Artificial intelligence prediction of the effect of rehabilitation in whiplash associated disorder

Abstract

The active cervical range of motion (aROM) is assessed by clinicians to inform their decision-making. Even with the ability of neck motion to discriminate injured from non-injured subjects, the mechanisms to explain recovery or persistence of WAD remain unclear. There are few studies of ROM examinations with precision tools using kinematics as predictive factors of recovery rate. The present paper will evaluate the performance of an artificial neural network (ANN) using kinematic variables to predict the overall change of aROM after a period of rehabilitation in WAD patients. To achieve this goal the neck kinematics of a cohort of 1082 WAD patients (55.1% females), with mean age 37.68 (SD 12.88) years old, from across Spain were used. Prediction variables were the kinematics recorded by the EBI® 5 in routine biomechanical assessments of these patients. These include normalized ROM, speed to peak and ROM coefficient of variation. The improvement of aROM was represented by the Neck Functional Holistic Analysis Score (NFHAS). A supervised multi-layer feed-forward ANN was created to predict the change in NFHAS. The selected architecture of the ANN showed a mean squared error of 308.07–272.75 confidence interval for a 95% in the Monte Carlo cross validation. The performance of the ANN was tested with a subsample of patients not used in the training. This comparison resulted in a medium correlation with R = 0.5. The trained neural network to predict the expected difference in NFHAS between baseline and follow up showed modest results. While the overall performance is moderately correlated, the error of this prediction is still too large to use the method in clinical practice. The addition of other clinically relevant factors could further improve prediction performance.

Machine learning approaches applied in spinal pain research

“…For example, one study reported that artificial neural networks (ANN) (96.9%) resulted in more accurate prediction in 2-year postsurgical satisfaction in patients with lumbar spinal stenosis, compared to logistic regression (88.4%) (Azimi et al , 2014). Most ML research in spinal pain have used highly flexible ML models -support vector machine (SVM) (Ashouri et al , 2017, Jiang et al , 2017, Lamichhane et al , 2021, Lee et al , 2019, Silva et al , 2015, and ANN (Fidalgo-Herrera et al , 2020, Hu et al , 2018, Magnusson et al , 1998. However, what constitutes the most important variable or the magnitude of effect each variable has on the prediction remains "hidden" in the ANN model.…”

“…The physiological data used for prediction in spinal pain ML studies typically consist of temporal (Ashouri, Abedi, 2017, Fidalgo-Herrera, Martínez-Beltrán, 2020, Hu, Kim, 2018, Magnusson, Bishop, 1998, spatial (Lamichhane, Jayasekera, 2021), and spatio-temporal functional variables (Jiang, Luk, 2017). An important pre-processing step in many ML methods is that the variables are required to lie on a scalar domain.…”

“…An important pre-processing step in many ML methods is that the variables are required to lie on a scalar domain. Some studies use Principal Components Analysis (PCA) (Ashouri, Abedi, 2017) on functional data to extract scalar features, whilst others directly extract scalar features from the original variables (Fidalgo-Herrera, Martínez-Beltrán, 2020, Jiang, Luk, 2017, Lamichhane, Jayasekera, 2021, Magnusson, Bishop, 1998. An important limitation of using dimension reduction techniques like PCA on functional data is a loss in spatial and/or temporal information, and often there is no strong prior knowledge as to what are the most important features to select.…”

Especificação e avaliação automática de atividades reabilitativas utilizando Redes de Módulos Neurais e vídeos capturados por uma câmera RGB

“…Outro trabalho de (FIDALGO-HERRERA et al, 2020) também utiliza sensores acoplados ao corpo. O método proposto analisa a performance de uma ANN utilizando parâmetros cinemáticos em pacientes com Whiplash Associated Disorders (WAD).…”