Development and validation of MMR prediction model based on simplified clinicopathological features and serum tumour markers

Cao, Yinghao; Peng, Tao; Liang, Han; Yang, Ming; Wu, Liang; Zhou, Zili; Zhang, Xudan; Han, Shengbo; Bao, Haijun; Cai, Kailin; Zhao, Ning

doi:10.1016/j.ebiom.2020.103060

Cited by 5 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In previous studies, [ 5 ] we analyzed clinicopathological data of 3274 participants from two institutions and assessed their predictive value in patients of all ages with CRC. We found that a columnar line graph created using simple clinicopathological indicators was able to accurately predict the status of MMR/MSI in patients with an AUC value of 0.754 (95% CI: 0.715–0.793) in the validation group.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Development and Interpretation of a Clinicopathological-Based Model for the Identification of Microsatellite Instability in Colorectal Cancer

et al. 2023

Self Cite

View full text Add to dashboard Cite

Chemotherapy is not recommended for patients with deficient mismatch repair (dMMR) in colorectal cancer (CRC); therefore, assessing the status of MMR is crucial for the selection of subsequent treatment. This study is aimed at building predictive models to accurately and rapidly identify dMMR. A retrospective analysis was performed at Wuhan Union Hospital between May 2017 and December 2019 based on the clinicopathological data of patients with CRC. The variables were subjected to collinearity, least absolute shrinkage and selection operator (LASSO) regression, and random forest (RF) feature screening analyses. Four sets of machine learning models (extreme gradient boosting (XGBoost), support vector machine (SVM), naive Bayes (NB), and RF) and a conventional logistic regression (LR) model were built for model training and testing. Receiver operating characteristic (ROC) curves were plotted to evaluate the predictive performance of the developed models. In total, 2279 patients were included in the study and were randomly divided into either the training or test group. Twelve clinicopathological features were incorporated into the development of the predictive models. The area under curve (AUC) values of the five predictive models were 0.8055 for XGBoost, 0.8174 for SVM, 0.7424 for NB, 8584 for RF, and 0.7835 for LR (Delong test, P value < 0.05). The results showed that the RF model exhibited the best recognition ability and outperformed the conventional LR method in identifying dMMR and proficient MMR (pMMR). Our predictive models based on routine clinicopathological data can significantly improve the diagnostic performance of dMMR and pMMR. The four machine learning models outperformed the conventional LR model.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Molecularly targeted therapies and chemotherapeutic agents are used to treat patients with dMMR CRC [ 4 ]. Recently, a growing body of evidence suggests that the individual treatment response of patients with CRC is strongly related to its molecular characteristics [ 5 ].…”

Section: Introductionmentioning

confidence: 99%

Development and Interpretation of a Clinicopathological-Based Model for the Identification of Microsatellite Instability in Colorectal Cancer

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…We have already built a simple model to predict the mismatch repair status of colorectal cancer patients based on clinicopathological parameters and tumour markers with good results in the previous phase. (5) This time, we will further focus on whether the machine learning approach is more effective than the conventional predictive model by constructing four machine learning models and a traditional logistic regression based on simple clinicopathological indicators.…”

Section: Discussionmentioning

confidence: 99%

“…(4) Recently, a growing body of evidence suggests that the individual treatment response of CRC patients is strongly related to its molecular characteristics. (5) Microsatellite instability (MSI) is the abnormal shortening or lengthening of 1-6 repeat base pair units of DNA, which is caused by inactivation of the DNA MMR system. (3,6,7) Colorectal cancer patients with microsatellite instability are more likely to nd Lynch syndrome.…”

Section: Introductionmentioning

confidence: 99%

Development and interpretation of a clinicopathological-based model for the identification of microsatellite instability in Colorectal Cancer

