Exploratory analysis using machine learning algorithms to predict pinch strength by anthropometric and socio-demographic features.

Objectives. This study examines the role of different machine learning (ML) algorithms to determine which socio-demographic factors and hand-forearm anthropometric dimensions can be used to accurately predict hand function. Methods. The cross-sectional study was conducted with 7119 healthy Iranian participants (3525 males and 3594 females) aged 10-89 years. Seventeen hand-forearm anthropometric dimensions were measured by JEGS digital caliper and a measuring tape. Tip-to-tip, key and three-jaw chuck pinches were measured using a calibrated pinch gauge. Subsequently, 21 features pertinent to socio-demographic factors and hand-forearm anthropometric dimensions were used for classification. Furthermore, 12 well-known classifiers were implemented and evaluated to predict pinches. Results. Among the 21 features considered in this study, hand length, stature, age, thumb length and index finger length were found to be the most relevant and effective components for each of the three pinch predictions. The k-nearest neighbor, adaptive boosting (AdaBoost) and random forest classifiers achieved the highest classification accuracy of 96.75, 86.49 and 84.66% to predict three pinches, respectively. Conclusions. Predicting pinch strength and determining the predictive hand-forearm anthropometric and socio-demographic characteristics using ML may pave the way to designing an enhanced tool handle and reduce common musculoskeletal disorders of the hand.

Stress influence on real-world driving identified by monitoring heart rate variability and morphologic variability of electrocardiogram signals: the case of intercity roads.

Objectives. This study examines which of the heart rate variability (HRV) and morphologic variability (MV) metrics may have the highest accuracy in different stress detection during real-world driving. Methods. The cross-sectional study was carried out among 93 intercity mini-bus male drivers aged 22-67 years. The Trillium 5000 Holter Recorder and GARMIN Virb Elite camera were used to determine heart rate and vehicle speed measurements along the path, respectively. We considered the HRV and MV metrics of electrocardiogram (ECG) signals including the mean RR interval (mRR), mean heart rate (mHR), normalized low-frequency spectrum (nLF), normalized high-frequency spectrum (nHF), normalized very low-frequency spectrum (nVLF), difference of normalized low-frequency spectrum and normalized high-frequency spectrum (dLFHF), and sympathovagal balance index (SVI). Results. The analysis showed that the HRV metrics mHR, mRR, nVLF, nLF, nHF, dLFHF and SVI are effective in mental stress detection while driving as compared to rest time. We obtained a high accuracy of stress detection for MV metrics as compared to the traditional HRV analysis, of approximately 92%. Conclusions. Our findings indicate that driver stress could be detected with an accuracy of 92% using MV metrics as an accurate physiological index of the driver's state.

A comparative investigation of machine learning algorithms for predicting safety signs comprehension based on socio-demographic factors and cognitive sign features.

This study examines whether the socio-demographic factors and cognitive sign features can be used for envisaging safety signs comprehensibility using predictive machine learning (ML) techniques. This study will determine the role of different machine learning components such as feature selection and classification to determine suitable factors for safety construction signs comprehensibility. A total of 2310 participants were requested to guess the meaning of 20 construction safety signs (four items for each of the mandatory, prohibition, emergency, warning, and firefighting signs) using the open-ended method. Moreover, the participants were asked to rate the cognitive design features of each sign in terms of familiarity, concreteness, simplicity, meaningfulness, and semantic closeness on a 0-100 rating scale. Subsequently, all eight features (age, experience, education level, familiarity, concreteness, meaningfulness, semantic closeness, and simplicity) were used for classification. Furthermore, the 14 most popular supervised classifiers were implemented and evaluated for safety sign comprehensibility prediction using these eight features. Also, filter and wrapper methods were used as feature selection techniques. Results of feature selection techniques indicate that among the eight features considered in this study, familiarity, simplicity, and meaningfulness are found to be the most relevant and effective components in predicting the comprehensibility of selected safety signs. Further, when these three features are used for classification, the K-NN classifier achieves the highest classification accuracy of 94.369% followed by medium Gaussian SVM which achieves a classification accuracy of 76.075% under hold-out data division protocol. The machine learning (ML) technique was adopted as a promising approach to addressing the issue of comprehensibility, especially in terms of determining factors affecting the safety signs' comprehension. The cognitive sign features of familiarity, simplicity, and meaningfulness can provide useful information in terms of designing user-friendly safety signs.

An integrated DEMATEL-ANP approach for identification and prioritization of factors affecting fall from height accidents in the construction industry.

