临床预测模型常用统计模型及其SAS实现

doi:10.3969/j.issn.1673-5765.2024.05.003

中国卒中杂志 ›› 2024, Vol. 19 ›› Issue (5): 496-505.DOI: 10.3969/j.issn.1673-5765.2024.05.003

临床预测模型常用统计模型及其SAS实现

杨凯璇，谷鸿秋

北京 100070 首都医科大学附属北京天坛医院国家神经系统疾病临床医学研究中心

收稿日期:2024-04-15 出版日期:2024-05-20 发布日期:2024-05-20
通讯作者: 谷鸿秋 guhongqiu@yeah.net
基金资助:
国家自然科学基金项目（72004146）
北京市医院管理中心“青苗”人才计划（QML20210501）
北京市医院管理中心“培育”人才计划（PX2021024）

Common Clinical Prediction Statistical Models and SAS Implementation

YANG Kaixuan, GU Hongqiu

China National Clinical Research Center for Neurological Diseases, Beijing Tiantan Hospital, Capital Medical University, Beijing 100070, China

Received:2024-04-15 Online:2024-05-20 Published:2024-05-20
Contact: GU Hongqiu, E-mail: guhongqiu@yeah.net

摘要/Abstract

摘要： 临床预测模型在医学研究中的应用越来越广泛，欲达到良好的预测性能，选择正确的模型非常关键。对于预测模型类型的选择，预测结局的类型起着决定性作用。本文从数据类型的角度出发，将结局变量分为连续变量（正态分布、偏态分布）、分类变量（二分类、无序多分类、有序多分类）以及时间-事件变量（无竞争风险、有竞争风险），分别介绍不同类型结局变量的特点、对应的模型、建模案例以及SAS实现程序，以期为研究者构建预测模型提供参考。

关键词: 临床预测模型; 统计模型; 逻辑回归

Abstract: The application of clinical prediction models in medical research is becoming increasingly widespread. To achieve good predictive performance, selecting the correct model is crucial. Regarding the choice of prediction model, the type of prediction outcome plays a decisive role. This paper, from the perspective of data types, divided outcomes into continuous variables (normal distribution, skewed distribution), categorical variables (binary, nominal, ordinal), and time-to-event variables (with or without competing risks), introducing the characteristics of different types of outcomes, the model types, examples and SAS programs to serve as a reference for researchers to develop prediction models.

Key words: Clinical prediction model; Statistical model; Logistic regression

中图分类号:

杨凯璇, 谷鸿秋. 临床预测模型常用统计模型及其SAS实现[J]. 中国卒中杂志, 2024, 19(5): 496-505.

YANG Kaixuan, GU Hongqiu. Common Clinical Prediction Statistical Models and SAS Implementation[J]. Chinese Journal of Stroke, 2024, 19(5): 496-505.

