Risk factors analysis and clinical prediction model construction of adenomatous polyps in patients with colorectal melanoma melanosis coli
10.3969/j.issn.1672-2159.2024.02.003
- VernacularTitle:大肠黑变病患者腺瘤性息肉发病的危险因素分析及临床预测模型构建
- Author:
Xue ZHANG
1
;
Zuo TANG
;
Xin YE
;
Li-Ming WEN
Author Information
1. 646000 西南医科大学附属医院消化内科
- Keywords:
Melanosis of colon;
Adenomatous polyps;
Risk factors;
Prediction model
- From:
Modern Interventional Diagnosis and Treatment in Gastroenterology
2024;29(2):126-134
- CountryChina
- Language:Chinese
-
Abstract:
Objective To explore the risk factors for the occurrence of adenomatous polyps in melanosis coli(MC),and to construct and validate a risk prediction model for the occurrence of adenomatous polyps in MC.Methods The clinical data of patients with melanosis coli who underwent colonoscopy in our hospital were retrospectively analyzed.The related risk factors,including gender,age,smoking history,drinking history,hypertension history,diabetes history,melanosis degree and so on,were collected.Establish a column chart model for predicting the risk of adenomatous polyps using R language,evaluate the model through C-index,calibration curve,and decision curve analysis(DCA),and validate the model internally using Bootstrap method.Results Gender,degree of melanosis,homocysteine,HbA1c,TSH,fecal occult blood,gallstones or polyps,HP infection were the independent influencing factors of adenomatous polyps in patients with melanosis of large intestine.The model had a good discrimination in predicting the risk of adenomatous polyps in patients with colorectal melanosis.Hosmer Lemeshow goodness of fit test showed that the P values of the training set and the validation set were 0.157 and 0.179,respectively(both＜0.05),indicating that the model fitted well.When the threshold probability of the training set and the validation level were both 0％to 100％,patients with melanosis of the colon may benefit from clinical intervention.Conclusion The risk model established by the above risk factors has good discrimination and good fit,which can provide reference for clinical decision-making.
