Performances of Prognostic Models in Stratifying Patients with Advanced Gastric Cancer Receiving First-line Chemotherapy: a Validation Study in a Chinese Cohort

Xu, Hui; Zhang, Xiaopeng; Wu, Zhijun; Feng, Ying; Zhang, Cheng; Xie, Minmin; Yang, Yahui; Zhang, Yi; Feng, Chong; Ma, Tai

doi:10.5230/jgc.2021.21.e26

Cited by 1 publication

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All the AUROCs of the three models exceed 0.75, which is higher than those in the previous reports ( Koo et al, 2011 ; Custodio et al, 2017 ; Ma et al, 2021 ). In addition, our earlier work selected the patients with AGC receiving first-line chemotherapy from the same local cohort and compared the performances of seven survival prediction models on it, showing the best model having an AUROC of 0.60 ( Xu et al, 2021 ). The present study does not impose restrictions on treatment or other factors, so the population is of wider heterogeneity, which may help the model generalize well due to closely reflecting the characteristics of the patients in a real-world setting.…”

Section: Discussionmentioning

confidence: 99%

“…Our previous work also developed a score-based model in a Chinese cohort with a c-index of 0.67 ( Ma et al, 2021 ). Meanwhile, we validated seven published models ( Chau et al, 2004 ; Lee et al, 2007 ; Kim et al, 2008 ; Koo et al, 2011 ; Takahari et al, 2014 ; Wang et al, 2016 ; Kim et al, 2020 ) in a Chinese population, and the results showed that the area under receiver operating characteristic (AUROC) curves was only about 0.60 ( Xu et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning models for predicting one-year survival in patients with metastatic gastric cancer who experienced upfront radical gastrectomy

Zhang

Zhang²,

Yang³

et al. 2022

Front. Mol. Biosci.

Self Cite

View full text Add to dashboard Cite

Tumor metastasis is a common event in patients with gastric cancer (GC) who previously underwent curative gastrectomy. It is meaningful to employ high-volume clinical data for predicting the survival of metastatic GC patients. We aim to establish an improved machine learning (ML) classifier for predicting if a patient with metastatic GC would die within 12 months. Eligible patients were enrolled from a Chinese GC cohort, and the complete detailed information from medical records was extracted to generate a high-dimensional dataset. Appropriate feature engineering and feature filter were conducted before modeling with eight algorithms. A 10-fold cross validation (CV) nested in a holdout CV (8:2) was employed for hyperparameter tuning and model evaluation. Model selection was based on the area under the receiver operating characteristic (AUROC) curve, recall, and precision. The selected model was globally explained using interpretable surrogate models. Of the total 399 cases (median survival of 8.2 months), 242 patients survived less than 12 months. The linear discriminant analysis (LDA), support vector machine (SVM), and random forest (RF) model had the highest AUROC (0.78 ± 0.021), recall (0.93 ± 0.031), and precision (0.80 ± 0.026), respectively. The LDA model created a new function that generally separated the two classes. The predicted probability of the SVM model was interpreted using a linear regression model visualized by a nomogram. The predicted class of the RF model was explained using a decision tree model. In summary, analyzing high-volume medical data by ML is helpful to produce an improved model for predicting the survival in patients with metastatic GC. The algorithm should be carefully selected in different practical scenarios.

show abstract