scholarly journals A non-lab nomogram of survival prediction in home hospice care patients with gastrointestinal cancer

2020 ◽  
Vol 19 (1) ◽  
Author(s):  
Muqing Wang ◽  
Xubin Jing ◽  
Weihua Cao ◽  
Yicheng Zeng ◽  
Chaofen Wu ◽  
...  
Keyword(s):  
Survival Time ◽  
Gastrointestinal Cancer ◽  
Hospice Care ◽  
Cox Regression ◽  
Karnofsky Performance Status ◽  
Training Dataset ◽  
Survival Prediction ◽  
Testing Dataset ◽  
Home Based ◽  
Home Hospice Care

Abstract Background Patients suffering from gastrointestinal cancer comprise a large group receiving home hospice care in China, however, little is known about the prediction of their survival time. This study aimed to develop a gastrointestinal cancer-specific non-lab nomogram predicting survival time in home-based hospice. Methods We retrospectively studied the patients with gastrointestinal cancer from a home-based hospice between 2008 and 2018. General baseline characteristics, disease-related characteristics, and related assessment scale scores were collected from the case records. The data were randomly split into a training set (75%) for developing a predictive nomogram and a testing set (25%) for validation. A non-lab nomogram predicting the 30-day and 60-day survival probability was created using the least absolute shrinkage and selection operator (LASSO) Cox regression. We evaluated the performance of our predictive model by means of the area under receiver operating characteristic curve (AUC) and calibration curve. Results A total of 1618 patients were included and divided into two sets: 1214 patients (110 censored) as training dataset and 404 patients (33 censored) as testing dataset. The median survival time for overall included patients was 35 days (IQR, 17–66). The 5 most significant prognostic variables were identified to construct the nomogram among all 28 initial variables, including Karnofsky Performance Status (KPS), abdominal distention, edema, quality of life (QOL), and duration of pain. In training dataset validation, the AUC at 30 days and 60 days were 0.723 (95% CI, 0.694–0.753) and 0.733 (95% CI, 0.702–0.763), respectively. Similarly, the AUC value was 0.724 (0.673–0.774) at 30 days and 0.725 (0.672–0.778) at 60 days in the testing dataset validation. Further, the calibration curves revealed good agreement between the nomogram predictions and actual observations in both the training and testing dataset. Conclusion This non-lab nomogram may be a useful clinical tool. It needs prospective multicenter validation as well as testing with Chinese clinicians in charge of hospice patients with gastrointestinal cancer to assess acceptability and usability.

scholarly journals Weighted Gene Co-expression Network Analysis Identified a Novel Thirteen-Gene Signature Associated With Progression, Prognosis, and Immune Microenvironment of Colon Adenocarcinoma Patients

2021 ◽  
Vol 12 ◽  
Author(s):  
Cangang Zhang ◽  
Zhe Zhao ◽  
Haibo Liu ◽  
Shukun Yao ◽  
Dongyan Zhao
Keyword(s):  
Network Analysis ◽  
Cox Regression ◽  
Colon Adenocarcinoma ◽  
Gene Signature ◽  
Training Dataset ◽  
Migration And Invasion ◽  
Overlapping Genes ◽  
Characteristic Analysis ◽  
Cox Regression Analysis ◽  
Testing Dataset

Colon adenocarcinoma (COAD) is one of the most common malignant tumors and has high migration and invasion capacity. In this study, we attempted to establish a multigene signature for predicting the prognosis of COAD patients. Weighted gene co-expression network analysis and differential gene expression analysis methods were first applied to identify differentially co-expressed genes between COAD tissues and normal tissues from the Cancer Genome Atlas (TCGA)-COAD dataset and GSE39582 dataset, and a total of 309 overlapping genes were screened out. Then, our study employed TCGA-COAD cohort as the training dataset and an independent cohort by merging the GES39582 and GSE17536 datasets as the testing dataset. After univariate and multivariate Cox regression analyses were performed for these overlapping genes and overall survival (OS) of COAD patients in the training dataset, a 13-gene signature was constructed to divide COAD patients into high- and low-risk subgroups with significantly different OS. The testing dataset exhibited the same results utilizing the same predictive signature. The area under the curve of receiver operating characteristic analysis for predicting OS in the training and testing datasets were 0.789 and 0.868, respectively, which revealed the enhanced predictive power of the signature. Multivariate Cox regression analysis further suggested that the 13-gene signature could independently predict OS. Among the 13 prognostic genes, NAT1 and NAT2 were downregulated with deep deletions in tumor tissues in multiple COAD cohorts and exhibited significant correlations with poorer OS based on the GEPIA database. Notably, NAT1 and NAT2 expression levels were positively correlated with infiltrating levels of CD8+ T cells and dendritic cells, exhibiting a foundation for further research investigating the antitumor immune roles played by NAT1 and NAT2 in COAD. Taken together, the results of our study showed that the 13-gene signature could efficiently predict OS and that NAT1 and NAT2 could function as biomarkers for prognosis and the immune response in COAD.

Identification of a Methylation-Driven Gene Panel for Survival Prediction in Colon Cancer

2020 ◽  
Author(s):  
Yaojun Peng ◽  
Jing Zhao ◽  
Fan Yin ◽  
Gaowa Sharen ◽  
Qiyan Wu ◽  
...  
Keyword(s):  
Dna Methylation ◽  
Colon Cancer ◽  
Cancer Patients ◽  
Cell Lines ◽  
Cox Regression ◽  
Gene Panel ◽  
Tnm Stage ◽  
Training Dataset ◽  
Survival Prediction ◽  
Analysis Tool

Abstract Background: Prediction and improvement of prognosis is important for effective clinical management of colon cancer patients. Accumulation of a variety of genetic as well as epigenetic changes in colon epithelial cells has been identified as one of the fundamental processes that drive the initiation and progression of colon cancer. This study aimed to explore functional genes regulated by DNA methylation and the potential of these DNA methylation changes to become biomarkers predictive of colon cancer prognosis.Methods: Methylation-driven genes (MDGs) were explored by applying an integrative analysis tool (MethylMix) to The Cancer Genome Atlas (TCGA) colon cancer project. TCGA colon cancer patients with available survival information (n=281) were randomly divided into training dataset (50%) for model construction and testing dataset (50%) for model validation. The prognostic MDG panel was identified in the training dataset by combining the Cox regression model with the least absolute shrinkage and selection operator regularization, a widely used approach to penalize the effect of multicollineatity. GSEA was employed to determine functional pathways associated with the prognostic 6-MDG panel. CD40 expression and methylation in colon cancer samples were also examined in datasets (expression profile [GSE8671] and methylation profile [GSE42752]) from Gene Expression Omnibus. Experimental confirmation of DNA methylation in colon cancer cell lines was performed using methylation specific PCR and bisulfite sequencing.Results: We identified and internal validated a prognostic methylation-driven gene panel consisting of six gene members (TMEM88, HOXB2, FGD1, TOGARAM1, ARHGDIB and CD40). High risk phenotype classified by the 6-MDGs panel was associated with cancer-related biological processes, including invasion and metastasis, angiogenesis and tumor immune microenvironment, among others. The prognostic value of the 6-MDGs panel was independent of TNM stage, and its combination with TNM stage and age could help improve survival prediction of colon cancer patients. Additionally, we validated that the expression of CD40 was regulated by promoter region methylation in colon cancer samples and cell lines. Conclusions: The proposed 6-MDGs panel represents a promising signature for estimating overall survival in patients with colon cancer.

Palliative Performance Scale Score at 1 Week After Palliative Care Unit Admission is More Useful for Survival Prediction in Patients With Advanced Cancer in South Korea

2018 ◽  
Vol 35 (9) ◽  
pp. 1168-1173 ◽  
Author(s):  
Seok-Joon Yoon ◽  
Sung-Eun Choi ◽  
Thomas W. LeBlanc ◽  
Sang-Yeon Suh
Keyword(s):  
Palliative Care ◽  
South Korea ◽  
Survival Time ◽  
Advanced Cancer ◽  
Cox Regression ◽  
Prognostic Index ◽  
Palliative Care Unit ◽  
Survival Prediction ◽  
Performance Scale ◽  
Over Time

Background: The Palliative Performance Scale (PPS) is a useful prognostic index in palliative care. Changes in PPS score over time may add useful prognostic information beyond a single measurement. Objective: To investigate the usefulness of repeated PPS measurement to predict survival time of inpatients with advanced cancer admitted to a palliative care unit (PCU) in South Korea. Design: Prospective observational cohort study. Setting/Patients: 138 patients with advanced cancer admitted to a PCU in a university hospital in South Korea from June 2015 to May 2016. Measurements: The PPS score was measured on enrollment and after 1 week. We used Cox regression analyses to calculate hazard ratios (HRs) to demonstrate the relationship between survival time and the groups categorized by PPS and changes in PPS score, after adjusting for clinical variables. Results: There were significant differences in survival time among 3 groups stratified by PPS (10-20, 30-50, and ≥60) after 1 week. A group with a PPS of 10 to 20 at 1 week had the highest risk (HR: 5.18 [95% confidence interval, 1.57-17.04]) for shortened survival. On the contrary, there were no significant differences among these groups by initial PPS alone. Similarly, change in PPS was prognostic; median survival was 13 (10.96-15.04) days for those whose PPS decreased after 1 week and 27 (10.18-43.82) days for those with stable or increased PPS ( P < .001). Conclusions: Measuring PPS over time can be very helpful for predicting survival in terminally ill patients with cancer, beyond a single PPS measure at PCU admission.

Correlation of Palliative Performance Scale and Survival in Patients With Cancer Receiving Home-Based Palliative Care

2018 ◽  
Vol 33 (2) ◽  
pp. 95-99 ◽  
Author(s):  
Jiaoli Cai ◽  
Denise N. Guerriere ◽  
Hongzhong Zhao ◽  
Peter C. Coyte
Keyword(s):  
Palliative Care ◽  
Survival Time ◽  
Cox Regression ◽  
Care Program ◽  
Survival Times ◽  
Telephone Interviews ◽  
Kaplan Meier ◽  
Home Based ◽  
A Prospective Study ◽  
Performance Scale

The main objective of this study was to examine whether and how the Palliative Performance Scale (PPS), a measure of a patient’s function, was predictive of survival time for those in receipt of home-based palliative care. This was a prospective study, which included 194 cancer patients from November 17, 2013, to August 18, 2015. Data were collected from biweekly telephone interviews with caregivers. Kaplan-Meier survival curves were estimated to assess how survival time was correlated with initial PPS scores after admission to the home-based palliative care program. A multivariate extended Cox regression model was used to examine the association between PPS and survival. The results showed that patients with higher PPS scores, that is, better function, had a lower hazard ratio (0.977; 95% confidence interval: 0.965-0.989) and hence longer survival times. The PPS can be used in predicting survival time for home-based palliative care patients.

scholarly journals Predicting Overall Survival Time in Glioblastoma Patients Using Gradient Boosting Machines Algorithm and Recursive Feature Elimination Technique

Cancers ◽  
2021 ◽  
Vol 13 (19) ◽  
pp. 4976
Author(s):  
Golestan Karami ◽  
Marco Giuseppe Orlando ◽  
Andrea Delli Pizzi ◽  
Massimo Caulo ◽  
Cosimo Del Gratta
Keyword(s):  
Overall Survival ◽  
Survival Time ◽  
Cox Regression ◽  
Feature Selection Method ◽  
Rate Of Change ◽  
Supervised Machine Learning ◽  
Recursive Feature Elimination ◽  
Gradient Boosting ◽  
Survival Prediction ◽  
Classifier Performance

Despite advances in tumor treatment, the inconsistent response is a major challenge among glioblastoma multiform (GBM) that lead to different survival time. Our aim was to integrate multimodal MRI with non-supervised and supervised machine learning methods to predict GBM patients’ survival time. To this end, we identified different compartments of the tumor and extracted their features. Next, we applied Random Forest-Recursive Feature Elimination (RF-RFE) to identify the most relevant features to feed into a GBoost machine. This study included 29 GBM patients with known survival time. RF-RFE GBoost model was evaluated to assess the survival prediction performance using optimal features. Furthermore, overall survival (OS) was analyzed using univariate and multivariate Cox regression analyses, to evaluate the effect of ROIs and their features on survival. The results showed that a RF-RFE Gboost machine was able to predict survival time with 75% accuracy. The results also revealed that the rCBV in the low perfusion area was significantly different between groups and had the greatest effect size in terms of the rate of change of the response variable (survival time). In conclusion, not only integration of multi-modality MRI but also feature selection method can enhance the classifier performance.

scholarly journals Survival after surgery among patients with cholangiocarcinoma in Northeast Thailand according to anatomical and morphological classification

BMC Cancer ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Chaiwat Tawarungruang ◽  
Narong Khuntikeo ◽  
Nittaya Chamadol ◽  
Vallop Laopaiboon ◽  
Jaruwan Thuanman ◽  
...  
Keyword(s):  
Survival Rate ◽  
Survival Time ◽  
Median Survival ◽  
Median Survival Time ◽  
Cox Regression ◽  
Survival Rates ◽  
Care Program ◽  
Tumor Location ◽  
Northeast Thailand ◽  
Curative Surgery

Abstract Background Cholangiocarcinoma (CCA) has been categorized based on tumor location as intrahepatic (ICCA), perihilar (PCCA) or distal (DCCA), and based on the morphology of the tumor of the bile duct as mass forming (MF), periductal infiltrating (PI) or intraductal (ID). To date, there is limited evidence available regarding the survival of CCA among these different anatomical and morphological classifications. This study aimed to evaluate the survival rate and median survival time after curative surgery among CCA patients according to their anatomical and morphological classifications, and to determine the association between these classifications and survival. Methods This study included CCA patients who underwent curative surgery from the Cholangiocarcinoma Screening and Care Program (CASCAP), Northeast Thailand. The anatomical and morphological classifications were based on pathological findings after surgery. Survival rates of CCA and median survival time since the date of CCA surgery and 95% confidence intervals (CI) were calculated. Multiple cox regression was performed to evaluate factors associated with survival which were quantified by hazard ratios (HR) and their 95% CIs. Results Of the 746 CCA patients, 514 had died at the completion of the study which constituted 15,643.6 person-months of data recordings. The incidence rate was 3.3 per 100 patients per month (95% CI: 3.0–3.6), with median survival time of 17.8 months (95% CI: 15.4–20.2), and 5-year survival rate of 24.6% (95% CI: 20.7–28.6). The longest median survival time was 21.8 months (95% CI: 16.3–27.3) while the highest 5-year survival rate of 34.8% (95% CI: 23.8–46.0) occurred in the DCCA group. A combination of anatomical and morphological classifications, PCCA+ID, was associated with the longest median survival time of 40.5 months (95% CI: 17.9–63.0) and the highest 5-year survival rate of 42.6% (95% CI: 25.4–58.9). The ICCA+MF combination was associated with survival (adjusted HR: 1.45; 95% CI: 1.01–2.09; P = 0.013) compared to ICCA+ID patients. Conclusions Among patients receiving surgical treatment, those with PCCA+ID had the highest 5-year survival rate, which was higher than in groups classified by only anatomical characteristics. Additionally, the patients with ICCA+MF tended to have unfavorable surgical outcomes. Showed the highest survival association. Therefore, further investigations into CCA imaging should focus on patients with a combination of anatomical and morphological classifications.

scholarly journals Screening the genome for HCC-specific CpG methylation signatures as biomarkers for diagnosis and prognosis evaluation

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Rui-kun Zhang ◽  
Jia-lin Liu
Keyword(s):  
Cox Regression ◽  
Malignant Tumors ◽  
Gene Expression Omnibus ◽  
The Cancer Genome Atlas ◽  
Survival Prediction ◽  
Training Set ◽  
Cpg Sites ◽  
Diagnosis And Prognosis ◽  
Patient Prognosis ◽  
Prognosis Evaluation

