Healthcare data is inherently sequential, encompassing time-series signals and longitudinal records. This chapter reviews key techniques for modeling such data, including recurrent neural networks, long short-term memory networks, one-dimensional convolutional neural networks, and bidirectional encoder representations from transformers for contextual text analysis. Interpretable models like generalized additive models are also discussed. Beyond deep learning, temporal feature extraction methods–such as wavelet time scattering, recurrence plots, fuzzy recurrence plots, and semi-variograms–as well as scalable recurrence graph networks for structured sequence modeling are explored. Together, these approaches provide powerful tools for advancing diagnostic accuracy and predictive healthcare analytics.