Effect of squat depth and barbell load on relative muscular effort in squatting

ABSTRACT: Bryanton, MA, Kennedy, MD, Carey, JP, and Chiu, LZF. Effect of squat depth and barbell load on relative muscular effort in squatting. J Strength Cond Res 26(10): 2820-2828, 2012-Resistance training is used to develop muscular strength and hypertrophy. Large muscle forces, in relation to the muscle's maximum force-generating ability, are required to elicit these adaptations. Previous biomechanical analyses of multi-joint resistance exercises provide estimates of muscle force but not relative muscular effort (RME). The purpose of this investigation was to determine the RME during the squat exercise. Specifically, the effects of barbell load and squat depth on hip extensor, knee extensor, and ankle plantar flexor RME were examined. Ten strength-trained women performed squats (50-90% 1 repetition maximum) in a motion analysis laboratory to determine hip extensor, knee extensor, and ankle plantar flexor net joint moment (NJM). Maximum isometric strength in relation to joint angle for these muscle groups was also determined. Relative muscular effect was determined as the ratio of NJM to maximum voluntary torque matched for joint angle. Barbell load and squat depth had significant interaction effects on hip extensor, knee extensor, and ankle plantar flexor RME (p < 0.05). Knee extensor RME increased with greater squat depth but not barbell load, whereas the opposite was found for the ankle plantar flexors. Both greater squat depth and barbell load increased hip extensor RME. These data suggest that training for the knee extensors can be performed with low relative intensities but require a deep squat depth. Heavier barbell loads are required to train the hip extensors and ankle plantar flexors. In designing resistance training programs with multi-joint exercises, how external factors influence RME of different muscle groups should be considered to meet training objectives.     

Lower extremity biomechanics during a regular and counterbalanced squat

If the efficiency of human movement patterns could be improved using exercise, this could lead to more effective musculoskeletal disease-injury prevention and rehabilitation programs. It has been suggested that an efficient squat movement pattern emphasizes the use of the large hip extensors instead of the smaller knee extensors. The purpose of this study was to determine whether a counterbalanced squat (CBS) could produce a more hip-dominant and less knee-dominant squat movement pattern as compared with a regular squat (RS). There were 31 recreationally trained college-aged participants (15 male, 16 female) who performed 10 squats (5 CBS and 5 RS), while segment kinematics, ground reaction forces, and muscle (gluteus maximus [GM], quadriceps, hamstrings) electromyographic (EMG) activations were recorded. Peak sagittal plane net joint moments and joint ranges of motion at the hip, knee, and ankle joints along with peak and integrated EMG activation levels for all 3 muscles were compared using analysis of variance (squat type × sex). The results revealed that the CBS increased the hip joint moment and GM activation, while it decreased the knee joint moment and quadriceps activation as compared with the RS. Therefore, the CBS produces a more hip-dominant and less knee-dominant squat movement pattern and could be used in exercise programs aimed at producing more hip-dominant movement patterns.     

The validity of summing lower extremity individual joint kinetic measures

In the analysis of human movement, researchers often sum individual joint kinetics to obtain a single measure of lower extremity function. The extent to which these summed measures relate to the mechanical objectives of the task has not been formally validated. The criterion validity of these measures was established with comparisons to the mechanical objective of two multiple-joint tasks. For the Work task 18 participants performed a loaded barbell squat using 4 resistances while instrumented for biomechanical analysis. For the Power they performed 2 predetermined amounts of work at both self-selected and fast speeds. Using inverse dynamics techniques, the peak net joint moment (PM) was calculated bilaterally in the sagittal plane at the ankle, knee, and hip and was summed into a single measure. This measure was correlated with the task objectives using simple linear regression. Similar procedures were used for the average net joint moment (AM), peak (PP), and average (AP) net joint moment power, and the net joint moment impulse (IM) and work (IP). For the Work task all 6 measures were significantly correlated with the task objective, but only AM, PM, and IP had correlation coefficients above 0.90. For the Power task, IM was not significantly correlated with the task objective, and only AP had a correlation coefficient above 0.90. These findings indicate that the validity of summing individual kinetic measures depends on both the measure chosen and the mechanical objective of the task.     

The influence of knee alignment on lower extremity kinetics during squats

The squat is an assessment of lower extremity alignment during movement, however there is little information regarding altered joint kinetics during poorly performed squats. The purpose of this study was to examine changes in joint kinetics and power from altered knee alignment during a squat. Thirty participants completed squats while displacing the knee medially, anteriorly, and with neutral alignment (control). Sagittal and frontal plane torques at the ankle, knee, and hip were altered in the descending and ascending phase of the squat in both the medial and anterior malaligned squat compared to the control squat. Ankle and trunk power increased and hip power decreased in the medial malaligned squat compared to the control squat. Ankle, knee, and trunk power increased and hip power decreased in the anterior malaligned squat compared to the control squat. Changes in joint torques and power during malaligned squats suggest that altered knee alignment increases ankle and trunk involvement to execute the movement. Increased anterior knee excursion during squatting may also lead to persistent altered loading of the ankle and knee. Sports medicine professionals using the squat for quadriceps strengthening must consider knee alignment to reduce ankle and trunk involvement during the movement.     

Bilateral differences in the net joint torques during the squat exercise

Bilateral movements are common in human movement, both as exercises and as daily activities. Because the movement patterns are similar, it is often assumed that there are no bilateral differences (BDs; differences between the left and right sides) in the joint torques that are producing these movements. The aim of this investigation was to test the assumption that the joint torques are equal between the left and right lower extremities by quantifying BDs during the barbell squat. Eighteen recreationally trained men (n = 9) and women (n = 9) completed 3 sets of 3 repetitions of the squat exercise, under 4 loading conditions: 25, 50, 75, and 100% of their 3 repetition maximum, while instrumented for biomechanical analysis. The average net joint moment (ANJM) and maximum flexion angle (MFA) for the hip, knee, and ankle as well as the average vertical ground reaction force (AVGRF) and the average distance from the ankle joint center to the center of pressure (ADCOP) were calculated. Group mean and individual data were analyzed (alpha = 0.05). At each joint, there was a significant main effect for side and load, no main effect for gender, with few significant interactions. The hip ANJM was 12.4% larger on the left side, the knee ANJM was 13.2% larger on the right side, and the ankle ANJM was 16.8% larger on the left side. Differences in MFAs between sides were less than 2 degrees for all 3 joints (all p > 0.20 except for the knee at 75% [p = 0.024] and 100% [p = 0.025]), but the AVGRF and the ADCOP were 6% and 11% larger on the left side. Few subjects exhibited the pattern identified with the group mean data, and no subject exhibited nonsignificant BDs for all 3 joints. These findings suggest that joint torques should not be assumed to be equal during the squat and that few individual subjects follow the pattern exhibited by group mean data.     

Modeling the stance leg in two-dimensional analyses of sprinting: inclusion of the MTP joint affects joint kinetics

Two-dimensional analyses of sprint kinetics are commonly undertaken but often ignore the metatarsalphalangeal (MTP) joint and model the foot as a single segment. Due to the linked-segment nature of inverse dynamics analyses, the aim of this study was to investigate the effect of ignoring the MTP joint on the calculated joint kinetics at the other stance leg joints during sprinting. High-speed video and force platform data were collected from four to five trials for each of three international athletes. Resultant joint moments, powers, and net work at the stance leg joints during the first stance phase after block clearance were calculated using three different foot models. By ignoring the MTP joint, peak extensor moments at the ankle, knee, and hip were on average 35% higher (p < .05 for each athlete), 40% lower (p < .05), and 9% higher (p > .05), respectively, than those calculated with the MTP joint included. Peak ankle and knee joint powers and net work at all joints were also significantly (p < .05) different. By ignoring a genuine MTP joint plantar flexor moment, artificially high peak ankle joint moments are calculated, and these also affect the calculated joint kinetics at the knee.     

Fatigue effects on the coordinative pattern during cycling: Kinetics and kinematics evaluation

The aim of the present study was to analyze the net joint moment distribution, joint forces and kinematics during cycling to exhaustion. Right pedal forces and lower limb kinematics of ten cyclists were measured throughout a fatigue cycling test at 100% of PO_MAX. The absolute net joint moments, resultant force and kinematics were calculated for the hip, knee and ankle joint through inverse dynamics. The contribution of each joint to the total net joint moments was computed. Decreased pedaling cadence was observed followed by a decreased ankle moment contribution to the total joint moments in the end of the test. The total absolute joint moment, and the hip and knee moments has also increased with fatigue. Resultant force was increased, while kinematics has changed in the end of the test for hip, knee and ankle joints. Reduced ankle contribution to the total absolute joint moment combined with higher ankle force and changes in kinematics has indicated a different mechanical function for this joint. Kinetics and kinematics changes observed at hip and knee joint was expected due to their function as power sources. Kinematics changes would be explained as an attempt to overcome decreased contractile properties of muscles during fatigue.     

Influence of figure skating skates on vertical jumping performance

The purpose of this study was to investigate the influence of wearing figure skating skates on vertical jump performance and interjoint co-ordinations described in terms of sequencing and timing of joint rotations. Ten national to international figure skaters were filmed while performing a squat jump (SJ) on a force platform. Three experimental conditions were successively realized: barefoot (BF), lifting a 1.5 kg weight (LW) corresponding to the skates' mass, attached on the distal extremity of each leg and wearing skates (SK). Jump height, angular kinematics as well as joints kinetics were calculated. Relative to the SJ height reached in the BF condition, SJ performance was significantly decreased by 2.1 and 5.5 cm in the LW and SK conditions, respectively. The restriction of ankle amplitude imposed by wearing skates was found to significantly limit the knee joint amplitude while the hip angular motion was not affected. Neither the skates' mass nor the limited ankle angular motion modified the proximo-distal organization of joint co-ordination observed when jumping barefoot. However, with plantar flexion restriction, the delay between hip and knee extensions increased while it was reduced between knee and ankle extensions. Work output at the knee and ankle joints were significantly lowered when wearing skates. The decrease of work at the knee was shown to result from an early flexing moment causing a premature deceleration of the knee and from a reduction of knee amplitude. Taken together, these results show a minimization of the participation of the knee when plantar flexion is limited. It was proposed that constraining the distal joint causes a reorganization of interjoint co-ordinations and a redistribution of the energy produced by knee extensors to the hip and ankle joints.     

Lower-limb joint work and power are modulated during load carriage based on load configuration and walking speed

Soldiers regularly transport loads weighing >20 kg at slow speeds for long durations. These tasks elicit high energetic costs through increased positive work generated by knee and ankle muscles, which may increase risk of muscular fatigue and decrease combat readiness. This study aimed to determine how modifying where load is borne changes lower-limb joint mechanical work production, and if load magnitude and/or walking speed also affect work production. Twenty Australian soldiers participated, donning a total of 12 body armor variations: six different body armor systems (one standard-issue, two commercially available [cARM1-2], and three prototypes [pARM1-3]), each worn with two different load magnitudes (15 and 30 kg). For each armor variation, participants completed treadmill walking at two speeds (1.51 and 1.83 m/s). Three-dimensional motion capture and force plate data were acquired and used to estimate joint angles and moments from inverse kinematics and dynamics, respectively. Subsequently, hip, knee, and ankle joint work and power were computed and compared between armor types and walking speeds. Positive joint work over the stance phase significantly increased with walking speed and carried load, accompanied by 2.3–2.6% shifts in total positive work production from the ankle to the hip (p < 0.05). Compared to using cARM1 with 15 kg carried load, carrying 30 kg resulted in significantly greater hip contribution to total lower-limb positive work, while knee and ankle work decreased. Substantial increases in hip joint contributions to total lower-limb positive work that occur with increases in walking speed and load magnitude highlight the importance of hip musculature to load carriage walking.     

Comparison of joint kinetics during free weight and flywheel resistance exercise

The most common modality for resistance exercise is free weight resistance. Alternative methods of providing external resistance have been investigated, in particular for use in microgravity environments such as space flight. One alternative modality is flywheel inertial resistance, which generates resistance as a function of the mass, distribution of mass, and angular acceleration of the flywheel. The purpose of this investigation was to characterize net joint kinetics of multijoint exercises performed with a flywheel inertial resistance device in comparison to free weights. Eleven trained men and women performed the front squat, lunge, and push press on separate days with free weight or flywheel resistance, while instrumented for biomechanical analysis. Front squats performed with flywheel resistance required greater contribution of the hip and ankle, and less contribution of the knee, compared to free weight. Push presses performed with flywheel resistance had similar impulse requirements at the knee compared to free weight, but greater impulse requirement at the hip and ankle. As used in this investigation, flywheel inertial resistance increases the demand on the hip extensors and ankle plantarflexors and decreases the mechanical demand on the knee extensors for lower extremity exercises such as the front squat and lunge. Exercises involving dynamic lower and upper extremity actions, such as the push press, may benefit from flywheel inertial resistance, due to the increased mechanical demand on the knee extensors.     

