Artificial intelligence for automatic classification of needle EMG signals: A scoping review.

OBJECTIVE: This scoping review provides an overview of artificial intelligence (AI), including machine and deep learning techniques, in the interpretation of clinical needle electromyography (nEMG) signals. METHODS: A comprehensive search of Medline, Embase and Web of Science was conducted to find peer-reviewed journal articles. All papers published after 2010 were included. The methodological quality of the included studies was assessed with CLAIM (checklist for artificial intelligence in medical imaging). RESULTS: 51 studies were identified that fulfilled the inclusion criteria. 61% used open-source EMGlab data set to develop models to classify nEMG signal in healthy, amyotrophic lateral sclerosis (ALS) and myopathy (25 subjects). Only two articles developed models to classify signals recorded at rest. Most articles reported high performance accuracies, but many were subject to bias and overtraining. CONCLUSIONS: Current AI-models of nEMG signals are not sufficient for clinical implementation. Suggestions for future research include emphasizing the need for an optimal training and validation approach using large datasets of clinical nEMG data from a diverse patient population. SIGNIFICANCE: The outcomes of this study and the suggestions made aim to contribute to developing AI-models that can effectively handle signal quality variability and are suitable for daily clinical practice in interpreting nEMG signals.

The effect of tremor on disability assessment in chronic inflammatory demyelinating polyradiculoneuropathy.

Tremor in chronic inflammatory demyelinating polyradiculoneuropathy (CIDP) is common, often unresponsive to treatment, and may contribute to disability. We aim to investigate whether tremor is associated with disability as measured in daily practice and clinical trials, independent of other impairments. We included 76 CIDP patients in this cross-sectional study. We assessed tremor with the Tremor Research Group essential tremor rating assessment scale (TETRAS) and the Fahn-Tolosa-Marin clinical rating scale (FTM). Disability was measured with the inflammatory Rasch-built overall disability scale (I-RODS) and the adjusted Inflammatory Neuropathy Cause and Treatment disability scale (INCAT-DS, categorized separately in arm score, or total score). Impairments including strength, sensory impairment, and fatigue were measured using specific impairment scales. We tested whether "the presence of a clinically relevant tremor" (based on TETRAS and FTM) or "tremor severity" (FTM part B sum score) was associated with disability scores (I-RODS, INCAT-DS total score, and INCAT-DS arm score), independent of the impairment scores, using multivariate regression. Both "the presence of a clinically relevant tremor" and "tremor severity" were significantly associated with disability measured by the INCAT-DS (arm score and total score), but not the I-RODS, independent of strength, sensory impairment, and fatigue. The explained variances were low. Clinically relevant tremor can (partly) explain disability in CIDP, as measured with the INCAT-DS, independent of muscle strength, sensory deficits, and fatigue. To assess disease activity in CIDP patients with tremor, both impairment and disability outcomes should be assessed, as disability is caused partly by tremor while the effect of immunotherapy on tremor seems limited.

Deriving reference values for nerve conduction studies from existing data using mixture model clustering.

OBJECTIVE: to obtain locally valid reference values (RVs) from existing nerve conduction study (NCS) data. METHODS: we used age, sex, height and limb temperature-based mixture model clustering (MMC) to identify normal and abnormal measurements on NCS data from two university hospitals. We compared MMC-derived RVs to published data; examined the effect of using different variables; validated MMC-derived RVs using independent data from 26 healthy control subjects and investigated their clinical applicability for the diagnosis of polyneuropathy. RESULTS: MMC-derived RVs were similar to published RVs. Clustering can be achieved using only sex and age as variables. MMC is likely to yield reliable results with fewer abnormal than normal measurements and when the total number of measurements is at least 300. Measurements from healthy controls fell within the 95% MMC-derived prediction interval in 97.4% of cases. CONCLUSIONS: MMC can be used to obtain RVs from existing data, providing a locally valid, accurate reflection of the (ab)normality of an NCS result. SIGNIFICANCE: MMC can be used to generate locally valid RVs for any test for which sufficient data are available.1.

Distal muscle weakness and optic atrophy without central nervous system involvement in a patient with a homozygous missense mutation in the C19ORF12-gene.

Variants of the C19ORF12-gene have been described in patients with spastic paraplegia type 43 and in patients with mitochondrial membrane protein-associated neurodegeneration (MPAN), a subtype of neurodegeneration associated with brain iron accumulation (NBIA). In both subtypes optic atrophy and neuropathy have been frequently described. This case report describes a patient with bilateral optic atrophy and severe distal muscle weakness based on motor neuropathy without involvement of the central nervous system. Exome sequencing revealed a homozygous pathogenic missense variant (c.187G>C;p.Ala63Pro) of the C19ORF12-gene while iron deposits were absent on repeat MR-imaging of the brain, thus showing that peripheral neuropathy and optic neuropathy can be the sole manifestations of the C19ORF12-related disease spectrum whereby iron accumulation in the brain may be absent.

Combined intravenous immunoglobulin and methylprednisolone as induction treatment in chronic inflammatory demyelinating polyneuropathy (OPTIC protocol): a prospective pilot study.

BACKGROUND AND PURPOSE: We hypothesized that combining intravenous immunoglobulin (IVIg) and intravenous methylprednisolone (IVMP) leads to more frequent remission compared with IVIg alone while maintaining the fast efficacy of IVIg. In this uncontrolled pilot study, we evaluated remission, rate of improvement and safety in patients with chronic inflammatory demyelinating polyradiculoneuropathy receiving induction treatment with combined IVIg and IVMP. METHODS: Consecutive treatment-naive patients with chronic inflammatory demyelinating polyradiculoneuropathy were treated with IVIg infusions, consisting of a 2 g/kg loading dose and 1 g/kg maintenance treatment every 3 weeks, combined with 3-weekly 1-g IVMP infusions, for a total of 18 weeks. The cumulative steroid dose was 7 g. Primary outcome was remission at 1 year in patients who completed the treatment schedule. Remission was defined as improvement at 18 weeks without the need for further immune treatment between end of the treatment schedule and 1-year follow-up. Improvement was defined as a minimal clinically important difference on the Inflammatory Rasch-Built Overall Disability Scale and/or an increase of ≥8 kPa in grip strength between baseline and week 18. RESULTS: A total of 20 patients were included; 17 completed the treatment schedule. A total of 13 (76%) of these patients improved at 18 weeks after start of treatment and 10 (59%) patients were in remission at 1 year. Serious adverse events were found in four patients. CONCLUSIONS: Short-term combined induction treatment with IVIg and IVMP induced remission in almost 60% of patients who completed the treatment schedule. Combined induction therapy was generally well tolerated. A randomized controlled trial is currently running to confirm efficacy and safety of IVMP as add-on treatment to IVIg.

Corticosteroids in chronic inflammatory demyelinating polyneuropathy : A retrospective, multicentre study, comparing efficacy and safety of daily prednisolone, pulsed dexamethasone, and pulsed intravenous methylprednisolone.

BACKGROUND: Chronic inflammatory demyelinating polyneuropathy (CIDP) can be treated with corticosteroids or intravenous immunoglobulins. Various corticosteroid regimens are currently used in CIDP, but it is unknown whether they are equally efficacious. In this retrospective study, we compared efficacy and safety of three corticosteroid regimens in CIDP patients. METHODS: We included treatment naïve patients that fulfilled the EFNS/PNS criteria for CIDP. Patients were treated with corticosteroids according to the local protocol of three CIDP expertise centres. Corticosteroid regimens consisted of daily oral prednisolone, pulsed oral dexamethasone, or pulsed intravenous methylprednisolone. Outcomes were number of responders to treatment, remission rate of treatment responders, overall probability of 5-year remission, and the occurrence of adverse events. RESULTS: A total of 125 patients were included. Sixty-seven (54%) patients received daily prednisone or prednisolone, 37 (30%) pulsed dexamethasone, and 21 (17%) pulsed intravenous methylprednisolone. Overall, 60% (95% CI 51-69%) responded to corticosteroids, with no significant difference between the three treatment regimens (p = 0.56). From the 75 responders, 61% (95% CI 50-73%) remained in remission, during a median follow-up of 55 months (range 1-197 months). The probability of responders reaching 5-year remission was 55% (95% Cl 44-70%), with no difference between the three groups. Adverse events leading to a change in treatment occurred in ten patients (8%). Two patients had a serious adverse event. CONCLUSION: Corticosteroids lead to improvement in 60% of patients and to remission in 61% of treatment responders. There were no differences between treatment modalities in terms of efficacy and safety.

Muscle imaging in inherited and acquired muscle diseases.

In this review we discuss the use of conventional (computed tomography, magnetic resonance imaging, ultrasound) and advanced muscle imaging modalities (diffusion tensor imaging, magnetic resonance spectroscopy) in hereditary and acquired myopathies. We summarize the data on specific patterns of muscle involvement in the major categories of muscle disease and provide recommendations on how to use muscle imaging in this field of neuromuscular disorders.

Effects of early and late diabetic neuropathy on sciatic nerve block duration and neurotoxicity in Zucker diabetic fatty rats.

BACKGROUND: The neuropathy of type II diabetes mellitus (DM) is increasing in prevalence worldwide. We aimed to test the hypothesis that in a rodent model of type II DM, neuropathy would lead to increased neurotoxicity and block duration after lidocaine-induced sciatic nerve block when compared with control animals. METHODS: Experiments were carried out in Zucker diabetic fatty rats aged 10 weeks (early diabetic) or 18 weeks (late diabetic, with or without insulin 3 units per day), and age-matched healthy controls. Left sciatic nerve block was performed using 0.2 ml lidocaine 2%. Nerve conduction velocity (NCV) and F-wave latency were used to quantify nerve function before, and 1 week after nerve block, after which sciatic nerves were used for neurohistopathology. RESULTS: Early diabetic animals did not show increased signs of nerve dysfunction after nerve block. In late diabetic animals without insulin vs control animals, NCV was 34.8 (5.0) vs 41.1 (4.1) ms s(-1) (P<0.01), and F-wave latency was 7.7 (0.5) vs 7.0 (0.2) ms (P<0.01), respectively. Motor nerve block duration was prolonged in late diabetic animals, but neurotoxicity was not. Late diabetic animals receiving insulin showed intermediate results. CONCLUSIONS: In a rodent type II DM model, nerves have increased sensitivity for short-acting local anaesthetics without adjuvants in vivo, as evidenced by prolonged block duration. This sensitivity appears to increase with the progression of neuropathy. Our results do not support the hypothesis that neuropathy due to type II DM increases the risk of nerve injury after nerve block.

Autonomic dysfunction in ICU-acquired weakness: a prospective observational pilot study.

PURPOSE: Intensive care unit-acquired weakness (ICU-AW) is a frequent complication of critical illness. It is unknown if patients with ICU-AW also have autonomic dysfunction, another frequent neurological complication of critical illness. We hypothesized that patients who develop ICU-AW also develop autonomic dysfunction. Furthermore, we hypothesized that patients with ICU-AW are more prone to develop autonomic dysfunction compared to patients without ICU-AW. METHODS: This was an observational cohort study of patients newly admitted to the ICU. Autonomic dysfunction was measured daily using heart rate variability (HRV) to a maximum of 15 days after admission. ICU-AW was diagnosed using the Medical Research Council score. Abnormal HRV was defined using age-matched reference values. The association between ICU-AW and HRV was analyzed using linear mixed effects models. RESULTS: We included 83 patients, 15 (18 %) of whom were diagnosed with ICU-AW. Of 279 HRV measurements, 204 could be analyzed. Abnormal HRV was found in all critically ill patients irrespective of the presence of ICU-AW (ICU-AW 100 % (IQR 71-100) vs. no ICU-AW 100 % (IQR 40-100); p = 0.40). Mechanical ventilation, sedation, norepinephrine, heart rate, and HRV artifacts were identified as confounders for HRV. ICU-AW was not associated with HRV. CONCLUSION: Abnormal HRV is frequent in critically ill patients, both with and without ICU-AW. It is unlikely that patients with ICU-AW are more prone to develop abnormal HRV. However, we found that abnormal HRV may not be an accurate indicator of autonomic dysfunction because of confounders.

Examination of cardiovascular and peripheral autonomic function in the ICU: a pilot study.

