Using fuzzy logic for diagnosis and classification of spasticity

Abstract

IntroductionSpasticity is a common sensory-motor control disorder characterized by increased velocity-dependent stretch reflex responses resulting from upper motor neuron (UMN) lesions (1). Spasticity is frequently observed in cases such as spinal cord injury, multiple sclerosis, traumatic brain damage, cerebral palsy, and stroke, which can be accompanied by cerebral and spinal pathology that is dispersed or regional (2). The pathophysiology of spasticity is complicated and it is rather difficult to understand the underlying mechanism since it is necessary to know the pathophysiological mechanism that would differentiate the UMN syndrome from other symptoms (3,4). Therefore, spasticity is a disorder that is both insufficiently defined and measured (5). There are three major approaches, clinical, neurophysiological, and biomechanical, for assessing spasticity.The Ashworth Scale (AS) and the modified Ashworth Scale (MAS) are the most commonly used clinical measures of spasticity. The validity, reliability, and sensitivity of the clinical scales, which are subject to interpretation and generally intensified upon passive movement resistance, are debatable (6-8). As a consequence, many studies have been conducted using biomechanical and electrophysiological measurements with the objective of evaluating spasticity, and the obtained results have been used to make correlations with the clinical scales (8-14). Surface electromyography (EMG) has been commonly used in electrophysiological measurements of spasticity (14-16). However, parameters extracted from surface EMG have been generally obtained from analysis by using only the time domain in previous studies, and results were generally based on correlations with the clinical scales rather than using stand-alone surface EMG as well as considering causality. Due to the fact that surface EMG signals are nonstationary and random signals, some pathological data might not be discriminated in the time axis. Therefore, it is possible to utilize the short-time Fourier transform (STFT) and the wavelet transform (WT) methods from the time and the frequency components of the signals found in the pathological symptoms (17,18).Background/aim: Spasticity is generally defined as a sensory-motor control disorder. However, there is no pathophysiological mechanism or appropriate measurement and evaluation standards that can explain all aspects of a possible spasticity occurrence. The objective of this study is to develop a fuzzy logic classifier (FLC) diagnosis system, in which a quantitative evaluation is performed by surface electromyography (EMG), and investigate underlying pathophysiological mechanisms of spasticity.Materials and methods: Surface EMG signals recorded from the tibialis anterior and medial gastrocnemius muscles of hemiplegic patients with spasticity and a healthy control group were analyzed in standing, resting, dorsal flexion, and plantar flexion positions. The signals were processed with different methods: by using their amplitudes in the time domain, by applying short...

Extended Fuzzy-Based Models of Production Data Analysis within AI-Based Industry 4.0 Paradigm

“…In the medical and health sciences alone, we found 1124 publications addressing the problem of classification using fuzzy logic. These include the classification of rare diseases or the grouping of patients [46][47][48], but also geological [49,50], climatic phenomena [51,52], human behavior [53], or crop maturity classifications [54].…”

Associations between lower-limb muscle activation and knee flexion in post-stroke individuals: A study on the stance-to-swing phases of gait

“…Results of the RMS and MNF also showed that the stroke affected the magnitude and frequency of the sEMG signals for the GS, but not for the BF ( Fig 5 ). Stroke led to decreased magnitude and frequency of GS, revealing atrophy of muscle fibers, lowered firing rate, weakened capacity of motor-units recruitment, reduced conduct velocity and muscle fatigue by hemiplegia for gait performance [ 15 , 24 ]. The stroke-induced neuromuscular abnormity in GS may result in less than necessary propulsion at the pre-swing phase and thus generate debilitated muscle force for knee flexion during swing stage, all of which could impair the AR of knee flexion in gait [ 25 ].…”

“…Li and Hong found when stroke patients took negative-heeled shoes during walking the sEMG amplitudes of GS and BF increased, accompanied by greater knee flexion [ 14 ]. Other studies reported that it was the GS but not the BF that exhibited reduced sEMG amplitude and frequency with decreased knee motion in post-stroke gait [ 15 , 16 ]. These studies inspired us that to further examine the amplitude and frequency information underlying the sEMG signals of the involved muscles would help better understand the causes and solutions of stiff-knee gait in post-stroke patients.…”

Fuzzy inference system (FIS) - long short-term memory (LSTM) network for electromyography (EMG) signal analysis

“…As the LSTM network requires a sequence of data points to train the network, analysis is done on the behaviour of the signals for the various movements to unify them to a single value for each timestamp. Fuzzy Logic provides a means to perform this action in a more interpretable form based on its natural fluctuations[34,35].…”