How to establish clinical prediction models

Yong Ho Lee, Heejung Bang, Dae Jung Kim

Research output: Contribution to journalReview article

33 Citations (Scopus)

Abstract

A clinical prediction model can be applied to several challenging clinical scenarios: Screening high-risk individuals for asymptomatic disease, predicting future events such as disease or death, and assisting medical decision-making and health education. Despite the impact of clinical prediction models on practice, prediction modeling is a complex process requiring careful statistical analyses and sound clinical judgement. Although there is no definite consensus on the best methodology for model development and validation, a few recommendations and checklists have been proposed. In this review, we summarize five steps for developing and validating a clinical prediction model: Preparation for establishing clinical prediction models; dataset selection; handling variables; model generation; and model evaluation and validation. We also review several studies that detail methods for developing clinical prediction models with comparable examples from real practice. After model development and vigorous validation in relevant settings, possibly with evaluation of utility/usability and fine-tuning, good models can be ready for the use in practice. We anticipate that this framework will revitalize the use of predictive or prognostic research in endocrinology, leading to active applications in real clinical practice.

Original languageEnglish (US)
Pages (from-to)38-44
Number of pages7
JournalEndocrinology and Metabolism
Volume31
Issue number1
DOIs
StatePublished - Mar 1 2016

Fingerprint

Asymptomatic Diseases
Endocrinology
Checklist
Health Education
Consensus
Research
Datasets
Clinical Decision-Making

Keywords

  • Clinical prediction model
  • Clinical usefulness
  • Development
  • Validation

ASJC Scopus subject areas

  • Endocrinology, Diabetes and Metabolism
  • Endocrinology

Cite this

How to establish clinical prediction models. / Lee, Yong Ho; Bang, Heejung; Kim, Dae Jung.

In: Endocrinology and Metabolism, Vol. 31, No. 1, 01.03.2016, p. 38-44.

Research output: Contribution to journalReview article

Lee, Yong Ho ; Bang, Heejung ; Kim, Dae Jung. / How to establish clinical prediction models. In: Endocrinology and Metabolism. 2016 ; Vol. 31, No. 1. pp. 38-44.
@article{08d25e0d00ac43f08ce3b7a64ee75a49,
title = "How to establish clinical prediction models",
abstract = "A clinical prediction model can be applied to several challenging clinical scenarios: Screening high-risk individuals for asymptomatic disease, predicting future events such as disease or death, and assisting medical decision-making and health education. Despite the impact of clinical prediction models on practice, prediction modeling is a complex process requiring careful statistical analyses and sound clinical judgement. Although there is no definite consensus on the best methodology for model development and validation, a few recommendations and checklists have been proposed. In this review, we summarize five steps for developing and validating a clinical prediction model: Preparation for establishing clinical prediction models; dataset selection; handling variables; model generation; and model evaluation and validation. We also review several studies that detail methods for developing clinical prediction models with comparable examples from real practice. After model development and vigorous validation in relevant settings, possibly with evaluation of utility/usability and fine-tuning, good models can be ready for the use in practice. We anticipate that this framework will revitalize the use of predictive or prognostic research in endocrinology, leading to active applications in real clinical practice.",
keywords = "Clinical prediction model, Clinical usefulness, Development, Validation",
author = "Lee, {Yong Ho} and Heejung Bang and Kim, {Dae Jung}",
year = "2016",
month = "3",
day = "1",
doi = "10.3803/EnM.2016.31.1.38",
language = "English (US)",
volume = "31",
pages = "38--44",
journal = "Endocrinology and Metabolism",
issn = "2093-596X",
publisher = "Korean Endocrine Society",
number = "1",

}

TY - JOUR

T1 - How to establish clinical prediction models

AU - Lee, Yong Ho

AU - Bang, Heejung

AU - Kim, Dae Jung

PY - 2016/3/1

Y1 - 2016/3/1

N2 - A clinical prediction model can be applied to several challenging clinical scenarios: Screening high-risk individuals for asymptomatic disease, predicting future events such as disease or death, and assisting medical decision-making and health education. Despite the impact of clinical prediction models on practice, prediction modeling is a complex process requiring careful statistical analyses and sound clinical judgement. Although there is no definite consensus on the best methodology for model development and validation, a few recommendations and checklists have been proposed. In this review, we summarize five steps for developing and validating a clinical prediction model: Preparation for establishing clinical prediction models; dataset selection; handling variables; model generation; and model evaluation and validation. We also review several studies that detail methods for developing clinical prediction models with comparable examples from real practice. After model development and vigorous validation in relevant settings, possibly with evaluation of utility/usability and fine-tuning, good models can be ready for the use in practice. We anticipate that this framework will revitalize the use of predictive or prognostic research in endocrinology, leading to active applications in real clinical practice.

AB - A clinical prediction model can be applied to several challenging clinical scenarios: Screening high-risk individuals for asymptomatic disease, predicting future events such as disease or death, and assisting medical decision-making and health education. Despite the impact of clinical prediction models on practice, prediction modeling is a complex process requiring careful statistical analyses and sound clinical judgement. Although there is no definite consensus on the best methodology for model development and validation, a few recommendations and checklists have been proposed. In this review, we summarize five steps for developing and validating a clinical prediction model: Preparation for establishing clinical prediction models; dataset selection; handling variables; model generation; and model evaluation and validation. We also review several studies that detail methods for developing clinical prediction models with comparable examples from real practice. After model development and vigorous validation in relevant settings, possibly with evaluation of utility/usability and fine-tuning, good models can be ready for the use in practice. We anticipate that this framework will revitalize the use of predictive or prognostic research in endocrinology, leading to active applications in real clinical practice.

KW - Clinical prediction model

KW - Clinical usefulness

KW - Development

KW - Validation

UR - http://www.scopus.com/inward/record.url?scp=84962745186&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962745186&partnerID=8YFLogxK

U2 - 10.3803/EnM.2016.31.1.38

DO - 10.3803/EnM.2016.31.1.38

M3 - Review article

VL - 31

SP - 38

EP - 44

JO - Endocrinology and Metabolism

JF - Endocrinology and Metabolism

SN - 2093-596X

IS - 1

ER -