Performance analysis of noninvasive electrophysiological methods for the assessment of diabetic sensorimotor polyneuropathy in clinical research: a systematic review and meta-analysis with trial sequential analysis

Understanding the role of hyperglycemia and the molecular mechanism associated with diabetic neuropathy and possible therapeutic strategies

Diabetic neuropathy is a neuro-degenerative disorder that encompasses numerous factors that impact peripheral nerves in the context of diabetes mellitus (DM). Diabetic peripheral neuropathy (DPN) is very prevalent and impacts 50% of diabetic patients. DPN is a length-dependent peripheral nerve lesion that primarily causes distal sensory loss, discomfort, and foot ulceration that may lead to amputation. The pathophysiology is yet to be fully understood, but current literature on the pathophysiology of DPN revolves around understanding various signaling cascades involving the polyol, hexosamine, protein-kinase C, AGE, oxidative stress, and poly (ADP ribose) polymerase pathways. The results of research have suggested that hyperglycemia target Schwann cells and in severe cases, demyelination resulting in central and peripheral sensitization is evident in diabetic patients. Various diagnostic approaches are available, but detection at an early stage remains a challenge. Traditional analgesics and opioids that can be used "as required" have not been the mainstay of treatment thus far. Instead, anticonvulsants and antidepressants that must be taken routinely over time have been the most common treatments. For now, prolonging life and preserving the quality of life are the ultimate goals of diabetes treatment. Furthermore, the rising prevalence of DPN has substantial consequences for occupational therapy because such therapy is necessary for supporting wellness, warding off other chronic-diseases, and avoiding the development of a disability; this is accomplished by engaging in fulfilling activities like yoga, meditation, and physical exercise. Therefore, occupational therapy, along with palliative therapy, may prove to be crucial in halting the onset of neuropathic-symptoms and in lessening those symptoms once they have occurred.

A Machine Learning-Based Severity Prediction Tool for the Michigan Neuropathy Screening Instrument

Diabetic sensorimotor polyneuropathy (DSPN) is a serious long-term complication of diabetes, which may lead to foot ulceration and amputation. Among the screening tools for DSPN, the Michigan neuropathy screening instrument (MNSI) is frequently deployed, but it lacks a straightforward rating of severity. A DSPN severity grading system has been built and simulated for the MNSI, utilizing longitudinal data captured over 19 years from the Epidemiology of Diabetes Interventions and Complications (EDIC) trial. Machine learning algorithms were used to establish the MNSI factors and patient outcomes to characterise the features with the best ability to detect DSPN severity. A nomogram based on multivariable logistic regression was designed, developed and validated. The extra tree model was applied to identify the top seven ranked MNSI features that identified DSPN, namely vibration perception (R), 10-gm filament, previous diabetic neuropathy, vibration perception (L), presence of callus, deformities and fissure. The nomogram's area under the curve (AUC) was 0.9421 and 0.946 for the internal and external datasets, respectively. The probability of DSPN was predicted from the nomogram and a DSPN severity grading system for MNSI was created using the probability score. An independent dataset was used to validate the model's performance. The patients were divided into four different severity levels, i.e., absent, mild, moderate, and severe, with cut-off values of 10.50, 12.70 and 15.00 for a DSPN probability of less than 50, 75 and 100%, respectively. We provide an easy-to-use, straightforward and reproducible approach to determine prognosis in patients with DSPN.

Nerve conduction velocity is independently associated with bone mineral density in type 2 diabetes mellitus

AIM

This study investigated the association between nerve conduction velocity (NCV) and bone mineral density (BMD) in patients with type 2 diabetes mellitus (T2DM).

METHODS

This study retrospectively collected medical data of T2DM patients who underwent dual-energy X-ray absorptiometry and nerve conduction study at the Shanghai Ruijin Hospital, Shanghai, China. The primary outcome was the total hip BMD T-score. The main independent variables were motor nerve conduction velocities (MCVs), sensory nerve conduction velocities (SCVs), and composite Z-scores of MCV and SCV. T2DM patients were divided into total hip BMD T-scores < -1 and total hip BMD T-scores ≥ -1 groups. The association between the primary outcome and main independent variables was evaluated by Pearson bivariate correlation and multivariate linear regression.

RESULTS

195 female and 415 male patients with T2DM were identified. In male patients with T2DM, bilateral ulnar, median, and tibial MCVs and bilateral sural SCVs were lower in the total hip BMD T-score < -1 group than T-score ≥ -1 group (P < 0.05). Bilateral ulnar, median, and tibial MCVs, and bilateral sural SCVs showed positive correlations with total hip BMD T-score in male patients with T2DM (P < 0.05). Bilateral ulnar and tibial MCVs, bilateral sural SCVs, and composite MCV SCV and MSCV Z-scores were independently and positively associated with total hip BMD T-score in male patients with T2DM, respectively (P < 0.05). NCV did not show significant correlation with the total hip BMD T-score in female patients with T2DM.

CONCLUSION

NCV showed positive association with total hip BMD in male patients with T2DM. A decline in NCV indicates an elevated risk of low BMD (osteopenia/osteoporosis) in male patients with T2DM.

Electrophysiological assessment in patients with COVID-19-related peripheral neuropathies and myopathies: a systematic review

Neurological manifestations associated with Coronavirus Disease-2019 (COVID-19) are commonly reported, but patients were not referred to perform the electrophysiological assessment. We aimed to review the existing literature on clinical studies on COVID-19 peripheral neuropathy to correlate patients' symptoms and characteristics with nerve conduction studies/electromyography (NCS/EMG) outcomes. This protocol is registered in the Open Science Framework (https://www.doi.org/10.17605/OSF.IO/ZF4PK). The systematic search included PubMed, ScienceDirect, and Google Scholar, for articles published from December 2019 to March 2022. A total of 727 articles were collected, and according to our inclusion and exclusion criteria, only 6 articles were included. Of 195 participants, only 175 underwent NCS/EMG assessment. Of these, 44 participants (25.1%) had abnormal EMG, 54 participants (30.8%) had abnormal motor NCS, and only 7 participants (4%) had abnormal sensory NCS. All cases presented with myopathy, while a limited number of cases presented with polyneuropathy. According to motor NCS and EMG, the most affected nerves were the tibial and peroneal in the lower extremities and the ulnar nerve in the upper extremities. Interestingly, the median nerve was reported to be associated with the severity and the rate of motor recovery of patients with COVID-19. COVID-19 generates a demyelinating motor neuropathy and myopathy. Clinicians are encouraged to refer patients with COVID-19 presenting with neurological symptoms to be assessed by electrophysiological methods to objectively determine the nature of their symptoms, follow their prognosis, and plan their rehabilitation.

Autonomic Nervous System Function and Central Pain Processing in People With Frozen Shoulder: A Case-control Study

OBJECTIVES

The pathophysiology of a frozen shoulder (FS) is thought to be related to chronic inflammation. Chronic inflammation may disturb the immune system and consequently the nervous system as part of an overarching system. The aim of this study was to determine the presence of disturbed autonomic nervous system function and altered central pain processing (CPP) in patients with FS. Secondarily, the presence of psychological variables (catastrophizing and hypervigilance) and self-reported associated symptoms of altered CPP in patients with FS were investigated.

METHODS

Patients with FS and healthy controls completed the Composite Autonomic Symptom Score (autonomic function) and underwent quantitative sensory testing to assess tactile sensitivity (ie, allodynia), pressure pain thresholds (PPTs, ie, hyperalgesia), temporal summation of pain, and Conditioned Pain Modulation (CPM). Psychological issues were explored with the Pain Catastrophizing Scale and the Pain Vigilance and Awareness Questionnaire, and self-reported symptoms associated with altered CPP were determined with the Central Sensitization Inventory.

RESULTS

Thirty-two patients with FS and 35 healthy controls were analyzed in the study. Patients with FS showed more self-reported autonomic symptoms and symptoms of altered CPP, higher levels of pain catastrophizing and hypervigilance, and are more sensitive to tactile touches and mechanical pressure compared with controls.

DISCUSSION

On the basis of the effect sizes, between-group differences in allodynia, hyperalgesia, catastrophizing, and hypervigilance were clinically relevant, but only local allodynia, hyperalgesia, catastrophizing, and hypervigilance were statistically different. Therefore, obvious altered CPP was not present at the group level in patients with FS compared with controls.

Performance Analysis of Conventional Machine Learning Algorithms for Diabetic Sensorimotor Polyneuropathy Severity Classification Using Nerve Conduction Studies

Background

Diabetic sensorimotor polyneuropathy (DSPN) is a major form of complication that arises in long-term diabetic patients. Even though the application of machine learning (ML) in disease diagnosis is very common and well-established in the field of research, its application in DSPN diagnosis using nerve conduction studies (NCS), is very limited in the existing literature.

Method

In this study, the NCS data were collected from the Diabetes Control and Complications Trial (DCCT) and its follow-up Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials. The NCS variables are median motor velocity (m/sec), median motor amplitude (mV), median motor F-wave (msec), median sensory velocity (m/sec), median sensory amplitude (μV), Peroneal Motor Velocity (m/sec), peroneal motor amplitude (mv), peroneal motor F-wave (msec), sural sensory velocity (m/sec), and sural sensory amplitude (μV). Three different feature ranking techniques were used to analyze the performance of eight different conventional classifiers.

Results

The ensemble classifier outperformed other classifiers for the NCS data ranked when all the NCS features were used and provided an accuracy of 93.40%, sensitivity of 91.77%, and specificity of 98.44%. The random forest model exhibited the second-best performance using all the ten features with an accuracy of 93.26%, sensitivity of 91.95%, and specificity of 98.95%. Both ensemble and random forest showed the kappa value 0.82, which indicates that the models are in good agreement with the data and the variables used and are accurate to identify DSPN using these ML models.

Conclusion

This study suggests that the ensemble classifier using all the ten NCS variables can predict the DSPN severity which can enhance the management of DSPN patients.

Machine Learning-Based Diabetic Neuropathy and Previous Foot Ulceration Patients Detection Using Electromyography and Ground Reaction Forces during Gait

Diabetic neuropathy (DN) is one of the prevalent forms of neuropathy that involves alterations in biomechanical changes in the human gait. Diabetic foot ulceration (DFU) is one of the pervasive types of complications that arise due to DN. In the literature, for the last 50 years, researchers have been trying to observe the biomechanical changes due to DN and DFU by studying muscle electromyography (EMG) and ground reaction forces (GRF). However, the literature is contradictory. In such a scenario, we propose using Machine learning techniques to identify DN and DFU patients by using EMG and GRF data. We collected a dataset from the literature which involves three patient groups: Control (n = 6), DN (n = 6), and previous history of DFU (n = 9) and collected three lower limb muscles EMG (tibialis anterior (TA), vastus lateralis (VL), gastrocnemius lateralis (GL)), and three GRF components (GRFx, GRFy, and GRFz). Raw EMG and GRF signals were preprocessed, and different feature extraction techniques were applied to extract the best features from the signals. The extracted feature list was ranked using four different feature ranking techniques, and highly correlated features were removed. In this study, we considered different combinations of muscles and GRF components to find the best performing feature list for the identification of DN and DFU. We trained eight different conventional ML models: Discriminant analysis classifier (DAC), Ensemble classification model (ECM), Kernel classification model (KCM), k-nearest neighbor model (KNN), Linear classification model (LCM), Naive Bayes classifier (NBC), Support vector machine classifier (SVM), and Binary decision classification tree (BDC), to find the best-performing algorithm and optimized that model. We trained the optimized the ML algorithm for different combinations of muscles and GRF component features, and the performance matrix was evaluated. Our study found the KNN algorithm performed well in identifying DN and DFU, and we optimized it before training. We found the best accuracy of 96.18% for EMG analysis using the top 22 features from the chi-square feature ranking technique for features from GL and VL muscles combined. In the GRF analysis, the model showed 98.68% accuracy using the top 7 features from the Feature selection using neighborhood component analysis for the feature combinations from the GRFx-GRFz signal. In conclusion, our study has shown a potential solution for ML application in DN and DFU patient identification using EMG and GRF parameters. With careful signal preprocessing with strategic feature extraction from the biomechanical parameters, optimization of the ML model can provide a potential solution in the diagnosis and stratification of DN and DFU patients from the EMG and GRF signals.

Myoelectric Pattern Recognition Performance Enhancement Using Nonlinear Features

The multichannel electrode array used for electromyogram (EMG) pattern recognition provides good performance, but it has a high cost, is computationally expensive, and is inconvenient to wear. Therefore, researchers try to use as few channels as possible while maintaining improved pattern recognition performance. However, minimizing the number of channels affects the performance due to the least separable margin among the movements possessing weak signal strengths. To meet these challenges, two time-domain features based on nonlinear scaling, the log of the mean absolute value (LMAV) and the nonlinear scaled value (NSV), are proposed. In this study, we validate the proposed features on two datasets, the existing four feature extraction methods, variable window size, and various signal-to-noise ratios (SNR). In addition, we also propose a feature extraction method where the LMAV and NSV are grouped with the existing 11 time-domain features. The proposed feature extraction method enhances accuracy, sensitivity, specificity, precision, and F1 score by 1.00%, 5.01%, 0.55%, 4.71%, and 5.06% for dataset 1, and 1.18%, 5.90%, 0.66%, 5.63%, and 6.04% for dataset 2, respectively. Therefore, the experimental results strongly suggest the proposed feature extraction method, for taking a step forward with regard to improved myoelectric pattern recognition performance.

BOND study: a randomised double-blind, placebo-controlled trial over 12 months to assess the effects of benfotiamine on morphometric, neurophysiological and clinical measures in patients with type 2 diabetes with symptomatic polyneuropathy

INTRODUCTION

Diabetic sensorimotor polyneuropathy (DSPN) affects approximately 30% of people with diabetes, while around half of cases are symptomatic. Currently, there are only few pathogenetically oriented pharmacotherapies for DSPN, one of which is benfotiamine, a prodrug of thiamine with a high bioavailability and favourable safety profile. While benfotiamine has shown positive effects in preclinical and short-term clinical studies, no long-term clinical trials are available to demonstrate disease-modifying effects on DSPN using a comprehensive set of disease-related endpoints.

METHODS AND ANALYSIS

The benfotiamine on morphometric, neurophysiological and clinical measures in patients with type 2 diabetes trial is a randomised double-blind, placebo-controlled parallel group monocentric phase II clinical trial to assess the effects of treatment with benfotiamine compared with placebo in participants with type 2 diabetes and mild to moderate symptomatic DSPN. Sixty participants will be 1:1 randomised to treatment with benfotiamine 300 mg or placebo two times a day over 12 months. The primary endpoint will be the change in corneal nerve fibre length assessed by corneal confocal microscopy (CCM) after 12 months of benfotiamine treatment compared with placebo. Secondary endpoints will include other CCM measures, skin biopsy and function indices, variables from somatic and autonomic nerve function tests, clinical examination and questionnaires, general health, health-related quality of life, cost, safety and blood tests.

ETHICS AND DISSEMINATION

The trial was approved by the competent authority and the local independent ethics committee. Trial results will be published in peer-reviewed journals, conference abstracts, and via online and print media.

TRIAL REGISTRATION NUMBER

DRKS00014832.

Corneal confocal microscopy for the diagnosis of diabetic peripheral neuropathy: A systematic review and meta-analysis

INTRODUCTION

Corneal confocal microscopy (CCM) is a rapid non-invasive ophthalmic imaging technique that identifies corneal nerve fiber damage. Small studies suggest that CCM could be used to assess patients with diabetic peripheral neuropathy (DPN).

AIM

To undertake a systematic review and meta-analysis assessing the diagnostic utility of CCM for sub-clinical DPN (DPN- ) and established DPN (DPN+ ).

DATA SOURCES

Databases (PubMed, Embase, Central, ProQuest) were searched for studies using CCM in patients with diabetes up to April 2020.

STUDY SELECTION

Studies were included if they reported on at least one CCM parameter in patients with diabetes.

DATA EXTRACTION

Corneal nerve fiber density (CNFD), corneal nerve branch density (CNBD), corneal nerve fiber length (CNFL), and inferior whorl length (IWL) were compared between patients with diabetes with and without DPN and controls. Meta-analysis was undertaken using RevMan V.5.3.

DATA SYNTHESIS

Thirty-eight studies including ~4,000 participants were included in this meta-analysis. There were significant reductions in CNFD, CNBD, CNFL, and IWL in DPN- vs controls (P < 0.00001), DPN+ vs controls (P < 0.00001), and DPN+ vs DPN- (P < 0.00001).

CONCLUSION

This systematic review and meta-analysis shows that CCM detects small nerve fiber loss in subclinical and clinical DPN and concludes that CCM has good diagnostic utility in DPN.

Diagnostic Tools, Biomarkers, and Treatments in Diabetic polyneuropathy and Cardiovascular Autonomic Neuropathy

The various manifestations of diabetic neuropathy, including distal symmetric sensorimotor polyneuropathy (DSPN) and cardiovascular autonomic neuropathy (CAN), are among the most prevalent chronic complications of diabetes. Major clinical complications of diabetic neuropathies, such as neuropathic pain, chronic foot ulcers, and orthostatic hypotension, are associated with considerable morbidity, increased mortality, and diminished quality of life. Despite the substantial individual and socioeconomic burden, the strategies to diagnose and treat diabetic neuropathies remain insufficient. This review provides an overview of the current clinical aspects and recent advances in exploring local and systemic biomarkers of both DSPN and CAN assessed in human studies (such as biomarkers of inflammation and oxidative stress) for better understanding of the underlying pathophysiology and for improving early detection. Current therapeutic options for DSPN are (I) causal treatment, including lifestyle modification, optimal glycemic control, and multifactorial risk intervention, (II) pharmacotherapy derived from pathogenetic concepts, and (III) analgesic treatment against neuropathic pain. Recent advances in each category are discussed, including non-pharmacological approaches, such as electrical stimulation. Finally, the current therapeutic options for cardiovascular autonomic complications are provided. These insights should contribute to a broader understanding of the various manifestations of diabetic neuropathies from both the research and clinical perspectives.

Force-Invariant Improved Feature Extraction Method for Upper-Limb Prostheses of Transradial Amputees

A force-invariant feature extraction method derives identical information for all force levels. However, the physiology of muscles makes it hard to extract this unique information. In this context, we propose an improved force-invariant feature extraction method based on nonlinear transformation of the power spectral moments, changes in amplitude, and the signal amplitude along with spatial correlation coefficients between channels. Nonlinear transformation balances the forces and increases the margin among the gestures. Additionally, the correlation coefficient between channels evaluates the amount of spatial correlation; however, it does not evaluate the strength of the electromyogram signal. To evaluate the robustness of the proposed method, we use the electromyogram dataset containing nine transradial amputees. In this study, the performance is evaluated using three classifiers with six existing feature extraction methods. The proposed feature extraction method yields a higher pattern recognition performance, and significant improvements in accuracy, sensitivity, specificity, precision, and F1 score are found. In addition, the proposed method requires comparatively less computational time and memory, which makes it more robust than other well-known feature extraction methods.

Performance Analysis of Conventional Machine Learning Algorithms for Diabetic Sensorimotor Polyneuropathy Severity Classification

Background: Diabetic peripheral neuropathy (DSPN), a major form of diabetic neuropathy, is a complication that arises in long-term diabetic patients. Even though the application of machine learning (ML) in disease diagnosis is a very common and well-established field of research, its application in diabetic peripheral neuropathy (DSPN) diagnosis using composite scoring techniques like Michigan Neuropathy Screening Instrumentation (MNSI), is very limited in the existing literature. Method: In this study, the MNSI data were collected from the Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials. Two different datasets with different MNSI variable combinations based on the results from the eXtreme Gradient Boosting feature ranking technique were used to analyze the performance of eight different conventional ML algorithms. Results: The random forest (RF) classifier outperformed other ML models for both datasets. However, all ML models showed almost perfect reliability based on Kappa statistics and a high correlation between the predicted output and actual class of the EDIC patients when all six MNSI variables were considered as inputs. Conclusions: This study suggests that the RF algorithm-based classifier using all MNSI variables can help to predict the DSPN severity which will help to enhance the medical facilities for diabetic patients.