Off-road machine controls: investigating the risk of carpal tunnel syndrome

Occupationally induced hand and wrist repetitive strain injuries (RSI) such as carpal tunnel syndrome (CTS) are a growing problem in North America. The purpose of this investigation was to apply a modification of the wrist flexion/extension models of Armstrong and Chaffin (1978, 1979) to determine if joystick controller use in oV-road machines could contribute to the development of CTS. A construction equipment cab in the laboratory was instrumented to allow force, displacement and angle measurements from 10 operators while they completed an ? 30-min joystick motion protocol. The investigation revealed that both the external fingertip and predicted internal wrist forces resulting from the use of these joysticks were very low, indicating that the CTS risk associated with this factor was slight. However, the results also indicated that, particularly for the ‘forward’ and ‘left’ right side motions and for all left side motions, force was exerted by other portions of the fingers and hand, thereby under-predicting the tendon tension and internal wrist forces. Wrist angles observed were highest for motions that moved the joysticks to the sides rather than front to back. Thus, the ‘right’ and ‘left’ motions for both hands posed a higher risk for CTS development. When the right hand moved into the ‘right’ position and the left hand moved into the ‘left’ position, the wrist went into extension in both cases. Results indicate that neither learning nor fatigue aVected the results.     

The development of risk assessment models for carpal tunnel syndrome: a case-referent study

The present study developed risk assessment models for carpal tunnel syndrome (CTS) which can provide information of the likelihood of developing CTS for an individual having certain personal characteristics and occupational risks. A case-referent study was conducted consisting of two case groups and one referent group: (1) 22 work-related CTS patients (W-CTS), (2) 25 non-work related CTS patients (NW-CTS), and (3) 50 healthy workers (HEALTHY) having had no CTS history. The classification of CTS patients into one of the case groups was determined according to the type of insurance covering their medical costs. Personal characteristics, psychosocial stresses at work, and physical work conditions were surveyed by using a questionnaire tailor-designed to CTS (reliability of each scale ? 0.7). By contrasting the risk information of each case group to that of the referent group, three logistic regression models were developed: W-CTS/HEALTHY, NW-CTS/HEALTHY, and C-CTS/HEALTHY (C-CTS, the combined group of W-CTS and NW-CTS). ROC analysis indicated that the models have satisfactory discriminability (d′ = ;1.91 to 2.51) and high classification accuracy (overall accuracy = 83 – 89%). Both W-CTS/HEALTHY and C-CTS/HEALTHY include personal and physical factors, while NW-CTS/HEALTHY involves only personal factors. This suggests that the injury causation of NW-CTS patients should be attributable mainly to their ‘high’ personal susceptibility to the disorder rather than exposure to adverse work conditions, while that of W-CTS patients be attributable to improper work conditions and CTS-prone personal characteristics in combination.     

The development of risk assessment models for carpal tunnel syndrome: a case-referent study

The present study developed risk assessment models for carpal tunnel syndrome (CTS) which can provide information of the likelihood of developing CTS for an individual having certain personal characteristics and occupational risks. A case-referent study was conducted consisting of two case groups and one referent group: (1) 22 work-related CTS patients (W-CTS), (2) 25 non-work related CTS patients (NW-CTS), and (3) 50 healthy workers (HEALTHY) having had no CTS history. The classification of CTS patients into one of the case groups was determined according to the type of insurance covering their medical costs. Personal characteristics, psychosocial stresses at work, and physical work conditions were surveyed by using a questionnaire tailor-designed to CTS (reliability of each scale > or = 0.7). By contrasting the risk information of each case group to that of the referent group, three logistic regression models were developed: W-CTS/HEALTHY, NW-CTS/HEALTHY, and C-CTS/HEALTHY (C-CTS, the combined group of W-CTS and NW-CTS). ROC analysis indicated that the models have satisfactory discriminability (d' = 1.91 to 2.51) and high classification accuracy (overall accuracy = 83-89%). Both W-CTS/HEALTHY and C-CTS/HEALTHY include personal and physical factors, while NW-CTS/HEALTHY involves only personal factors. This suggests that the injury causation of NW-CTS patients should be attributable mainly to their 'high' personal susceptibility to the disorder rather than exposure to adverse work conditions, while that of W-CTS patients be attributable to improper work conditions and CTS-prone personal characteristics in combination.     

Effects of exercise on carpal tunnel syndrome symptoms

This is a study of whether participation in an exercise programme for increasing upper extremity flexibility, strength, and circulation has any effects on symptoms of carpal tunnel syndrome (CTS). Two groups (exercise and control) of seven participants each who did repetitive hand motion tasks were studied. The exercise group participated in daily arm, hand, and other upper-extremity exercises for 8 weeks. The control group did not participate in the exercise programme. Dependent (response) variables monitored were motor nerve conduction latency through the carpal tunnel, grip strength, and subjective comfort in the dominant hands of participants. Test results indicated no statistically significant differences in nerve conduction latency or subjective comfort between the two groups. Significant differences did develop in grip strengths over time, suggesting that the exercise group may have benefited physiologically from the exercise programme.     

Functional psychomotor deficits associated with carpal tunnel syndrome

A reliable task was developed for investigating functional deficits associated with carpal tunnel syndrome (CTS). A rapid pinch and release psychomotor task utilizing muscles of the hand innervated by the median nerve was administered using a strain gauge dynamometer and providing limited force feedback. The motor performance characteristics studied were speed and force control. An experiment was conducted for studying the effects of force level, hand dominance, test-retest reliability, learning, and inter-subject variability using 13 subjects free from any hand disabilities or symptoms. A companion study was also conducted using 17 normal subjects and ten subjects diagnosed having CTS to investigate differences between CTS and control subjects. Dominant hands performed 4% to 8% better than the non-dominant hands by having a greater pinch rate, a smaller overshoot force, and less time above the upper force level and below the lower force level. Control subjects performed 25% to 82% better than CTS subjects. Age contributed 6% of the total variance for pinch rate and 7% of the total variance for the time below the lower force level. The results suggest that people suffering from CTS may experience similar functional psychomotor deficits in daily living and manual work activities.     

Strength and range of motion of females with carpal tunnel syndrome

An experimental study was conducted to evaluate the grip and fingertip pinch strength, and range of motion of females with carpal tunnel syndrome (CTS). The range of motion of the wrist was measured in the sagittal, frontal, and transverse planes. Strength and range of motion measurements were also conducted on a control group. Results indicate that some strength and range of motion measures of the females with CTS were significantly different from that of the control group. Also, measurements in different planes caused significant differences in some range of motions of the wrist for both the CTS and the control groups.     

Prevalence of carpal tunnel syndrome among employees at a poultry processing plant

Objective

To determine prevalence of carpal tunnel syndrome (CTS) among poultry processing employees while taking into account non-occupational factors and assess any association between CTS prevalence and exposure groups.

Methods

Performed a cross-sectional survey to assess CTS (n = 318). A CTS case was defined as an employee with self-reported CTS symptoms, an abnormal hand symptom diagram, and an abnormal nerve conduction study (NCS). Log-binomial regression was used to estimate prevalence ratios.

Results

Three hundred and one participants had sufficient symptom information or NCS data to be classified. 126 (42%) of 301 participants had evidence of CTS. In the adjusted analysis, the highest exposure group had CTS prevalence that was significantly higher than that for the lower exposure group [PR: 1.61; 95% CI = (1.20, 2.17)].

Conclusions

Increasing levels of hand activity and force were associated with increased CTS prevalence among participants. Recommendations were provided to reduce exposure to these risk factors.     

Effect of carpal tunnel syndrome on grip force coordination on hand tools

This study investigated coordination of the grip force on and force applied with a hand tool using a precision pinch grip. A simulated hand tool was developed to measure grip force exerted on the tool as a function of the force transmitted from the tool to an external object in a dynamic force matching paradigm. Grip force coordination measures reflected subjects' abilities to modulate grip force in parallel with the tool application force and their abilities to minimize excessive grip force. These measures were calculated for seven subjects with a diagnosis of carpal tunnel syndrome (CTS) and seven age- and gender-matched controls. The absolute magnitude of excessive grip force (safety margin) was unreliable because of the high intrasubject variability in coefficient of friction measurements. Linear regression equations predicting coefficient of friction from pinch force magnitude had low r2 coefficients of determination and were generally not statistically significant (p > 0.05). Relative comparisons of grip force control showed that individuals with CTS exhibited a statistically significant (p < 0.05) increase in ratio of grip force to application force (54% higher than controls) and a significant (p < 0.05) decrease in modulation of pinch force with application force (12% lower than controls). These results suggest that individuals with CTS lose some ability to coordinate efficiently grip force on hand tools and exert higher grip forces on tools, at equivalent application forces, than controls. This is believed to be a result of tactile sensibility deficits associated with CTS. As a result, workers with CTS may be at increased risk of accelerating the progression of their musculoskeletal disorder.     

A gap detection tactility test for sensory deficits associated with carpal tunnel syndrome

An automated gap detection tactility test was investigated for quantifying sensory deficits associated with carpal tunnel syndrome (CTS). The test, which involved sensing a tiny gap in an otherwise smooth surface by probing with the finger, had functional resemblance to many work-related tactile activities such as detecting scratches or surface defects. Gap detection thresholds were measured using the converging staircase method of limits paradigm. Sixteen normal subjects between 21 and 66 years of age were tested for studying important factors affecting gap detection thresholds. Actively probing with the index finger had a threshold almost an order of magnitude more sensitive (mean = 0·19mm, SD = 0·llmm) than passive touch (mean =1·63mm. SD = 0·62mm), which was similar to two-point discrimination. Average thresholds decreased by 24% as contact force increased from 25 to 75?g. Performance in this tactility test quickly stabilized and showed little learning effects over the period of the test, as evidenced by the lack of significant differences between six replicates. The results were highly repeatable. No significant threshold differences were observed between test and retest trials on different days, or between dominant and non-dominant hands. A contact force of 50?g was recommended as optimal for this test since it required moderate force but resulted in a smaller threshold compared with 25 or 75?g. A companion study was conducted using eight normal subjects and ten subjects diagnosed as having CTS. Average gap detection threshold, when finger probing was allowed, was 0·20?mm (SD = 0·11?min) for the normal subjects and increased two-fold to 0·40?mm (SD = 0·19?mm) for the CTS subjects. Average gap detection threshold, when the finger probing was not allowed, was 1·71?mm (SD = 0·53mm) for the normal subjects and increased by 48% to 2·53?mm (SD = 0·87?mm) for the CTS subjects. The results suggest that people suffering from CTS may experience similar functional deficits in daily living and work activities. The small inter-subject variability makes this test a candidate for having utility as a monitoring test for loss of cutaneous tactile sensitivity.     

A fuzzy linguistic model for the prediction of carpal tunnel syndrome risks in an occupational environment

This research presents the development and evaluation of a fuzzy linguistic model designated to predict the risk of carpal tunnel syndrome (CTS) in an occupational setting. CTS has become one of the largest problems facing ergonomists and the medical community because it is developing in epidemic proportions within the occupational environment. In addition, practitioners are interested in identifying accurate methods for evaluating the risk of CTS in an occupational setting. It is hypothesized that many factors impact an individual's likelihood of developing CTS and the eventual development of CTS. This disparity in the occurrence of CTS for workers with similar backgrounds and work activities has confused researchers and has been a stumbling block in the development of a model for widespread use in evaluating the development of CTS. Thus this research is an attempt to develop a method that can be used to predict the likelihood of CTS risk in a variety of environments. The intent is that this model will be applied eventually in an occupational setting, thus model development was focused on a method that provided a usable interface and the desired system inputs can also be obtained without the benefit of a medical practitioner. The methodology involves knowledge acquisition to identify and categorize a holistic set of risk factors that include task-related, personal, and organizational categories. The determination of relative factor importance was accomplished using analytic hierarchy processing (AHP) analysis. Finally a mathematical representation of the CTS risk was accomplished by utilizing fuzzy set theory in order to quantify linguistic input parameters. An evaluation of the model including determination of sensitivity and specificity is conducted and the results of the model indicate that the results are fairly accurate and this method has the potential for widespread use. A significant aspect of this research is the comparison of this technique to other methods for assessing presence of CTS. The results of this evaluation technique are compared with more traditional methods for assessing the presence of CTS.     

A comparison of logistic regression to decision tree induction in the diagnosis of carpal tunnel syndrome.

This paper aims to compare and contrast two types of model (logistic regression and decision tree induction) for the diagnosis of carpal tunnel syndrome using four ordered classification categories. Initially, we present the classification performance results based on more than two covariates (multivariate case). Our results suggest that there is no significant difference between the two methods. Further to this investigation, we present a detailed comparison of the structure of bivariate versions of the models. The first surprising result of this analysis is that the classification accuracy of the bivariate models is slightly higher than that of the multivariate ones. In addition, the bivariate models lend themselves to graphical analysis, where the corresponding decision regions can easily be represented in the two-dimensional covariate space. This analysis reveals important structural differences between the two models.     

Pooling job physical exposure data from multiple independent studies in a consortium study of carpal tunnel syndrome

Pooling data from different epidemiological studies of musculoskeletal disorders (MSDs) is necessary to improve statistical power and to more precisely quantify exposure–response relationships for MSDs. The pooling process is difficult and time-consuming, and small methodological differences could lead to different exposure–response relationships. A sub-committee of a six-study research consortium studying carpal tunnel syndrome: (i) visited each study site, (ii) documented methods used to collect physical exposure data and (iii) determined compatibility of exposure variables across studies. Certain measures of force, frequency of exertion and duty cycle were collected by all studies and were largely compatible. A portion of studies had detailed data to investigate simultaneous combinations of force, frequency and duration of exertions. Limited compatibility was found for hand/wrist posture. Only two studies could calculate compatible Strain Index scores, but Threshold Limit Value for Hand Activity Level could be determined for all studies. Challenges of pooling data, resources required and recommendations for future researchers are discussed.

Practitioner Summary: There is a need for standardised measures and measurement protocols of physical exposure for the upper extremity. This study may provide guidance for those planning to conduct an epidemiological study on quantified job physical exposures, or planning to merge physical exposure data from similar studies with some methodologic differences.     

Experience report: investigating bug fixes in machine learning frameworks/libraries

Machine learning (ML) techniques and algorithms have been successfully and widely used in various areas including software engineering tasks. Like other software projects, bugs are also common in ML projects and libraries. In order to more deeply understand the features related to bug fixing in ML projects, we conduct an empirical study with 939 bugs from five ML projects by manually examining the bug categories, fixing patterns, fixing scale, fixing duration, and types of maintenance. The results show that (1) there are commonly seven types of bugs in ML programs; (2) twelve fixing patterns are typically used to fix the bugs in ML programs; (3) 68.80% of the patches belong to micro-scale-fix and small-scale-fix; (4) 66.77% of the bugs in ML programs can be fixed within one month; (5) 45.90% of the bug fixes belong to corrective activity from the perspective of software maintenance. Moreover, we perform a questionnaire survey and send them to developers or users of ML projects to validate the results in our empirical study. The results of our empirical study are basically consistent with the feedback from developers. The findings from the empirical study provide useful guidance and insights for developers and users to effectively detect and fix bugs in MLprojects.     

Effects of computer mouse design and task on carpal tunnel pressure

Computer mouse use has become an integral part of office work in the past decade. Intensive mouse use has been associated with increased risk of upper extremity musculoskeletal disorders, including carpal tunnel syndrome. Sustained, elevated fluid pressure in the carpal tunnel may play a role in the pathophysiology of carpal tunnel syndrome. Carpal tunnel pressure was measured in 14 healthy individuals while they performed tasks using three different computer mice. Participants performed a multidirectional dragging (‘drag and drop’) task starting with the hand resting (static posture) on the mouse. With one mouse, an additional pointing (‘point-and-click’) task was performed. All mice were associated with similar wrist extension postures (p= 0.41) and carpal tunnel pressures (p= 0.48). Pressures were significantly greater during dragging and pointing tasks than when resting the hand (static posture) on the mouse (p= 0.003). The mean pressures during the dragging tasks were 28.8- 33.1 mmHg, ～ 12 mmHg greater than the static postures. Pressures during the dragging task were higher than the pointing task (33.1 versus 28.0 mmHg), although the difference was borderline non-significant (p= 0.06). In many participants the carpal tunnel pressures measured during mouse use were greater than pressures known to alter nerve function and structure, indicating that jobs with long periods of intensive mouse use may be at an increased risk of median mononeuropathy. A recommendation is made to minimize wrist extension, minimize prolonged dragging tasks and frequently perform other tasks with the mousing hand.     

Effects of computer mouse design and task on carpal tunnel pressure

Computer mouse use has become an integral part of office work in the past decade. Intensive mouse use has been associated with increased risk of upper extremity musculoskeletal disorders, including carpal tunnel syndrome. Sustained, elevated fluid pressure in the carpal tunnel may play a role in the pathophysiology of carpal tunnel syndrome. Carpal tunnel pressure was measured in 14 healthy individuals while they performed tasks using three different computer mice. Participants performed a multidirectional dragging ('drag and drop') task starting with the hand resting (static posture) on the mouse. With one mouse, an additional pointing ('point-and-click') task was performed. All mice were associated with similar wrist extension postures (p = 0.41) and carpal tunnel pressures (p = 0.48). Pressures were significantly greater during dragging and pointing tasks than when resting the hand (static posture) on the mouse (p = 0.003). The mean pressures during the dragging tasks were 28.8-33.1 mmHg, approximately 12 mmHg greater than the static postures. Pressures during the dragging task were higher than the pointing task (33.1 versus 28.0 mmHg), although the difference was borderline non-significant (p = 0.06). In many participants the carpal tunnel pressures measured during mouse use were greater than pressures known to alter nerve function and structure, indicating that jobs with long periods of intensive mouse use may be at an increased risk of median mononeuropathy. A recommendation is made to minimize wrist extension, minimize prolonged dragging tasks and frequently perform other tasks with the mousing hand.     

The Strain Index (SI) and Threshold Limit Value (TLV) for Hand Activity Level (HAL): risk of carpal tunnel syndrome (CTS) in a prospective cohort

A cohort of 536 workers was enrolled from 10 diverse manufacturing facilities and was followed monthly for six years. Job physical exposures were individually measured. Worker demographics, medical history, psychosocial factors, current musculoskeletal disorders (MSDs) and nerve conduction studies (NCS) were obtained. Point and lifetime prevalence of carpal tunnel syndrome (CTS) at baseline (symptoms + abnormal NCS) were 10.3% and 19.8%. During follow-up, there were 35 new CTS cases (left, right or both hands). Factors predicting development of CTS included: job physical exposure (American conference of governmental industrial hygienists Threshold Limit Value (ACGIH TLV) for Hand Activity Level (HAL) and the Strain Index (SI)), age, BMI, other MSDs, inflammatory arthritis, gardening outside of work and feelings of depression. In the adjusted models, the TLV for HAL and the SI were both significant per unit increase in exposure with hazard ratios (HR) increasing up to a maximum of 5.4 (p = 0.05) and 5.3 (p = 0.03), respectively; however, similar to other reports, both suggested lower risk at higher exposures. Data suggest that the TLV for HAL and the SI are useful metrics for estimating exposure to biomechanical stressors. PRACTITIONER SUMMARY: This study was conducted to determine how well the TLV for HAL and the SI predict risk of CTS using a prospective cohort design with survival analysis. Both the TLV for HAL and the SI were found to predict risk of CTS when adjusted for relevant covariates.     

Consumer credit risk: Individual probability estimates using machine learning

Consumer credit scoring is often considered a classification task where clients receive either a good or a bad credit status. Default probabilities provide more detailed information about the creditworthiness of consumers, and they are usually estimated by logistic regression. Here, we present a general framework for estimating individual consumer credit risks by use of machine learning methods. Since a probability is an expected value, all nonparametric regression approaches which are consistent for the mean are consistent for the probability estimation problem. Among others, random forests (RF), k-nearest neighbors (kNN), and bagged k-nearest neighbors (bNN) belong to this class of consistent nonparametric regression approaches. We apply the machine learning methods and an optimized logistic regression to a large dataset of complete payment histories of short-termed installment credits. We demonstrate probability estimation in Random Jungle, an RF package written in C++ with a generalized framework for fast tree growing, probability estimation, and classification. We also describe an algorithm for tuning the terminal node size for probability estimation. We demonstrate that regression RF outperforms the optimized logistic regression model, kNN, and bNN on the test data of the short-term installment credits.     

Application of two non-linear prediction tools to the estimation of tunnel boring machine performance

Predicting tunnel boring machine (TBM) performance is a crucial issue for the accomplishment of a mechanical tunnel project, excavating via full face tunneling machine. Many models and equations have previously been introduced to estimate TBM performance based on properties of both rock and machine employing various statistical analysis techniques. However, considering the nature of the problem, it is relatively difficult to estimate tunnel boring machine performance by linear prediction models. Artificial neural networks (ANNs) and non-linear multiple regression models have great potential for establishing such prediction models. The purpose of the present study is the construction of non-linear multivariable prediction models to estimate TBM performance as a function of rock properties. For this purpose, rock properties and machine data were collected from recently completed TBM tunnel project in the City of New York, USA and consequently the database was established to develop performance prediction models utilizing the ANN and the non-linear multiple regression methods. This paper presents the results of study into the application of the non-linear prediction approaches providing the acceptable precise performance estimations.