[1]徐方笛,范晓东.基于Deepsurv模型预测非转移性前列腺癌患者的生存率[J].医学信息,2024,37(08):52-55.[doi:10.3969/j.issn.1006-1959.2024.08.009]
　XU Fang-di,FAN Xiao-dong.Prediction on Survival Rate of Patients with Non-metastatic Prostate Cancer Based on Deepsurv Model[J].Journal of Medical Information,2024,37(08):52-55.[doi:10.3969/j.issn.1006-1959.2024.08.009]
点击复制

基于Deepsurv模型预测非转移性前列腺癌患者的生存率()
分享到：

医学信息[ISSN:1006-1959/CN:61-1278/R]

卷:
37卷
期数:
2024年08期
页码:
52-55
栏目:
临床信息学
出版日期:
2024-04-15

文章信息/Info

Title:
Prediction on Survival Rate of Patients with Non-metastatic Prostate Cancer Based on Deepsurv Model
文章编号:
1006-1959（2024）08-0052-04
作者:
徐方笛; 范晓东
（吉林化工学院信息与控制工程学院1，理学院2，吉林 吉林 132022）
Author(s):
XU Fang-di; FAN Xiao-dong
(College of Information and Control Engineering1,Faculty of Science2,Jilin Institute of Chemical Technology,Jilin 132022,Jilin,China)
关键词:
Deepsurv深度神经网络模型; 非转移性前列腺癌; 生存预测
Keywords:
Deepsurv deep neural network model; Non-metastatic prostate cancer; Survival prediction
分类号:
R737.25
DOI:
10.3969/j.issn.1006-1959.2024.08.009
文献标志码:
A
摘要:
目的 建立Deepsurv深度神经网络模型与Cox比例风险回归模型并比较两种模型对非转移性前列腺癌症患者生存时间的预测性能。方法 从SEER数据库中选择2014-2018年确定诊断为非转移性前列腺癌的男性患者，将患者数据集按照8∶2划分为训练集和测试集，构建Deepsurv深度神经网络模型的基本结构。利用随机超参数优化搜索算法获得预定义范围内的最优网络超参数，建立模型后在训练集上训练，并在测试集上测试。通过一致性指数（C-index）、ROC曲线下面积（AUC）和Brier分数（Brier Score）比较Deepsurv深度神经网络模型和Cox比例风险回归模型对非转移性前列腺癌症患者1、3年生存情况的预测性能。结果 建立了以患者年龄、前列腺特异性抗原（PSA）水平、前列腺癌组织恶性程度（Gleason分级）、肿瘤分期（T分期）和活检核心阳性总数为预后因素的预测模型。Deepsurv深度神经网络模型的C-index为0.713，高于Cox比例风险回归模型的0.654；Deepsurv深度神经网络模型预测患者1、3年生存率的Brier Score为0.312、0.229，低于Cox比例风险回归模型的0.356、0.241；ROC曲线显示，Deepsurv深度神经网络模型预测患者1、3年生存率的AUC为0.680、0.652，高于Cox比例风险回归模型的0.631、0.649。结论 Deepsurv深度神经网络模型在预测非转移性前列腺癌患者的生存方面的表现优于传统的Cox比例风险回归模型。
Abstract:
Objective To establish a Deepsurv deep neural network model and a Cox proportional hazard regression model and compare the predictive performance of the two models on the survival time of patients with non-metastatic prostate cancer.Methods Male patients diagnosed with non-metastatic prostate cancer from 2014 to 2018 were selected from the SEER database. The patient data set was divided into training set and test set according to 8∶2. The basic structure of the Deepsurv deep neural network model was constructed. The random hyperparameter optimization search algorithm was used to obtain the optimal network hyperparameters within the predefined range. After the model was established, it was trained on the training set and tested on the test set. The predictive performance of Deepsurv deep neural network model and Cox proportional hazard regression model for 1-year and 3-year survival of patients with non-metastatic prostate cancer was compared by consistency index (C-index), area under the ROC curve (AUC) and Brier score (Brier Score).Results A predictive model was established with patient age, prostate specific antigen (PSA) level, malignant degree of prostate cancer tissue (Gleason grade), tumor stage (T stage) and total number of positive biopsy cores as prognostic factors. The C-index of the Deepsurv deep neural network model was 0.713, which was higher than 0.654 of the Cox proportional hazard regression model. The Brier Scores of the Deepsurv deep neural network model for predicting the 1-year and 3-year survival rates of patients were 0.312 and 0.229, which were lower than 0.356 and 0.241 of the Cox proportional hazard regression model. The ROC curve showed that the AUC of the Deepsurv deep neural network model for predicting the 1-year and 3-year survival rates of patients was 0.680 and 0.652, which was higher than 0.631 and 0.649 of the Cox proportional hazards regression model.Conclusion Deepsurv deep neural network model is superior to the traditional Cox proportional hazard regression model in predicting the survival of patients with non-metastatic prostate cancer.

