Predicting the survival of patients with pancreatic neuroendocrine neoplasms using deep learning: A study based on Surveillance, Epidemiology, and End Results database

被引:7
作者
Jiang, Chen [1 ]
Wang, Kan [2 ]
Yan, Lizhao [3 ]
Yao, Hailing [1 ]
Shi, Huiying [1 ,4 ]
Lin, Rong [1 ,4 ]
机构
[1] Huazhong Univ Sci & Technol, Union Hosp, Tongji Med Coll, Dept Gastroenterol, Wuhan, Peoples R China
[2] Huazhong Univ Sci & Technol, Union Hosp, Tongji Med Coll, Dept Cardiovasc Surg, Wuhan, Peoples R China
[3] Huazhong Univ Sci & Technol, Union Hosp, Tongji Med Coll, Dept Hand Surg, Wuhan, Peoples R China
[4] Huazhong Univ Sci & Technol, Union Hosp, Tongji Med Coll, Dept Gastroenterol, Wuhan 430022, Peoples R China
来源
CANCER MEDICINE | 2023年 / 12卷 / 11期
基金
中国国家自然科学基金;
关键词
deep learning; DeepSurv; pancreatic neuroendocrine neoplasms; survival analysis; TUMORS; MANAGEMENT;
D O I
10.1002/cam4.5949
中图分类号
R73 [肿瘤学];
学科分类号
100214 ;
摘要
Background The study aims to evaluate the performance of three advanced machine learning algorithms and a traditional Cox proportional hazard (CoxPH) model in predicting the overall survival (OS) of patients with pancreatic neuroendocrine neoplasms (PNENs).Method The clinicopathological dataset obtained from the Surveillance, Epidemiology, and End Results database was randomly assigned to the training set and testing set at a ratio of 7:3. The concordance index (C-index) and integrated Brier score (IBS) were used to compare the predictive performance of the models. The accuracy of the model in predicting the 5-year and 10-year survival rates was compared using the receiver operating characteristic curve, decision curve analysis (DCA) and calibration curve.Results This study included 3239 patients with PNENs in total. The DeepSurv model had the highest C-index of 0.7882 in the testing set and training set and the lowest IBS of 0.1278 in the testing set compared with the CoxPH, neural multitask logistic and random survival forest models (C-index = 0.7501, 0.7616, and 0.7612, respectively; IBS = 0.1397, 0.1418, and 0.1432, respectively). Moreover, the DeepSurv model had the highest accuracy in predicting 5- and 10-year OS rates (area under the curve: 0.87 and 0.90). DCA showed that the DeepSurv model had high potential for clinical decisions in 5- and 10-year OS models. Finally, we developed an online application based on the DeepSurv model for clinical use ().Conclusions All four models analyzed above can predict the prognosis of PNENs well, among which the DeepSurv model has the best prediction performance.
引用
收藏
页码:12413 / 12424
页数:12
相关论文
共 29 条
  • [1] Amin MB, 2017, AJCC CANC STAGING MA
  • [2] ENETS Consensus Guidelines for the Management of Patients with Digestive Neuroendocrine Neoplasms: Colorectal Neuroendocrine Neoplasms
    Caplin, Martyn
    Sundin, Anders
    Nillson, Ola
    Baum, Richard P.
    Klose, Klaus J.
    Kelestimur, Fahrettin
    Ploeckinger, Ursula
    Papotti, Mauro
    Salazar, Ramon
    Pascher, Andreas
    [J]. NEUROENDOCRINOLOGY, 2012, 95 (02) : 88 - 97
  • [3] Trends in the Incidence, Prevalence, and Survival Outcomes in Patients With Neuroendocrine Tumors in the United States
    Dasari, Arvind
    Shen, Chan
    Halperin, Daniel
    Zhao, Bo
    Zhou, Shouhao
    Xu, Ying
    Shih, Tina
    Yao, James C.
    [J]. JAMA ONCOLOGY, 2017, 3 (10) : 1335 - 1342
  • [4] Artificial intelligence in cancer research, diagnosis and therapy
    Elemento, Olivier
    Leslie, Christina
    Lundin, Johan
    Tourassi, Georgia
    [J]. NATURE REVIEWS CANCER, 2021, 21 (12) : 747 - 752
  • [5] A meta-analysis of Prognostic factor of Pancreatic neuroendocrine neoplasms
    Gao, Yong
    Gao, Hao
    Wang, Guangfu
    Yin, Lingdi
    Xu, Wenbin
    Peng, Yunpeng
    Wu, Junli
    Jiang, Kuirong
    Miao, Yi
    [J]. SCIENTIFIC REPORTS, 2018, 8
  • [6] EVALUATING THE YIELD OF MEDICAL TESTS
    HARRELL, FE
    CALIFF, RM
    PRYOR, DB
    LEE, KL
    ROSATI, RA
    [J]. JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 1982, 247 (18): : 2543 - 2546
  • [7] Machine Learning-Guided Adjuvant Treatment of Head and Neck Cancer
    Howard, Frederick Matthew
    Kochanny, Sara
    Koshy, Matthew
    Spiotto, Michael
    Pearson, Alexander T.
    [J]. JAMA NETWORK OPEN, 2020, 3 (11)
  • [8] DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network
    Katzman, Jared L.
    Shaham, Uri
    Cloninger, Alexander
    Bates, Jonathan
    Jiang, Tingting
    Kluger, Yuval
    [J]. BMC MEDICAL RESEARCH METHODOLOGY, 2018, 18
  • [9] Kim DW, 2019, SCI REP-UK, V9, DOI [10.1038/s41598-019-43372-7, 10.1038/s41598-018-36760-y]
  • [10] Predicting Metastasis Risk in Pancreatic Neuroendocrine Tumors Using Deep Learning Image Analysis
    Klimov, Sergey
    Xue, Yue
    Gertych, Arkadiusz
    Graham, Rondell P.
    Jiang, Yi
    Bhattarai, Shristi
    Pandol, Stephen J.
    Rakha, Emad A.
    Reid, Michelle D.
    Aneja, Ritu
    [J]. FRONTIERS IN ONCOLOGY, 2021, 10