Objectives. The decision-making trial and evaluation laboratory (DEMATEL) technique integrated with the analytic network process (ANP) is used for determination and prioritization of cause-effect relationships among factors affecting construction falls. Methods. Considering the 135 fall accidents collected between 2013 and 2018 from 15 residential construction projects, 70 factors and sub-factors affecting the occurrence of construction falls were determined based on safety experts' opinions. Questionnaires based on the former and the latter were then distributed among 10 occupational health and safety specialists to determine the effectiveness of the factors. The interactions and important degree of each factor are specified, using the DEMATEL-ANP approach. Results. Findings showed that organizational factors and their sub-factors have the greatest impact on construction falls and were considered as causal variables (D - R > 0), while individual and environmental factors were considered as the effect variables (D - R < 0). The results of prioritization using the ANP method showed that the work platform altitude, psychological/occupational stresses and interactions were ranked as the first through third priorities affecting the falls, respectively. Conclusions. It is necessary to implement a systematic strategy to reduce the unsafe conditions in construction projects and to pay more attention to organizational factors.

The Validity and Inter-Rater Reliability of a Video-Based Posture-Matching Tool to Estimate Cumulative Loads on the Lower Back.

Background: Low back pain (LBP) is known as one of the most common work-related musculoskeletal disorders. Spinal cumulative loads (CLs) during manual material handling (MMH) tasks are the main risk factors for LBP. However, there is no valid and reliable quantitative lifting analysis tool available for quantifying CLs among Iranian workers performing MMH tasks. Objective: This study aimed to investigate the validity and inter-rater reliability of a posture-matching load assessment tool (PLAT) for estimating the L5-S1 static cumulative compression (CC) and shear (CS) loads based on predictive regression equations. Material and Methods: This experimental study was conducted among six participants performing four lifting tasks, each comprised of five trials during which their posture was recorded via a motion capture (Vicon) and simultaneously a three-camera system located at three different angles (0°, 45°, and 90°) to the sagittal plane. Results: There were no significant differences between the two CLs estimated by PLAT from the three-camera system and the gold-standard Vicon. In addition, ten raters estimated CLs of the tasks using PLAT in three sessions. The calculated intra-class correlation coefficients for the estimated CLs within each task revealed excellent inter-rater reliability (> 0.75), except for CS in the first and third tasks, which were good (0.6 to 0.75). Conclusion: The proposed posture-matching approach provides a valid and reliable ergonomic assessment tool suitable for assessing spinal CLs during various lifting activities.

Normative data for handgrip strength in Iranian healthy children and adolescents aged 7-18 years: comparison with international norms.

BACKGROUND: Grip strength is an essential component of physical fitness. The objective of this study was to develop normative handgrip strength data for Iranian healthy boys and girls comparing their handgrip strength with international reference values. METHODS: Handgrip strength was measured in 2637 healthy children/adolescents (1391 boys and 1246 girls), aged 7-18 years, using a standard adjustable Jamar hand dynamometer (Model 5030 J1, Sammons Preston Rolyan, Bolingbrook, IL, USA). Body mass (kg) and stature (cm) were measured and body mass index was computed in kg/m2. The sample was stratified by gender, age, and hand preference. RESULTS: Handgrip strength increased with age and was considerably higher in boys than in girls for all age groups (p < 0.001). Grip strength had a parallel and linear growth for both genders until the age of about 11 years and showed a steeper upward slope in boys than in girls thereafter. The findings of the current investigation were significantly different from those of the previously published normative data, especially for boys over the age of 12 years and girls in the age range of 7-18 years (p < 0.001). This difference was mainly in such a way that the Iranians had lower handgrip strength. CONCLUSIONS: The differences between present results and those of similar available in the literature in this field emphasize the significant role of using normative data specific to a particular population in research or clinical settings.

Foot trajectories and loading rates in a transfemoral amputee for six different commercial prosthetic knees: An indication of adaptability.

BACKGROUND: The relationship between the functional loading rate and heel velocities was assessed in an active unilateral transfemoral amputee (UTFA) for adaptation to six different commercial prosthetic knees. OBJECTIVE: To Investigate the short-term process of adaptability for UTFA for two types of prosthetic knees were evaluated, based on the correlation between heel vertical velocity and transient loading rate. METHODS: The loading rate was calculated from the slope of ground reaction forces (GRF) and the corresponding time. The heel velocities and GRF were obtained by a motion analysis system. RESULTS: Biomechanical adaptation was evident following a short period of prosthetic knee use based upon the mean transient impact (loading rate) and the heel vertical velocity in slow, normal and fast walking. Trend lines of transient impact versus vertical heel velocity for a set of actively controlled variable damping (microprocessor) and mechanically passive prosthetic knees were all negatively correlated, except for an amputated leg during normal pace and healthy leg during fast pace. For an amputee to adapt well to a prescribed prosthesis excellent coordination between the intact and amputated limbs is required to control placement of the amputated leg to achieve a gait comparable to healthy subjects. CONCLUSION: There are many factors such as the hip, knee flexion/extension and the ankle plantarflexion/dorsiflexion contributing to the control of the transient impact of an amputee during walking. Therefore, for enhanced control of a prosthetic knee, a multifaceted approach is required. This study showed that UTFA adaption to different prosthetic knees in the short term with slower than self-selected speed is completely achievable based on the negative correlation of ground reaction forces versus linear velocity. Reduced speed may provide the prosthetists with the vision of the amputees' progression of adaptation with a newly prescribed prosthetic knee.

