Key result
Prediction models using all available EHR data predicted mortality over 7 time horizons with c-statistics ranging from 0.72-0.76, with discrete time models performing better than time-to-event models.
Why the study?
Which categories of EHR data elements are needed to predict mortality over different time horizons in older patients undergoing hemodialysis?
Observational
Yes
Which categories of EHR data elements are needed to predict mortality over different time horizons in older patients undergoing hemodialysis?
Effect estimate: c-statistic 0.72-0.76
Different categories of EHR data are predictive of mortality over different time horizons in hemodialysis patients, with vital signs driving near-term predictions and demographics/comorbidities driving long-term predictions.
Moderate EHR model accuracy in hemodialysis warrants caution before clinical use; leaves open optimal data-element selection across time horizons.
OBJECTIVE: Electronic health records (EHRs) are a resource for "big data" analytics, containing a variety of data elements. We investigate how different categories of information contribute to prediction of mortality over different time horizons among patients undergoing hemodialysis treatment. MATERIAL AND METHODS: We derived prediction models for mortality over 7 time horizons using EHR data on older patients from a national chain of dialysis clinics linked with administrative data using LASSO (least absolute shrinkage and selection operator) regression. We assessed how different categories of information relate to risk assessment and compared discrete models to time-to-event models. RESULTS: The best predictors used all the available data (c-statistic ranged from 0.72-0.76), with stronger models in the near term. While different variable groups showed different utility, exclusion of any particular group did not lead to a meaningfully different risk assessment. Discrete time models performed better than time-to-event models. CONCLUSIONS: Different variable groups were predictive over different time horizons, with vital signs most predictive for near-term mortality and demographic and comorbidities more important in long-term mortality.
No takes yet. Share an insight, caveat, or question.
Goldstein et al. (2016) conducted an observational in Hemodialysis. Prediction models using EHR data was evaluated on Mortality over 7 time horizons (c-statistic 0.72-0.76). Prediction models using all available EHR data predicted mortality over 7 time horizons with c-statistics ranging from 0.72-0.76, with discrete time models performing better than time-to-event models.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: