Artificial Intelligence Models for Predicting Iron Deficiency Anemia and Iron Serum Level Based on Accessible Laboratory Data

Iron deficiency anemia (IDA) is the most common nutritional deficiency worldwide. Measuring serum iron is time consuming, expensive and not available in most hospitals. In this study, based on four accessible laboratory data (MCV, MCH, MCHC, Hb/RBC), we developed an artificial neural network (ANN) and an adaptive neuro-fuzzy inference system (ANFIS) to diagnose the IDA and to predict serum iron level. Our results represent that the neural network analysis is superior to ANFIS and logistic regression models in diagnosing IDA. Moreover, the results show that the ANN is likely to provide an accurate test for predicting serum iron levels with high accuracy and acceptable precision.

[1]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[2]  J A Swets,et al.  Measuring the accuracy of diagnostic systems. , 1988, Science.

[3]  J. Cook,et al.  Iron deficiency: definition and diagnosis , 1989, Journal of internal medicine.

[4]  Kathleen Steinhöfel,et al.  Artificial intelligence in medicine , 1989 .

[5]  G L Wied,et al.  Artificial neural networks and their use in quantitative pathology. , 1990, Analytical and quantitative cytology and histology.

[6]  P K Sharpe,et al.  Artificial neural networks within medical decision support systems. , 1994, Scandinavian journal of clinical and laboratory investigation. Supplementum.

[7]  Patrick van der Smagt,et al.  Introduction to neural networks , 1995, The Lancet.

[8]  K. J. Dalton,et al.  Artificial neural networks for decision support in clinical medicine. , 1995, Annals of medicine.

[9]  J V Tu,et al.  Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. , 1996, Journal of clinical epidemiology.

[10]  M. Worwood.  The laboratory assessment of iron status--an update. , 1997, Clinica chimica acta; international journal of clinical chemistry.

[11]  G Reibnegger,et al.  Artificial Neural Networks in Laboratory Medicine and Medical Outcome Prediction , 1999, Clinical chemistry and laboratory medicine.

[12]  J. Haas,et al.  Iron-Deficiency Anemia: Reexamining the Nature and Magnitude of the Public Health Problem Iron Deficiency and Reduced Work Capacity: A Critical Review of the Research to Determine a Causal Relationship 1,2 , 2001 .

[13]  Michael N. Vrahatis,et al.  Artificial nonmonotonic neural networks , 2001, Artif. Intell..

[14]  P. Snow,et al.  Introduction to artificial neural networks for physicians: Taking the lid off the black box , 2001, The Prostate.

[15]  J. Halterman,et al.  Iron deficiency and cognitive achievement among school-aged children and adolescents in the United States. , 2001, Pediatrics.

[16]  Yu-Chuan Li,et al.  Neural network modeling to predict the hypnotic effect of propofol bolus induction , 2002, AMIA.

[17]  Paulo J. G. Lisboa,et al.  A review of evidence of health benefit from artificial neural networks in medical intervention , 2002, Neural Networks.

[18]  Yu-Chuan Li,et al.  Stratification of Adverse Outcomes by Preoperative Risk Factors in Coronary Artery Bypass Graft Patients: An Artificial Neural Network Prediction Model , 2003, AMIA.

[19]  David A Winkler,et al.  Neural networks as robust tools in drug lead discovery and development , 2004, Molecular biotechnology.

[20]  B. Grosbois,et al.  [Human iron deficiency]. , 2005, Bulletin de l'Academie nationale de medecine.

[21]  B. Grosbois,et al.  Les carences en fer chez l’homme , 2005 .

[22]  Mohammad Ghodsi,et al.  Comparison of artificial neural network and logistic regression models for prediction of mortality in head trauma based on initial clinical data , 2005, BMC Medical Informatics Decis. Mak..

[23]  Shahriar Gharibzadeh,et al.  Modeling force-velocity relation in skeletal muscle isotonic contraction using an artificial neural network , 2007, Biosyst..

[24]  U. Ghoshal,et al.  Models for prediction of mortality from cirrhosis with special reference to artificial neural network: a critical review , 2008, Hepatology international.

[25]  Shahriar Gharibzadeh,et al.  A Novel Method for Diagnosing Cirrhosis in Patients with Chronic Hepatitis B: Artificial Neural Network Approach , 2011, Journal of Medical Systems.