Approaches to Predicting Outcomes in Patients with Acute Kidney Injury

Autor: Chirag R. Parikh, Joshua Bia, F. Perry Wilson, Danielle L. Saly, Jeffrey M. Testani, Alina Yang, Aditya Biswas, Janice Oh, Corey Triebwasser, Qisi Sun, Chess Stetson, Kris S. Chaisanguanthum
Rok vydání: 2017
Předmět:
Male
Time Factors
medicine.medical_treatment
030232 urology & nephrology
lcsh:Medicine
Biochemistry
law.invention
Mathematical and Statistical Techniques
0302 clinical medicine
Randomized controlled trial
law
Medicine and Health Sciences
Medicine
030212 general & internal medicine
lcsh:Science
Principal Component Analysis
Multidisciplinary
Mortality rate
Acute Kidney Injury
Middle Aged
Prognosis
Nephrology
Creatinine
Predictive value of tests
Physical Sciences
Regression Analysis
Female
Anatomy
Statistics (Mathematics)
Research Article
medicine.medical_specialty
Death Rates
Feature selection
Linear Regression Analysis
Research and Analysis Methods
Risk Assessment
03 medical and health sciences
Predictive Value of Tests
Renal Dialysis
Medical Dialysis
Linear regression
Humans
Hemoglobin
Statistical Methods
Intensive care medicine
Dialysis
Aged
Demography
Receiver operating characteristic
business.industry
lcsh:R
Biology and Life Sciences
Proteins
Kidneys
Renal System
Length of Stay
Models
Theoretical
Stepwise regression
Multivariate Analysis
People and Places
lcsh:Q
business
Biomarkers
Mathematics
Zdroj: PLoS ONE
PLoS ONE, Vol 12, Iss 1, p e0169305 (2017)
ISSN: 1932-6203
Popis: Despite recognition that Acute Kidney Injury (AKI) leads to substantial increases in morbidity, mortality, and length of stay, accurate prognostication of these clinical events remains difficult. It remains unclear which approaches to variable selection and model building are most robust. We used data from a randomized trial of AKI alerting to develop time-updated prognostic models using stepwise regression compared to more advanced variable selection techniques. We randomly split data into training and validation cohorts. Outcomes of interest were death within 7 days, dialysis within 7 days, and length of stay. Data elements eligible for model-building included lab values, medications and dosages, procedures, and demographics. We assessed model discrimination using the area under the receiver operator characteristic curve and r-squared values. 2241 individuals were available for analysis. Both modeling techniques created viable models with very good discrimination ability, with AUCs exceeding 0.85 for dialysis and 0.8 for death prediction. Model performance was similar across model building strategies, though the strategy employing more advanced variable selection was more parsimonious. Very good to excellent prediction of outcome events is feasible in patients with AKI. More advanced techniques may lead to more parsimonious models, which may facilitate adoption in other settings.
Databáze: OpenAIRE
Externí odkaz: