Browse
Submit Data
Databases
API
Help

Dataset Information

21 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Machine learning-based approach for disease severity classification of carpal tunnel syndrome.

ABSTRACT: Identifying the severity of carpal tunnel syndrome (CTS) is essential to providing appropriate therapeutic interventions. We developed and validated machine-learning (ML) models for classifying CTS severity. Here, 1037 CTS hands with 11 variables each were retrospectively analyzed. CTS was confirmed using electrodiagnosis, and its severity was classified into three grades: mild, moderate, and severe. The dataset was randomly split into a training (70%) and test (30%) set. A total of 507 mild, 276 moderate, and 254 severe CTS hands were included. Extreme gradient boosting (XGB) showed the highest external validation accuracy in the multi-class classification at 76.6% (95% confidence interval [CI] 71.2-81.5). XGB also had an optimal model training accuracy of 76.1%. Random forest (RF) and k-nearest neighbors had the second-highest external validation accuracy of 75.6% (95% CI 70.0-80.5). For the RF and XGB models, the numeric rating scale of pain was the most important variable, and body mass index was the second most important. The one-versus-rest classification yielded improved external validation accuracies for each severity grade compared with the multi-class classification (mild, 83.6%; moderate, 78.8%; severe, 90.9%). The CTS severity classification based on the ML model was validated and is readily applicable to aiding clinical evaluations.

SUBMITTER: Park D

PROVIDER: S-EPMC8408248 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Carpal tunnel syndrome in fabry disease.

Project description:Carpal tunnel syndrome (CTS) is a common peripheral mononeuropathy affecting up to 4% of the general population, typically women in late middle age. The incidence in patients with Fabry disease (FD) is unclear, but may affect 25% of patients with this X-linked lysosomal storage disease. We report three cases of CTS in young Caucasian male patients with classical FD, who developed CTS symptoms with supportive nerve conduction study (NCS) findings. Two patients had bilateral CTS and two had evidence of concurrent ulnar nerve neuropathy on NCS, suggesting a systemic process contributed to nerve compression. All were receiving enzyme replacement therapy (ERT) and had a moderate burden of FD complications. It is possible that an increase in connective tissue in the intracarpal canal in FD patients may be incited by injury to fibroblasts, via either accumulation of globotriaosylceramide (GL3) or local ischaemia through endothelial injury. The former hypothesis may be a more plausible explanation for the development of CTS, as histology of the flexor retinaculae from our patients has demonstrated fibroblasts with characteristic vacuolation and excessive myxomatous stroma, despite endothelial clearance of GL3 in these patients receiving ERT. CTS should not be overlooked in FD patients and young patients presenting with CTS should be evaluated for an underlying systemic or genetic disorder. Surgical carpal tunnel decompression was effective in our patients, already troubled by long-standing acroparesthesia, in providing sustained relief of symptoms.

| S-EPMC3509834 | biostudies-literature

Developing Machine Learning Algorithms to Support Patient-centered, Value-based Carpal Tunnel Decompression Surgery.

Project description:BackgroundCarpal tunnel syndrome (CTS) is extremely common and typically treated with carpal tunnel decompression (CTD). Although generally an effective treatment, up to 25% of patients do not experience meaningful benefit. Given the prevalence, this amounts to considerable morbidity and cost without return. Being able to reliably predict which patients would benefit from CTD preoperatively would support more patient-centered and value-based care.MethodsWe used registry data from 1916 consecutive patients undergoing CTD for CTS at a regional hand center between 2010 and 2019. Improvement was defined as change exceeding the respective QuickDASH subscale's minimal important change estimate. Predictors included a range of clinical, demographic and patient-reported variables. Data were split into training (75%) and test (25%) sets. A range of machine learning algorithms was developed using the training data and evaluated with the test data. We also used a machine learning technique called chi-squared automatic interaction detection to develop flowcharts that could help clinicians and patients to understand the chances of a patient improving with surgery.ResultsThe top performing models predicted functional and symptomatic improvement with accuracies of 0.718 (95% confidence interval 0.660, 0.771) and 0.759 (95% confidence interval 0.708, 0.810), respectively. The chi-squared automatic interaction detection flowcharts could provide valuable clinical insights from as little as two preoperative questions.ConclusionsPatient-reported outcome measures and machine learning can support patient-centered and value-based healthcare. Our algorithms can be used for expectation management and to rationalize treatment risks and costs associated with CTD.

| S-EPMC9015194 | biostudies-literature

Ultrasonography Findings of the Carpal Tunnel after Endoscopic Carpal Tunnel Release for Carpal Tunnel Syndrome.

Project description:ObjectiveTo investigate changes in the median nerve, retinaculum, and carpal tunnel on ultrasound after successful endoscopic carpal tunnel release (ECTR).Materials and methodsThis prospective study involved 37 wrists in 35 patients (5 male, 30 female; mean age ± standard deviation [SD], 56.9 ± 6.7 years) with primary carpal tunnel syndrome (CTS). An in-house developed scoring system (0-3) was used to gauge the clinical improvement after ECTR. Ultrasound was performed before ECTR, and at 1, 3, and 12 months post-ECTR. Changes in the median nerve, flexor retinaculum, and carpal tunnel morphology on ultrasound after ECTR were analyzed. Ultrasound parameters for different clinical improvement groups were compared.ResultsAll patients improved clinically after ECTR. The average clinical improvement score ± SD at 12 months post-ECTR was 2.2 ± 0.7. The median nerve cross-sectional area proximal and distal to the tunnel decreased at all time intervals post-ECTR but remained swollen compared to normal values. Serial changes in the median nerve caliber and retinacular bowing after ECTR were more pronounced at the tunnel outlet than at the tunnel inlet. The flexor retinaculum had reformed in 25 (68%) of 37 wrists after 12 months.ConclusionPostoperative changes in median nerve and retinaculum parameters were most pronounced at the tunnel outlet. Even in patients with clinical improvement after ECTR, nearly all ultrasound parameters remain abnormal at one year post-ECTR. These ultrasound parameters should not necessarily be relied upon to diagnose persistent CTS after ECTR.

| S-EPMC8236373 | biostudies-literature

Splinting for carpal tunnel syndrome.

Project description: Not available

| S-EPMC9969978 | biostudies-literature

Carpal tunnel syndrome with paracoccidioidomycosis.

Project description: Not available

| S-EPMC3414040 | biostudies-literature

Efficacy of Keyhole Approach to Carpal Tunnel Syndrome under Ambulatory Strategy.

Project description:The carpal tunnel syndrome is one of the most common entrapment neuropathies found in humans. Currently, the gold standard is surgical treatment using different modalities. The minimally invasive strategy with high resolution capacity and less morbidity is still a challenge. Methods. Prospective nonrandomised clinical trial in which a minimally invasive microsurgical approach was used following the keyhole principle in 55 consecutive patients and 65 hands under local anesthesia and ambulatory strategy. They were evaluated with stringent inclusion criteria with the Levine severity and functional status scale and with a 2-year follow-up. Results. 90% showed immediate improvement dropping to grades 1-2 in all items of the scale referring to pain and numbness. 97% reported improvement, as of the first month, and 3% reported persistence of symptoms, although at a lesser degree and with no functional limitation. No incidents were identified during the procedure and 98% of patients were discharged within an hour after the surgical procedure. Conclusions. The microsurgical approach described following the keyhole principle is a treatment option that, under local anesthesia and ambulatory management, may represent an alternative strategy of an effective treatment reducing the morbidity. This trial is registered with Clinical Trials Protocol Identifier NCT03062722.

| S-EPMC5397629 | biostudies-literature

Relative Motion of the Connective Tissue in Carpal Tunnel Syndrome: The Relation with Disease Severity and Clinical Outcome.

Project description:Excursion of the median nerve and the surrounding subsynovial connective tissue (SSCT) is diminished in patients with carpal tunnel syndrome (CTS). This study sought to determine if SSCT excursion could be utilized to predict surgical outcome. Idiopathic CTS patients were reviewed with ultrasound and electrodiagnostic tests at baseline. A speckle tracking algorithm was used to determine SSCT relative to tendon motion (shear index). Analysis of variance tests were used to compare SSCT motion with disease severity at baseline. Adjusted linear regressions were used to test the association with patient-reported outcome. A total of 90 CTS patients were analyzed and found to have an average shear index of 79% (95% confidence interval: 76.3%-81.6%). SSCT motion was lower in CTS patients with increasing electrophysiological severity (p = 0.0475). There was no significant association of pre-operative SSCT motion with symptomatic improvement (p = 0.268). Overall, SSCT motion is decreased in CTS patients, but exhibits limited correlation with clinical severity.

| S-EPMC7429249 | biostudies-literature

Severity of Carpal Tunnel Syndrome and Diagnostic Accuracy of Hand and Body Anthropometric Measures.

