TY - JOUR
T1 - An algorithmic approach to understand trace elemental homeostasis in serum samples of Parkinson disease
AU - Pande, M. B.Sanjay
AU - Nagabhushan, P.
AU - Hegde, Murlidhar L.
AU - Rao, T. S.Sathyanarayana
AU - Rao, K. S.Jagannatha
N1 - Funding Information:
The authors wish to thank Vice Chancellor, University of Mysore, Director, CFTRI, Mysore, Principal, JSS Medical College and Hospital, Mysore and Sri Venkateswara Institute of Medical Science, India for their encouragement. Sanjay Pande is thankful to ICMR for awarding SRF and Murlidhar L. Hegde is thankful to CSIR for awarding JRF. P. Nagabhushan a Fellow of Institution of Engineers (FIE) is a professor in Department of Studies in Computer Science, University of Mysore, Mysore, India. He holds BE (1980), MTech (1983) and Ph.D. (1988). He has been a visiting professor and invited researcher at USA, Japan, France and many universities in India. He has been actively associated with many funded research projects. His areas of research interest include Cognition–Recognition, Pattern Recognition, Image Analysis, Dimensionality Reduction, Data Mining, Document Image Analysis, Advanced Exploratory Data Analysis and related problems. He has been actively involved as a referee/reviewer and resource person in his areas of research interest for journals, conferences, workshops, funding agencies and statutory bodies of the Government. M.B. Sanjay Pande is a Senior Research Fellow of Indian Council of Medical Research, India and currently a doctoral student jointly in Department of Studies in Computer Science, University of Mysore, Mysore and Central Food Technological Research Institute, Mysore, India. He holds Diploma in Computer Science(1989), BE in Computer Science (1996) and MTech in Biomedical Engineering (1999). His areas of research interest include Bioinformatics, Pattern Recognition, Psychiatric Disorders. Muralidhar L. Hegde M.Sc. Biochemistry (2000) and currently doing doctoral program in the area Genomics in Parkinson disease in University of Mysore, India. He is a CSIR fellow at CFTRI, Mysore, India. T.S. Sathyanarayana Rao is MD(1983) in Psychiatry. He is heading the Department of Psychiatry at JSS Medical College and Hospital, Mysore, India. His areas of research are Bipolar disorders, Sexology, Genetics and other neuropsychiatry disorders. He is the Chief Editor for Indian Journal of Psychiatry. He is the Fellow of Indian Psychiatric Society. K.S. Jagannatha Rao M.Sc. (1979) and Ph.D. in Zoology (1984). He is a senior scientist at Department of Biochemistry and Nutrition, CFTRI, Mysore, India. His area of research is in Toxicogenomics and toxic protein–nucleic acid interaction studies in Neurological disorders and computational neuroscience. He has published papers in several leading international journals and has several international collaborations on Genomics. He has been actively involved with many funded research projects.
Copyright:
Copyright 2018 Elsevier B.V., All rights reserved.
PY - 2005/7
Y1 - 2005/7
N2 - A classical problem in neurological disorders is to understand the progression of disorder and define the trace elements (metals) which play a role in deviating a sample from normal to an abnormal state, which implies the need to create a reference knowledge base (KB) employing the control samples drawn from normal/healthy set in the context of the said neurological disorder, and in sequel to analytically understand the deviations in the cases of disorders/abnormalities/unhealthy samples. Hence building up a computational model involves mining the healthy control samples to create a suitable reference KB and designing an algorithm for estimating the deviation in case of unhealthy samples. This leads to realizing an algorithmic cognition-recognition model, where the cognition stage establishes a reference model of a normal/healthy class and the recognition stage involves discriminating whether a given test sample belongs to a normal class or not. Further if the sample belongs to a specified reference base (normal) then the requirement is to understand how strong the affiliation is, and if otherwise (abnormal) how far away the sample is from the said reference base. In this paper, an exploratory data analysis based model is proposed to carry out such estimation analysis by designing distribution and parametric models for the reference base. Further, the knowledge of the reference base in case of the distribution model is expressed in terms of zones with each zone carrying a weightage factor. Different distance measures are utilized for the subsequent affiliation analysis (City block with distribution model and Doyle's with Parametric model). Results of an experimental study based on the database of trace elemental analysis in human serum samples from control and Parkinson's neurological disorder are presented to corroborate the performance of the computational algorithm.
AB - A classical problem in neurological disorders is to understand the progression of disorder and define the trace elements (metals) which play a role in deviating a sample from normal to an abnormal state, which implies the need to create a reference knowledge base (KB) employing the control samples drawn from normal/healthy set in the context of the said neurological disorder, and in sequel to analytically understand the deviations in the cases of disorders/abnormalities/unhealthy samples. Hence building up a computational model involves mining the healthy control samples to create a suitable reference KB and designing an algorithm for estimating the deviation in case of unhealthy samples. This leads to realizing an algorithmic cognition-recognition model, where the cognition stage establishes a reference model of a normal/healthy class and the recognition stage involves discriminating whether a given test sample belongs to a normal class or not. Further if the sample belongs to a specified reference base (normal) then the requirement is to understand how strong the affiliation is, and if otherwise (abnormal) how far away the sample is from the said reference base. In this paper, an exploratory data analysis based model is proposed to carry out such estimation analysis by designing distribution and parametric models for the reference base. Further, the knowledge of the reference base in case of the distribution model is expressed in terms of zones with each zone carrying a weightage factor. Different distance measures are utilized for the subsequent affiliation analysis (City block with distribution model and Doyle's with Parametric model). Results of an experimental study based on the database of trace elemental analysis in human serum samples from control and Parkinson's neurological disorder are presented to corroborate the performance of the computational algorithm.
KW - Affiliation analysis
KW - Distribution model
KW - Doyle's distance computations
KW - Parametric model
KW - Parkinson's disorder
KW - Trace elemental knowledge base
KW - Weightage factors
KW - Zonalization
UR - http://www.scopus.com/inward/record.url?scp=15744361815&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=15744361815&partnerID=8YFLogxK
U2 - 10.1016/S0010-4825(04)00064-2
DO - 10.1016/S0010-4825(04)00064-2
M3 - Article
C2 - 15780860
AN - SCOPUS:15744361815
SN - 0010-4825
VL - 35
SP - 475
EP - 493
JO - Computers in Biology and Medicine
JF - Computers in Biology and Medicine
IS - 6
ER -