Dataset Information

Prognostic Models for Predicting Overall Survival in Patients with Primary Gastric Cancer: A Systematic Review.

ABSTRACT: Background:This study was designed to review the methodology and reporting of gastric cancer prognostic models and identify potential problems in model development. Methods:This systematic review was conducted following the CHARMS checklist. MEDLINE and EMBASE were searched. Information on patient characteristics, methodological details, and models' performance was extracted. Descriptive statistics was used to summarize the methodological and reporting quality. Results:In total, 101 model developments and 32 external validations were included. The median (range) of training sample size, number of death, and number of final predictors were 360 (29 to 15320), 193 (14 to 9560), and 5 (2 to 53), respectively. Ninety-one models were developed from routine clinical data. Statistical assumptions were reported to be checked in only nine models. Most model developments (94/101) used complete-case analysis. Discrimination and calibration were not reported in 33 and 55 models, respectively. The majority of models (81/101) have never been externally validated. None of the models have been evaluated regarding clinical impact. Conclusions:Many prognostic models have been developed, but their usefulness in clinical practice remains uncertain due to methodological shortcomings, insufficient reporting, and lack of external validation and impact studies. Impact:Future research should improve methodological and reporting quality and emphasize more on external validation and impact assessment.

SUBMITTER: Feng Q

PROVIDER: S-EPMC6766665 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prognostic Models for Predicting Overall Survival in Patients with Primary Gastric Cancer: A Systematic Review.

Feng Qi Q May Margaret T MT Ingle Suzanne S Lu Ming M Yang Zuyao Z Tang Jinling J

BioMed research international 20190918

<h4>Background</h4>This study was designed to review the methodology and reporting of gastric cancer prognostic models and identify potential problems in model development.<h4>Methods</h4>This systematic review was conducted following the CHARMS checklist. MEDLINE and EMBASE were searched. Information on patient characteristics, methodological details, and models' performance was extracted. Descriptive statistics was used to summarize the methodological and reporting quality.<h4>Results</h4>In t ...[more]

PMID: 31641669

Similar Datasets

Project description:BackgroundInflammatory markers are associated with tumor genesis and progression, but their prognostic significance in osteosarcoma remains unclear. Therefore, we discussed the prognostic value of related inflammatory markers in osteosarcoma through a meta-analysis and systematic review. These inflammatory markers include C-reactive protein (CRP), neutrophil to lymphocyte ratio (NLR), lymphocyte to monocyte ratio (LMR), platelet to lymphocyte ratio (PLR), and Glasgow prognostic score (GPS).MethodsThe Chinese National Knowledge Infrastructure (CNKI), Wanfang, Chinese Scientific Journals (VIP), PubMed, Embase, and Cochrane libraries were searched. The design of meta-analysis was made based on the PICOS (population, intervention/exposure, control, outcomes, and study design) principles, and STATA 15.1 was used to analyze the data. The Newcastle-Ottawa scale (NOS) was used to assess the quality of included studies. Hazard ratios (HRs) for overall survival (OS) and disease-specific survival (DPS) were extracted for the investigation of the prognostic value of inflammatory markers.ResultsTwelve researches with 2162 osteosarcoma patients were included in total. The pooled results showed that elevated NLR, CRP, and GPS are all greatly related to shortening of OS among patients with osteosarcoma (HR = 1.68, P = 0.007, 95% CI: 1.15-2.45; HR = 1.96, P = 0.002, 95% CI: 1.28-3.00; HR = 2.54, P < 0.0001, 95% CI: 1.95-3.31, respectively), and CRP level is significantly associated with shortening of DPS among patients with osteosarcoma (HR = 2.76, 95% CI:2.01-3.80, P < 0.0001), additionally. However, the correlation between LMR or PLR and the prognosis of osteosarcoma is not statistically significant (HR = 0.60, 95% CI: 0.30-1.18, P = 0.138; HR = 1.13, 95% CI: 0.85-1.49, P = 0.405, respectively). The outcomes of subgroup analysis to NLR and CRP suggested that histology, ethnicity, metastasis, and sample size all have an impact on its prognosis of patients with osteosarcoma.ConclusionWorsened prognosis may be related to high levels of NLR, CRP, and GPS before treatment rather than LMR or PLR, which can provide the basis for clinicians to judge the outcomes of prognosis. Trial Registration. PROSPERO (CRD42021249954), https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=249954.

