Carpal tunnel syndrome prediction with machine learning algorithms using anthropometric and strength-based measurement.

OBJECTIVES: Carpal tunnel syndrome (CTS) stands as the most prevalent upper extremity entrapment neuropathy, with a multifaceted etiology encompassing various risk factors. This study aimed to investigate whether anthropometric measurements of the hand, grip strength, and pinch strength could serve as predictive indicators for CTS through machine learning techniques. METHODS: Enrollment encompassed patients exhibiting CTS symptoms (n = 56) and asymptomatic healthy controls (n = 56), with confirmation via electrophysiological assessments. Anthropometric measurements of the hand were obtained using a digital caliper, grip strength was gauged via a digital handgrip dynamometer, and pinch strengths were assessed using a pinchmeter. A comprehensive analysis was conducted employing four most common and effective machine learning algorithms, integrating thorough parameter tuning and cross-validation procedures. Additionally, the outcomes of variable importance were presented. RESULTS: Among the diverse algorithms, Random Forests (accuracy of 89.474%, F1-score of 0.905, and kappa value of 0.789) and XGBoost (accuracy of 86.842%, F1-score of 0.878, and kappa value of 0.736) emerged as the top-performing choices based on distinct classification metrics. In addition, using variable importance calculations specific to these models, the most important variables were found to be wrist circumference, hand width, hand grip strength, tip pinch, key pinch, and middle finger length. CONCLUSION: The findings of this study demonstrated that wrist circumference, hand width, hand grip strength, tip pinch, key pinch, and middle finger length can be utilized as reliable indicators of CTS. Also, the model developed herein, along with the identified crucial variables, could serve as an informative guide for healthcare professionals, enhancing precision and efficacy in CTS prediction.

Effects of COVID-19 on brain and cerebellum: a voxel based morphometrical analysis.

OBJECTIVE: COVID-19 is caused by SARS-CoV-2 virus and turned into a pandemic in a short time, affects many organs and systems, especially the nervous system. In the present study, it was aimed to determine the morphological and volumetric changes in cortical and subcortical structures in recovered COVID-19 patients. BACKGROUND: We think that COVID-19 has a long-term effect on cortical and subcortical structures. METHODS: In our study, 50 post-COVID-19 patients and 50 healthy volunteers participated. In both groups, brain parcellations were made with Voxel-Based Morphometry (VBM) and regions showing density changes in the brain and cerebellum were determined. Gray matter (GM), white matter, cerebrospinal fluid and total intracranial volume were calculated. RESULTS: Neurological symptoms developed in 80% of COVID-19 patients. In post-COVID-19 patients, a decrease in GM density was detected in pons, gyrus frontalis inferior, gyri orbitales, gyrus rectus, gyrus cinguli, lobus parietalis, gyrus supramarginalis, gyrus angularis, hippocampus, lobulus semilunaris superior of cerebellum, declive, and Brodmann area 7-11-39-40. There was a significant decrease in GM density in these regions and an increase in GM density in amygdala (p<0.001). The GM volume of post-COVID-19 group was found to be less than in the healthy group. CONCLUSIONS: As a result, it was seen that COVID-19 negatively affected many structures related to the nervous system. This study is a pioneering study to determine the consequences of COVID-19, especially in the nervous system, and to determine the etiology of these possible problems (Tab. 4, Fig. 5, Ref. 25). Text in PDF www.elis.sk Keywords: COVID-19, pandemic, Voxel-based morphometry (VBM), brain, magnetic resonance imaging (MRI).

Determination of five times-sit-to-stand test performance in patients with multiple sclerosis: validity and reliability.

PURPOSE/AIM: Although Five Times-Sit-To-Stand test (FTSST) performance is known to be a valid and reliable method in people with chronic stroke, Parkinson's disease, and balance disorder, it has not been widely studied in patients with Multiple sclerosis (MS). The main aim of this study was to evaluate validity and reliability of the FTSST in patients with MS. METHODS: The first outcome measure of the study was the FTSST, which was conducted by two different researchers. Secondary outcome measures were Biodex Stability System (BSS), 10-meter walk test, time up go test (TUG), EDSS scoring, Fatigue Severity Scale (FSS), Barthel Index, Quadriceps Muscle strength test, Functional Reach test. Intraclass correlation coefficient (ICC) was used for the validity and reliability of the FTSST, which was made by two different researchers, and Pearson Correlation Analysis was used to determine its relationship with other measurements. RESULTS: Interrater and test-retest reliability for the FTSST were excellent (Intraclass correlation coefficients of 0.98 and 0.99, respectively). A statistically significant correlation was found between all secondary outcome measures and FTSST (p < 0.05). CONCLUSION: FTSST is considered to be a valid, reliable, easy, and rapid method for evaluating lower extremity muscle strength and balance in patients with MS.

The Turkish Version of Pain Assessment in Advanced Dementia (PAINAD) Scale.

INTRODUCTION: This study was conducted to test the reliability and validity of the Turkish version of the "Pain Assessment In Advanced Dementia (PAINAD) Scale". METHODS: One hundred and six older adults with advanced dementia (AD) were recruited in the study. Detailed medical history and demographic data of the participants were recorded. Initially, the Turkish version of PAINAD (PAINAD-TR), which was prepared by means of "back-translation", was applied. Along with this scale, Mini Mental State Examination, Clinical Dementia Rating scale, and Visual Analog Scale were also used. RESULTS: The Cronbach's α coefficient was 0.82 and 0.85 for the test and re-test, respectively. For the test-retest reliability of the PAINAD-TR scale, values of the intraclass correlation coefficient (ICC) and 95% confidence interval (CI) were 0.812 and 0.763-0.850 respectively. According to the results of a factor analysis carried out on the scale, a 2-domain structure was proved. CONCLUSION: The PAINAD-TR scale can be used for the assessment and management of pain in non-communicative older adults with AD.

Reliability and validity of the Turkish version of Pain Assessment Checklist for Seniors with Limited Ability to Communicate (PACSLAC-T)

Background/aim: This study aimed to assess validity and reliability of the Turkish version of Pain Assessment Checklist for Seniors with Limited Ability to Communicate (PACSLAC-T). Materials and methods: The individuals who met inclusion criteria of the study were in patients of a hospital and a long-term care facility. Mini Mental Status Exam (MMSE), Cornell Dementia Depression Scale (CDDS), Global Deterioration Scale (GDS), visual analogue scale (VAS), and PACSLAC-T were administered to all subjects. The scales were repeated with an interval of two weeks for test­retest reliability. Results: A total of 112 patients with dementia were included in the study. The intraclass correlation coefficient ICC for test­retest reliability of the PACSLAC-T was 0.713 with a 95% confidence interval of 0.486­0.843. The Cronbach's α coefficient for total PACSLAC-T was 0.842 for test and 0.888 for retest, which indicated substantial internal consistency. In convergent validity, there were significant correlations between PACSLAC-T total score VAS (r = 0.684, P < 0.001), while no correlation was found between PACSLAC-T total score and CDDS (r = 0.127, P = 0.094), and GDS (r = 0.096, P = 0.167). Also, significant correlations were found between PACSLAC-T total score and MMSE (r = ­0.468, P = 0.016). Conclusion: This study showed that PACSLAC-T could be a promising tool for the management of pain in older adults with limited communication skills.