Analysis of Prognostic Factors of Rectal Cancer and Construction of a Prognostic Prediction Model Based on Bayesian Network

被引:11
作者
Li, Ruikai [1 ]
Zhang, Chi [2 ]
Du, Kunli [1 ]
Dan, Hanjun [1 ]
Ding, Ruxin [3 ]
Cai, Zhiqiang [2 ]
Duan, Lili [1 ]
Xie, Zhenyu [1 ]
Zheng, Gaozan [1 ]
Wu, Hongze [1 ]
Ren, Guangming [4 ]
Dou, Xinyu [4 ]
Feng, Fan [1 ]
Zheng, Jianyong [1 ]
机构
[1] Fourth Mil Med Univ, Xijing Hosp, Dept Gastrointestinal Surg, Xian, Peoples R China
[2] Northwestern Polytech Univ, Sch Mechantron, Dept Ind Engn, Xian, Peoples R China
[3] Yanan Univ, Dept Cell Biol & Genet, Med Coll, Yanan, Peoples R China
[4] Xian Med Univ, Grad Work Dept, Xian, Peoples R China
基金
中国国家自然科学基金;
关键词
Bayesian network; clinicopathological factor; prediction model; prognosis; rectal cancer; SURVIVAL PREDICTION; CURATIVE RESECTION; BELIEF NETWORK; DECISION; NOMOGRAM; SUPPORT;
D O I
10.3389/fpubh.2022.842970
中图分类号
R1 [预防医学、卫生学];
学科分类号
1004 ; 120402 ;
摘要
BackgroundThe existing prognostic models of rectal cancer after radical resection ignored the relationships among prognostic factors and their mutual effects on prognosis. Thus, a new modeling method is required to remedy this defect. The present study aimed to construct a new prognostic prediction model based on the Bayesian network (BN), a machine learning tool for data mining, clinical decision-making, and prognostic prediction. MethodsFrom January 2015 to December 2017, the clinical data of 705 patients with rectal cancer who underwent radical resection were analyzed. The entire cohort was divided into training and testing datasets. A new prognostic prediction model based on BN was constructed and compared with a nomogram. ResultsA univariate analysis showed that age, Carcinoembryonic antigen (CEA), Carbohydrate antigen19-9 (CA19-9), Carbohydrate antigen 125 (CA125), preoperative chemotherapy, macropathology type, tumor size, differentiation status, T stage, N stage, vascular invasion, KRAS mutation, and postoperative chemotherapy were associated with overall survival (OS) of the training dataset. Based on the above-mentioned variables, a 3-year OS prognostic prediction BN model of the training dataset was constructed using the Tree Augmented Naive Bayes method. In addition, age, CEA, CA19-9, CA125, differentiation status, T stage, N stage, KRAS mutation, and postoperative chemotherapy were identified as independent prognostic factors of the training dataset through multivariate Cox regression and were used to construct a nomogram. Then, based on the testing dataset, the two models were evaluated using the receiver operating characteristic (ROC) curve. The results showed that the area under the curve (AUC) of ROC of the BN model and nomogram was 80.11 and 74.23%, respectively. ConclusionThe present study established a BN model for prognostic prediction of rectal cancer for the first time, which was demonstrated to be more accurate than a nomogram.
引用
收藏
页数:9
相关论文
共 29 条
[1]   Prognostic and Oncologic Significance of Perineural Invasion in Sporadic Colorectal Cancer [J].
Alotaibi, Abdulrahman Muaod ;
Lee, Jong Lyul ;
Kim, Jihun ;
Lim, Seok-Byung ;
Yu, Chang Sik ;
Kim, Tae Won ;
Kim, Jong Hoon ;
Kim, Jin Cheon .
ANNALS OF SURGICAL ONCOLOGY, 2017, 24 (06) :1626-1634
[2]   Adult Overweight and Survival from Breast and Colorectal Cancer in Swedish Women [J].
Arnold, Melina ;
Charvat, Hadrien ;
Freisling, Heinz ;
Noh, Hwayoung ;
Adami, Hans-Olov ;
Soerjomataram, Isabelle ;
Weiderpass, Elisabete .
CANCER EPIDEMIOLOGY BIOMARKERS & PREVENTION, 2019, 28 (09) :1518-1524
[3]   A prognostic Bayesian network that makes personalized predictions of poor prognostic outcome post resection of pancreatic ductal adenocarcinoma [J].
Bradley, Alison ;
Van der Meer, Robert ;
McKay, Colin J. .
PLOS ONE, 2019, 14 (09)
[4]   Analysis of prognostic factors for survival after surgery for gallbladder cancer based on a Bayesian network [J].
Cai, Zhi-qiang ;
Guo, Peng ;
Si, Shu-bin ;
Geng, Zhi-min ;
Chen, Chen ;
Cong, Long-long .
SCIENTIFIC REPORTS, 2017, 7
[5]   Decision of surgical approach for advanced gallbladder adenocarcinoma based on a Bayesian network [J].
Cong, Long-Long ;
Cai, Zhi-Qiang ;
Guo, Peng ;
Chen, Chen ;
Liu, De-Chun ;
Li, Wen-Zhi ;
Wang, Lin ;
Zhao, Yaling ;
Si, Shu-Bin ;
Geng, Zhi-Min .
JOURNAL OF SURGICAL ONCOLOGY, 2017, 116 (08) :1123-1131
[6]   From complex questionnaire and interviewing data to intelligent Bayesian network models for medical decision support [J].
Constantinou, Anthony Costa ;
Fenton, Norman ;
Marsh, William ;
Radlinski, Lukasz .
ARTIFICIAL INTELLIGENCE IN MEDICINE, 2016, 67 :75-93
[7]   Colorectal cancer [J].
Dekker, Evelien ;
Tanis, Pieter J. ;
Vleugels, Jasper L. A. ;
Kasi, Pashtoon M. ;
Wallace, Michael B. .
LANCET, 2019, 394 (10207) :1467-1480
[8]   Development and validation of nomogram combining serum biomarker for predicting survival in patients with resected rectal cancer [J].
Fan, Shaonan ;
Li, Ting ;
Zhou, Ping ;
Peng, Qiliang ;
Zhu, Yaqun .
BIOSCIENCE REPORTS, 2019, 39
[9]  
FIELDING LP, 1986, LANCET, V2, P904
[10]   Bayesian network classifiers [J].
Friedman, N ;
Geiger, D ;
Goldszmidt, M .
MACHINE LEARNING, 1997, 29 (2-3) :131-163