Application of entropy for automated detection of neurological disorders with electroencephalogram signals: A review of the last decade (2012-2022)

An automated Neurological Disorder detection system can be considered as a cost-effective and resource efficient tool for medical healthcare applications. In detection, electroencephalograms are commonly used, but their low signal intensity nonlinear features difficult to analyze visually. A promising approach processing of electroencephalogram signals is the concept entropy, method measure chaos in signal. The aim this study was find out effective entropy measures machine learning approaches that produced output. Using Preferred Reporting Items Systematic Reviews Meta-Analyses (PRISMA) guidelines our method, we have identified 84 studies published between 2012 2022 has investigated epilepsy, Parkinson’s disease, autism, Attention Deficit Hyperactive disorder, schizophrenia, Alzheimer’s depression, alcohol use disorder with considering measures. We show Support Vector Machines most used model, consistent performance whereas sample measure, followed by approximate entropy. For epilepsy feature log energy multi-scale Disease, multi scale Shannon applied attention deficit hyperactive spectral adopted employed disorder. According majority studies, there growing concern about increase neuro patients heavy burden associated prevalence diagnosis. Based on these conclude Computer-Aided Design systems would economically advantageous detecting Disorders. To incorporate into mainstream health care system, future research could focus multi-modal its interpretation explanation. believe first review combined electroencephalograms, possibility 8 distinct neurological disorders. limited papers accuracy evaluation metric. findings synthesis previous provides clear pathway identifies practical solution using potential applications other kinds analysis.