Developing prediction models for clinical use using logistic regression: an overview

Abstract

Prediction models help healthcare professionals and patients make clinical decisions. The goal of an accurate prediction model is to provide patient risk stratification to support tailored clinical decision-making with the hope of improving patient outcomes and quality of care. Clinical prediction models use variables selected because they are thought to be associated (either negatively or positively) with the outcome of interest. Building a model requires data that are computer-interpretable and reliably recorded within the time frame of interest for the prediction. Such models are generally defined as either diagnostic, likelihood of disease or disease group classification, or prognostic, likelihood of response or risk of recurrence. We describe a set of guidelines and heuristics for clinicians to use to develop a logistic regression-based prediction model for binary outcomes that is intended to augment clinical decision-making.

Keywords: Review; logistic regression; predictive model.

Figure 1

Comparing performance of TREAT model to Mayo Clinic model using Brier scores. From ref (4). TREAT, Thoracic Research Evaluation And Treatment.

Figure 2

Comparing discrimination of TREAT model to Mayo Clinic model using AUC. From ref (4). TREAT, Thoracic Research Evaluation And Treatment; AUC, area under the receiver operating characteristic curve.