Jiang

Cao

Yan

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Background:Chemotherapy is not recommended for patients with deficient mismatch repair(dMMR)in colorectal cancer(CRC), so assessing the status of MMR is crucial for the selection of subsequent treatment. Therefore, this study aims to build predictive models to accurately and rapidly identify dMMR.Methods:A retrospective analysis based on the clinicopathological data of patients with colorectal cancer from May 2017 to December 2019 at Wuhan Union Hospital was performed. The variables were subjected to co-linearity analysis, least absolute shrinkage and selection operator (LASSO) regression and random forest (RF) feature screening. Four sets of machine learning models (i.e., extreme gradient boosting (XGBoost), support vector machine (SVM), naive bayes (NB), and random forest and a conventional logistic regression (LR) model were built for training and testing. Receiver operating characteristic (ROC) curves are plotted to evaluate the predictive performance.Findings:A total of 2279 patients were included in the analysis and were randomly divided into a training group and a test group.The final 12 clinicopathological features were incorporated into the predictive models. The Area Under the curve (AUC) values of the five predictive models were 0.8931 in XGBoost, 0.8906 in SVM, 0.8512 in NB, 0.9088 in RF and 0.8319 in LR. The results showed that the random forest exhibited the best recognition ability and outperformed the conventional logistic regression method in identifing dMMR and proficient mismatch repair (pMMR).Conclusion:Our predictive models built on routine clinicopathological data can significantly improve the diagnostic performance of dMMR and pMMR. Meanwhile, four machine learning models outperformed conventional logistic regression model.

show abstract

“…Numerous prognostic factors utilizing peripheral biochemical biomarkers have been validated (4)(5)(6). Dysregulated lipid levels have been consistently linked to the occurrence, risk, and progression of CRC.…”

Section: Introductionmentioning

confidence: 99%

Apolipoprotein A-I levels in the survival of patients with colorectal cancer: a retrospective study

Xie,

Wei,

Wang

et al. 2024

Front. Endocrinol.

View full text Add to dashboard Cite

BackgroundAbnormal lipid levels have been associated with cancer incidence and progression. However, limited studies have investigated the relationship between apolipoprotein A-I (ApoA-I) and colorectal cancer (CRC). This study assessed the significance of ApoA-I levels in progression-free survival (PFS) and overall survival (OS) of patients with CRC.MethodsSurvival curves were compared using Kaplan–Meier analysis, while the predictive values of various lipid indicators in CRC prognosis were evaluated based on receiver operating characteristic curves. The factors influencing PFS and OS in patients with CRC were analyzed using Cox proportional hazards regression models. Finally, the relationship between ApoA-I level and disease recurrence was investigated through logistic regression analysis. The optimal Apo-I level was determined through maximally selected rank statistics.ResultsUsing the optimal ApoA-I cutoff value (0.9 g/L), the 1,270 patients with CRC were categorized into low (< 0.9 g/L, 275 cases) and high (≥0.9 g/L, 995 cases) ApoA-I groups. Compared with other lipid indicators, ApoA-I demonstrated superior predictive accuracy. The high ApoA-I group exhibited significantly higher survival rates than the low ApoA-I group (PFS, 64.8% vs. 45.2%, P < 0.001; OS, 66.1% vs. 48.6%, P < 0.001). Each one-standard-deviation increase in ApoA-I level was related to a 12.0% decrease in PFS risk (hazard ratio [HR] 0.880; 95% confidence interval [CI], 0.801–0.968; P = 0.009) and an 11.2% decrease in OS risk (HR 0.888; 95%CI, 0.806–0.978; P = 0.015). Logistic regression analysis revealed that patients with low ApoA-I had a 32.5% increased risk of disease recurrence (odds ratio [OR] 0.675; 95%CI, 0.481–0.946; P = 0.0225) compared with those with high ApoA-I. PFS/OS nomograms based on ApoA-I demonstrated excellent prognostic prediction accuracy.ConclusionsSerum ApoA-I level may be a valuable and non-invasive tool for predicting PFS and OS in patients with CRC.

show abstract

Development and validation of MMR prediction model based on simplified clinicopathological features and serum tumour markers

Cited by 5 publications

References 44 publications

Development and Interpretation of a Clinicopathological-Based Model for the Identification of Microsatellite Instability in Colorectal Cancer

Development and Interpretation of a Clinicopathological-Based Model for the Identification of Microsatellite Instability in Colorectal Cancer

Development and interpretation of a clinicopathological-based model for the identification of microsatellite instability in Colorectal Cancer

Apolipoprotein A-I levels in the survival of patients with colorectal cancer: a retrospective study

Contact Info

Product

Resources

About