A clinical prediction nomogram to assess risk of colorectal cancer among patients with type 2 diabetes

Abstract

Colorectal cancer remains a major health burden worldwide and is closely related to type 2 diabetes. this study aimed to develop and validate a colorectal cancer risk prediction model to identify high-risk individuals with type 2 diabetes. Records of 930 patients with type 2 diabetes were reviewed and data were collected from 1 November 2013 to 31 December 2019. Clinical and demographic parameters were analyzed using univariable and multivariable logistic regression analysis. The nomogram to assess the risk of colorectal cancer was constructed and validated by bootstrap resampling. Predictors in the prediction nomogram included age, sex, other blood-glucose-lowering drugs and thiazolidinediones. The nomogram demonstrated moderate discrimination in estimating the risk of colorectal cancer, with Hosmer-Lemeshow test P = 0.837, an unadjusted C-index of 0.713 (95% CI 0.670-0.757) and a bootstrap-corrected C index of 0.708. In addition, the decision curve analysis demonstrated that the nomogram would be clinically useful. We have developed a nomogram that can predict the risk of colorectal cancer in patients with type 2 diabetes. The nomogram showed favorable calibration and discrimination values, which may help clinicians in making recommendations about colorectal cancer screening for patients with type 2 diabetes. Colorectal cancer is one of the most common and aggressive clinical gastrointestinal cancer that causes a serious threat to human life and health 1 , accounting for approximately seven hundred thousand annual deaths worldwide 2. Despite the rapid development of diagnostic and treatment methods, the 5-year survival rate for colorectal cancer is ≈ 50% overall 3 , although this rate for colorectal cancer diagnosed in the early stages is > 90% 4. The reason for this abysmal prognosis is that the vast majority of colorectal cancer patients are diagnosed at an advanced stage 5. Therefore, early diagnosis of colorectal cancer is particularly important. Unfortunately, huge resources have been invested in the prevention and early diagnosis of colorectal cancer, but there is a limitation on the effective and early diagnosis of colorectal cancer 6. Screening can reduce the incidence and mortality of colorectal cancer by 30% and 50%, respectively 7. Current screening methods for colorectal cancer mainly include flexible sigmoidoscopy, colonoscopy, fecal occult blood testing, double-contrast barium enema, stool DNA testing, and computed tomographic colonography 8. However, these examinations are invasive or time-consuming or expensive, and it is not feasible to screen the general population for colorectal cancer. To improve the early diagnosis of this disease, we need to broaden our understanding of it. International screening guidelines recommend that screening for colorectal cancer starts at 50 years of age for the average risk group and 50-75 years of age as the target age group for colorectal cancer screening 9,10. It is worth mentioning that diabetes is one of the indicators of the average risk group evaluation in...

A Novel Diagnostic Biomarker, PZP, for Detecting Colorectal Cancer in Type 2 Diabetes Mellitus Patients Identified by Serum-Based Mass Spectrometry

“…Moreover, CRC patients with T2DM receiving medical treatment with metformin experienced fewer distant metastases, associated with slower progression of CRC ( Powell et al, 2020 ). A retrospective study pointed out that patients in the T2DM + CRC group were older than those in the T2DM group in a randomly selected cohort, which was consistent with our research ( Feng et al, 2020 ). Therefore, it is very important to carry out CRC screening in elderly T2DM patients.…”

Latent trajectories of frailty and risk prediction models among geriatric community dwellers: an interpretable machine learning perspective

“…In the training set, we combined 10-fold cross validation and grid search to determine the best hyperparameters based on the best accuracy in validation set. Finally, the test set were subjected to 1000 times bootstrap resampling for internal validation [ 37 ]. The model performance can be lowered by class imbalance, therefore, synthetic minority over-sampling technique (SMOTE), combining oversampling with under-sampling, was applied for resampling by analyzing minority sample then adding new cases to dataset in the training set [ 38 ].…”

Construction of a new clinical staging system for colorectal cancer based on the lymph node ratio: A validation study

“…The global burden of CRC has been estimated to increase by 60%, with more than 2.2 million new cases and 1.1 million cancer deaths by 2030 ( 2 ). Although the diagnosis and treatment of CRC have improved in the previous years, the 5-year survival rate for CRC was only 50% ( 3 ). Currently, the American Joint Committee on Cancer (AJCC) 8th version tumor node metastasis (TNM) staging system is the most widely used tool for predicting the survival of CRC patients ( 4 ).…”