Intelligent Systems Developed for the Early Detection of Chronic Kidney Disease

is paper aims to construct intelligence models by applying the technologies of arti�cial neural networks including backpropagation network (BPN), generalized feedforward neural networks (GRNN), and modular neural network (MNN) that are developed, respectively, for the early detection of chronic kidney disease (CKD). e comparison of accuracy, sensitivity, and speci�city among three models is subse�uently performed. e model of best performance is chosen. By leveraging the aid of this system, CKD physicians can have an alternative way to detect chronic kidney diseases in early stage of a patient. Meanwhile, it may also be used by the public for self-detecting the risk of contracting CKD.


Introduction
According to the statistical data announced by the Department of Health of Taiwan's government in 2010 [1], the mortality caused by kidney disease has been ranked in the 10th place in all causes of death in Taiwan and thousands of others are at increased risk.e mortality caused from kidney disease is estimated as 12.5 in every 100,000 people.As a result, it costs as high as 35 percent of health insurance budget to treat the chronic kidney disease (CKD) patients with the age over 65 years old and end-stage kidney disease patients in all ages.It occupies a huge amount of expenditures in national insurance budget.
Regarding the measurement of serious levels of CKD, presently glomerular �ltration rate (GFR) is the most commonly measuring indicator used in health institutions to estimate kidney health function.e physician in the health institution can calculate GFR from patient's blood creatinine, age, race, gender, and other factors depending upon the type of formal-recognized computation formulas [2,3] employed.e GFR may indicate the health of a patent's kidney and can also be taken to determine the stage of severity of a patient with or without kidney disease.
In this paper, we aim to develop a feasible intelligent model for detecting CKD for evaluating the severity of a patient with or without CKD.e input data for model development and testing is collected from the health examination which is periodically carried out by the collaborative teaching hospital of this research.

The Major Methods for Measuring Chronic Kidney Disease
As it is mentioned in prior section, the GFR is the most common method used to measure kidney health function.
It refers to the water �lterability of glomerular of people's kidney.e normal value should be between 90 and 120 mL/min/1.73m 2 (i.e., measured by mL per minute per 1.73 m 2 ).ere are three common computation methods of GFR, which are (1)  sometimes may enter into ��h stage pretty soon resulted in the necessity of dialysis or kidney transplant.Again, National Kidney Foundation's Kidney Disease Outcomes Quality Initiative (KDOQI) [3] provides a conceptual framework for the diagnosis of the severity stages of CKD based on the different function levels of glomerular �ltration rate (GFR).e new system represented a signi�cant conceptual change, since kidney disease historically had been categorized mainly by causes.e diagnosis of CKD relies on markers of kidney damage and/or a reduction in GFR.Stages 1 and 2 de�ne conditions of kidney damage in the presence of a GFR of at least 90 mL/min/1.73m 2 or 60 to 89 mL/min/1.73m 2 , respectively, and stages 3 to 5 de�ne conditions of moderately and severely reduced GFR irrespective of markers of kidney damage.e summary of this guideline is shown in Table 1 [3].However, Levey et al. [5] especially mentioned that although this guideline was endorsed by the Kidney Disease: Improving Global Outcomes (KDIGO) in 2004 and this framework was constantly promoted to increase the attention to chronic kidney disease in clinical practice, research, and public health, it had also generated debate.It is the position of KDIGO and KDOQI that the de�nition and classi�cation should re�ect patient prognosis and that an analysis of outcomes would answer key questions underlying the debate.e common de�nition of CKD has facilitated comparisons between studies.Nevertheless, there are limitations to this classi�cation system, which is by its nature simple and necessarily arbitrary in terms of specifying the thresholds for de�nition and different stages.When the classi�cation system was developed in 2002 [3], the evidence base used for the development of this guideline was much smaller than the CKD evidence base today.erefore, this guideline has been constantly revised from then on.
In Taiwan, the Taiwan Society of Nephrology (TSN) also presented the self-detecting method of kidney for the public.At present, the MDRD formula [3,6] is recognized as a mostly common method adopted by kidney physicians to estimate GFR from serum creatinine level.erefore, in this paper we take MDRD to calculate the GFR for the detection.e method of computational formula is shown in formula (1).e input data for the GFR calculation of each individual case in health examination are provided by the collaborative teaching hospital.We also used the calculated results as the desired (targeted) value to develop our neural network models.One has GFR = 186 × creatinine −1.154 × age −0.203  mL/ min 1.73 m 2  .(1) Note: For female the result should be multiplied by a factor of 0.742.It is specially worthy of note that the recent study from Matsushita et al. [7] indicates that although the Modi�cation of Diet in Renal Disease (MDRD) study equation is recommended for estimating GFR, the Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) has proposed an alternative equation, which is known as CKD-EPI.e CKD-EPI applies different coefficients to the same 4 variables which include age, sex, race, and serum creatinine level, used in the MDRD study equation.e study takes the data from more than one million participant cases residing in 40 countries or regions.ey �nd that the CKD-EPI equation estimates measured GFR more accurately than the MDRD study equation in most of the study areas.It shows approximately one-fourth of cases were reclassi�ed to a higher estimated GFR category by the CKD-EPI equation compared with the MDRD study equation.In this one-fourth of cases are reclassi�ed upward in GFR �gure by CKD-EPI, 24.4% in the general population cohorts, 15.4% in the high risk cohorts, and 6.6% in the CKD cohorts.is improvement by CKD-EPI classi�cation may lower the prevalence of CKD.Participant cases who are reclassi�ed upward had lower risks of mortality and end-stage renal disease (ESRD) compared with those not reclassi�ed [7].e arti�cial neural network (ANN), usually simply called neural network (NN), is a mathematical model or computational model that is inspired by the structure and/or functional aspects of biological neural networks.Kriesel [6] indicated neural networks were a bioinspired mechanism of data processing that enables computers to learn technically similar to human-being brain.A neural network consists of an interconnected group of arti�cial neurons, and it processes information using a connectionist approach to computation.In most cases, an ANN is an adaptive system that changes its structure based on external (input) or internal information that �ows through the network during the learning phase.It is properly the most prestigious and adoptable model in all application models in the �eld of arti�cial intelligence.
ere are many different types of neural network models derived from the generic structure of ANN.In this paper's study, three neural network models employed for the experiment and comparison include the back-propagation neural network (BPNN) [6,8], the generalized feedforward neural network (GFNN) [9,10], and the modular neural network (MNN) [11].e generic architectures of three-layer back-propagation neural network, generalized feedforward neural network and modular neural network are illustrated in Figures 1, 2, and 3, respectively.Input layer e input data set for developing neural networks are collected from the cases of health examination provided by the collaborative hospital of this study.1161 heath examination cases covering past few years are selected.Before they are input for training and testing network models, a data preprocessing is processed to remove duplication and correct the error, inconsistency, and missing �elds in each case record.Among these cases, there exit some unknown duplication cases which have unknown causes, they are identi�ed and removed.Some cases have error in certain �elds such as the �gure being beyond its reasonable range or in a �uestionable high or low level.is is oen seen in the �gures for some physiological test.We try to con�rm these �gures with the authority of health examination center of hospital and try to correct it, otherwise they are removed.Some cases show postal code error or appear inconsistent with the personal contact address or vice versa, using different representation to refer the same meaning, which is commonly seen in gender �led and name �eld.More signi�cantly, because not every subject conducts a complete health examination, certain �elds used for risk measurement are missing.ese cases are simply removed as well because they can not be used for model development.By this process, we can ensure the accuracy, completeness, and integrity of input data.Aer data preprocessing, only most accurate 430 patient cases remain for the development of intelligent models.Among these cases, 145 cases are prediagnosed as negative with CKD, and 285 cases are prediagnosed as positive.e details are shown in Table 4.  5 shows these two best settings of parameters.e classi�cation accuracy, sensitivity, and speci�city with respect to Model FA and FB, respectively, are shown in Table 6.In Table 6, the metric of "accuracy" is used to measure the classi�cation of accuracy with the proportion of the sum of the number of true positives and the number of true negatives.e metric of "sensitivity" is used to measure the proportion of actual positives which are correctly classi�ed as such.e metric of "speci�city" is used to measure the proportion of negatives which are correctly identi�ed.From the results shown in formula gains better results in all three measures.ese results show that a hybrid model with the combination of BPN and GA seams does not improve the model performance in accuracy measure but it is helpful to improve sensitivity measure.

e Model Development of Generalized Feedforward
Neural Network.Table 7 shows the best network parameters settings for the development of generalized feedforward neural network (GFNN�.e classi�cation accuracy, sensitivity, and speci�city with respect to Model FA and FB, respectively, are shown in Table 8.As the results in Table 8 show, pure GFNN obtains a perfect classi�cation percentage in three measures including accuracy, sensitivity, and speci�city in training stage while GFNN plus GA apparently may gain better results in testing.However, they also show the results gained from GFNN are not so good in all three measures as those gained from BPN and BPN plus GA, respectively.

e Model Development of Modular Neural Network.
Table 9 shows the parameters for the test of modular neural network (MNN�.e classi�cation accuracy, sensitivity, and speci�city with respect to Model FA and FB, respectively, are shown in Table 10.As the testing results in Table 10 show, pure MNN is the same as prior two models which may obtain a perfect classi�cation percentage in three measures in training stage, but MNN plus GA apparently may gain worse results in testing stage, which is different from the results shown in prior two models.

