Median nerve ultrasound in carpal tunnel syndrome with normal electrodiagnostic tests

Carpal tunnel syndrome related to rheumatic disease (Review)

Carpal tunnel syndrome (CTS) is the most commonly occurring type of entrapment neuropathy in the world. Several conditions may contribute to the development of CTS, such as obesity, repetitive wrist movements, pregnancy, genetic predisposition and rheumatoid arthritis (RA) inflammation. CTS is characterized by a wide range of pathophysiological factors, including increased pressure, mechanical trauma and ischemic damage to the median nerve that runs through the wrist tunnel. In the present narrative literature review, the way rheumatic diseases (RDs) contribute to CTS occurrence is investigated. The epidemiological, clinical, paraclinical and pathogenesis aspects of the relationship are examined. CTS is the most common neurological finding in RA, and incidences of RA, psoriatic arthritis and CTS are closely related. The association of CTS with systemic lupus erythematosus, Sjögren's syndrome, Behcet's disease and systemic sclerosis is weaker. In these cases, the prevalence of CTS is similar to that in the general population. As the occurrence of CTS is increasing, understanding the common mechanism and making an early diagnosis are required to limit pain and costs. When patients with RD present with symptoms such as wrist pain, tingling sensations or numbness in their fingers, CTS should be suspected. This suspicion should not be interpreted in terms of RD. To accurately evaluate patients with RD, a detailed electrophysiological examination should be included in the evaluation process. A diagnostic algorithm should include neuromuscular ultrasound or magnetic resonance imaging for patients with RD.

Application of radiomics model based on ultrasound image features in the prediction of carpal tunnel syndrome severity

OBJECTIVE

The aim of our study is to develop and validate a radiomics model based on ultrasound image features for predicting carpal tunnel syndrome (CTS) severity.

METHODS

This retrospective study included 237 CTS hands (106 for mild symptom, 68 for moderate symptom and 63 for severe symptom). There were no statistically significant differences among the three groups in terms of age, gender, race, etc. The data set was randomly divided into a training set and a test set in a ratio of 7:3. Firstly, a senior musculoskeletal ultrasound expert measures the cross-sectional area of median nerve (MN) at the scaphoid-pisiform level. Subsequently, a recursive feature elimination (RFE) method was used to identify the most discriminative radiomic features of each MN at the entrance of the carpal tunnel. Eventually, a random forest model was employed to classify the selected features for prediction. To evaluate the performance of the model, the confusion matrix, receiver operating characteristic (ROC) curves, and F1 values were calculated and plotted correspondingly.

RESULTS

The prediction capability of the radiomics model was significantly better than that of ultrasound measurements when 10 robust features were selected. The training set performed perfect classification with 100% accuracy for all participants, while the testing set performed accurate classification of severity for 76.39% of participants with F1 values of 80.00, 63.40, and 84.80 for predicting mild, moderate, and severe CTS, respectively. Comparably, the F1 values for mild, moderate, and severe CTS predicted based on the MN cross-sectional area were 76.46, 57.78, and 64.00, respectively..

CONCLUSION

This radiomics model based on ultrasound images has certain value in distinguishing the severity of CTS, and was slightly superior to using only MN cross-sectional area for judgment. Although its diagnostic efficacy was still inferior to that of neuroelectrophysiology. However, this method was non-invasive and did not require additional costs, and could provide additional information for clinical physicians to develop diagnosis and treatment plans.

Diabetes Increases Median Nerve Cross-Sectional Area but Not Disease Severity in Patients with Carpal Tunnel Syndrome

Background

Ultrasonography (US) is a useful diagnostic modality for diagnosis of carpal tunnel syndrome (CTS). Diabetes mellitus is increasingly prevalent and is a risk factor for CTS. Given the increasing use of US in the diagnosis of CTS, our goal was to evaluate the influence of diabetes on CTS severity and the cross-sectional area (CSA) of the median nerve in patients with CTS.

Methods

Patients with clinically diagnosed CTS were seen in the outpatient setting from October 2014 to February 2021. Median nerve CSA and patient reported severity measures were obtained: Boston Carpal Tunnel Syndrome Questionnaire (BCTSQ) and CTS-6. For patients with diabetes, additional parameters were collected including most recent A1c, insulin pharmacotherapy, and polypharmacy.

Results

Ninety-nine patients (122 nerves) without diabetes and 55 patients (82 nerves) with diabetes were recruited for the study. Patients in the diabetes group were more obese and older and had a significantly increased median nerve CSA compared with patients without diabetes. Obesity was associated with higher median nerve CSA in all patients but not in patients with diabetes. There was no difference in disease severity in patients with and without diabetes as reported by BCTSQ or CTS-6 scores. In patients with diabetes, there was significantly decreased median nerve CSA with A1c of 6.5 or higher and a trend to decreased CSA with polypharmacy. There was no influence of insulin therapy on median nerve CSA.

Conclusion

Diabetes is associated with higher median nerve CSA in patients with CTS of similar disease severity. The increased median nerve CSA in patients with diabetes may be reflective of diabetes-related microvascular changes. Interestingly, the trend to decreased median nerve CSA in patients with suboptimal diabetic control (A1c ≥ 6.5) may suggest eventual degenerative changes to the median nerve. In summary, clinicians should be cautious with interpreting a larger median nerve CSA as more severe CTS in patients with diabetes.

Level of Evidence

Level 3 Diagnostic.

Application of ultrasound images-based radiomics in carpal tunnel syndrome: Without measuring the median nerve cross-sectional area

PURPOSE

By constructing a prediction model of carpal tunnel syndrome (CTS) based on ultrasound images, it can automatically and accurately diagnose CTS without measuring the median nerve cross-sectional area (CSA).

METHODS

A total of 268 wrists ultrasound images of 101 patients diagnosed with CTS and 76 controls in Ningbo NO.2 Hospital from December 2021 to August 2022 were retrospectively analyzed. The radiomics method was used to construct the Logistic model through the steps of feature extraction, feature screening, reduction, and modeling. The area under the receiver operating characteristic curve was calculated to evaluate the performance of the model, and the diagnostic efficiency of the radiomics model was compared with two radiologists with different experience.

RESULTS

The 134 wrists in the CTS group included 65 mild CTS, 42 moderate CTS, and 17 severe CTS. In the CTS group, 28 wrists median nerve CSA were less than the cut-off value, 17 wrists were missed by Dr. A, 26 wrists by Dr. B, and only 6 wrists were missed by radiomics model. A total of 335 radiomics features were extracted from each MN, of which 10 features were significantly different between compressed and normal nerves, and were used to construct the model. The area under curve (AUC) value, sensitivity, specificity, and accuracy of the radiomics model in the training set and testing set were 0.939, 86.17%, 87.10%, 86.63%, and 0.891, 87.50%, 80.49%, and 83.95%, respectively. The AUC value, sensitivity, specificity, and accuracy of the two doctors in the diagnosis of CTS were 0.746, 75.37%, 73.88%, 74.63% and 0.679, 68.66%, 67.16%, and 67.91%, respectively. The radiomics model was superior to the two-radiologist diagnosis, especially when there was no significant change in CSA.

CONCLUSION

Radiomics based on ultrasound images can quantitatively analyze the subtle changes in the median nerve, and can automatically and accurately diagnose CTS without measuring CSA, especially when there was no significant change in CSA, which was better than radiologists.

Pearls & Oy-sters: Case of Atypical Peripheral Nerve Findings Following Paclitaxel for Breast Cancer

Neuromuscular ultrasound (NMUS) is a valuable tool in establishing a diagnosis of carpal tunnel syndrome (CTS) and can be particularly helpful in patients with clinical CTS but normal nerve conduction studies (NCSs). This case involves the uncommon presentation of enlarged median nerves on NMUS with normal NCS in a patient with breast cancer who developed chemotherapy-induced peripheral neuropathy and CTS after taxane treatment. This case demonstrates that CTS should not be excluded based on electrodiagnostic studies alone, and comorbid CTS should be considered in patients receiving neurotoxic chemotherapy, even in the setting of normal NCS.

The Application of Ultrasound Image-Based Radiomics in the Diagnosis of Mild Carpal Tunnel Syndrome

OBJECTIVES

The ultrasound diagnosis of mild carpal tunnel syndrome (CTS) is challenging. Radiomics can identify image information that the human eye cannot recognize. The purpose of our study was to explore the value of ultrasound image-based radiomics in the diagnosis of mild CTS.

METHODS

This retrospective study included 126 wrists in the CTS group and 88 wrists in the control group. The radiomics features were extracted from the cross-sectional ultrasound images at the entrance of median nerve carpal tunnel, and the modeling was based on robust features. Two radiologists with different experiences diagnosed CTS according to two guidelines. The area under receiver (AUC) operating characteristic curve, sensitivity, specificity, and accuracy were used to evaluate the diagnostic efficacy of the two radiologists and the radiomics model.

RESULTS

According to guideline one, the AUC values of the two radiologists for CTS were 0.72 and 0.67, respectively; according to guideline two, the AUC were 0.73 and 0.68, respectively. The radiomics model achieved the best accuracy when 16 important robust features were selected. The AUC values of training set and test set were 0.92 and 0.90, respectively.

CONCLUSIONS

The radiomics label based on ultrasound images had excellent diagnostic efficacy for mild CTS. It is expected to help radiologists to identify early CTS patients as soon as possible, especially for inexperienced doctors.

Ultrasound-based radiomics in the diagnosis of carpal tunnel syndrome: The influence of regions of interest delineation method on mode

BACKGROUND

In the recent years, artificial intelligence (AI) algorithms have been used to accurately diagnose musculoskeletal diseases. However, it is not known whether the particular regions of interest (ROI) delineation method would affect the performance of the AI algorithm.

PURPOSE

The purpose of this study was to investigate the influence of ROI delineation methods on model performance and observer consistency.

METHODS

In this retrospective analysis, ultrasound (US) measures of median nerves affected with carpal tunnel syndrome (CTS) were compared to median nerves in a control group without CTS. Two methods were used for delineation of the ROI: (1) the ROI along the hyperechoic medial edge of the median nerve but not including the epineurium (MN) (ROI1); and (2) the ROI including the hyperechoic epineurium (ROI2), respectively. The intra group correlation coefficient (ICC) was used to compare the observer consistency of ROI features (i.e. the corresponding radiomics parameters). Parameters α₁ and α₂ were obtained based on the ICC of ROI₁ features and ROI₂ features. The ROC analysis was used to determine the area under the curve (AUC) and evaluate the performance of the radiologists and network. In addition, four indices, namely sensitivity, specificity, positive prediction and negative prediction were analyzed too.

RESULTS

A total of 136 wrists of 77 CTS group and 136 wrists of 74 control group were included in the study. Control group was matched to CTS group according to the age and sex. The observer consistency of ROI features delineated by the two schemes was different, and the consistency of ROI₁ features was higher (α1 ˃ α2). The intra-observer consistency was higher than the inter-observer consistency regardless of the scheme, and the intra-observer consistency was higher when chose scheme one. The performances of models based on the two ROI features were different, although the AUC of each model was greater than 0.8.The model performed better when the MN epineurium was included in the ROI. Among five artificial intelligence algorithms, the Forest models (model₁ achieved an AUC of 0.921 in training datasets and 0.830 in testing datasets; model₂ achieved an AUC of 0.967 in training datasets and 0.872 in testing datasets.) obtained the highest performance, followed by the support vector machine (SVM) models and the Logistic models. The performances of the models were significantly better than the inexperienced radiologist (Dr. B. Z. achieved an AUC of 0.702).

CONCLUSION

Different ROI delineation methods may affect the performance of the model and the consistency of observers. Model performance was better when the ROI contained the MN epineurium, and observer consistency was higher when the ROI was delineated along the hyperechoic medial border of the MN.

Ultrasonographic measurement of median nerve and wrist skin thickness in patients with carpal tunnel syndrome: relationship with clinical, electrophysiologic and functionality

The study aimed to investigate the relationship between the proximal and distal cross-sectional area (CSA) of the median nerve and wrist skin thickness measured by ultrasound in patients with carpal tunnel syndrome (CTS), demographics, disease characteristics, electrophysiological measurements, symptom severity, functionality, and symptom severity. 98 patients with electrophysiological diagnoses of CTS in the dominant hand were included in the study. Proximal and distal CSAs of the median nerve and wrist skin thickness were measured ultrasonographically. Demographic and disease characteristics of the patients were recorded. Patients were evaluated with the Historical-Objective scale (Hi- Ob) for clinical staging, the Functional status scale (FSS) for functional status, and the Boston symptom severity scale (BSSS) for symptom severity. Ultrasonographic findings were correlated with demographic and disease characteristics, electrophysiological findings, Hi-Ob scala, Functional status scale (FSS), and Boston symptom severity scale (BSSS). Proximal median nerve CSA median was 11.0 (7.0-14.0) mm2, distal median nerve CSA median was 10.5 (5.0-18.0) mm2, and wrist skin thickness was measured 1.10 (0.6-1.40) mm. Median nerve CSAs were positively correlated with the CTS stage and FSS, negatively correlated with the sensory nerve action potential of the median nerve (SNAP) and the compound muscle action potential of the median nerve (CMAP) ( p<0.05). Wrist skin thickness was positively correlated with disease characteristics, including the presence of paresthesia and loss of dexterity and FSS and BSSS levels. Ultrasonographic measurements in CTS are associated with functionality rather than demographics. Especially the increase in wrist skin thickness leads to an increase in symptom severity.

Predicting CTS Diagnosis and Prognosis Based on Machine Learning Techniques

Carpal tunnel syndrome (CTS) is a clinical disease that occurs due to compression of the median nerve in the carpal tunnel. The determination of the severity of carpal tunnel syndrome is essential to provide appropriate therapeutic interventions. Machine learning (ML)-based modeling can be used to classify diseases, make decisions, and create new therapeutic interventions. It is also used in medical research to implement predictive models. However, despite the growth in medical research based on ML and Deep Learning (DL), CTS research is still relatively scarce. While a few studies have developed models to predict diagnosis of CTS, no ML model has been presented to classify the severity of CTS based on comprehensive clinical data. Therefore, this study developed new classification models for determining CTS severity using ML algorithms. This study included 80 patients with other diseases that have an overlap in symptoms with CTS, such as cervical radiculopathysasas, de quervian tendinopathy, and peripheral neuropathy, and 80 CTS patients who underwent ultrasonography (US)-guided median nerve hydrodissection. CTS severity was classified into mild, moderate, and severe grades. In our study, we aggregated the data from CTS patients and patients with other diseases that have an overlap in symptoms with CTS, such as cervical radiculopathysasas, de quervian tendinopathy, and peripheral neuropathy. The dataset was randomly split into training and test data, at 70% and 30%, respectively. The proposed model achieved promising results of 0.955%, 0.963%, and 0.919% in terms of classification accuracy, precision, and recall, respectively. In addition, we developed a machine learning model that predicts the probability of a patient improving after the hydro-dissection injection process based on the aggregated data after three different months (one, three, and six). The proposed model achieved accuracy after six months of 0.912%, after three months of 0.901%, and after one month 0.877%. The overall performance for predicting the prognosis after six months outperforms the prediction after one and three months. We utilized statistics tests (significance test, Spearman's correlation test, and two-way ANOVA test) to determine the effect of injection process in CTS treatment. Our data-driven decision support tools can be used to help determine which patients to operate on in order to avoid the associated risks and expenses of surgery.

Carpal tunnel syndrome in rheumatoid arthritis patients: the role of combined ultrasonographic and electrophysiological assessment

Background

Carpal tunnel syndrome (CTS) is known as one of the most common neurological extra-articular manifestations in rheumatoid arthritis (RA) patients. Studies on CTS in RA depend mostly on electrophysiological assessment. Few studies have used ultrasonography for evaluation of the local causes with much focus on wrist arthritis and tenosynovitis as the main cause of entrapment neuropathy of the median nerve in RA. The aim of our study is to assess the local causes of carpal tunnel syndrome in rheumatoid arthritis patients by ultrasonography and whether inflammatory or anomalous variations could affect decision-making and patient management.

Results

Carpal tunnel syndrome was diagnosed in 71 out of 74 examined RA wrists by nerve conduction studies (NCSs) and was categorized from minimal to severe according to Padua et al.’s (Ital J Neurol Sci 18:145–50, 1997) grading criteria. Median nerve CSA at the level of the carpal tunnel inlet and flattening ratio showed statistically significant relation with CTS severity. Bifid MN was found in 20 wrists (10 mild CTS wrists and 10 moderate CTS wrists), a persistent median artery was found in 4 wrists with moderate CTS, and an accessory muscle bundle was present in 3 wrists (2 mild CTS and 1 moderate CTS). The majority of the examined hands (85.1%) showed flexor tendon tenosynovitis at the wrist level and radio-carpal joint synovitis. The US7-joint score using GSUS7 & PDUS7 for synovitis, tenosynovitis and erosions showed significant relation with patients’ disease activity by DAS28 score. Significant relations between CTS severity and the following nerve conduction studies’ parameters, median nerve distal motor latency (DML), motor/sensory NCV, peak sensory latency, amplitude of SNAP, and median-radial latency difference test, were observed.

Conclusion

Synovial inflammation and local causes of median nerve compression such as bifid median nerve, persistent median artery, and accessory muscle bundle are collectively contributing factors in the etiology of carpal tunnel syndrome in rheumatoid arthritis patients. Ultrasonographic visualization of these inflammatory and anomalous variations enables early detection of CTS and highlights the possibility of non-arthritic-related causes. Using the 7-joint ultrasound (US7) score for assessment of synovitis, tenosynovitis, and erosions in rheumatoid arthritis patients is of valuable role in reflecting inflammation and its relation to the development of CTS in RA patients.

The Correlation of Carpal Tunnel Pressure with Clinical Outcomes following Ultrasonographically-Guided Percutaneous Carpal Tunnel Release

Background: To evaluate the correlation between carpal tunnel pressure (CTP) and the clinical presentations, and to explore the possible predictors for the postoperative recovery pattern in patients with carpal tunnel syndrome (CTS). Materials and Methods: Consecutive patients with idiopathic CTS following percutaneous ultrasound-guided carpal tunnel release (UCTR) were enrolled. CTP was measured preoperatively and immediately after operation. The Boston Carpal Tunnel Questionnaire (BCTQ) and the cross-sectional area (CSA) of median nerve were recorded preoperatively and at 1, 3, and 12 months postoperatively. Results: 37 patients (37 hands; 8 men and 29 females; median age, 59.0 years) were enrolled. CTP significantly decreased immediately from 40.0 (28.0−58.0) to 13.0 (8.0−20.0) mmHg after UCTR. BCTQ scores significantly improved at 1 month postoperatively, and the improvement trend persisted until 12 months postoperatively (p < 0.001). Preoperative CTP was positively correlated with preoperative CSA and preoperative BCTQ scores (p < 0.05, all). Using group-based trajectory modeling, all patients were categorized into the “gradual recovery” or “fast recovery” group. Higher preoperative CTP was significantly associated with a faster recovery pattern (odds ratio: 1.32). Conclusions: Preoperative CTP was well correlated with the clinical presentations and might be a useful predictor for the postoperative clinical recovery pattern.

Assessment of carpal tunnel syndrome via ultrasonography among hospital workers: a screening study

Background

Carpal tunnel syndrome is a reasonably common disorder among working individuals. It may also be a cause of functional impairment. The aim of the study was to screen for the presence of carpal tunnel syndrome among hospital workers by non-invasive ultrasound.

Results

The prevalence of carpal tunnel syndrome diagnosed by ultrasound among hospital workers was 21.5%. Age and Boston carpal tunnel questionnaire scale were positively correlated to median nerve cross sectional area.

Conclusions

Ultrasound can be used as a non-invasive and convenient method for screening for carpal tunnel syndrome.

The Neurophysiological Severity of Carpal Tunnel Syndrome Cannot Be Predicted by Median Nerve Cross-Sectional Area and Wrist-to-Forearm Ratio

PURPOSE

The median nerve cross-sectional area at the wrist (CSA) and the wrist-to-forearm ratio of the cross-sectional areas (WFR) are ultrasound parameters used in the diagnosis and grading of carpal tunnel syndrome. This study aimed to determine the diagnostic accuracy of the CSA and WFR as well as to compare their diagnostic value.

METHODS

A retrospective evaluation was conducted of a cohort of 218 patients who had undergone nerve conduction studies (NCSs) and an ultrasound of the median nerve. The examined wrists were classified into an NCS negative and three NCS positive (mild, moderate, and severe) categories. The CSA and WFR were compared across the categories.

RESULTS

The CSA and WFR were significantly smaller in the NCS negative category than in the NCS positive categories. The WFR was significantly smaller in the mild category than in the moderate category. The CSA could not be used to differentiate across the NCS positive categories.

CONCLUSIONS

The CSA and WFR are satisfactorily reliable in detecting carpal tunnel syndrome, but they cannot be considered as surrogate indicators of electrophysiological severity.

Accurate automated diagnosis of carpal tunnel syndrome using radiomics features with ultrasound images: A comparison with radiologists' assessment

PURPOSE

Ultrasonography is the most common imaging modality used to diagnose carpal tunnel syndrome (CTS). Recently artificial intelligence algorithms have been used to diagnose musculoskeletal diseases accurately without human errors using medical images. In this work, a computer-aided diagnosis (CAD) system is developed using radiomics features extracted from median nerves (MN) to diagnose CTS accurately.

METHOD

This study is performed on 228 wrists from 65 patients and 57 controls, with an equal number of control and CTS wrists. Nerve conduction study (NCS) is considered as the gold standard in this study. Two radiologists used two guides to evaluate and categorize the pattern and echogenicity of MNs. Radiomics features are extracted from B-mode ultrasound images (Ultrasomics), and the robust features are fed into support vector machine classifier for automated classification. The diagnostic performances of two radiologists and the CAD system are evaluated using ROC analysis.

RESULTS

The agreement of two radiologists was excellent for both guide 1 and 2. The honey-comb pattern clearly appeared in control wrists (based on guide 1). In addition, CTS wrists indicated significantly lower number of fascicles in MNs (based on guide 2). The area under ROC curve (AUC) of the radiologist 1 and 2 are 0.658 and 0.667 based on guide 1 and 0.736 and 0.721 based on guide 2, respectively. The CAD system indicated higher performance than two radiologists with AUC of 0.926.

CONCLUSION

The proposed CAD system shows the benefit of using ultrasomics features and can assist radiologists to diagnose CTS accurately.

Carpal tunnel syndrome in patients with rheumatoid arthritis and psoriatic arthritis: an electrophysiological and ultrasonographic study

This study aimed to investigate the carpal tunnel syndrome (CTS) in patients with rheumatoid arthritis (RA) and psoriatic arthritis (PsA), compare the electrophysiological and ultrasonographic findings and evaluate related variables. Cut-off value of median nerve cross-sectional area (MCSA) was determined for the diagnosis of CTS. 70 RA patients, 39 PsA patients, a control group of 70 healty people were included in this study. Demographic characteristics, disease activity and functional status were recorded. Patients were referred for nerve conduction studies performed according to the American Academy of Neurology standards. Sonographic examination was carried on for MCSA evaluation. The mean age of patients was 51.87 ± 8.47, 50.61 ± 11.33, 49.75 ± 10.52 years and female ratio was 72.9%, 71.8%, 75.7% in RA, PsA and controls, respectively. Electrophysiologically, CTS frequency was found to be 13.2%, 15.4%, 3.5% in RA, PsA, control group, respectively, and a significant difference was found compared to the control group (p < 0.05). Ultrasonographically MCSA was measured as 8.52 ± 2.19 mm², 8.97 ± 2.41 mm², 7.09 ± 1.83 mm² in RA, PsA, control group, respectively, a significant difference was observed compared to the control group (p < 0.05). As a result of the Receiver Operating Characteristics analysis, the thereshold value of MCSA for CTS was determined as 10.5 mm².The frequency of CTS was found to be 30% in RA and 41% in PsA. The frequency of CTS with both ENMG and USG (MCSA) were higher in patients with RA and PsA as compared to the control group. Although it was not statistically significant, CTS frequency was higher in PsA than RA. To our knowledge this is the first study assessing CTS in patients with PsA, and adressing MCSA cut off value for CTS diagnosis in RA and PsA.