Lower extremity control during turns initiated with and without hip external rotation

The pirouette turn is often initiated in neutral and externally rotated hip positions by dancers. This provides an opportunity to investigate how dancers satisfy the same mechanical objectives at the whole-body level when using different leg kinematics. The purpose of this study was to compare lower extremity control strategies during the turn initiation phase of pirouettes performed with and without hip external rotation. Skilled dancers (n=5) performed pirouette turns with and without hip external rotation. Joint kinetics during turn initiation were determined for both legs using ground reaction forces (GRFs) and segment kinematics. Hip muscle activations were monitored using electromyography. Using probability-based statistical methods, variables were compared across turn conditions as a group and within-dancer. Despite differences in GRFs and impulse generation between turn conditions, at least 90% of each GRF was aligned with the respective leg plane. A majority of the net joint moments at the ankle, knee, and hip acted about an axis perpendicular to the leg plane. However, differences in shank alignment relative to the leg plane affected the distribution of the knee net joint moment when represented with respect to the shank versus the thigh. During the initiation of both turns, most participants used ankle plantar flexor moments, knee extensor moments, flexor and abductor moments at the push leg׳s hip, and extensor and abductor moments at the turn leg׳s hip. Representation of joint kinetics using multiple reference systems assisted in understanding control priorities.     

The role of intersegmental dynamics during rapid limb oscillations

The interactive dynamic effects of muscular, inertial and gravitational moments on rapid, multi-segmented limb oscillations were studied. Using three-segment, rigid-body equations of motion, hip, knee and ankle intersegmental dynamics were calculated for the steady-state cycles of the paw-shake response in adult spinal cats. Hindlimb trajectories were filmed to obtain segmental kinematics, and myopotentials of flexors and extensors at each of the three joints were recorded synchronously with the ciné film. The segmental oscillations that emerged during the paw-shake response were a consequence of an interplay between active and passive musculotendinous forces, inertial forces, and gravity. During steady-state oscillations, the amplitudes of joint excursions, peak angular velocities, and peak angular accelerations increased monotonically and significantly in magnitude from the proximal joint (hip) to the most distal joint (ankle). In contrast to these kinematic relationships, the maximal values of net moments at the hip and knee were equal in magnitude, but of significantly lower magnitude than the large net moment at the ankle joint. At both the ankle and the knee, the flexor and extensor muscle moments were equal, but at the hip the magnitude of the peak flexor muscle moment was significantly greater than the extensor muscle moment. Muscle moments at the hip not only acted to counterbalance accelerations of the more distal segments, but also acted to maintain the postural orientation of the hindlimb. Large muscle moments at the knee functioned to counterbalance the large inertial moments generated by the large angular accelerations of the paw. At the ankle, the muscle moments dominated the generation of the paw accelerations. At the ankle and the knee, muscle moments controlled limb dynamics by slowing and reversing joint motions, and the active muscle forces contributing to ankle and knee moments were derived from lengthening of active musculotendinous units. In contrast to the more distal joints, the active muscles crossing the hip predominantly shortened as a result of the interplay among inertial forces and gravitational moments. The muscle function and kinetic data explain key features of the complex interactions that occur between central control mechanisms and multi-segmented, oscillating limb segments during the paw-shake response.     

Comparison of the human-exosuit interaction using ankle moment and ankle positive power inspired walking assistance

Previous ankle exoskeleton assistance techniques that were able to demonstrate metabolic reductions can be categorized into those that delivered moment profiles similar to the biological ankle moment throughout the stance phase, and others that delivered positive power only during push off. Both assistance techniques and a powered-off condition were compared in treadmill walking (1.5 m s⁻¹) with a soft exosuit. We hypothesized that both techniques can result in a similar metabolic reduction when providing a similar level of average positive exosuit power at each ankle (0.12 W kg⁻¹) and hip (0.02 W kg⁻¹) while the underlying global center-of-mass and local joint biomechanics would be different. We found a similar net metabolic rate reduction of 15% relative to walking with the suit powered-off for both techniques. The ankle moment inspired technique showed larger magnitudes of reductions for biological moment and power at the hip and the ankle. The ankle power inspired technique might benefit from higher biological efficiency, when reducing positive instead of negative power at the knee and when almost keeping the isometric function of the plantarflexors before push-off. Changes at the ankle caused energetic reductions at the knee, hip and the center-of-mass. A major contribution to metabolic reduction might be based on them. As the lower limb biomechanics that led to these reductions were different, we believe that humans alter their gait to maximize their energetic benefit based on the exosuit assistance. For further insights on mechanisms that lead to metabolic reduction, joint mechanics and muscle-tendon dynamics must be analyzed in combination.     

Gait biomechanics of skipping are substantially different than those of running

The inherit injury risk associated with high-impact exercises calls for alternative ways to achieve the benefits of aerobic exercise while minimizing excessive stresses to body tissues. Skipping presents such an alternative, incorporating double support, flight, and single support phases. We used ground reaction forces (GRFs), lower extremity joint torques and powers to compare skipping and running in 20 healthy adults. The two consecutive skipping steps on each limb differed significantly from each other, and from running. Running had the longest step length, the highest peak vertical GRF, peak knee extensor torque, and peak knee negative and positive power and negative and positive work. Skipping had the greater cadence, peak horizontal GRF, peak hip and ankle extensor torques, peak ankle negative power and work, and peak ankle positive power. The second vs first skipping step had the shorter step length, higher cadence, peak horizontal GRF, peak ankle extensor torque, and peak ankle negative power, negative work, and positive power and positive work. The first skipping step utilized predominately net negative joint work (eccentric muscle action) while the second utilized predominately net positive joint work (concentric muscle action). The skipping data further highlight the persistence of net negative work performed at the knee and net positive work performed at the ankle across locomotion gaits. Evidence of step segregation was seen in distribution of the braking and propelling impulses and net work produced across the hip, knee, and ankle joints.ConclusionsSkipping was substantially different than running and was temporally and spatially asymmetrical with successive foot falls partitioned into a dominant function, either braking or propelling whereas running had a single, repeated step in which both braking and propelling actions were performed equally.     

Effect of knee position on hip and knee torques during the barbell squat

Some recommendations suggest keeping the shank as vertical as possible during the barbell squat, thus keeping the knees from moving past the toes. This study examined joint kinetics occurring when forward displacement of the knees is restricted vs. when such movement is not restricted. Seven weight-trained men (mean +/- SD; age = 27.9 +/- 5.2 years) were videotaped while performing 2 variations of parallel barbell squats (barbell load = body weight). Either the knees were permitted to move anteriorly past the toes (unrestricted) or a wooden barrier prevented the knees from moving anteriorly past the toes (restricted). Differences resulted between static knee and hip torques for both types of squat as well as when both squat variations were compared with each other (p < 0.05). For the unrestricted squat, knee torque (N.m; mean +/- SD) = 150.1 +/- 50.8 and hip torque = 28.2 +/- 65.0. For the restricted squat, knee torque = 117.3 +/- 34.2 and hip torque = 302.7 +/- 71.2. Restricted squats also produced more anterior lean of the trunk and shank and a greater internal angle at the knees and ankles. The squat technique used can affect the distribution of forces between the knees and hips and on the kinematic properties of the exercise. PRACTICAL APPLICATIONS: Although restricting forward movement of the knees may minimize stress on the knees, it is likely that forces are inappropriately transferred to the hips and low-back region. Thus, appropriate joint loading during this exercise may require the knees to move slightly past the toes.     

The effects of knee support on the sagittal lower-body joint kinematics and kinetics of deep squats

Little work has been done to examine the deep squat position (>130° sagittal knee flexion). In baseball and softball, catchers perform this squat an average of 146 times per nine-inning game. To alleviate some of the stress on their knees caused by this repetitive loading, some catchers wear foam knee supports.ObjectivesThis work quantifies the effects of knee support on lower-body joint kinematics and kinetics in the deep squat position.MethodsSubjects in this study performed the deep squat with no support, foam support, and instrumented support. In order to measure the force through the knee support, instrumented knee supports were designed and fabricated. We then developed an inverse dynamic model to incorporate the support loads. From the model, joint angles and moments were calculated for the three conditions.ResultsWith support there is a significant reduction in the sagittal moment at the knee of 43% on the dominant side and 63% on the non-dominant side compared to without support. These reductions are a result of the foam supports carrying approximately 20% of body weight on each side.ConclusionKnee support reduces the moment necessary to generate the deep squat position common to baseball catchers. Given the short moment arm of the patella femoral tendon, even small changes in moment can have a large effect in the tibial-femoral contact forces, particularly at deep squat angles. Reducing knee forces may be effective in decreasing incidence of osteochondritis dissecans.     

Lower extremity biomechanics during weightlifting exercise vary across joint and load

The purpose of this study was to determine the effect of load on lower extremity biomechanics during the pull phase of the clean. Kinematic and kinetic data of the 3 joints of the lower extremity were collected while participants performed multiple sets of cleans at 3 percentages: 65, 75, and 85% of 1 repetition maximum (1RM). General linear models with repeated measures were used to assess the influence of load on angular velocities, net torques, powers, and rates of torque development at the ankle, knee, and hip joint. The results suggest that the biomechanical demands required from the lower extremities change with the lifted load and to an extent depend on the respective joint. Most notably, the hip and knee extended significantly faster than the ankle independent of load, whereas the hip and ankle generally produced significantly higher torques than the knee did. Torque, rate of torque development (RTD), and power were maximimal at 85% of 1RM for the ankle joint and at 75% of 1RM for the knee joint. Torque and RTD at the hip were maximal at loads >75% of 1RM. This study provides important novel information about the mechanical demands of a weightlifting exercise and should be heeded in the design of resistance training programs.     

A musculoskeletal model of the human lower extremity: the effect of muscle, tendon, and moment arm on the moment-angle relationship of musculotendon actuators at the hip, knee, and ankle

We have developed a musculoskeletal model of the human lower extremity for computer simulation studies of musculotendon function and muscle coordination during movement. This model incorporates the salient features of muscle and tendon, specifies the musculoskeletal geometry and musculotendon parameters of 18 musculotendon actuators, and defines the active isometric moment of these actuators about the hip, knee, and ankle joints in the sagittal plane. We found that tendon slack length, optimal muscle-fiber length, and moment arm are different for each actuator, thus each actuator develops peak isometric moment at a different joint angle. The joint angle where an actuator produces peak moment does not necessarily coincide with the joint angle where: (1) muscle force peaks, (2) moment arm peaks, or (3) the in vivo moment developed by maximum voluntary contractions peaks. We conclude that when tendon is neglected in analyses of musculotendon force or moment about joints, erroneous predictions of human musculotendon function may be stated, not only in static situations as studied here, but during movement as well.     

Biomechanical model and evaluation of a linear motion squat type exercise

A biomechanical model of a squat exercise performed on a device using a bar that is restricted to a linear motion was developed. Hip and knee moments were evaluated at varying foot positions. The range of motion of the exercise was limited by the knee joint angle beginning at an 80 degrees angle (flexed) to a 179 degrees joint angle (extended). Variations in foot placement were evaluated for differences in torque applied about the transverse axes of the user's knee and hip joints. Because the user's feet were positioned farther forward (anterior), the moment about the knee decreased whereas the moment about the hip increased. Positive moments were those that resulted in forces to flex the knee and hip joints. Positive knee moments were determined in all conditions when the knee was flexed and became negative when the knee was at or near full extension. The model always produced positive moments about the hip. Thus, foot position is a critical factor in hip and knee moments, and therefore in the muscle groups stressed, in a linear motion squat type exercise.     

Predicting net joint moments during a weightlifting exercise with a neural network model

The purpose of this study was to develop and train a Neural Network (NN) that uses barbell mass and motions to predict hip, knee, and ankle Net Joint Moments (NJM) during a weightlifting exercise. Seven weightlifters performed two cleans at 85% of their competition maximum while ground reaction forces and 3-D motion data were recorded. An inverse dynamics procedure was used to calculate hip, knee, and ankle NJM. Vertical and horizontal barbell motion data were extracted and, along with barbell mass, used as inputs to a NN. The NN was then trained to model the association between the mass and kinematics of the barbell and the calculated NJM for six weightlifters, the data from the remaining weightlifter was then used to test the performance of the NN – this was repeated 7 times with a k-fold cross-validation procedure to assess the NN accuracy. Joint-specific predictions of NJM produced coefficients of determination (r²) that ranged from 0.79 to 0.95, and the percent difference between NN-predicted and inverse dynamics calculated peak NJM ranged between 5% and 16%. The NN was thus able to predict the spatiotemporal patterns and discrete peaks of the three NJM with reasonable accuracy, which suggests that it is feasible to predict lower extremity NJM from the mass and kinematics of the barbell. Future work is needed to determine whether combining a NN model with low cost technology (e.g., digital video and free digitising software) can also be used to predict NJM of weightlifters during field-testing situations, such as practice and competition, with comparable accuracy.