Usefulness of artificial neural networks to predict follow-up dietary protein intake in hemodialysis patients

Gabutti, Luca; Burnier, Michel; Mombelli, Giorgio; Malé, Francesca; Pellegrini, Lisa; Marone, Claudio
July 2004
Kidney International;Jul2004, Vol. 66 Issue 1, p399
Academic Journal
Usefulness of artificial neural networks to predict follow-up dietary protein intake in hemodialysis patients. Background. Artificial neural networks (ANN) represent a promising alternative to classical statistical and mathematic methods to solve multidimensional nonlinear problems. The aim of the study was to verify, by comparing the performance of ANN with that of experienced nephrologists, whether ANN are useful tools in hemodialysis to predict the follow-up (=1 month after the observation used for the prediction) dietary protein intake (PCR), and whether their performance is influenced by the size of the population and by the data pool used to built the model. Methods. A combined retrospective and prospective observational study was performed in two Swiss dialysis units (84 chronic hemodialysis patients, 500 monthly clinical observations and biochemical test results). Using mathematical models based on linear regressions to evaluate the variables, ANN were built and then prospectively and interinstitutionally compared with the ability of six experienced nephrologists to predict the follow-up PCR. Results. ANN compared with nephrologists gave a more accurate correlation between estimated and calculated follow-up PCR ( P < 0.001). The same superiority of ANN was also seen in the ability to detect a follow-up PCR <1.00 g/kg/day expressed as a percentage of correct predictions, sensitivity, specificity, and predictivity. The interinstitutional performance of the ANN is positively influenced by the size and the variability of the population used to build the mathematical model. Conclusion. The use of ANN significantly improves the ability of the experienced nephrologist to estimate and to detect an unsatisfactory (<1.00 g/kg/day) follow-up PCR. The size of the population selected to build the ANN is critical for his performance.


Related Articles

  • Nutrition in hemodialysis patients previously on a supplemented very low protein diet. Vendrely, Benoît; Chauveau, Philippe; Barthe, Nicole; El Haggan, Wael; Castaing, Françoise; De Précigout, Valérie; Combe, Christian; Aparicio, Michel // Kidney International;Apr2003, Vol. 63 Issue 4, p1491 

    Nutrition in hemodialysis patients previously on a supplemented very low protein diet. Background. Nutritional safety of protein-restricted diets in patients with chronic renal failure is controversial. In the present study, we have assessed the evolution of nutritional status after initiation...

  • Very low-protein diet plus ketoacids in chronic kidney disease and risk of death during end-stage renal disease: a historical cohort controlled study. Bellizzi, Vincenzo; Chiodini, Paolo; Cupisti, Adamasco; Viola, Battista Fabio; Pezzotta, Mauro; De Nicola, Luca; Minutolo, Roberto; Barsotti, Giuliano; Piccoli, Giorgina Barbara; Di Iorio, Biagio // Nephrology Dialysis Transplantation;Jan2015, Vol. 30 Issue 1, p71 

    “…the assiduous efforts of nephrologists around the world to search for a protective effect of reducing protein intake in CKD patients should be commended…”Background Very low-protein intake during chronic kidney disease (CKD) improves metabolic disorders and may delay...

  • Interventional Nephrology: A Growing Strategy for Optimal Patient Care. Banerjee, Satyaki; Thompson-Roach, Hayley // Nephrology Nursing Journal;Nov/Dec2008, Vol. 35 Issue 6, p599 

    The authors discuss the use of interventional nephrology as a strategy for optimal patient care. The focus of interventional nephrologists on performing procedures related to hemodialysis vascular access has reportedly led to improvements in coordination of care between such professionals. One...

  • An Adaptive Approach to Market Development Forecasting. Wang, S. // Neural Computing & Applications;1999, Vol. 8 Issue 1 

    In the field of time series models for forecasting, the commonly accepted fact is that no one model could be shown to be superior to all others. An effective time series model for forecasting must incorporate the specific characteristics of the targeted problem domain. This paper proposes a...

  • Cortical memory dynamics. Kairiss, Edward W.; Miranker, Willard L. // Biological Cybernetics;1998, Vol. 78 Issue 4, p277 

    Abstract. Biological memories have a number of unique features, including (1) hierarchical, reciprocally interacting layers, (2) lateral inhibitory interactions within layers, and (3) Hebbian synaptic modifications. We incorporate these key features into a mathematical and computational model in...

  • The integration of broiler chicken threonine responses data into neural network models. Ahmadi, H.; Golian, A. // Poultry Science;Nov2010, Vol. 89 Issue 11, p2535 

    In making general recommendations for amino acids, researchers might survey various published data on the responses of poultry to amino acids. In this way, the use of appropriate mathematical and statistical approaches may help researchers draw appropriate conclusions. The purpose of this study...

  • North Queensland nephrology pioneers. Washington, Wendy; de Jersey, Peter // Renal Society of Australasia Journal;Jul2009, Vol. 5 Issue 2, p59 

    In 1970 the first renal unit in Queensland outside the Brisbane was established in Rockhampton. The early challenging pioneering days are summarised. Technology and issues of distance were challenges in the vast regional distances of North Queensland.

  • Ketoanalogues May Help Delay Dialysis Initiation.  // Renal & Urology News;Sep2012, Vol. 11 Issue 9, p22 

    The article evaluates the effectiveness of a ketoanalogue-supplemented very-low-protein diet (sVLPD) over conventional LPD in delaying dialysis initiation in patients with chronic kidney disease by professors Liliana Garneata and Gabriel Mircescu in Bucharest, Romania.

  • Should protein intake be restricted in predialysis patients? WALSER, MACKENZIE; MITCH, WILLIAM E.; MARONI, BRADLEY J.; KOPPLE, JOEL D. // Kidney International;Mar1999, Vol. 55 Issue 3, p771 

    Examines whether protein intake should be restricted in predialysis patients. Benefits of a nutritional regimen; Symptoms and signs in patients with protein-restricted diets; Effect of protein restriction on the rate of loss of renal function; Objections to the use of low-protein regimes;...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics