Relative performances of artificial neural network and regression mapping tools in evaluation of spinal loads and muscle forces during static lifting

Combining the probabilistic finite element model and artificial neural network to study nutrient levels in the human intervertebral discs

BACKGROUND

Diffusion distance and diffusivity are known to affect nutrient transport rates, but the probabilistic analysis of these two factors remains vacant. There is a lack of effective tools to evaluate disc nutrient levels.

METHODS

Five-hundred-disc samples with different combinations of morphological and water content parameters were generated, which were used to evaluate nutrient levels in unloaded and loaded states. Spearman correlation coefficients between inputs and responses were calculated. Artificial neural networks were trained to predict nutrient concentrations based on the dataset generated by the probabilistic finite element model.

FINDINGS

In unloaded and loaded states, the minimum oxygen concentration of nucleus pulposus was negatively correlated with disc height (r = -0.83, p < 0.01 and r = -0.76, p < 0.01, respectively), and the minimum glucose concentration of annulus fibrosus was positively correlated with its water content (r = 0.68, p < 0.01 and r = 0.73, p < 0.01, respectively). The maximum lactate concentration of cartilage endplate was affected by endplate thickness (r = 0.94, p < 0.01 and r = 0.95, p < 0.01, respectively). For trained neural networks, nutrient concentrations could be well predicted, with coefficients of determination greater than 0.95 and mean absolute percentage errors less than 5 %.

INTERPRETATION

This study underscores the importance of disc height, annulus fibrosus water content, and endplate thickness in regulating nutrient levels, and precise control of these parameters should be prioritized in the design of tissue-engineered discs. Moreover, artificial neural networks might be a promising tool for evaluating nutrient levels.

Predicting Knee Joint Contact Forces During Normal Walking Using Kinematic Inputs With a Long-Short Term Neural Network

Knee joint contact forces are commonly estimated via surrogate measures (i.e., external knee adduction moments or musculoskeletal modeling). Despite its capabilities, modeling is not optimal for clinicians or persons with limited experience. The purpose of this study was to design a novel prediction method for knee joint contact forces that is simplistic in terms of required inputs. This study included marker trajectories and instrumented knee forces during normal walking from the "Grand Challenge" (n = 6) and "CAMS" (n = 2) datasets. Inverse kinematics were used to derive stance phase hip (sagittal, frontal, transverse), knee (sagittal, frontal), ankle (sagittal), and trunk (frontal) kinematics. A long-short term memory network (LSTM) was created using matlab to predict medial and lateral knee force waveforms using combinations of the kinematics. The Grand Challenge and CAMS datasets trained and tested the network, respectively. Musculoskeletal modeling forces were derived using static optimization and joint reaction tools in OpenSim. Waveform accuracy was determined as the proportion of variance and root-mean-square error between network predictions and in vivo data. The LSTM network was highly accurate for medial forces (R2 = 0.77, RMSE = 0.27 BW) and required only frontal hip and knee and sagittal hip and ankle kinematics. Modeled medial force predictions were excellent (R2 = 0.77, RMSE = 0.33 BW). Lateral force predictions were poor for both methods (LSTM R2 = 0.18, RMSE = 0.08 BW; modeling R2 = 0.21, RMSE = 0.54 BW). The designed LSTM network outperformed most reports of musculoskeletal modeling, including those reached in this study, revealing knee joint forces can accurately be predicted by using only kinematic input variables.

Evaluation of ground reaction forces and centers of pressure predicted by AnyBody Modeling System during load reaching/handling activities and effects of the prediction errors on model-estimated spinal loads

Full-body and lower-extremity human musculoskeletal models require feet ground reaction forces (GRFs) and centers of pressure (CoPs) as inputs to predict muscle forces and joint loads. GRFs/CoPs are traditionally measured via floor-mounted forceplates that are usually restricted to research laboratories thus limiting their applicability in real occupational and clinical setups. Alternatively, GRFs/CoPs can be estimated via inverse dynamic approaches as also implemented in the Anybody Modeling System (AnyBody Technology, Aalborg, Denmark). The accuracy of Anybody in estimating GRFs/CoPs during load-handling/reaching activities and the effect of its prediction errors on model-estimated spinal loads remain to be investigated. Twelve normal- and over-weight individuals performed total of 480 static load-handling/reaching activities while measuring (by forceplates) and predicting (by AnyBody) their GRFs/CoPs. Moreover, the effects of GRF/CoP prediction errors on the estimated spinal loads were evaluated by inputting measured or predicted GRFs/CoPs into subject-specific musculoskeletal models. Regardless of the subject groups (normal-weight or overweight) and tasks (load-reaching or load-handling), results indicated great agreements between the measured and predicted GRFs (normalized root-mean-squared error, nRMSEs < 14% and R2 > 0.90) and between their model-estimated spinal loads (nRMSEs < 14% and R2 > 0.83). These agreements were good but relatively less satisfactory for CoPs (nRMSEs < 17% and 0.57 < R2 < 0.68). The only exception, requiring a more throughout investigation, was the situation when the ground-foot contact was significantly reduced during the activity. It appears that occupational/clinical investigations performed in real workstation/clinical setups with no access to forceplates may benefit from the AnyBody GRF/CoP prediction tools for a wide range of load-reaching/handling activities.

An artificial neural network for full-body posture prediction in dynamic lifting activities and effects of its prediction errors on model-estimated spinal loads

Musculoskeletal models have indispensable applications in occupational risk assessment/management and clinical treatment/rehabilitation programs. To estimate muscle forces and joint loads, these models require body posture during the activity under consideration. Posture is usually measured via video-camera motion tracking approaches that are time-consuming, costly, and/or limited to laboratories. Alternatively, posture-prediction tools based on artificial intelligence can be trained using measured postures of several subjects performing many activities. We aimed to use our previous posture-prediction artificial neural network (ANN), developed based on many measured static postures, to predict posture during dynamic lifting activities. Moreover, effects of the ANN posture-prediction errors on dynamic spinal loads were investigated using subject-specific musculoskeletal models. Seven individuals each performed twenty-five lifting tasks while their full-body three-dimensional posture was measured by a 10-camera Vicon system and also predicted by the ANN as functions of the hand-load positions during the lifting activities. The measured and predicted postures (i.e., coordinates of 39 skin markers) and their model-estimated L5-S1 loads were compared. The overall root-mean-squared-error (RMSE) and normalized (by the range of measured values) RMSE (nRMSE) between the predicted and measured postures for all markers/tasks/subjects was equal to 7.4 cm and 4.1 %, respectively (R2 = 0.98 and p < 0.05). The model-estimated L5-S1 loads based on the predicted and measured postures were generally in close agreements as also confirmed by the Bland-Altman analyses; the nRMSE for all subjects/tasks was < 10 % (R2 > 0.7 and p > 0.05). In conclusion, the easy-to-use ANN can accurately predict posture in dynamic lifting activities and its predicted posture can drive musculoskeletal models.

Multi-task artificial neural networks and their extrapolation capabilities to predict full-body 3D human posture during one- and two-handed load-handling activities

Machine-learning based human posture-prediction tools can potentially be robust alternatives to motion capture measurements. Existing posture-prediction approaches are confined to two-handed load-handling activities performed at heights below 120 cm from the floor and to predicting a limited number of body-joint coordinates/angles. Moreover, the extrapolating power of these tools beyond the range of the input dataset they were trained for (e.g., for underweight, overweight, or left-handed individuals) has not been investigated. In this study, we trained/validated/tested two posture-prediction (for full-body joint coordinates and angles) artificial neural networks (ANNs) using both 70%/15%/15% random-hold-out and leave-one-subject-out methods, based on a comprehensive kinematic dataset of forty-one full-body skin markers collected from twenty right-handed normal-weight (BMI = 18-26 kg/m2) subjects. Subjects performed 204 one- and two-handed unloaded activities at different vertical (0 to 180 cm from the floor) and horizontal (up to 60 cm lateral and/or anterior) destinations. Subsequently, the extrapolation capability of the trained/validated/tested ANNs was evaluated using data collected from fifteen additional subjects (unseen by the ANNs); three individuals in five groups: underweight, overweight, obese, left-handed individuals, and subjects with a hand-load. Results indicated that the ANNs predicted body joint coordinates and angles during various activities with errors of ∼ 25 mm and ∼ 10°, respectively; considerable improvements when compared to previous posture-prediction ANNs. Extrapolation errors of our ANNs generally remained within the error range of existing ANNs with obesity and being left-handed having, respectively, the most and least compromising effects on their accuracy. These easy-to-use ANNs appear, therefore, to be robust alternatives to common posture-measurement approaches.

Convolutional LSTM: a deep learning approach to predict shoulder joint reaction forces

We developed a Convolutional LSTM (ConvLSTM) network to predict shoulder joint reaction forces using 3D shoulder kinematics data containing 30 different shoulder activities from eight human subjects. We considered simulation outcomes from the AnyBody musculoskeletal model as the baseline force dataset to validate ConvLSTM model predictions. Results showed a good correlation (>80% accuracy, r ≥ 0.82) between ConvLSTM predicted and AnyBody estimated force values, the generalization of the developed model for novel task type (p-value = 0.07 ∼ 0.33), and a better prediction accuracy for the ConvLSTM model than conventional CNN and LSTM models.

Computational lumbar spine models: A literature review

BACKGROUND

Computational spine models of various types have been employed to understand spine function, assess the risk that different activities pose to the spine, and evaluate techniques to prevent injury. The areas in which these models are applied has expanded greatly, potentially beyond the appropriate scope of each, given their capabilities. A comprehensive understanding of the components of these models provides insight into their current capabilities and limitations.

METHODS

The objective of this review was to provide a critical assessment of the different characteristics of model elements employed across the spectrum of lumbar spine modeling and in newer combined methodologies to help better evaluate existing studies and delineate areas for future research and refinement.

FINDINGS

A total of 155 studies met selection criteria and were included in this review. Most current studies use either highly detailed Finite Element models or simpler Musculoskeletal models driven with in vivo data. Many models feature significant geometric or loading simplifications that limit their realism and validity. Frequently, studies only create a single model and thus can't account for the impact of subject variability. The lack of model representation for certain subject cohorts leaves significant gaps in spine knowledge. Combining features from both types of modeling could result in more accurate and predictive models.

INTERPRETATION

Development of integrated models combining elements from different model types in a framework that enables the evaluation of larger populations of subjects could address existing voids and enable more realistic representation of the biomechanics of the lumbar spine.

InverseMuscleNET: Alternative Machine Learning Solution to Static Optimization and Inverse Muscle Modeling

InverseMuscleNET, a machine learning model, is proposed as an alternative to static optimization for resolving the redundancy issue in inverse muscle models. A recurrent neural network (RNN) was optimally configured, trained, and tested to estimate the pattern of muscle activation signals. Five biomechanical variables (joint angle, joint velocity, joint acceleration, joint torque, and activation torque) were used as inputs to the RNN. A set of surface electromyography (EMG) signals, experimentally measured around the shoulder joint for flexion/extension, were used to train and validate the RNN model. The obtained machine learning model yields a normalized regression in the range of 88-91% between experimental data and estimated muscle activation. A sequential backward selection algorithm was used as a sensitivity analysis to discover the less dominant inputs. The order of most essential signals to least dominant ones was as follows: joint angle, activation torque, joint torque, joint velocity, and joint acceleration. The RNN model required 0.06 s of the previous biomechanical input signals and 0.01 s of the predicted feedback EMG signals, demonstrating the dynamic temporal relationships of the muscle activation profiles. The proposed approach permits a fast and direct estimation ability instead of iterative solutions for the inverse muscle model. It raises the possibility of integrating such a model in a real-time device for functional rehabilitation and sports evaluation devices with real-time estimation and tracking. This method provides clinicians with a means of estimating EMG activity without an invasive electrode setup.

The role of machine learning in the primary prevention of work-related musculoskeletal disorders: A scoping review

To determine the applications of machine learning (ML) techniques used for the primary prevention of work-related musculoskeletal disorders (WMSDs), a scoping review was conducted using seven literature databases. Of the 4,639 initial results, 130 primary research studies were deemed relevant for inclusion. Studies were reviewed and classified as a contribution to one of six steps within the primary WMSD prevention research framework by van der Beek et al. (2017). ML techniques provided the greatest contributions to the development of interventions (48 studies), followed by risk factor identification (33 studies), underlying mechanisms (29 studies), incidence of WMSDs (14 studies), evaluation of interventions (6 studies), and implementation of effective interventions (0 studies). Nearly a quarter (23.8%) of all included studies were published in 2020. These findings provide insight into the breadth of ML techniques used for primary WMSD prevention and can help identify areas for future research and development.

Improved artificial neural networks for 3D body posture and lumbosacral moment predictions during manual material handling activities

Body posture measurement approaches, required in biomechanical models to assess risk of musculoskeletal injuries, are usually costly and/or impractical for use in real workplaces. Therefore, we recently developed three artificial neural networks (ANNs), based on measured posture data on several individuals, to predict whole body 3D posture (coordinates of 15 markers located on body's main joints), segmental orientations (Euler angles of 14 body segments), and lumbosacral (L5-S1) moments during static manual material handling (MMH) activities (ANN_Posture, ANN_Angle, and ANN_Moment, respectively). These ANNs require worker's body height, body weight (only for ANN_Moment), hand-load 3D position, and its mass as inputs to accurately predict 3D marker coordinates (RMSE = 7.0 cm), segmental orientations (RMSE = 29.9°) and L5-S1 moments (RMSE = 16.5 N.m) for various static MMH activities. The current work aims to further improve the accuracy of these ANNs by performing outlier elimination and data normalization (as effective tools to improve the accuracy of ANNs) as well as by introducing participant's knee flexion angle (i.e., lifting technique: stoop, semi-squat, and full-squat) and body weight as new inputs into these ANNs. Results indicate that the RMSE of the new ANN_Posture, ANN_Angle, and ANN_Moment reduced by, respectively, ∼43%, 10%, and 29% (from 7.0 cm, 29.9°, and 16.5 Nm in the original ANNs to, respectively, 4.0 cm, 27.0°, and 11.8 Nm). Such significant improvements in the predictive power of our ANNs further confirm their effectiveness as alternative posture-prediction approaches requiring minimal in vivo data collection in real workplaces.

Artificial neural network can improve the accuracy of a markerless skeletal model in L5/S1 position estimation during symmetric lifting

This study investigated whether using an artificial neural network (ANN) method for L5/S1 position estimation based on the Kinect markerless skeletal model can produce more accurate data than measurements using the original Kinect skeletal model during symmetric lifting tasks. Twenty participants performed three symmetric lifting tasks twice at three vertical lifting height paths. Their postural data were simultaneously collected by a Kinect and a reference motion tracking system (MTS). The Kinect-based data are used as the model inputs, while its outputs are based on MTS. Three-layer ANN models to predict the L5/S1 position over the entire lifting duration were trained by identifying the relationship between the seven inputs (the participant's height and weight and the Kinect-based trunk angle, left knee angle, and left hip joint coordinates on the X-axis, Y-axis, and Z-axis) and three outputs (the reference L5/S1 position on the X-axis, Y-axis, and Z-axis). As a measure of error, the distances between the reference anatomical L5/S1 position and the predicted positions (by the ANN-Kinect system and the Kinect system) were calculated and compared. The results showed that introducing the ANN method can significantly (p < 0.0001) reduce the L5/S1 position estimation error (5.12 ± 1.83 cm) in comparison with directly using the original data output from the skeletal model driven by Kinect data (20.54 ± 3.24 cm). This method provides an alternative for L5/S1 position estimation while retaining the advantages of using Kinect such as portability, easy of use, and being equipped with the function of automatic skeletal identification.

Predicting Cervical Spine Compression and Shear in Helicopter Helmeted Conditions Using Artificial Neural Networks

OCCUPATIONAL APPLICATIONSMilitary helicopter pilots around the globe are at high risk of neck pain related to their use of helmet-mounted night vision goggles. Unfortunately, it is difficult to design alternative helmet configurations that reduce the biomechanical exposures on the cervical spine during flight because the time and resource costs associated with assessing these exposures in vivo are prohibitive. Instead, we developed artificial neural networks (ANNs) to predict cervical spine compression and shear given head-trunk kinematics and joint moments in the lower neck, data readily available from digital human models. The ANNs detected differences in cervical spine compression and anteroposterior shear between helmet configuration conditions during flight-relevant head movement, consistent with results from a detailed model based on in vivo electromyographic data. These ANNs may be useful in helping to prevent neck pain related to military helicopter flight by facilitating virtual biomechanical assessment of helmet configurations upstream in the design process.

A Review on the Use of Artificial Intelligence in Spinal Diseases

Artificial neural networks (ANNs) have been used in a wide variety of real-world applications and it emerges as a promising field across various branches of medicine. This review aims to identify the role of ANNs in spinal diseases. Literature were searched from electronic databases of Scopus and Medline from 1993 to 2020 with English publications reported on the application of ANNs in spinal diseases. The search strategy was set as the combinations of the following keywords: “artificial neural networks,” “spine,” “back pain,” “prognosis,” “grading,” “classification,” “prediction,” “segmentation,” “biomechanics,” “deep learning,” and “imaging.” The main findings of the included studies were summarized, with an emphasis on the recent advances in spinal diseases and its application in the diagnostic and prognostic procedures. According to the search strategy, a set of 3,653 articles were retrieved from Medline and Scopus databases. After careful evaluation of the abstracts, the full texts of 89 eligible papers were further examined, of which 79 articles satisfied the inclusion criteria of this review. Our review indicates several applications of ANNs in the management of spinal diseases including (1) diagnosis and assessment of spinal disease progression in the patients with low back pain, perioperative complications, and readmission rate following spine surgery; (2) enhancement of the clinically relevant information extracted from radiographic images to predict Pfirrmann grades, Modic changes, and spinal stenosis grades on magnetic resonance images automatically; (3) prediction of outcomes in lumbar spinal stenosis, lumbar disc herniation and patient-reported outcomes in lumbar fusion surgery, and preoperative planning and intraoperative assistance; and (4) its application in the biomechanical assessment of spinal diseases. The evidence suggests that ANNs can be successfully used for optimizing the diagnosis, prognosis and outcome prediction in spinal diseases. Therefore, incorporation of ANNs into spine clinical practice may improve clinical decision making.

Machine learning approach to predict center of pressure trajectories in a complete gait cycle: a feedforward neural network vs. LSTM network

Center of pressure (COP) trajectories of human can maintain regulation of forward progression and stability of lateral sway during walking. The insole pressure system can only detect COP trajectories of each foot during single stance. In this study, we developed artificial neural network models that could present COP trajectories in an integrated coordinate system during a complete gait cycle using pressure information of the insole system. A feed forward artificial neural network (FFANN) and a long short-term memory (LSTM) model were developed. For FFANN, among 198 pressure sensors from Pedar-X insoles, proper input variables were selected using sequential forward selection to reduce input dimension. The LSTM model used all 198 signals as inputs because of its self-learning characteristic. As results of cross-validation, the FFANN model showed correlation coefficients of 0.98-0.99 and 0.93-0.95 in anterior/posterior and medial/lateral directions, respectively. For the LSTM model, correlation coefficients were similar to those of FFANN. However, the relative root mean square error (12.5%) of the FFANN model was higher than that (9.8%) of the LSTM model in medial/lateral direction (p = 0.03). This study can be used for quantitative evaluation of clinical diagnosis and rehabilitation status for patient with various diseases through further training using varied databases. Graphical abstract Architectures of neural networks developed in this study (a feed forward artificial neural network; b LSTM network).

Coupled artificial neural networks to estimate 3D whole-body posture, lumbosacral moments, and spinal loads during load-handling activities

Biomechanical modeling approaches require body posture to evaluate the risk of spine injury during manual material handling. The procedure to measure body posture via motion-analysis techniques as well as the subsequent calculations of lumbosacral moments and spine loads by, respectively, inverse-dynamic and musculoskeletal models are complex and time-consuming. We aim to develop easy-to-use yet accurate artificial neural networks (ANNs) that predict 3D whole-body posture (ANN_posture), segmental orientations (ANN_angle), and lumbosacral moments (ANN_moment) based on our measurements during load-handling activities. Fifteen individuals each performed 135 load-handling activities by reaching (0 kg) or handling (5 and 10 kg) weights located at nine different horizontal and five vertical (0, 30, 60, 90, and 120 cm from the floor) locations. Whole-body posture was measured via a motion capture system and lumbosacral moments were calculated via a 3D top-down eight link-segment inverse-dynamic model. ANN_posture, ANN_angle, and ANN_moment were trained (RMSEs = 6.7 cm, 29.8°, and 16.2 Nm, respectively) and their generalization capability was tested (RMSE = 7.0 cm and R² = 0.97, RMSE = 29.9° and R² = 0.85, and RMSE = 16.5 Nm and R² = 0.97, respectively). These ANNs were subsequently coupled to our previously-developed/validated ANN_load, which predicts spinal loads during 3D load-handling activities. The results showed outputs of the coupled ANNs for L4-L5 intradiscal pressure (IDPs) during a number of activities were in agreement with measured IDPs (RMSE = 0.37 MPa and R² = 0.89). Hence, coupled ANNs were found to be robust tools to evaluate posture, lumbosacral moments, spinal loads, and thus risk of injury during load-handling activities.

Single Inertial Sensor-Based Neural Networks to Estimate COM-COP Inclination Angle During Walking

A biomechanical understanding of gait stability is needed to reduce falling risk. As a typical parameter, the COM-COP (center of mass-center of pressure) inclination angle (IA) could provide valuable insight into postural control and balance recovery ability. In this study, an artificial neural network (ANN) model was developed to estimate COM-COP IA based on signals using an inertial sensor. Also, we evaluated how different types of ANN and the cutoff frequency of the low-pass filter applied to input signals could affect the accuracy of the model. An inertial measurement unit (IMU) including an accelerometer, gyroscope, and magnetometer sensors was fabricated as a prototype. The COM-COP IA was calculated using a 3D motion analysis system including force plates. In order to predict the COM-COP IA, a feed-forward ANN and long-short term memory (LSTM) network was developed. As a result, the feed-forward ANN showed a relative root-mean-square error (rRMSE) of 15% while the LSTM showed an improved accuracy of 9% rRMSE. Additionally, the LSTM displayed a stable accuracy regardless of the cutoff frequency of the filter applied to the input signals. This study showed that estimating the COM-COP IA was possible with a cheap inertial sensor system. Furthermore, the neural network models in this study can be implemented in systems to monitor the balancing ability of the elderly or patients with impaired balancing ability.

The Path to Deliver the Most Realistic Follower Load for a Lumbar Spine in Standing Posture: A Finite Element Study

A spine is proven to be subjected to a follower load which is a compressive load of physiologic magnitude acting on the whole spine. The path of the follower load approximates the tangent to the curve of the spine in in vivo neutral standing posture. However, the specific path location of the follower load is still unclear. The aim of this study is to find out the most realistic location of the follower load path (FLP) for a lumbar spine in standing. A three-dimensional (3D) nonlinear finite element model (FEM) of lumbosacral vertebrae (L1-S1) with consideration of the calibrated material properties was established and validated by comparing with the experimental data. We show that the shape of the lumbosacral spine is strongly affected by the location of FLP. An evident nonlinear relationship between the FLP location and the kinematic response of the L1-S1 lumbosacral spine exists. The FLP at about 4 and 3 mm posterior to the curve connecting the center of the vertebral bodies delivers the most realistic location in standing for healthy people and patients having low back pains (LPBs), respectively. Moreover, the “sweeping” method introduced in this study can be applicable to all individualized FEM to determine the location of FLP.

The 'Arm Force Field' method to predict manual arm strength based on only hand location and force direction

This paper describes the development of a novel method (termed the 'Arm Force Field' or 'AFF') to predict manual arm strength (MAS) for a wide range of body orientations, hand locations and any force direction. This method used an artificial neural network (ANN) to predict the effects of hand location and force direction on MAS, and included a method to estimate the contribution of the arm's weight to the predicted strength. The AFF method predicted the MAS values very well (r² = 0.97, RMSD = 5.2 N, n = 456) and maintained good generalizability with external test data (r² = 0.842, RMSD = 13.1 N, n = 80). The AFF can be readily integrated within any DHM ergonomics software, and appears to be a more robust, reliable and valid method of estimating the strength capabilities of the arm, when compared to current approaches.

Surrogate modeling of deformable joint contact using artificial neural networks

Deformable joint contact models can be used to estimate loading conditions for cartilage-cartilage, implant-implant, human-orthotic, and foot-ground interactions. However, contact evaluations are often so expensive computationally that they can be prohibitive for simulations or optimizations requiring thousands or even millions of contact evaluations. To overcome this limitation, we developed a novel surrogate contact modeling method based on artificial neural networks (ANNs). The method uses special sampling techniques to gather input-output data points from an original (slow) contact model in multiple domains of input space, where each domain represents a different physical situation likely to be encountered. For each contact force and torque output by the original contact model, a multi-layer feed-forward ANN is defined, trained, and incorporated into a surrogate contact model. As an evaluation problem, we created an ANN-based surrogate contact model of an artificial tibiofemoral joint using over 75,000 evaluations of a fine-grid elastic foundation (EF) contact model. The surrogate contact model computed contact forces and torques about 1000 times faster than a less accurate coarse grid EF contact model. Furthermore, the surrogate contact model was seven times more accurate than the coarse grid EF contact model within the input domain of a walking motion. For larger input domains, the surrogate contact model showed the expected trend of increasing error with increasing domain size. In addition, the surrogate contact model was able to identify out-of-contact situations with high accuracy. Computational contact models created using our proposed ANN approach may remove an important computational bottleneck from musculoskeletal simulations or optimizations incorporating deformable joint contact models.

Comparative evaluation of six quantitative lifting tools to estimate spine loads during static activities

Different lifting analysis tools are commonly used to assess spinal loads and risk of injury. Distinct musculoskeletal models with various degrees of accuracy are employed in these tools affecting thus their relative accuracy in practical applications. The present study aims to compare predictions of six tools (HCBCF, LSBM, 3DSSPP, AnyBody, simple polynomial, and regression models) for the L4-L5 and L5-S1 compression and shear loads in twenty-six static activities with and without hand load. Significantly different spinal loads but relatively similar patterns for the compression (R(2) > 0.87) were computed. Regression models and AnyBody predicted intradiscal pressures in closer agreement with available in vivo measurements (RMSE ≈ 0.12 MPa). Due to the differences in predicted spinal loads, the estimated risk of injury alters depending on the tool used. Each tool is evaluated to identify its shortcomings and preferred application domains.

Artificial neural networks in neurosurgery

Artificial neural networks (ANNs) effectively analyze non-linear data sets. The aimed was A review of the relevant published articles that focused on the application of ANNs as a tool for assisting clinical decision-making in neurosurgery. A literature review of all full publications in English biomedical journals (1993-2013) was undertaken. The strategy included a combination of key words 'artificial neural networks', 'prognostic', 'brain', 'tumor tracking', 'head', 'tumor', 'spine', 'classification' and 'back pain' in the title and abstract of the manuscripts using the PubMed search engine. The major findings are summarized, with a focus on the application of ANNs for diagnostic and prognostic purposes. Finally, the future of ANNs in neurosurgery is explored. A total of 1093 citations were identified and screened. In all, 57 citations were found to be relevant. Of these, 50 articles were eligible for inclusion in this review. The synthesis of the data showed several applications of ANN in neurosurgery, including: (1) diagnosis and assessment of disease progression in low back pain, brain tumours and primary epilepsy; (2) enhancing clinically relevant information extraction from radiographic images, intracranial pressure processing, low back pain and real-time tumour tracking; (3) outcome prediction in epilepsy, brain metastases, lumbar spinal stenosis, lumbar disc herniation, childhood hydrocephalus, trauma mortality, and the occurrence of symptomatic cerebral vasospasm in patients with aneurysmal subarachnoid haemorrhage; (4) the use in the biomechanical assessments of spinal disease. ANNs can be effectively employed for diagnosis, prognosis and outcome prediction in neurosurgery.

Lumbopelvic rhythm during forward and backward sagittal trunk rotations: combined in vivo measurement with inertial tracking device and biomechanical modeling

BACKGROUND

The ratio of total lumbar rotation over pelvic rotation (lumbopelvic rhythm) during trunk sagittal movement is essential to evaluate spinal loads and discriminate between low back pain and asymptomatic population.

METHODS

Angular rotations of the pelvis and lumbar spine as well as their sagittal rhythm during forward flexion and backward extension in upright standing of eight asymptomatic males are measured using an inertial tracking device. The effect of variations in the lumbopelvic ratio during trunk flexion on spinal loads is quantified using a detailed musculoskeletal model.

FINDINGS

The mean of peak voluntary flexion rotations of the thorax, pelvis, and lumbar was 121° (SD 9.9), 53.0° (SD 5.2), and 60.2° (SD 8.6), respectively. The mean lumbopelvic ratios decreased from 2.51 in 0-30° of trunk flexion to 1.34 in 90-120° range during forward bending while it increased from 1.23 in 90-120° range to 2.86 in 0-30° range during backward extension. Variations in the lumbopelvic ratio from 0.5 to 3 (with an interval of 0.25) at any trunk flexion angle generally reduced the L5-S1 compression and shear forces by up to 21 and 45%, respectively. The measured lumbopelvic ratios resulted overall in near-optimal (minimal) L5-S1 compression forces.

INTERPRETATION

A simultaneous rhythm between the lumbar and pelvis movements was found during both forward and backward trunk movements. While the lumbar spine contributed more to the trunk rotation during early and final stages of forward flexion and backward extension, respectively, the pelvis contributed more during final and early stages of forward flexion and backward extension, respectively. Our healthy subjects adapted a lumbopelvic coordination that diminished L5-S1 compression force.