Performance Comparison of Models
e performances of three neural network models developed for comparison in this paper in terms of detection (i.e., classi�cation� accuracy measure are summarized and shown in Tables 11 and 12, respectively.Table 11 shows the detection accuracy in three pure neural network models while is result may conclude that GA provides no bene�t in the yield of better detection performance with the adoption of the key factors used in computation formula as the input to all models in testing.
According to the detection performance shown in Tables 11 and 12, we conclude that BPN might be the best��tting Model FA among three fundamental neural network models employed in detecting CKD while the models BPN and GFNN with GA embedded, respectively, might be the best hybrid models for CKD detection but only GFNN plus GA can gain enhancement in detection performance in both sets of in�uence factors as input.ese conclusions should be further veri�ed and compared with other models selected for test in later studies before they can be assured.

Conclusion
We conclude that neural network models developed for CKD detection may effectively and feasibly equip medical staff with the ability to make precise diagnosis and treatment to the patient.
In the future study, further model modi�cation and testing for the intelligence models developed in this paper should be conducted to enhance the accuracy in detection performance and to ensure they are sufficiently good for being truly employed in medical practice.In the meantime, different intelligence models can be widely and persistently applied for system development in this domain application as well in order to search for a best one model to be adopted.In the future system development, it is worthwhile to deploy the system to the cloud platform so that the public users can also use this system to conduct a self-detection of having had CKD.
model of three-layer back-propagation neural network.
e set of in�uence factors derived from GFR computation formulas is shown in Table2and another set of key in�uence factors selected and determined in this paper as the input of neural networks is shown in Table3, respectively.e classi�cation performances of two input sets for model development are compared.
T 3: e in�uence factors for the classi�cation of neural networks for C�D detection.
model of combining each individual neural network and genetic algorithm (GA) is also conducted in this research.In other words, GA will be taken to combine with backpropagation neural network, feedforward neural network, and modular neural network, respectively, in model development and comparison as well.

Table 6
, a pretty good classi�cation result is gained with BPN both for Model FA and FB, while it shows a signi�cant drop in classi�cation performance in model testing stage both in BPN and BPN plus GA.By the results shown in Table6, pure BPN model may gain better results in accuracy measure, while BPN plus GA may gain better results in sensitivity measure.e result also shows the model with the adoption of the key factors used in computation T 6: e performance gained from back-propagation neural network models.
Table12shows the detection accuracy with GA model embedded in three respective pure models.We found BPN may gain the best accuracy regardless of in both Model FA and Model FB which are measured with 94.75% and 72.42% accuracy shown in Table11, respectively in model testing.However, Model FA, which is the test by adopting the key factors used in computation formula, may gain much better performance than Model FB, which is the test by adopting the key factors selected in this paper.esameresultisgainedwiththeGAembedded in each fundamental model in test.As the results observed from Table12, both BPN plus GA and GFNN plus GA gain close results in accuracy measure which is much better than MNN plus GA.By further observation from the results of model test shown in Section 4, it is found that almost all models employed in test may gain near 100% accuracy in CKD detection in the training stage regardless of which sets of in�uence factors used in model training.However, if further model testing is conducted, it is found that the network models with the input of in�uence factors of CKD used by physicians employed in the computational formula always show better detection performance in all three aspects of measure including accuracy, sensitivity, and speci�city measures.As we can see from Table11, the BPN gains the highest 94.75% accuracy measure in the testing stage among three fundamental neural network models while GFNN gains only 86.63% in accuracy measure which is the lowest performance in three models.roughfurtherobservationsfrom test results as it is shown in Table12, we �nd the hybrid network model of GFNN with GA embedded may signi�cantly show improvement in detection performance in all three measures from its fundamental model in the testing stage although the reversed T 8: e performance gained from generalized feedforward neural network models.
Advances in Arti�cial Neural Systems 7 T 12: Detection accuracy in three neural network models with GA.