In the Policy Sciences of Harold Lasswell, Douglas Torgerson asks an important question–whether the logic of policy sciences can inspire democratic hope for social betterment. His response is refreshing and psychoanalytically-informed optimism, whereas a jurisprudential detour of the NHS’s legacy as the most important application of policy sciences in another discipline calls for agnosticism. Revisiting the application of policy sciences in international law suggests that the very logic of policy sciences, under the influence of a defective form of naturalism, disables its potential for inclusive democracy.
Objective: Machine learning applications for longitudinal electronic health records often forecast the risk of events at fixed time points, whereas survival analysis achieves dynamic risk prediction by estimating time-to-event distributions. Here, we propose a novel conditional variational autoencoder-based method, DySurv, which uses a combination of static and longitudinal measurements from electronic health records to estimate the individual risk of death dynamically.
Materials and methods: DySurv directly estimates the cumulative risk incidence function without making any parametric assumptions on the underlying stochastic process of the time-to-event. We evaluate DySurv on 6 time-to-event benchmark datasets in healthcare, as well as 2 real-world intensive care unit (ICU) electronic health records (EHR) datasets extracted from the eICU Collaborative Research (eICU) and the Medical Information Mart for Intensive Care database (MIMIC-IV).
Results: DySurv outperforms other existing statistical and deep learning approaches to time-to-event analysis across concordance and other metrics. It achieves time-dependent concordance of over 60% in the eICU case. It is also over 12% more accurate and 22% more sensitive than in-use ICU scores like Acute Physiology and Chronic Health Evaluation (APACHE) and Sequential Organ Failure Assessment (SOFA) scores. The predictive capacity of DySurv is consistent and the survival estimates remain disentangled across different datasets.
Discussion: Our interdisciplinary framework successfully incorporates deep learning, survival analysis, and intensive care to create a novel method for time-to-event prediction from longitudinal health records. We test our method on several held-out test sets from a variety of healthcare datasets and compare it to existing in-use clinical risk scoring benchmarks.
Conclusion: While our method leverages non-parametric extensions to deep learning-guided estimations of the survival distribution, further deep learning paradigms could be explored.
Mobility accounts for the largest share of CO2 emissions generated by tourism industry. The extent of CO2 resulting from tourists' long-distance travel depends strongly on the transport mode used. To reduce these emissions, destinations should engage in promoting a shift from flying and driving to traveling on rail. This study hypothesizes that the entire mobility chain, that is, long-distance travel and mobility at destination, represents an interconnected bundle of services. Using data from a Discrete Choice Experiment conducted with visitors to a tourist destination in Austrian Alps, we estimated the effects of attributes of long-distance travel by personal vehicle and rail (travel time, travel costs, number of transfers) and effects of attributes of local mobility services offered at the destination (transit frequency, carsharing, mobility hub). The outcomes indicate that local mobility services are highly relevant for transport mode choice of tourists and can increase the market share of rail significantly.