Project description:Objective The goal of this study was to evaluate the efficacy of machine learning (ML) techniques in predicting survival for chordoma patients in comparison with the standard Cox proportional hazards (CoxPH) model. Methods Using a Surveillance, Epidemiology, and End Results database of consecutive newly diagnosed chordoma cases between January 2000 and December 2018, we created and validated three ML survival models as well as a traditional CoxPH model in this population-based cohort study. Randomly, the dataset was divided into training and validation datasets. Tuning hyperparameters on the training dataset involved a 1000-iteration random search with fivefold cross-validation. Concordance index (C-index), Brier score, and integrated Brier score were used to evaluate the performance of the model. The receiver operating characteristic (ROC) curves, calibration curves, and area under the ROC curves (AUC) were used to assess the reliability of the models by predicting 5- and 10-year survival probabilities. Results A total of 724 chordoma patients were divided into training (n = 508) and validation (n = 216) cohorts. Cox regression identified nine significant prognostic factors (p < 0.05). ML models showed superior performance over CoxPH model, with DeepSurv having the highest C-index (0.795) and the best discrimination for 5- and 10-year survival (AUC 0.84 and 0.88). Calibration curves revealed strong correlation between DeepSurv predictions and actual survival. Risk stratification by DeepSurv model effectively discriminated high- and low-risk groups (p < 0.01). The optimized DeepSurv model was implemented into a web application for clinical use that can be found at https://hust-chengp-ml-chordoma-app-19rjyr.streamlitapp.com/. Conclusion ML algorithms based on time-to-event results are effective in chordoma prediction, with DeepSurv having the best discrimination performance and calibration. Supplementary Information The online version contains supplementary material available at 10.1186/s13018-023-04105-9.

Project description:BackgroundThe prognosis of patients for lung adenocarcinoma (LUAD) is known to vary widely; the 5-year overall survival rate is just 63% even for the pathological IA stage. Thus, in order to identify high-risk patients and facilitate clinical decision making, it is vital that we identify new prognostic markers that can be used alongside TNM staging to facilitate risk stratification.MethodsWe used mRNA expression from The Cancer Genome Atlas (TCGA) cohort to identify a prognostic gene signature and combined this with clinical data to develop a predictive model for the prognosis of patients for lung adenocarcinoma. Kaplan-Meier curves, Lasso regression, and Cox regression, were used to identify specific prognostic genes. The model was assessed via the area under the receiver operating characteristic curve (AUC-ROC) and validated in an independent dataset (GSE50081) from the Gene Expression Omnibus (GEO).ResultsOur analyses identified a four-gene prognostic signature (CENPH, MYLIP, PITX3, and TRAF3IP3) that was associated with the overall survival of patients with T1-4N0-2M0 in the TCGA dataset. Multivariate regression suggested that the total risk score for the four genes represented an independent prognostic factor for the TCGA and GEO cohorts; the hazard ratio (HR) (high risk group vs low risk group) were 2.34 (p < 0.001) and 2.10 (p = 0.017). Immune infiltration estimations, as determined by an online tool (TIMER2.0) showed that CD4+ T cells were in relative abundance in the high risk group compared to the low risk group in both of the two cohorts (both p < 0.001). We established a composite prognostic model for predicting OS, combined with risk-grouping and clinical factors. The AUCs for 1-, 3-, 5- year OS in the training set were 0.750, 0.737, and 0.719; and were 0.645, 0.766, and 0.725 in the validation set. The calibration curves showed a good match between the predicted probabilities and the actual probabilities.ConclusionsWe identified a four-gene predictive signature which represents an independent prognostic factor and can be used to identify high-risk patients from different TNM stages of LUAD. A new prognostic model that combines a prognostic gene signature with clinical features exhibited better discriminatory ability for OS than traditional TNM staging.

Dataset Information

Prognostic Models for Predicting Overall Survival in Patients with Primary Gastric Cancer: A Systematic Review.

Publications

Prognostic Models for Predicting Overall Survival in Patients with Primary Gastric Cancer: A Systematic Review.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets