How to develop a more accurate risk prediction model when there are few events

被引：486

作者：

Pavlou, Menelaos ^{[1
]}

Ambler, Gareth ^{[1
]}

Seaman, Shaun R. ^{[2
]}

Guttmann, Oliver ^{[3
]}

Elliott, Perry ^{[4
]}

King, Michael ^{[5
]}

Omar, Rumana Z. ^{[1
]}

机构：

[1] UCL, Dept Stat Sci, London WC1E 6BT, England

[2] MRC, Cambridge, England

[3] UCL, Inst Cardiovasc Sci, Sch Life & Med Sci, London WC1E 6BT, England

[4] Heart Hosp, Inherited Cardiac Dis Unit, London, England

[5] UCL, Div Psychiat, London WC1E 6BT, England

来源：

BMJ-BRITISH MEDICAL JOURNAL | 2015年 / 351卷

基金：

英国医学研究理事会;

关键词：

REGRESSION-ANALYSIS; PROGNOSIS;

D O I：

10.1136/bmj.h3868

中图分类号：

R5 [内科学];

学科分类号：

1002 ; 100201 ;

摘要：

When the number of events is low relative to the number of predictors, standard regression could produce overfitted risk models that make inaccurate predictions. Use of penalised regression may improve the accuracy of risk prediction

引用

页数：5

共 22 条

[1] Generic, simple risk stratification model for heart valve surgery [J].

Ambler, G ;

Omar, RZ ;

Royston, P ;

Kinsman, R ;

Keogh, BE ;

Taylor, KM .

CIRCULATION, 2005, 112 (02) :224-231

[2] An evaluation of penalised survival methods for developing prognostic models with rare events [J].

Ambler, G. ;

Seaman, S. ;

Omar, R. Z. .

STATISTICS IN MEDICINE, 2012, 31 (11-12) :1150-1161

[3]

Collins GS, 2015, ANN INTERN MED, V162, P55, DOI [10.7326/M14-0697, 10.1002/bjs.9736, 10.1016/j.eururo.2014.11.025, 10.1016/j.jclinepi.2014.11.010, 10.1038/bjc.2014.639, 10.1186/s12916-014-0241-z, 10.1136/bmj.g7594, 10.7326/M14-0698]

[4] General cardiovascular risk profile for use in primary care - The Framingham Heart Study [J].