Longitudinal healthcare analytics for disease management: Empirical demonstration for low back pain
Authors: Mueller-Peltzer, Michael; Feuerriegel, Stefan; Molgaard Nielsen, Anne; Kongsted, Alice; Vach, Werner; Neumann, Dirk
Journal: Decision Support Systems (2020)
DOI: 10.1016/j.dss.2020.113271
Clinician guidelines recommend health management to tailor the form of care to the expected course of diseases Hence, in order to decide upon a suitable treatment plan, health professionals benefit from decision support, i.e., predictions about how a disease is to evolve. In clinical practice, such a prediction model requires interpretability. Interpretability, however, is often precluded by complex dynamic models that would be capable of capturing the intrapersonal variability of disease trajectories. Therefore, we develop a cross-sectional ARMA model that allows for inference of the expected course of symptoms. Distinct from traditional time series models, it generalizes to cross-sectional settings and thus patient cohorts (i.e., it is estimated to multiple instead of single disease trajectories). Our model is evaluated according to a longitudinal 52-week study involving 928 patients with low back pain. It achieves a favorable prediction performance while maintaining interpretability. In sum, we provide decision support by informing health professionals about whether symptoms will have the tendency to stabilize or continue to be severe