Towards ergonomics working - machine learning algorithms and musculoskeletal modeling

Ergonomic workplaces lead to fewer work-related musculoskeletal disorders and thus fewer sick days. There are various guidelines to help avoid harmful situations. However, these recommendations are often rather crude and often neglect the complex interaction of biomechanical loading and psychological stress. This study investigates whether machine learning algorithms can be used to predict mechanical and stress-related muscle activity for a standardized motion. For this purpose, experimental data were collected for trunk movement with and without additional psychological stress. Two different algorithms (XGBoost and TensorFlow) were used to model the experimental data. XGBoost in particular predicted the results very well. By combining it with musculoskeletal models, the method shown here can be used for workplace analysis but also for the development of real-time feedback systems in real workplace environments.

Influence of Lumbar Lordosis on Posterior Rod Strain in Long-Segment Construct During Biomechanical Loading: A Cadaveric Study

Objective: The lordotic shape of the lumbar spine differs substantially between individuals. Measuring and recording strain during spinal biomechanical tests is an effective method to infer stresses on spinal implants and predict failure mechanisms. The geometry of the spine may have a significant effect on the resultant force distribution, thereby directly affecting rod strain.Methods: Seven fresh-frozen cadaveric specimens (T12-sacrum) underwent standard (7.5 Nm) nondestructive sagittal plane tests: flexion and extension. The conditions tested were intact and pedicle screws and rods (PSR) at L1-sacrum. The posterior right rod was instrumented with strain gauges between L3–4 (index level) and the L5–S1 pedicle screw. All specimens underwent lateral radiographs before testing. Lordotic angles encompassing different levels (L5–S1, L4–S1, L3–S1, L2–S1, and L1–S1) were measured and compared with rod strain. Data were analyzed using Pearson correlation analyses.Results: Strong positive correlations were observed between lordosis and posterior rod strain across different conditions. The L3–S1 lordotic angle in the unloaded intact condition correlated with peak rod strain at L3–4 with PSR during flexion (R = 0.76, p = 0.04). The same angle in the unloaded PSR condition correlated with peak strain in the PSR condition during extension (R = -0.79, p = 0.04). The unloaded intact L2–S1 lordotic angle was significantly correlated with rod strain at L3–4 in the PSR condition during flexion (R = 0.85, p = 0.02) and extension (R = -0.85, p = 0.02) and with rod strain at L5–S1 in the PSR condition during flexion (R = 0.84, p = 0.04).Conclusion: Lordosis measured on intact and instrumented conditions has strong positive correlations with posterior rod strain in cadaveric testing.

Inter-individual variability in a repetitive lifting task

Trunk kinematics directly impact the biomechanical loading of the tissues of the low back. Quantifying the variability in trunk kinematics may provide deeper insights into biomechanical loading and low back injury risk. Inter-lifter variability in trunk kinematics was assessed as twenty participants performed a repetitive lifting task at three levels of the NIOSH Lifting Index. Trunk kinematics were captured and Levene’s test of homogeneity of variance was used to test the hypothesis that variance in kinematic parameters increased as a function of level of lifting index. Results showed considerable levels of variability in all kinematics parameters, and for sagittal range of motion, mean sagittal velocity, transverse range of motion, and mean transverse velocity the variance was significantly affected (p<0.05) by level of lifting index. The results of this study demonstrate that variability (both inter- and intra-lifter) should be considered as one considers the relative risk of a lifting task.

Relationship between the kinematics of wrist/finger joint movements and muscle loading during typing in people with different skill levels

Background Musculoskeletal disorders caused by computer use are associated with socio-economic problems. Reducing the biomechanical loading caused by hand movements could reduce the occurrence of such disorders. However, most participants recruited for past experimental studies had a certain level of typing skill, and differences in the biomechanical loading of those with different typing skills have not been examined. This study aimed to quantify the relationship between the movements of the wrist and finger joints and the loading on the forearm muscles and to clarify the differences between typists of different skill levels. Methods A 3D motion capture system measured wrist and index finger joint movements, and surface electromyography measured muscle activities for the right hand during a typing task. We compared wrist and finger joint movements and forearm muscle loading during typing, keystroke time, and key release time between skilled and unskilled typists. Findings Skilled typists move their wrists and fingers faster with less muscle activity during typing, the active tension of their finger flexor muscles during keystrokes are high, and they have higher mechanical stresses on the finger flexor tendons during keystrokes. Unskilled typists develop strategies to prevent excessive stiffness in their wrist joints when making keystrokes. They are expected to have a higher cumulative loading on the extensor muscles of the wrist during key release. Interpretation Biomechanical loading in typing skill is different, which may make it possible to predict disability. This could provide information on the changes in physical parameters and environments to prevent disability.

Does Delivery Length Impact Measures of Whole-Body Biomechanical Load During Pace Bowling?

Purpose: To investigate whether changes in delivery length (ie, short, good, and full) lead to alterations in whole-body biomechanical loading as determined by ground reaction force during front-foot contact of the delivery stride for pace bowlers. Current load-monitoring practices of pace bowling in cricket assume equivocal biomechanical loading as only the total number of deliveries are monitored irrespective of delivery length. Methods: A total of 16 male pace bowlers completed a 2-over spell at maximum intensity while targeting different delivery lengths (short, 7–10 m; good, 4–7 m; and full, 0–4 m from the batter’s stumps). In-ground force plates were used to determine discrete (vertical and braking force, impulse, and loading rates) and continuous front-foot contact ground reaction force. Repeated-measures analysis of variance (P < .05), effects size, and statistical parametrical mapping were used to determine differences between delivery lengths. Results: There were no significant differences between short, good, and full delivery lengths for the discrete and continuous kinetic variables investigated (P = .19–1.00), with trivial to small effect sizes. Conclusion: There were minimal differences in front-foot contact biomechanics for deliveries of different lengths (ie, short, good, and full). These data reinforce current pace bowling load-monitoring practices (ie, counting the number of deliveries), as changes in delivery length do not affect the whole-body biomechanical loading experienced by pace bowlers. This is of practical importance as it retains simplicity in load-monitoring practice that is used widely across different competition levels and ages.

Validating the Paradigm That Biomechanical Forces Regulate Embryonic Cardiovascular Morphogenesis and Are Fundamental in the Etiology of Congenital Heart Disease

The goal of this review is to provide a broad overview of the biomechanical maturation and regulation of vertebrate cardiovascular (CV) morphogenesis and the evidence for mechanistic relationships between function and form relevant to the origins of congenital heart disease (CHD). The embryonic heart has been investigated for over a century, initially focusing on the chick embryo due to the opportunity to isolate and investigate myocardial electromechanical maturation, the ability to directly instrument and measure normal cardiac function, intervene to alter ventricular loading conditions, and then investigate changes in functional and structural maturation to deduce mechanism. The paradigm of “Develop and validate quantitative techniques, describe normal, perturb the system, describe abnormal, then deduce mechanisms” was taught to many young investigators by Dr. Edward B. Clark and then validated by a rapidly expanding number of teams dedicated to investigate CV morphogenesis, structure–function relationships, and pathogenic mechanisms of CHD. Pioneering studies using the chick embryo model rapidly expanded into a broad range of model systems, particularly the mouse and zebrafish, to investigate the interdependent genetic and biomechanical regulation of CV morphogenesis. Several central morphogenic themes have emerged. First, CV morphogenesis is inherently dependent upon the biomechanical forces that influence cell and tissue growth and remodeling. Second, embryonic CV systems dynamically adapt to changes in biomechanical loading conditions similar to mature systems. Third, biomechanical loading conditions dynamically impact and are regulated by genetic morphogenic systems. Fourth, advanced imaging techniques coupled with computational modeling provide novel insights to validate regulatory mechanisms. Finally, insights regarding the genetic and biomechanical regulation of CV morphogenesis and adaptation are relevant to current regenerative strategies for patients with CHD.

Influence of basketball shoe midsole inserts featuring different mechanical rebound properties on biomechanical loading and subjective perception during a side-cutting maneuver

This study examined the influence of basketball shoe midsole inserts with different forefoot and rearfoot rebound properties on biomechanical loading and subjective perception during a side-cutting maneuver. Eleven male basketball players executed side cutting in four shoe conditions mechanically characterized for their rearfoot/forefoot rebound: compliant/compliant, springy/springy, compliant/springy, and springy/compliant. Lower extremity kinetics and kinematics (normalized to body mass), as well as subjective perception, were measured. During the weight-acceptance phase, there were no differences between shoes in all biomechanical variables, except a slightly greater ankle range of motion (1.2° greater than the other three shoes) in the frontal plane for shoe compliant/springy. During the push-off phase, shoe springy/springy led to a greater ankle plantarflexion moment (1.21 Nm/kg greater than the other three shoes, p < 0.001) and knee internal rotation moment (0.09 Nm/kg greater than the other three shoes, p = 0.012), while shoe compliant/springy resulted in a greater ankle range of motion in the frontal plane (1.4° greater than the other three shoes, p < 0.001). Perception data showed no statistically significant difference among any shoes. In conclusion, springy inserts of basketball shoe midsoles induced a biomechanical loading effect. Perception of players being unaffected indicates the importance of biomechanical evaluation to examine the effects of the given shoe modifications during side cutting.