Dataset Information

SOURCE: A Registry-Based Prediction Model for Overall Survival in Patients with Metastatic Oesophageal or Gastric Cancer.

ABSTRACT: Prediction models are only sparsely available for metastatic oesophagogastric cancer. Because treatment in this setting is often preference-based, decision-making with the aid of a prediction model is wanted. The aim of this study is to construct a prediction model, called SOURCE, for the overall survival in patients with metastatic oesophagogastric cancer. Data from patients with metastatic oesophageal (n = 8010) or gastric (n = 4763) cancer diagnosed during 2005?2015 were retrieved from the nationwide Netherlands cancer registry. A multivariate Cox regression model was created to predict overall survival for various treatments. Predictor selection was performed via the Akaike Information Criterion and a Delphi consensus among experts in palliative oesophagogastric cancer. Validation was performed according to a temporal internal-external scheme. The predictive quality was assessed with the concordance-index (c-index) and calibration. The model c-indices showed consistent discriminative ability during validation: 0.71 for oesophageal cancer and 0.68 for gastric cancer. The calibration showed an average slope of 1.0 and intercept of 0.0 for both tumour locations, indicating a close agreement between predicted and observed survival. With a fair c-index and good calibration, SOURCE provides a solid foundation for further investigation in clinical practice to determine its added value in shared decision making.

SUBMITTER: van den Boorn HG

PROVIDER: S-EPMC6406639 | biostudies-literature | 2019 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

SOURCE: A Registry-Based Prediction Model for Overall Survival in Patients with Metastatic Oesophageal or Gastric Cancer.

van den Boorn Héctor G HG Abu-Hanna Ameen A Ter Veer Emil E van Kleef Jessy Joy JJ Lordick Florian F Stahl Michael M Ajani Jaffer A JA Guimbaud Rosine R Park Se Hoon SH Dutton Susan J SJ Bang Yung-Jue YJ Boku Narikazu N Mohammad Nadia Haj NH Sprangers Mirjam A G MAG Verhoeven Rob H A RHA Zwinderman Aeilko H AH van Oijen Martijn G H MGH van Laarhoven Hanneke W M HWM van Laarhoven Hanneke W M HWM

Cancers 20190205 2

Prediction models are only sparsely available for metastatic oesophagogastric cancer. Because treatment in this setting is often preference-based, decision-making with the aid of a prediction model is wanted. The aim of this study is to construct a prediction model, called SOURCE, for the overall survival in patients with metastatic oesophagogastric cancer. Data from patients with metastatic oesophageal (<i>n</i> = 8010) or gastric (<i>n</i> = 4763) cancer diagnosed during 2005⁻2015 were retriev ...[more]

PMID: 30764578

Similar Datasets

Project description:Background and objectivesInvestigations of the prognosis are vital for better patient management and decision-making in patients with advanced metastatic renal cell carcinoma (mRCC). The purpose of this study is to evaluate the capacity of emerging Artificial Intelligence (AI) technologies to predict three- and five-year overall survival (OS) for mRCC patients starting their first-line of systemic treatment.Patients and methodsThe retrospective study included 322 Italian patients with mRCC who underwent systemic treatment between 2004 and 2019. Statistical analysis included the univariate and multivariate Cox proportional-hazard model and the Kaplan-Meier analysis for the prognostic factors' investigation. The patients were split into a training cohort to establish the predictive models and a hold-out cohort to validate the results. The models were evaluated by the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. We assessed the clinical benefit of the models using decision curve analysis (DCA). Then, the proposed AI models were compared with well-known pre-existing prognostic systems.ResultsThe median age of patients in the study was 56.7 years at RCC diagnosis and 78% of participants were male. The median survival time from the start of systemic treatment was 29.2 months; 95% of the patients died during the follow-up that finished by the end of 2019. The proposed predictive model, which was constructed as an ensemble of three individual predictive models, outperformed all well-known prognostic models to which it was compared. It also demonstrated better usability in supporting clinical decisions for 3- and 5-year OS. The model achieved (0.786 and 0.771) AUC and (0.675 and 0.558) specificity at sensitivity 0.90 for 3 and 5 years, respectively. We also applied explainability methods to identify the important clinical features that were found to be partially matched with the prognostic factors identified in the Kaplan-Meier and Cox analyses.ConclusionsOur AI models provide best predictive accuracy and clinical net benefits over well-known prognostic models. As a result, they can potentially be used in clinical practice for providing better management for mRCC patients starting their first-line of systemic treatment. Larger studies would be needed to validate the developed model.