Virtual prototyping of a semi-active transfemoral prosthetic leg.

This article presents a virtual prototyping study of a semi-active lower limb prosthesis to improve the functionality of an amputee during prosthesis-environment interaction for level ground walking. Articulated ankle-foot prosthesis and a single-axis semi-active prosthetic knee with active and passive operating modes were considered. Data for level ground walking were collected using a photogrammetric method in order to develop a base-line simulation model and with the hip kinematics input to verify the proposed design. The simulated results show that the semi-active lower limb prosthesis is able to move efficiently in passive mode, and the activation time of the knee actuator can be reduced by approximately 50%. Therefore, this semi-active system has the potential to reduce the energy consumption of the actuators required during level ground walking and requires less compensation from the amputee due to lower deviation of the vertical excursion of body centre of mass.

Quantifying the centre of rotation pattern in a multi-body model of the lumbar spine.

Understanding the kinematics of the spine provides paramount knowledge for many aspects of the clinical analysis of back pain. More specifically, visualisation of the instantaneous centre of rotation (ICR) enables clinicians to quantify joint laxity in the segments, avoiding a dependence on more inconclusive measurements based on the range of motion and excessive translations, which vary in every individual. Alternatively, it provides motion preserving designers with an insight into where a physiological ICR of a motion preserving prosthesis can be situated in order to restore proper load distribution across the passive and active elements of the lumbar region. Prior to the use of an unconstrained dynamic musculoskeletal model system, based on multi-body models capable of transient analysis, to estimate segmental loads, the model must be kinematically evaluated for all possible sensitivity due to ligament properties and the initial locus of intervertebral disc (IVD). A previously calibrated osseoligamentous model of lumbar spine was used to evaluate the changes in ICR under variation of the ligament stiffness and initial locus of IVD, when subjected to pure moments from 0 to 15 Nm. The ICR was quantified based on the closed solution of unit quaternion that improves accuracy and prevents coordinate singularities, which is often observed in Euler-based methods and least squares principles. The calculation of the ICR during flexion/extension revealed complexity and intrinsic nonlinearity between flexion and extension. This study revealed that, to accommodate a good agreement between in vitro data and the multi-body model predictions, in flexion more laxity is required than in extension. The results showed that the ICR location is concentrated in the posterior region of the disc, in agreement with previous experimental studies. However, the current multi-body model demonstrates a sensitivity to the initial definition of the ICR, which should be recognised as a limitation of the method. Nevertheless, the current simulations suggest that, due to the constantly evolving path of the ICR across the IVD during flexion-extension, a movable ICR is a necessary condition in multi-body modelling of the spine, in the context of whole body simulation, to accurately capture segmental kinematics and kinetics.

A multibody modelling approach to determine load sharing between passive elements of the lumbar spine.

The human spinal segment is an inherently complex structure, a combination of flexible and semi-rigid articulating elements stabilised by seven principal ligaments. An understanding of how mechanical loading is shared among these passive elements of the segment is required to estimate tissue failure stresses. A 3D rigid body model of the complete lumbar spine has been developed to facilitate the prediction of load sharing across the passive elements. In contrast to previous multibody models, this model includes a non-linear, six degrees of freedom intervertebral disc, facet bony articulations and all spinal ligaments. Predictions of segmental kinematics and facet joint forces, in response to pure moment loading (flexion-extension), were compared to published in vitro data. On inclusion of detailed representation of the disc and facets, the multibody model fully captures the non-linear flexibility response of the spinal segment, i.e. coupled motions and a mobile instantaneous centre of rotation. Predicted facet joint forces corresponded well with reported values. For the loading case considered, the model predicted that the ligaments are the main stabilising elements within the physiological motion range; however, the disc resists a greater proportion of the applied load as the spine is fully flexed. In extension, the facets and capsular ligaments provide the principal resistance. Overall patterns of load distribution to the spinal ligaments are in agreement with previous predictions; however, the current model highlights the important role of the intraspinous ligament in flexion and the potentially high risk of failure. Several important refinements to the multibody modelling of the passive elements of the spine have been described, and such an enhanced passive model can be easily integrated into a full musculoskeletal model for the prediction of spinal loading for a variety of daily activities.