Artificial neural networks to predict 3D spinal posture in reaching and lifting activities; Applications in biomechanical models.

Spinal posture is a crucial input in biomechanical models and an essential factor in ergonomics investigations to evaluate risk of low back injury. In vivo measurement of spinal posture through the common motion capture techniques is limited to equipped laboratories and thus impractical for workplace applications. Posture prediction models are therefore considered indispensable tools. This study aims to investigate the capability of artificial neural networks (ANNs) in predicting the three-dimensional posture of the spine (S1, T12 and T1 orientations) in various activities. Two ANNs were trained and tested using measurements from spinal postures of 40 male subjects by an inertial tracking device in various static reaching and lifting (of 5kg) activities. Inputs of each ANN were position of the hand load and body height, while outputs were rotations of the three foregoing segments relative to their initial orientation in the neutral upright posture. Effect of posture prediction errors on the estimated spinal loads in symmetric reaching activities was also investigated using a biomechanical model. Results indicated that both trained ANNs could generate outputs (three-dimensional orientations of the segments) from novel sets of inputs that were not included in the training processes (root-mean-squared-error (RMSE)<11° and coefficient-of-determination (R)>0.95). A graphic user interface was designed and made available to facilitate use of the ANNs. The difference between the mean of each measured angle in a reaching task and the corresponding angle in a lifting task remained smaller than 8°. Spinal loads estimated by the biomechanical model based on the predicted postures were on average different by < 12% from those estimated based on the exact measured postures (RMSE=173 and 35N for the L5-S1 compression and shear loads, respectively).