Abstract Background Hepatocellular carcinoma (HCC) is one of the most common and invasive malignant tumors in the world. The change in DNA methylation is a key event in HCC. Methods Methylation datasets for HCC and 17 other types of cancer were downloaded from The Cancer Genome Atlas (TCGA). The CpG sites with large differences in methylation between tumor tissues and paracancerous tissues were identified. We used the HCC methylation dataset downloaded from the TCGA as the training set and removed the overlapping sites among all cancer datasets to ensure that only CpG sites specific to HCC remained. Logistic regression analysis was performed to select specific biomarkers that can be used to diagnose HCC, and two datasets—GSE157341 and GSE54503—downloaded from GEO as validation sets were used to validate our model. We also used a Cox regression model to select CpG sites related to patient prognosis. Results We identified 6 HCC-specific methylated CpG sites as biomarkers for HCC diagnosis. In the training set, the area under the receiver operating characteristic (ROC) curve (AUC) for the model containing all these sites was 0.971. The AUCs were 0.8802 and 0.9711 for the two validation sets from the GEO database. In addition, 3 other CpG sites were analyzed and used to create a risk scoring model for patient prognosis and survival prediction. Conclusions Through the analysis of HCC methylation datasets from the TCGA and Gene Expression Omnibus (GEO) databases, potential biomarkers for HCC diagnosis and prognosis evaluation were ascertained.

scholarly journals A genomic mutation signature predicts the clinical outcomes of immunotherapy and characterizes immunophenotypes in gastrointestinal cancer

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Xi Jiao ◽  
Xin Wei ◽  
Shuang Li ◽  
Chang Liu ◽  
Huan Chen ◽  
...  
Keyword(s):  
Gastrointestinal Cancer ◽  
Prognostic Value ◽  
Cox Regression ◽  
Prognostic Biomarker ◽  
Cancer Center ◽  
Genomic Profile ◽  
Prognostic Signature ◽  
Powerful Predictor ◽  
Potential Biomarker ◽  
Peking University

AbstractThe association between genetic variations and immunotherapy benefit has been widely recognized, while such evidence in gastrointestinal cancer remains limited. We analyzed the genomic profile of 227 immunotherapeutic gastrointestinal cancer patients treated with immunotherapy, from the Memorial Sloan Kettering (MSK) Cancer Center cohort. A gastrointestinal immune prognostic signature (GIPS) was constructed using LASSO Cox regression. Based on this signature, patients were classified into two subgroups with distinctive prognoses (p < 0.001). The prognostic value of the GIPS was consistently validated in the Janjigian and Pender cohort (N = 54) and Peking University Cancer Hospital cohort (N = 92). Multivariate analysis revealed that the GIPS was an independent prognostic biomarker. Notably, the GIPS-high tumor was indicative of a T-cell-inflamed phenotype and immune activation. The findings demonstrated that GIPS was a powerful predictor of immunotherapeutic survival in gastrointestinal cancer and may serve as a potential biomarker guiding immunotherapy treatment decisions.

scholarly journals Automatic detection and segmentation of adenomatous colorectal polyps during colonoscopy using Mask R-CNN

2020 ◽  
Vol 15 (1) ◽  
pp. 588-596 ◽  
Author(s):  
Jie Meng ◽  
Linyan Xue ◽  
Ying Chang ◽  
Jianguang Zhang ◽  
Shilong Chang ◽  
...  
Keyword(s):  
Deep Neural Networks ◽  
Alimentary Tract ◽  
Multiple Scale ◽  
Colorectal Polyps ◽  
Training Dataset ◽  
Cad System ◽  
Multicenter Trials ◽  
Testing Dataset ◽  
Adenoma Detection ◽  
Aided Diagnosis

AbstractColorectal cancer (CRC) is one of the main alimentary tract system malignancies affecting people worldwide. Adenomatous polyps are precursors of CRC, and therefore, preventing the development of these lesions may also prevent subsequent malignancy. However, the adenoma detection rate (ADR), a measure of the ability of a colonoscopist to identify and remove precancerous colorectal polyps, varies significantly among endoscopists. Here, we attempt to use a convolutional neural network (CNN) to generate a unique computer-aided diagnosis (CAD) system by exploring in detail the multiple-scale performance of deep neural networks. We applied this system to 3,375 hand-labeled images from the screening colonoscopies of 1,197 patients; of whom, 3,045 were assigned to the training dataset and 330 to the testing dataset. The images were diagnosed simply as either an adenomatous or non-adenomatous polyp. When applied to the testing dataset, our CNN-CAD system achieved a mean average precision of 89.5%. We conclude that the proposed framework could increase the ADR and decrease the incidence of interval CRCs, although further validation through large multicenter trials is required.

Sign in / Sign up

Export Citation Format

Share Document