on the tumor-immune microenvironment (TIME) and tumor progression across various non-small-cell lung cancer (NSCLC) patient populations is yet to be elucidated. Our comprehensive analysis of multiple independent single-cell and bulk RNA-seq datasets of patient NSCLC samples generated reliable, unique TRM signatures, through which we inferred the abundance of TRM in NSCLC. We discovered that TRM abundance is consistently positively correlated with CD4+ T helper 1 cells, M1 macrophages, and resting dendritic cells in the TIME. In addition, TRM signatures are strongly associated with immune checkpoint and stimulatory genes and the prognosis of NSCLC patients. A TRM-based machine learning model to predict patient survival was validated and an 18-gene risk score was further developed to effectively stratify patients into low-risk and high-risk categories, wherein patients with high-risk scores had significantly lower overall survival than patients with low-risk. The prognostic value of the risk score was independently validated by the Cancer Genome Atlas Program (TCGA) dataset and multiple independent NSCLC patient datasets. Notably, low-risk NSCLC patients with higher TRM infiltration exhibited enhanced T-cell immunity, nature killer cell activation, and other TIME immune responses related pathways, indicating a more active immune profile benefitting from immunotherapy. However, the TRM signature revealed low TRM abundance and a lack of prognostic association among lung squamous cell carcinoma patients in contrast to adenocarcinoma, indicating that the two NSCLC subtypes are driven by distinct TIMEs. Altogether, this study provides valuable insights into the complex interactions between TRM and TIME and their impact on NSCLC patient prognosis. The development of a simplified 18-gene risk score provides a practical prognostic marker for risk stratification.

The Effect of PET/CT-Derived Parameters on the Prediction of Survival in Lung Cancer Patients

Background: The ability to predict the survival of patients with non-small cell lung cancer (NSCLC) can provide a basis for individualized treatment and follow-up. Determination of positron emission tomography/computed tomography (PET/CT) parameters, i.e., maximum standardized uptake value (SUVmax), mean standardized uptake value (SUVmean), metabolic tumor volume (MTV), and total lesion glycolysis (TLG), may improve predictions of survival for NSCLC patients. Objectives: To determine the relationship between the PET/CT-derived parameters SUVmax, SUVmean, MTV, and TLG and survival in NSCLC patients. Patients and Methods: Patients with NSCLC diagnosed at our clinic between January 2019 and October 2020 were evaluated retrospectively using data obtained from the electronic database. The study population consisted of 132 patients over 18 years of age who had a PET/CT scan before receiving any treatment for NSCLC. During their initial PET/CT evaluation, SUVmax, SUVmean, MTV, and TLG were calculated. Correlations between the variables were analyzed using Spearman’s correlation test, and the associations of the variables with patient survival were determined using the Cox proportional hazards regression model. Results: The overall 2-year survival rate of the patients was 36.6%. In the univariate analysis, MTV and TLG, but not SUVmax or SUVmean, were significantly associated with survival (P = 0.8, P = 0.003, and P = 0.045, respectively). In the multivariate analysis, MTV was related to a higher risk of death in patients with adenocarcinoma, lymph node involvement, or distant metastasis. By contrast, TLG was associated with a lower risk of death in patients with adenocarcinoma (ACA) or distant metastasis. Conclusion: Among the parameters obtained in PET/CT studies, SUVmax and SUVmean were not related to the survival of patients with NSCLC. However, MTV was associated with a higher risk of death, while TLG was associated with a lower risk of death in patients with adenocarcinoma or distant metastasis. Further studies with larger samples are needed to validate these results.