Related Experiment Video
Updated: May 3, 2026
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Independent external validation of the LIFE-HF clinical prediction model using the GUIDE-IT trial
Ricky D Turgeon1,2, Nathaniel M Hawkins2, Mohsen Sadatsafavi1
1Collaboration for Outcomes Research and Evaluation, Faculty of Pharmaceutical Sciences, University of British Columbia, Room 5523-2405 Wesbrook Mall, Vancouver, British Columbia, Canada V6T 1Z3.
Insights
The LIFE-HF models for heart failure (HF) prognosis showed good discrimination but underpredicted risk in a North American cohort. The mortality model may aid decision-making, but the composite model needs further validation.
Area of Science:
- Cardiology
- Medical Prognostics
- Health Outcomes Research
Background:
- Accurate prognostication is crucial for heart failure (HF) management.
- The LIFE-HF models are novel tools for predicting HF outcomes.
- Independent external validation of LIFE-HF models is needed.
Purpose of the Study:
- To externally validate the LIFE-HF models in a contemporary North American population.
- To assess the performance of LIFE-HF models for predicting 1-year all-cause death and a composite of death or HF hospitalization.
Main Methods:
- External validation using patient-level data from the GUIDE-IT trial.
- Assessment of discrimination (AUROC) and calibration (O/E ratios, slopes, curves).
- Evaluation of prediction error and net clinical benefit using decision curve analysis.
Main Results:
- The mortality model showed good discrimination (AUROC 0.77) but underprediction and underfitting.
- The composite model demonstrated moderate discrimination (AUROC 0.69) with underprediction and overfitting.
- The mortality model provided net clinical benefit, unlike the composite model.
Conclusions:
- LIFE-HF models exhibit good discrimination but systematically underpredict 1-year risk in high-risk HF patients.
- The mortality model shows potential for supporting risk-informed clinical decisions.
- The composite model requires additional validation before clinical application.
Introduction:
Accurate prognostication is central to decision-making in heart failure (HF). The recently-developed LIFE-HF models offer promise, but their performance has not been independently and externally validated. The aim of this study was to assess the external validity of the LIFE-HF models in a contemporary North American population.
Methods:
We externally validated the LIFE-HF models for 1-year all-cause death and the composite of death or HF hospitalization using patient-level data from the GUIDE-IT trial. All LIFE-HF predictors were available; missing data were handled using multiple imputation. Predicted risks were calculated using original LIFE-HF model equations. We assessed model discrimination using time-dependent area under the receiver operating characteristic curve (AUROC), calibration [observed-to-expected (O/E) ratios, calibration slopes and curves], overall prediction error, and net benefit using decision curve analysis.
Results:
The validation cohort included 801 participants (median age 64 years, 69% male). The mortality model demonstrated good discrimination [AUROC 0.77, 95% confidence interval (CI): 0.72-0.82], but underprediction (O/E 1.28, 95% CI: 1.01-1.54) and underfitting (calibration slope 1.58, 95% CI: 1.20-1.95). The composite model showed moderate discrimination (AUROC 0.69, 95% CI: 0.64-0.73), underprediction (O/E 1.40, 95% CI: 1.25-1.54), and overfitting (calibration slope 0.82, 95% CI: 0.63-1.00). Decision curve analysis showed net clinical benefit for the mortality model, but not the composite model, over a broad range of risk thresholds.
Conclusion:
In a contemporary, high-risk North American HF with reduced ejection fraction cohort, the LIFE-HF models showed good discrimination but systematically underpredicted 1-year risk. The mortality model may support risk-informed decision-making, whereas the composite model requires further validation.
Related Concept Videos
01:03Data Validation
Nursing assessment guides are generally based on holistic models rather than medical...
01:16Clinical Trials
There are four phases in a clinical trial. A phase one...
01:11Clinical Trials: Overview
01:23Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
01:15Bioavailability Study Design: Healthy Subjects Versus Patients