参考文献/References:

[1]Taitt HE.Global Trends and Prostate Cancer: A Review of Incidence,Detection, and Mortality as Influenced by Race, Ethnicity, and Geographic Location[J].American Journal of Men’s Health,2018,12(6):807-823.[2]Donovan JL,Hamdy FC,Lane JA.Patient-reported Outcomes after Monitoring, Surgery,or Radiotherapy for Prostate Cancer[J].The New England Journal of Medicine,2016,375(15):1425-1437.[3]Hamdy FC,Donovan JL,Lane JA.10-Year Outcomes after Monitoring, Surgery, or Radi-otherapy for Localized Prostate Cancer[J].The New England Journal of Medicine,2016,375(15):1415-1424.[4]Wilt TJ,Jones KM,Barry MJ,et al.Follow-up of Prostatectomy versusObservation for Early Prostate Cancer[J].The New England Journal of Medicine,2017,377(2):132-142.[5]李世海,李强,张卫东,等.前列腺癌长期持续内分泌治疗的临床特点及预后因素分析[J].临床泌尿外科杂志,2020,35(11):891-896.[6]张悦,武振宇.第二原发结直肠癌对前列腺癌患者生存情况影响的分析[J].中国卫生统计,2020,37(3):444-447.[7]Katzman JL,Shaham U,Cloninger A,et al.DeepSurv: personalized treatment recomme-nder system using a Cox proportional hazards deep neural network[J].BMC Medical Research Methodology,2018,18(1):18-24.[8]Austin PC.Generating survival times to simulate cox proportional hazards models with time-varying covariates[J].Stat Med,2012,31(29):3946-3958.[9]Lee C,Light A,Alaa A,et al.Application of a novel machine learning framework for pr-edicting non-metastatic prostate cancer-specific mortality in men using the Surveillance,Epidemiology, and End Results (SEER) database[J].The Lancet Digital Health,2021,3(3):e138-e146.[10]Sanda MG,Cadeddu JA,Kirkby E,et al.Clinically localized prostate cancer: AUA/ASTRO/SUOguideline. Part I: risk stratification, shared decision making, and care options[J].The Journal of Urology,2018,199(3):683-690.[11]Zelic R,Garmo H,Zugna D,et al.Predicting prostate cancer death with different pretreatmentrisk stratification tools: a head-to-head comparison in a nationwide cohort-study[J].Eur Urol,2020,77(2):180-188.[12]Bergstra J,Bengio Y.Random search for hyper-parameter optimization[J].J Mach Learn Res,2012,13(1):281-305.[13]邱海波,曹素梅,徐瑞华.基于2020年全球流行病学数据分析中国癌症发病率、死亡率和负担的时间趋势及与美国和英国数据的比较[J].癌症,2022,41(4):165-177.[14]Gerds TA,Schumacher M.Consistent estimation of the expected Brier score in gener-al survival models with right-censored event times[J].Biometr J,2006,48(6):1029-1040.[15]Heagerty PJ,Lumley T,Pepe MS.Time-dependent ROC curves for censored survival data and a diagnostic marker[J].Biometrics,2000,56(2):337-344.[16]田春兰,王烈宏.基于SEER数据库分析年轻T期宫颈癌患者生存的影响[J].医学信息,2023,36(7):36-40.[17]殷桂草,田浩宇,田锋,等.以PSA筛查为基础前列腺癌早期诊断与治疗的研究[J].蚌埠医学院学报,2023,48(4):441-444.[18]Doll KM,Rademaker A,Sosa JA.Practical Guide to Surgical Data Sets: Surveillance,Epi-demiology,and End Results(SEER) Database[J].JAMA Surg,2018,153(6):588-589.[19]Mi X,Zou F,Zhu R.Bagging and deep learning in optimal individualized treatment rules[J].Biometrics,2019,75(2):674-684.[20]任昱恺,林宗祥,韦柏充,等.基于SEER数据库肺腺鳞癌淋巴结转移预测模型的构建[J].河南医学研究,2022,31(7):1198-1203.

更新日期/Last Update: 1900-01-01