Granular computing for assessment of mild traumatic brain injury

Melaku Ayenew Bogale, University of Texas at El Paso

Abstract

Mild traumatic brain injury (mTBI) is one of the most common neurological disorders. It is a serious public health problem in the United States. Although, penetrating (open) brain injuries that result in extended period of loss of consciousness (LOC) usually gets attention and well taken care of by the emergency departments, mild traumatic brain injury with no visible sign of damage, may be undetected or misdiagnosed. The clinical assessments and evaluations are mostly based on subjective cognitive and behavioral tests. Many people after suffering mTBI complain about decreased balance, coordination and stability even though the clinical evaluations show no sign of abnormality. mTBI related functional impairments are diverse and vary significantly from individual to individual. Objective measurements, assessments and characterization of mTBI related gait deficit requires the integration of data from multiple domains. The current assessments and analysis mTBI is based on motion capture system that involves longer time data processing and force platform reaction force recording that need large walking space.^ For people with neurological disorders gait analysis is used to provide diagnose, evaluation and treatment planning information. The benefit of gait analysis is well established that it has now become a part of routine process in many rehabilitation centers. Recognition and understanding of a "normal" gait patterns and behavior are very crucial in the clinical gait analysis process for the purpose of identification of pathological gait. The observed or measured "normal" gait patterns or parameters serve as a reference or standard against which a pathological gait can be compared. Studying gait parameters over a gait cycle, particularly, comparison of established reference patterns with that of the neurological impaired subject's data over a cycle is a common way of assessment and evaluation. However, waveform analysis and comparison of averaged gait parameters over a gait cycle may not be sensitive enough to detect any subtle variation or irregularity among mTBI subjects. Therefore, instead of looking for differences or variations over one gait cycle, one may have to divide a give cycle into chunks or parts so that very localized comparisons and analysis could be made.^ We hypothesis that mTBI subjects under dual-task paradigm will show very significant stride-to-stride stability variations and these variations could be detected by making very localized stride-to-stride comparison analysis. Therefore, we propose a method that makes use of the data collected from different domains under dual-task gait protocols and granular computational algorithm for efficient data analysis. This system is capable of doing the required localized or step-to-step computational driven comparison analysis.^ The purpose of this research is to develop fuzzy-granular computing driven system to assess and characterize functional and gait deficits individually after mild traumatic brain injury. The comprehensive goal of this research work is to develop an intelligent system to objectively measure and categorize gait variations after mTBI by integrating multiple data from different domains under the dual task paradigm. This research employs the method of fuzzy inferential and fuzzy-granular computing algorithms. This is an interdisciplinary research that integrates engineering, mathematics and computer science.^ Both able-bodied and mTBI subjects will be recruited for this study. Dual-task gait protocol or attention divided gait will be used. Ground reaction forces, joint angles of the ankle, knee and the hip and muscle activity data will be collected concurrently and stored for subsequent computational analysis. ^

Subject Area

Applied Mathematics

Recommended Citation

Bogale, Melaku Ayenew, "Granular computing for assessment of mild traumatic brain injury" (2012). ETD Collection for University of Texas, El Paso. AAI1512551.
http://digitalcommons.utep.edu/dissertations/AAI1512551

Share

COinS