External validation of the 2-year mortality prediction tool in hemodialysis patients developed using a Bayesian network
Maelys Granal, Sophie Brokhes-Le Calvez, Yves Dimitrov, François Chantrel, Claire Borni-Duval, Clotilde Muller, May Délia, Thierry Krummel, Thierry Hannedouche, Micher Ducher, Jean-Pierre Fauvel- Transplantation
- Nephrology
Abstract
Background and hypothesis
In recent years, a number of predictive models have appeared to predict the risk of medium-term mortality in haemodialysis patients, but only one, limited to patients aged over 70, has undergone sufficiently powerful external validation. Recently, using a national learning database and an innovative approach based on Bayesian networks and 14 carefully selected predictors, we have developed a clinical prediction tool to predict all-cause mortality at 2 years in all incident haemodialysis patients. In order to generalise the results of this tool and propose its use in routine clinical practice, we carried out an external validation using an independent external validation database.
Methods
A regional, multicenter, observational, retrospective cohort study was conducted to externally validate the tool for predicting 2-year all-cause mortality in incident and prevalent hemodialysis patients. This study recruited a total of 142 incident and 697 prevalent adult hemodialysis patients followed up in one of the 8 AURAL Alsace dialysis centers.
Results
In Incident patients, the 2-year all-cause mortality prediction tool had an area under the receiver curve of 0.73, an accuracy of 65%, a sensitivity of 71%, a specificity of 63%. In prevalent patients, the performance for the external validation were similar in terms of AUC-ROC, accuracy, and specificity but was lower in term of sensitivity.
Conclusion
The tool for predicting all-cause mortality at 2 years, developed using a Bayesian network and 14 routinely available explanatory variables, obtained satisfactory external validation in incident patients, but sensitivity was insufficient in prevalent patients.