Hybrid deep learning with stacked dilated causal convolutions for health forecasting using multivariate time-series data

Abstract

Health forecasting using time-series data facilitates preventive medicine and healthcare interventions by predicting future health events. This thesis introduces a novel hybrid deep-learning architecture for health forecasting that combines the Stackeddilated-causal Convolutional Neural Network and Bidirectional Long Short-Term Memory (SCNN-BiLSTM). Stacked-dilated-causal Convolutional Neural Networks provide full history-coverage of the input window while maintaining the causal structure such that each output in a temporal sequence depends on all previous elements. Two use-case scenarios were studied to examine the effectiveness of the proposed SCNNBiLSTM architecture: (1) hospital admission forecasting for mental health patients and (2) infectious disease forecasting. In hospital admission forecasting, the number of admissions for mental health patients at the Thunder Bay Regional Health Sciences Centre was predicted using multivariate time-series data. In the one-step forecast, the CNN-BiLSTM hybrid model outperformed various statistical and neural network techniques. Consequently, this hybrid model involving a standard CNN was compared with the proposed SCNNBiLSTM to determine if having full history-coverage improved forecasting performance for long-term forecasting. This experiment revealed that the SCNN-BiLSTM outperformed the standard CNN-BiLSTM hybrid model for multi-step forecasting. [...]