参考文献

[1] HUANG C C，CHOU K H，LEE W J，et al. Brain white matter hyperintensities-predicted age reflects neurovascular health in middle-to-old aged subjects[J/OL]. Age Ageing，2022，51（5）：afac106[2024-04-10]. https://doi.org/10.1093/ageing/afac106.
[2] CUI T T，WANG Z Y，GU H，et al. Gamma distribution based predicting model for breast cancer drug response based on multi-layer feature selection[J/OL]. Front Genet，2023，14：1095976[2024-04-10]. https://doi.org/10.3389/fgene.2023.1095976.
[3] CARTER E M，POTTS H W. Predicting length of stay from an electronic patient record system：a primary total knee replacement example[J/OL]. BMC Med Inf Decis Mak，2014，14：26[2024-04-10]. https://doi.org/10.1186/1472-6947-14-26.
[4] LE GAL G，RIGHINI M，ROY P M，et al. Prediction of pulmonary embolism in the emergency department：the revised Geneva score[J]. Ann Intern Med，2006，144（3）：165-171.
[5] NIJMAN R G，VERGOUWE Y，THOMPSON M，et al. Clinical prediction model to aid emergency doctors managing febrile children at risk of serious bacterial infections：diagnostic study[J/OL]. BMJ，2013，346：f1706[2024-04-10]. https://doi.org/10.1136/bmj.f1706.
[6] ZHANG M Y，MLYNASH M，SAINANI K L，et al. Ordinal prediction model of 90-day modified Rankin scale in ischemic stroke[J/OL]. Front Neurol，2021，12：727171[2024-04-10]. https://doi.org/10.3389/fneur.2021.727171.
[7] GALOVIC M，DÖHLER N，ERDÉLYI-CANAVESE B，et al. Prediction of late seizures after ischaemic stroke with a novel prognostic model（the SeLECT score）：a multivariable prediction model development and validation study[J]. Lancet Neurol，2018，17（2）：143-152.
[8] CHOI E，SANYAL N，DING V Y，et al. Development and validation of a risk prediction model for second primary lung cancer[J]. J Natl Cancer Inst，2022，114（1）：87-96.
[9] SHUI A M，KIM P，ARIBINDI V，et al. Dynamic risk prediction for hospital-acquired pressure injury in adult critical care patients[J/OL]. Crit Care Explor，2021，3（11）：e0580[2024-04-10]. https://doi.org/10.1097/CCE.0000000000000580.
[10] NGUYEN H，IVERS R，JAN S，et al. Analysis of out-of-pocket costs associated with hospitalised injuries in Vietnam[J/OL]. BMJ Glob Health，2017，2（1）：e000082[2024-04-10]. https://doi.org/10.1136/bmjgh-2016-000082.
[11] JAJA B N R，SAPOSNIK G，LINGSMA H F，et al. Development and validation of outcome prediction models for aneurysmal subarachnoid haemorrhage：the SAHIT multinational cohort study[J/OL]. BMJ，2018，360：j5745[2024-04-10]. https://doi.org/10.1136/bmj.j5745.
[12] QI M M，SHAO X F，LI D，et al. Establishment and validation of a clinical model for predicting diabetic ketosis in patients with type 2 diabetes mellitus[J/OL]. Front Endocrinol（Lausanne），2022，13：967929[2024-04-10]. https://doi.org/10.3389/fendo.2022.967929.
[13] YANG X L，LI J X，HU D S，et al. Predicting the 10-year risks of atherosclerotic cardiovascular disease in Chinese population：the China-PAR project（prediction for ASCVD risk in China）[J]. Circulation，2016，134（19）：1430-1440.
[14] GERDS T A，SCHEIKE T H，ANDERSEN P K. Absolute risk regression for competing risks：interpretation，link functions，and prediction[J]. Stat Med，2012，31（29）：3921-3930.
[15] FINE J P，GRAY R J. A proportional hazards model for the subdistribution of a competing risk[J]. J Am Stat Assoc，1999，94（446）：496-509.
[16] STEYERBERG E W. Clinical prediction models：a practical approach to development，validation，and updating[M]. 2nd ed. Switzerland：Springer，2019：87-88.
[17] DE GLAS N A，KIDERLEN M，VANDENBROUCKE J P，et al. Performing survival analyses in the presence of competing risks：a clinical example in older breast cancer patients[J/OL]. J Natl Cancer Inst，2015，108（5）：djv366[2024-04-10]. https://doi.org/10.1093/jnci/djv366.
[18] CHRISTODOULOU E，MA J，COLLINS G S，et al. A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models[J/OL]. J Clin Epidemiol，2019，110：12-22[2024-04-10]. https://doi.org/10.1016/j.jclinepi.2019.02.004.

临床预测模型常用统计模型及其SAS实现

Common Clinical Prediction Statistical Models and SAS Implementation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

[1]	谷鸿秋. 临床预测模型的困境与机遇[J]. 中国卒中杂志, 2024, 19(5): 481-487.
[2]	姜英玉, 谷鸿秋. 临床预测模型开发与验证的样本量估算[J]. 中国卒中杂志, 2024, 19(5): 489-495.
[3]	陈麒百, 曾吟. 临床预测模型在医保付费中的应用前景探索[J]. 中国卒中杂志, 2024, 19(5): 520-523.
[4]	谷鸿秋, 杨凯璇, 姜英玉, 杜柯瑾, 饶蓁蓁, 杨昕, 王春娟, 熊云云, 荆京, 李子孝. 缺血性卒中患者卒中复发风险预测模型研究进展及展望 [J]. 中国卒中杂志, 2023, 18(07): 731-739.
[5]	王昊玥, 王俊峰. 临床预测模型研究中的常见误区[J]. 中国卒中杂志, 2023, 18(07): 758-769.
[6]	马佳丽, 王玉青, 王恺闻, 东晶晶, 李永秋. 脑小血管病总负荷的影响因素探索及临床预测模型建立[J]. 中国卒中杂志, 2022, 17(05): 523-528.