Predictive classification of clinical ball catching trials with recurrent neural networks

Motor disturbances arising from neurodegenerative and neurodevelopmental disorders, such as Spinocerebellar Ataxias and Autism Spectrum Disorders, can strongly affect a patient’s quality of life. A classification of clinical catching trials might give insight into the existence of pathological alterations in the relation of arm and ball movements. Accurate, but also early decisions are required to classify a catching attempt before the catcher's first ball contact. To ensure clinically valuable results, we postulate a confidence threshold of 75%. Hence, three competing objectives have to be optimized at the same time: accuracy, earliness and decision-making confidence. Here we propose a coupled classification and prediction approach for early time series classification: a predictive, generative recurrent neural network (RNN) forecasts the next data points of ball trajectories based on already available observations; a discriminative RNN continuously generates classification guesses based on the available data points and the unrolled sequence predictions. We compare our approach, which we refer to as predictive sequential classification (PSC), to state-of-the-art sequence learners, including long short-term memory networks (LSTMs) and temporal convolutional networks (TCNs). On this hard real-world task we can consistently demonstrate the superiority of PSC over all other models in terms of accuracy and confidence with respect to earliness of recognition. Specifically, PSC is able to confidently classify the success of catching trials as early as 123 milliseconds before the first ball contact. Our findings show that PSC with its two-model design can simultaneously optimize accuracy, earliness and confidence of decision-making, thus constituting a promising approach for early time series classification, when accurate and confident decisions are required.