Project description:ObjectiveTo study the diagnostic properties of hand/wrist and body measures according to validated clinical and electrophysiological carpal tunnel syndrome (CTS) severity scales.MethodsWe performed a prospective case-control study. For each case, two controls were enrolled. Two five-stage clinical and electrophysiological scales were used to evaluate CTS severity. Anthropometric measurements were collected and obesity indicators and hand/wrist ratios were calculated. Area under the receiver operating characteristic curves (AUC), sensitivity, specificity, and likelihood ratios were calculated separately by gender.ResultsWe consecutively enrolled 370 cases and 747 controls. The wrist-palm ratio, waist-hip-height ratio and waist-stature ratio showed the highest proportion of cases with abnormal values in the severe stages of CTS for clinical and electrophysiological severity scales in both genders. Accuracy tended to increase with CTS severity for females and males. In severe stage, most of the indexes presented moderate accuracy in both genders. Among subjects with severe CTS, the wrist-palm ratio presented the highest AUC for hand measures in the clinical and electrophysiological severity scales both in females (AUC 0.83 and 0.76, respectively) and males (AUC 0.91 and 0.82, respectively). Among subjects with severe CTS, the waist-stature ratio showed the highest AUC for body measures in the clinical and electrophysiological severity scales both in females (AUC 0.78 and 0.77, respectively) and males (AUC 0.84 and 0.76, respectively). The results of waist-hip-height ratio AUC were similar.ConclusionsWrist-palm ratio, waist-hip-height ratio and waist-stature ratio could contribute to support the diagnostic hypothesis of severe CTS that however has to be confirmed by nerve conduction study.

| S-EPMC5074522 | biostudies-literature

Carpal Tunnel Syndrome in Patients with Tremor Dominant Parkinson's Disease.

Project description:Unilateral hand tremor is one of the cardinal symptoms of Parkinson's disease. Additionally, mechanical traumatic hand movement is one of the risk factors for carpal tunnel syndrome. Our objective in this study was to examine whether repetitive mechanical movement may be related to the development of carpal tunnel syndrome in Parkinson's disease with unilateral hand tremor using neurophysiological methods.The study participants included 33 de novo Parkinson's disease patients with unilateral hand tremor, and we compared the tremor hand and non-tremor hand within the same patients.Seven (21.2%) of the 33 patients had carpal tunnel syndrome. All of carpal tunnel syndrome patients showed neurophysiological abnormalities in both the hand without tremor and the hand with tremor. In addition, in patients without carpal tunnel syndrome, the sensory nerve action potential was lower in the hand without tremor than in the hand with tremor, although there were no significant differences.We concluded that hand tremor in de novo Parkinson's disease patients was not directly related to the development of carpal tunnel syndrome. In contrast, more frequent use of hand without tremor may induce mechanical loading and may be associated with CTS in the hand without tremor. Early diagnosis of Parkinson's disease and proper education in hand use may be essential for preventing carpal tunnel syndrome in Parkinson's disease tremor patients.

| S-EPMC4474427 | biostudies-other

Association between the catechol-o-methyltransferase val158met polymorphism with susceptibility and severity of carpal tunnel syndrome.

Project description:Carpal tunnel syndrome (CTS) is the most common entrapment neuropathy of the upper extremity. In this study, we aimed to clarify the relationships between the catechol-O-methyltransferase (COMT) gene Val158Met (rs4680) polymorphism and development, functional and clinical status of CTS. Ninety-five women with electro diagnostically confirmed CTS and 95 healthy controls were enrolled in the study. The functional and clinical status of the patients was measured by the Turkish version of the Boston Questionnaire and intensity of pain related to the past 2 weeks was evaluated on a visual analog scale (VAS). The Val158Met polymorphism was determined using the polymerase chain reaction-restriction fragment length polymorphism (PCR-RFLP), method. We divided patients according to the genotypes of the Val158Met polymorphism as Val/Val, Val/Met and Met/Met. There were not any significant differences in terms of Val158Met polymorphisms between patients and healthy controls (p >0.05). We also did not find any relationships between the Val158Met polymorphism and CTS (p >0.05). In conclusion, although we did not find any relationships between CTS and the Val158Met polymorphism, we could not generalize this result to the general population. Future studies are warranted to conclude precise associations.

| S-EPMC5026268 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data