UNLABELLED: Critical illness may affect the autonomic nervous system. Decreased cardiovascular autonomic function measured by heart rate variability (HRV) has been reported in critically ill patients but limited information exists about other autonomic functions. The cold face test (CFT) and skin wrinkle test (SWT) have never been investigated in critically ill patients. Feasibility and safety of the CFT and SWT were investigated in critically ill patients. EXCLUSION CRITERIA: polyneuropathy, autonomic neuropathy, admission after stroke, spinal cord injury or cardiac arrest. For the CFT, a cold pack was applied to the forehead to measure the maximal increase in RR interval. The simulated SWT was used and wrinkling was assessed on a five-point scale. HRV was investigated using power spectral analysis of continuous 5-min ECG recordings. Twelve critically ill patients were included (mean age 54). No adverse effects for the CFT and SWT were noted. The CFT could be performed in 10 patients and showed an abnormal response in 9. The SWT could be performed in 11 patients; results were abnormal in 6. HRV analysis showed decreased HRV in all patients. CFT and HRV responses were correlated with each other, no correlation was found between SWT and CFT or HRV results. The CFT and SWT are feasible and safe in critically ill patients. Cardiovascular dysfunction may be more prevalent in critical illness than peripheral sympathetic dysfunction. Influence of confounders and further validation of these tests needs to be investigated.

Age-related changes in motor unit number estimates in adult patients with Charcot-Marie-Tooth type 1A.

BACKGROUND: Charcot-Marie-Tooth disease type 1A (CMT1A) is known as a demyelinating hereditary neuropathy. Secondary axonal dysfunction is the most important determinant of disease severity. In adult patients, clinical progression may be because of further axonal deterioration as was shown with compound muscle action potential (CMAP) amplitude reductions over time. The motor unit number estimation (MUNE) technique may be more accurate to determine the number of axons as it is not disturbed by the effect of reinnervation. The purpose of this study was to investigate the number and size of motor units in relation to age in patients and controls. METHODS: In a cross-sectional design, we assessed arm and hand strength and performed electrophysiological examinations, including CMAP amplitudes and MUNE of the thenar muscles using high-density surface EMG in 69 adult patients with CMT1A and 55 age-matched healthy controls. RESULTS: In patients, lower CMAP amplitudes and MUNE values were related to hand weakness. The CMAP amplitude and MUNE value of the thenar muscles were significantly lower in patients than in controls. CMAP amplitudes declined with age in controls, but not in patients. MUNE values declined with age in both patients and controls. CONCLUSIONS: The age-dependent decrease in the number of motor units was not significantly different between patients with CMT1A and controls, indicating that loss of motor units in adult patients is limited.

[From gene to disease; Charcot-Marie-Tooth disease or the hereditary motor and sensory neuropathies]. / Van gen naar ziekte; de ziekte van Charcot-Marie-Tooth ofwel de hereditaire motorische en sensorische neuropathieën.

Charcot-Marie-Tooth disease is a clinically and genetically heterogeneous group of inherited neuropathies. The common clinical symptoms include distal muscle weakness, wasting and impaired distal sensation, more in the legs than in the arms, and reduced or absent reflexes. Moreover, foot and hand deformities are often encountered. A distinction between a primarily demyelinating or axonal neuropathy is often possible by means of nerve conduction studies. The major groups of inheritance are the autosomal dominant CMT1 (demyelinating), CMT2 (axonal) and the X-linked type (CMTX), but there are also autosomal recessive demyelinating (CMT4) and axonal (AR-CMT2) forms. The number of genes and loci is steadily increasing, with genes encoding proteins involved in myelin maintenance and axonal function, but also with genes encoding proteins, the function of which in peripheral nerve maintenance is notyet clear. Despite the increase in the number of known genes, especially for CMT2, there are many patients in whom no mutation can yet be found.

Luteotrophic activity of ectopically developing rat blastocysts.

The production of a luteotrophic hormone by ectopically transplanted rat blastocysts was demonstrated by transfer of blastocysts to the kidneys of cyclic and pseudopregnant mice and isogeneic rats. Pseudopregnancy was induced in nearly all cyclic mice bearing trophoblastic outgrowths but not in cyclic rats. In both mice and rats prolongation of pseudopregnancy was observed following ectopic transplantation of rat blastocysts at the time of normal egg implantation. It is concluded that ectopically developing rat trophoblastic tissue produces a luteotrophic hormone.

Lactate concentrations in pre-ovulatory follicles of pro-oestrous rats before and after onset of oocyte maturation.

Lactate concentrations were determined in pre-ovulatory follicles of rats at pro-oestrus before and after onset of oocyte maturation. It appeared that high concentrations prevail before and after the time of the expected LH surge (27 mM). The level in serum was about 5 mM. Explanted oocytes obtained from pre-puberal rats and surrounded by cumulus cells, matured in the presence of 20 mM lactate as sole exogenous energy source. It is argued that oxygen may be the limiting factor suppressing oocyte maturation in vivo.