Using motor unit potential characterizations to estimate neuromuscular disorder level of involvement

A clinical decision support system for diagnosis and severity quantification of lumbosacral radiculopathy using intramuscular electromyography signals

Interpreting intramuscular electromyography (iEMG) signals for diagnosing and quantifying the severity of lumbosacral radiculopathy is challenging due to the subjective evaluation of signals. To address this limitation, a clinical decision support system (CDSS) was developed for the diagnosis and quantification of the severity of lumbosacral radiculopathy based on intramuscular electromyography (iEMG) signals. The CDSS uses the EMG interference pattern method (QEMG IP) to directly extract features from the iEMG signal and provide a quantitative expression of injury severity for each muscle and overall radiculopathy severity. From 126 time and frequency domain features, a set of five features, including the crest factor, mean absolute value, peak frequency, zero crossing count, and intensity, were selected. These features were derived from raw iEMG signals, empirical mode decomposition, and discrete wavelet transform, and the wrapper method was utilized to determine the most significant features. The CDSS was trained and tested on a dataset of 75 patients, achieving an accuracy of 93.3%, sensitivity of 93.3%, and specificity of 96.6%. The system shows promise in assisting physicians in diagnosing lumbosacral radiculopathy with high accuracy and consistency using iEMG data. The CDSS's objective and standardized diagnostic process, along with its potential to reduce the time and effort required by physicians to interpret EMG signals, makes it a potentially valuable tool for clinicians in the diagnosis and management of lumbosacral radiculopathy. Future work should focus on validating the system's performance in diverse clinical settings and patient populations.

Electrophysiological Muscle Classification Using Multiple Instance Learning and Unsupervised Time and Spectral Domain Analysis

OBJECTIVE

Electrophysiological muscle classification (EMC) is a crucial step in the diagnosis of neuromuscular disorders. Existing quantitative techniques are not sufficiently robust and accurate to be reliably clinically used. Here, EMC is modeled as a multiple instance learning (MIL) problem and a system to infer unsupervised motor unit potential (MUP) labels and create supervised muscle classifications is presented.

METHODS

The system has five main steps: MUP representation using morphological, stability, and near fiber parameters as well as spectral features extracted from wavelet coefficients; MUP feature selection using unsupervised Laplacian scores; MUP clustering using neighborhood distance entropy consistency to find representations of MUP normality and abnormality; muscle representation by embedding its MUP cluster associations in a feature vector; and muscle classification using support vector machines or random forests.

RESULTS

The evaluation data consist of 63, 83, 93, and 84 sets of MUPs recorded in deltoid, vastus medialis, first dorsal interosseous, and tibialis anterior muscles, respectively. The proposed system discovered representations of normal, myopathic, and neurogenic MUPs for each specific muscle type and resulted in an average classification accuracy of 98%, which is higher than in previous works.

CONCLUSION

Modeling EMC as an instance of the MIL solves the traditional problem of characterizing MUPs without full supervision. Furthermore, finding representations of MUP normality and abnormality using morphological, stability, near fiber, and spectral features improve muscle classification.

SIGNIFICANCE

The proposed method is able to characterize MUPs with respect to disease categories, with no a priori information.

Probabilistic muscle characterization using QEMG: application to neuropathic muscle

Clinicians who use electromyographic (EMG) signals to help determine the presence or absence of abnormality in a muscle often, with varying degrees of success, evaluate sets of motor unit potentials (MUPs) qualitatively and/or quantitatively to characterize the muscle in a clinically meaningful way. The resulting muscle characterization can be improved using automated analysis. As such, the intent of this study was to evaluate the performance of automated, conventional Means/Outlier and Probabilistic methods in converting MUP statistics into a concise, and clinically relevant, muscle characterization. Probabilistic methods combine the set of MUP characterizations, derived using Pattern Discovery (PD), of all MUPs detected from a muscle into a characterization measure that indicates normality or abnormality. Using MUP data from healthy control subjects and patients with known neuropathic disorders, a Probabilistic method that used Bayes' rule to combine MUP characterizations into a Bayesian muscle characterization (BMC) achieved a categorization accuracy of 79.7% compared to 76.4% using the Mean method (P > 0.1) for biceps muscles and 94.6% accuracy for the BMC method compared to 85.8% using the Mean method (P < 0.01) for first dorsal interosseous muscles. The BMC method can facilitate the determination of "possible," "probable," or "definite" levels for a given muscle categorization (e.g., neuropathic) whereas the conventional Means and Outlier methods support only a dichotomous "normal" or "abnormal" decision. This work demonstrates that the BMC method can provide information that may be more useful in supporting clinical decisions than that provided by the conventional Means or Outlier methods.