Using machine learning algorithms to enhance the diagnostic performance of electrical impedance myography

Neurophysiological and imaging biomarkers of lower motor neuron dysfunction in motor neuron diseases/amyotrophic lateral sclerosis: IFCN handbook chapter

This chapter discusses comprehensive neurophysiological biomarkers utilised in motor neuron disease (MND) and, in particular, its commonest form, amyotrophic lateral sclerosis (ALS). These encompass the conventional techniques including nerve conduction studies (NCS), needle and high-density surface electromyography (EMG) and H-reflex studies as well as novel techniques. In the last two decades, new methods of assessing the loss of motor units in a muscle have been developed, that are more convenient than earlier methods of motor unit number estimation (MUNE),and may use either electrical stimulation (e.g. MScanFit MUNE) or voluntary activation (MUNIX). Electrical impedance myography (EIM) is another novel approach for the evaluation that relies upon the application and measurement of high-frequency, low-intensity electrical current. Nerve excitability techniques (NET) also provide insights into the function of an axon and reflect the changes in resting membrane potential, ion channel dysfunction and the structural integrity of the axon and myelin sheath. Furthermore, imaging ultrasound techniques as well as magnetic resonance imaging are capable of detecting the constituents of morphological changes in the nerve and muscle. The chapter provides a critical description of the ability of each technique to provide neurophysiological insight into the complex pathophysiology of MND/ALS. However, it is important to recognise the strengths and limitations of each approach in order to clarify utility. These neurophysiological biomarkers have demonstrated reliability, specificity and provide additional information to validate and assess lower motor neuron dysfunction. Their use has expanded the knowledge about MND/ALS and enhanced our understanding of the relationship between motor units, axons, reflexes and other neural circuits in relation to clinical features of patients with MND/ALS at different stages of the disease. Taken together, the ultimate goal is to aid early diagnosis, distinguish potential disease mimics, monitor and stage disease progression, quantify response to treatment and develop potential therapeutic interventions.

Assessing paraspinal muscle atrophy with electrical impedance myography: Limitations and insights

Paraspinal muscle atrophy is gaining attention in spine surgery due to its link to back pain, spinal degeneration and worse postoperative outcomes. Electrical impedance myography (EIM) is a noninvasive diagnostic tool for muscle quality assessment, primarily utilized for patients with neuromuscular diseases. However, EIM's accuracy for paraspinal muscle assessment remains understudied. In this study, we investigated the correlation between EIM readings and MRI-derived muscle parameters, as well as the influence of dermal and subcutaneous parameters on these readings. We retrospectively analyzed patients with lumbar spinal degeneration who underwent paraspinal EIM assessment between May 2023 to July 2023. Paraspinal muscle fatty infiltration (FI) and functional cross-sectional area (fCSA), as well as the subcutaneous thickness were assessed on MRI scans. Skin ultrasound imaging was assessed for dermal thickness and the echogenicities of the dermal and subcutaneous layers. All measurements were performed on the bilaterally. The correlation between EIM readings were compared with ultrasound and MRI parameters using Spearman's correlation analyses. A total of 20 patients (65.0% female) with a median age of 69.5 years (IQR, 61.3-73.8) were analyzed. The fCSA and FI did not significantly correlate with the EIM readings, regardless of frequency. All EIM readings across frequencies correlated with subcutaneous thickness, echogenicity, or dermal thickness. With the current methodology, paraspinal EIM is not a valid alternative to MRI assessment of muscle quality, as it is strongly influenced by the dermal and subcutaneous layers. Further studies are required for refining the methodology and confirming our results.

