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

Abstract

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.

Nonlinear model for estimating respiratory volume based on thoracoabdominal breathing movements

“…The if‐then rules of the ANFIS model are used to formulate the conditional statements that comprise fuzzy logic. Although these rules are powerful for distinguishing categorical variables with good accuracy, they cannot accurately predict continuous variables 47 …”

“…Although these rules are powerful for distinguishing categorical variables with good accuracy, they cannot accurately predict continuous variables. 47 Neural networks, which were derived from studies of the nervous systems, process information in parallel and are useful for pattern recognition. The nonlinear, adaptive and parallel processing features of ANN models have been used to obtain greater performance accuracy in outcome prediction, as compared with conventional statistical methods.…”

Modelling of Transcranial Magnetic Stimulation in One-Year Follow-Up Study of Patients with Minor Ischaemic Stroke

“…ANN proved to be very useful in the current analysis as it allowed us to assess the role of potential predictors of CMCT and MEP at month 12 as continuous outcomes, without the possible constraints of parametric models (e.g., normal distribution of the outcome, etc.). To note, ANN had been successfully used in other medical fields [Mecocci, 2002;Grossi, 2011;Azarkhish et al, 2012;etc. ] and, in neurology, in particular [Mecocci, 2002;Shanthi et al, 2009; for a recent overview see Atanassova & Dimitrov, 2011].…”

A fuzzy expert system design for iron deficiency anemia

“…Many methods exist in the literature to be utilized in the determination systems in the medical field. Among them, Fuzzy Logic [1][2][3][4], Fuzzy Neural Network [5,6], Synthetic Neural Networks [7,8], Expert Systems [9,11] and derivations of these methods have been mostly used. Some medical studies carried out with the method of fuzzy system which forms the basis of this study are given briefly in the following paragraphs.…”

“…Azarkish et al [7] tried to specify the iron deficiency anemia and iron serum levels in the ANN and ANFIS systems that are developed by them. They used the laboratory data for patients ranged in age from 38-73 years.…”