Prediction of the hemoglobin level in hemodialysis patients using machine learning techniques

Patients who suffer from chronic renal failure (CRF) tend to suffer from an associated anemia as well. Therefore, it is essential to know the hemoglobin (Hb) levels in these patients. The aim of this paper is to predict the hemoglobin (Hb) value using a database of European hemodialysis patients provided by Fresenius Medical Care (FMC) for improving the treatment of this kind of patients. For the prediction of Hb, both analytical measurements and medication dosage of patients suffering from chronic renal failure (CRF) are used. Two kinds of models were trained, global and local models. In the case of local models, clustering techniques based on hierarchical approaches and the adaptive resonance theory (ART) were used as a first step, and then, a different predictor was used for each obtained cluster. Different global models have been applied to the dataset such as Linear Models, Artificial Neural Networks (ANNs), Support Vector Machines (SVM) and Regression Trees among others. Also a relevance analysis has been carried out for each predictor model, thus finding those features that are most relevant for the given prediction.

[1]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[2]  S. C. Johnson.  Hierarchical clustering schemes , 1967, Psychometrika.

[3]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[4]  Sergios Theodoridis,et al.  Pattern Recognition , 1998, IEEE Trans. Neural Networks.

[5]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[6]  M. Brier,et al.  Randomized trial of model predictive control for improved anemia management. , 2010, Clinical journal of the American Society of Nephrology : CJASN.

[7]  R Bellazzi,et al.  Drug delivery optimization through Bayesian networks. , 1992, Proceedings. Symposium on Computer Applications in Medical Care.

[8]  S. Fishbane,et al.  Hemoglobin cycling in hemodialysis patients treated with recombinant human erythropoietin. , 2005, Kidney international.

[9]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[10]  Hong-Jian Zhu,et al.  Role of ERK1/2 and p38 mitogen-activated protein kinases in the regulation of thrombospondin-1 by TGF-beta1 in rat proximal tubular cells and mouse fibroblasts. , 2005, Journal of the American Society of Nephrology : JASN.

[11]  R. Koenker,et al.  Regression Quantiles , 2007 .

[12]  Ethem Alpaydin,et al.  Introduction to machine learning , 2004, Adaptive computation and machine learning.

[13]  Sergios Theodoridis,et al.  Pattern Recognition, Fourth Edition , 2008 .

[14]  D. Marcelli,et al.  Managing Complexity at Dialysis Service Centers across Europe , 2006, Blood Purification.

[15]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[16]  Andrew R. Webb,et al.  Statistical Pattern Recognition , 1999 .

[17]  Jacek M. Zurada,et al.  Individualization of pharmacological anemia management using reinforcement learning , 2005, Neural Networks.

[18]  Jürgen Schmidhuber,et al.  A reinforcement learning approach for individualizing erythropoietin dosages in hemodialysis patients , 2009, Expert Syst. Appl..

[19]  J. Lazarus,et al.  Effect of variability in anemia management on hemoglobin outcomes in ESRD. , 2003, American journal of kidney diseases : the official journal of the National Kidney Foundation.

[20]  Stephen Grossberg,et al.  The ART of adaptive pattern recognition by a self-organizing neural network , 1988, Computer.

[21]  S. Fishbane,et al.  Hemoglobin variability in epoetin-treated hemodialysis patients. , 2003, Kidney international.

[22]  M. Brier,et al.  Predictive modeling for improved anemia management in dialysis patients , 2011, Current opinion in nephrology and hypertension.

[23]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[24]  VectorRegressionAlex J. Smola.  A Tutorial on Support Vector Regression Produced as Part of the Esprit Working Group in Neural and Computational Learning Ii, Neurocolt2 27150 , 1998 .

[25]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[26]  Adrian Covic,et al.  Erythropoiesis Stimulatory Agent- Resistant Anemia in Dialysis Patients: Review of Causes and Management , 2009, Blood Purification.

[27]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .

[28]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[29]  M. Burnier,et al.  Would artificial neural networks implemented in clinical wards help nephrologists in predicting epoetin responsiveness? , 2006, BMC nephrology.

[30]  Kdoqi.  KDOQI Clinical Practice Guideline and Clinical Practice Recommendations for anemia in chronic kidney disease: 2007 update of hemoglobin target. , 2007 .