The Use of Virtual Tissue Constructs That Include Morphological Variability to Assess the Potential of Electrical Impedance Spectroscopy to Differentiate between Thyroid and Parathyroid Tissues during Surgery

Electrical impedance spectroscopy (EIS) has been proposed as a promising noninvasive method to differentiate healthy thyroid from parathyroid tissues during thyroidectomy. However, previously reported similarities in the in vivo measured spectra of these tissues during a pilot study suggest that this separation may not be straightforward. We utilise computational modelling as a method to elucidate the distinguishing characteristics in the EIS signal and explore the features of the tissue that contribute to the observed electrical behaviour. Firstly, multiscale finite element models (or 'virtual tissue constructs') of thyroid and parathyroid tissues were developed and verified against in vivo tissue measurements. A global sensitivity analysis was performed to investigate the impact of physiological micro-, meso- and macroscale tissue morphological features of both tissue types on the computed macroscale EIS spectra and explore the separability of the two tissue types. Our results suggest that the presence of a surface fascia layer could obstruct tissue differentiation, but an analysis of the separability of simulated spectra without the surface fascia layer suggests that differentiation of the two tissue types should be possible if this layer is completely removed by the surgeon. Comprehensive in vivo measurements are required to fully determine the potential for EIS as a method in distinguishing between thyroid and parathyroid tissues.

Advancing electrical impedance myography one small step at a time

See article on pages 288–294 in this issue.

The role of artificial intelligence in electrodiagnostic and neuromuscular medicine: Current state and future directions

The rapid advancements in artificial intelligence (AI), including machine learning (ML), and deep learning (DL) have ushered in a new era of technological breakthroughs in healthcare. These technologies are revolutionizing the way we utilize medical data, enabling improved disease classification, more precise diagnoses, better treatment selection, therapeutic monitoring, and highly accurate prognostication. Different ML and DL models have been used to distinguish between electromyography signals in normal individuals and those with amyotrophic lateral sclerosis and myopathy, with accuracy ranging from 67% to 99.5%. DL models have also been successfully applied in neuromuscular ultrasound, with the use of segmentation techniques achieving diagnostic accuracy of at least 90% for nerve entrapment disorders, and 87% for inflammatory myopathies. Other successful AI applications include prediction of treatment response, and prognostication including prediction of intensive care unit admissions for patients with myasthenia gravis. Despite these remarkable strides, significant knowledge, attitude, and practice gaps persist, including within the field of electrodiagnostic and neuromuscular medicine. In this narrative review, we highlight the fundamental principles of AI and draw parallels with the intricacies of human brain networks. Specifically, we explore the immense potential that AI holds for applications in electrodiagnostic studies, neuromuscular ultrasound, and other aspects of neuromuscular medicine. While there are exciting possibilities for the future, it is essential to acknowledge and understand the limitations of AI and take proactive steps to mitigate these challenges. This collective endeavor holds immense potential for the advancement of healthcare through the strategic and responsible integration of AI technologies.

Combining electromyographic and electrical impedance data sets through machine learning: A study in D2-mdx and wild-type mice

INTRODUCTION/AIMS

Needle impedance-electromyography (iEMG) assesses the active and passive electrical properties of muscles concurrently by using a novel needle with six electrodes, two for EMG and four for electrical impedance myography (EIM). Here, we assessed an approach for combining multifrequency EMG and EIM data via machine learning (ML) to discriminate D2-mdx muscular dystrophy and wild-type (WT) mouse skeletal muscle.

METHODS

iEMG data were obtained from quadriceps of D2-mdx mice, a muscular dystrophy model, and WT animals. EIM data were collected with the animals under deep anesthesia and EMG data collected under light anesthesia, allowing for limited spontaneous movement. Fourier transformation was performed on the EMG data to provide power spectra that were sampled across the frequency range using three different approaches. Random forest-based, nested ML was applied to the EIM and EMG data sets separately and then together to assess healthy versus disease category classification using a nested cross-validation procedure.

RESULTS

Data from 20 D2-mdx and 20 WT limbs were analyzed. EIM data fared better than EMG data in differentiating healthy from disease mice with 93.1% versus 75.6% accuracy, respectively. Combining EIM and EMG data sets yielded similar performance as EIM data alone with 92.2% accuracy.

DISCUSSION

We have demonstrated an ML-based approach for combining EIM and EMG data obtained with an iEMG needle. While EIM-EMG in combination fared no better than EIM alone with this data set, the approach used here demonstrates a novel method of combining the two techniques to characterize the full electrical properties of skeletal muscle.

Surface Electrical Impedance Myography Detects Skeletal Muscle Atrophy in Aged Wildtype Zebrafish and Aged gpr27 Knockout Zebrafish

Throughout a vertebrate organism's lifespan, skeletal muscle mass and function progressively decline. This age-related condition is termed sarcopenia. In humans, sarcopenia is associated with risk of falling, cardiovascular disease, and all-cause mortality. As the world population ages, projected to reach 2 billion older adults worldwide in 2050, the economic burden on the healthcare system is also projected to increase considerably. Currently, there are no pharmacological treatments for sarcopenia, and given the long-term nature of aging studies, high-throughput chemical screens are impractical in mammalian models. Zebrafish is a promising, up-and-coming vertebrate model in the field of sarcopenia that could fill this gap. Here, we developed a surface electrical impedance myography (sEIM) platform to assess skeletal muscle health, quantitatively and noninvasively, in adult zebrafish (young, aged, and genetic mutant animals). In aged zebrafish (~85% lifespan) as compared to young zebrafish (~20% lifespan), sEIM parameters (2 kHz phase angle, 2 kHz reactance, and 2 kHz resistance) robustly detected muscle atrophy (p < 0.000001, q = 0.000002; p = 0.000004, q = 0.000006; p = 0.000867, q = 0.000683, respectively). Moreover, these same measurements exhibited strong correlations with an established morphometric parameter of muscle atrophy (myofiber cross-sectional area), as determined by histological-based morphometric analysis (r = 0.831, p = 2 × 10-12; r = 0.6959, p = 2 × 10-8; and r = 0.7220; p = 4 × 10-9, respectively). Finally, the genetic deletion of gpr27, an orphan G-protein coupled receptor (GPCR), exacerbated the atrophy of skeletal muscle in aged animals, as evidenced by both sEIM and histology. In conclusion, the data here show that surface EIM techniques can effectively discriminate between healthy young and sarcopenic aged muscle as well as the advanced atrophied muscle in the gpr27 KO animals. Moreover, these studies show how EIM values correlate with cell size across the animals, making it potentially possible to utilize sEIM as a "virtual biopsy" in zebrafish to noninvasively assess myofiber atrophy, a valuable measure for muscle and gerontology research.

Electrical impedance myography combined with quantitative assessment techniques in paretic muscle of stroke survivors: Insights and challenges

Aging is a non-modifiable risk factor for stroke and the global burden of stroke is continuing to increase due to the aging society. Muscle dysfunction, common sequela of stroke, has long been of research interests. Therefore, how to accurately assess muscle function is particularly important. Electrical impedance myography (EIM) has proven to be feasible to assess muscle impairment in patients with stroke in terms of micro structures, such as muscle membrane integrity, extracellular and intracellular fluids. However, EIM alone is not sufficient to assess muscle function comprehensively given the complex contributors to paretic muscle after an insult. This article discusses the potential to combine EIM and other common quantitative methods as ways to improve the assessment of muscle function in stroke survivors. Clinically, these combined assessments provide not only a distinct advantage for greater accuracy of muscle assessment through cross-validation, but also the physiological explanation on muscle dysfunction at the micro level. Different combinations of assessments are discussed with insights for different purposes. The assessments of morphological, mechanical and contractile properties combined with EIM are focused since changes in muscle structures, tone and strength directly reflect the muscle function of stroke survivors. With advances in computational technology, finite element model and machine learning model that incorporate multi-modal evaluation parameters to enable the establishment of predictive or diagnostic model will be the next step forward to assess muscle function for individual with stroke.