Project description:Background and purposeChemoradiotherapy is the standard treatment for moderate and advanced oesophageal cancer. The aim of this study was to establish a predictive model based on enhanced computed tomography examination, and to evaluate its clinical value for detecting locoregional recurrence-free survival (LRFS) in cases of oesophageal squamous cell carcinoma after radiotherapy.Materials and methodsIn total, 218 patients with pathologically diagnosed oesophageal squamous cell carcinoma who received radical chemoradiotherapy from July 2016 to December 2017 were collected in this study. Patients were randomly divided into either a training group (n=153) or a validation group (n=65) in a 7:3 ratio. Clinical patient information was then recorded. The enhanced computed tomography scan images of the patients were imported into 3D-slicer software (version 4.8.1), and the radiomic features were extracted by the Python programme package. In the training group, the dimensionality reduction of the radiomic features was implemented by Lasso regression, and then a radiological label, the model of predicting LRFS, was established and evaluated. To achieve a better prediction performance, the radiological label was combined with clinical risk factor information to construct a radiomics nomogram. A receiver operating characteristic curve was used to evaluate the efficacy of different models. Calibration curves were used to assess the consistency between the predicted and observed recurrence risk, and the Hosmer-Lemeshow method was used to test model fitness. The C-index evaluated the discriminating ability of the prediction model. Decision curve analysis was used to determine the clinical value of the constructed prediction model.ResultsOf the 218 patients followed up in this study, 44 patients (28.8%) in the training group and 21 patients (32.3%) in the validation group experienced recurrence. There was no difference in LRFS between the two groups (χ2 = 0.525, P=0.405). Lasso regression was used in the training group to select six significant radiomic features. The radiological label established using these six features had a satisfactory prediction performance. The C-index was 0.716 (95% CI: 0.645-0.787) in the training group and 0.718 (95% CI: 0.612-0.825) in the validation group. The radiomics nomogram, which included the radiological label and clinical risk factors, achieved a better prediction than the radiological label alone. The C-index was 0.742 (95% CI: 0.674-0.810) in the training group and 0.715 (95% CI: 0.609-0.820) in the validation group. The results of the calibration curve and decision curve analyses indicated that the radiomics nomogram was superior in predicting LRFS of oesophageal carcinoma after radiotherapy.ConclusionsA radiological label was successfully established to predict the LRFS of oesophageal squamous cell carcinoma after radiotherapy. The radiomics nomogram was complementary to the clinical prognostic features and could improve the prediction of the LRFS after radiotherapy for oesophageal cancer.

Project description:Aims. This study is aimed at identifying a prognostic signature for cervical cancer. Main Methods. The gene expression data and clinical information of cervical cancer and normal cervical tissues were acquired from The Cancer Genome Atlas and from three datasets of the Gene Expression Omnibus database. DESeq2 and Limma were employed to screen differentially expressed genes (DEGs). The overlapping DEGs among all datasets were considered the final DEGs. Then, the functional enrichment analysis was performed. Moreover, the Cox proportional hazards regression was performed to establish a prognostic signature of the DEGs. The Kaplan-Meier analysis was applied to test the model. Relationships between gene expression and clinicopathological parameters in cervical cancer, including age, HPV status, histology, stage, and lymph node metastasis, were analysed by the chi-square test. The somatic mutations of these prognostic genes were assessed through cBioPortal. The robustness of the model was verified in another two independent validation cohorts. Key Findings. In total, 169 overlapping upregulated genes and 29 overlapping downregulated genes were identified in cervical cancer compared with normal cervical tissues. Functional enrichment analysis indicated that the DEGs were mainly enriched in DNA replication, the cell cycle, and the p53 signalling pathway. Finally, a 5-gene- (ITM2A, DSG2, SPP1, EFNA1, and MMP1) based prognostic signature was built. According to this model, each patient was given a prognostic-related risk value. The Kaplan-Meier analysis showed that a higher risk was related to worse overall survival in cervical cancer, with an area under the receiver operating characteristic curve of 0.811 for 15 years. The validity of this model in the prediction of cervical cancer outcome was verified in another two independent datasets. In addition, our study also found that the low expression of ITM2A was associated with cervical adenocarcinoma. Interestingly, DSG2 was associated with the HPV status of cervical cancer. Significance. Our study constructed a prognostic model in cervical cancer and discovered two novel genes, ITM2A and DSG2, associated with cervical carcinogenesis and survival.

Dataset Information

SOURCE: A Registry-Based Prediction Model for Overall Survival in Patients with Metastatic Oesophageal or Gastric Cancer.

Publications

SOURCE: A Registry-Based Prediction Model for Overall Survival in Patients with Metastatic Oesophageal or Gastric Cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets