A Novel Metric for Developing Easy-to-Use and Accurate Clinical Prediction Models

The Time-cost Information Criterion

Bibliographic Data

ID9099219
AuthorsSei J Lee (0000-0001-7864-5341, Department of Medicine, Division of Geriatrics, University of California, San Francisco, corresponding author), Alexander K Smith (0000-0002-9276-0861, Department of Medicine, Division of Geriatrics, University of California, San Francisco, corresponding author), L Grisell Diaz-Ramirez (Department of Medicine, Division of Geriatrics, University of California, San Francisco), L Grisell Diaz‐Ramirez (0000-0003-1621-9309, San Francisco VA Medical Center, corresponding author), Kenneth E Covinsky (Department of Medicine, Division of Geriatrics, University of California, San Francisco, corresponding author), Siqi Gan (0009-0004-8050-570X, Department of Medicine, Division of Geriatrics, University of California, San Francisco, corresponding author), Catherine L Chen (0000-0002-1424-6664, Department of Anesthesia & Perioperative Care, University of California), William J Boscardin (Department of Medicine, Division of Geriatrics, University of California, San Francisco, corresponding author)
Year2021
Volume59
Issue5
Pages418-424
Publication date2021-05-01
Peer ReviewedYes
Open AccessNo
TypeARTICLE
VenueMedical Care (JOURNAL)
Journal identifiersISSN: 0025-7079 • E-ISSN: 1537-1948
PublisherOvid Technologies (Wolters Kluwer Health) (PUBLISHER)
DOI10.1097/mlr.0000000000001510
PMID33528231
OpenAlexW3128797352
LanguageEN
References cited20

BACKGROUND: Guidelines recommend that clinicians use clinical prediction models to estimate future risk to guide decisions. For example, predicted fracture risk is a major factor in the decision to initiate bisphosphonate medications. However, current methods for developing prediction models often lead to models that are accurate but difficult to use in clinical settings. OBJECTIVE: The objective of this study was to develop and test whether a new metric that explicitly balances model accuracy with clinical usability leads to accurate, easier-to-use prediction models. METHODS: We propose a new metric called the Time-cost Information Criterion (TCIC) that will penalize potential predictor variables that take a long time to obtain in clinical settings. To demonstrate how the TCIC can be used to develop models that are easier-to-use in clinical settings, we use data from the 2000 wave of the Health and Retirement Study (n=6311) to develop and compare time to mortality prediction models using a traditional metric (Bayesian Information Criterion or BIC) and the TCIC. RESULTS: We found that the TCIC models utilized predictors that could be obtained more quickly than BIC models while achieving similar discrimination. For example, the TCIC identified a 7-predictor model with a total time-cost of 44 seconds, while the BIC identified a 7-predictor model with a time-cost of 119 seconds. The Harrell C-statistic of the TCIC and BIC 7-predictor models did not differ (0.7065 vs. 0.7088, P=0.11). CONCLUSION: Accounting for the time-costs of potential predictor variables through the use of the TCIC led to the development of an easier-to-use mortality prediction model with similar discrimination

Data science · Metric (unit) · Operations management · Artificial Intelligence in Healthcare and Education · Bone health and osteoporosis research · Computer Science · Engineering · Statistical Methods in Epidemiology

Tools

Open DOIOpen Access