The value of probabilistic forecasting in emergency medical resource planning under uncertainty

PurposeMost epidemic transmission forecasting methods can only provide deterministic outputs. This study aims to show that probabilistic forecasting, in contrast, is suitable for stochastic demand modeling and emergency medical resource planning under uncertainty.Design/methodology/approachTwo probabilistic forecasting methods, i.e. quantile regression convolutional neural network and kernel density estimation, are combined to provide the conditional quantiles and conditional densities of infected populations. The value of probabilistic forecasting in improving decision performances and controlling decision risks is investigated by an empirical study on the emergency medical resource planning for the COVID-19 pandemic.FindingsThe managerial implications obtained from the empirical results include (1) the optimization models using the conditional quantile or the point forecasting result obtain better results than those using the conditional density; (2) for sufficient resources, decision-makers' risk preferences can be incorporated to make tradeoffs between the possible surpluses and shortages of resources in the emergency medical resource planning at different quantile levels; and (3) for scarce resources, the differences in emergency medical resource planning at different quantile levels greatly decrease or disappear because of the existing of forecasting errors and supply quantity constraints.Originality/valueVery few studies concern probabilistic epidemic transmission forecasting methods, and this is the first attempt to incorporate deep learning methods into a two-phase framework for data-driven emergency medical resource planning under uncertainty. Moreover, the findings from the empirical results are valuable to select a suitable forecasting method and design an efficient emergency medical resource plan.

Evaluation of the Quality of Medical Care to the Population at the Level of Day Stations and Emergency Stations

Insufficient availability of emergency medical services to the rural population is noted. The dynamics of the growth of calls to emergency medical services testifies to the fact that emergency medical institutions have taken over part of inpatient services for the provision of emergency care to patients with chronic diseases and acute colds.

A registry-based observational study comparing emergency calls assessed by emergency medical dispatchers with and without support by registered nurses

Background The requirement concerning formal education for emergency medical dispatcher (EMD) is debated and varies, both nationally and internationally. There are few studies on the outcomes of emergency medical dispatching in relation to professional background. This study aimed to compare calls handled by an EMD with and without support by a registered nurse (RN), with respect to priority level, accuracy, and medical condition. Methods A retrospective observational study, performed on registry data from specific regions during 2015. The ambulance personnel’s first assessment of the priority level and medical condition was used as the reference standard. Outcomes were: the proportion of calls dispatched with a priority in concordance with the ambulance personnel’s assessment; over- and undertriage; the proportion of most adverse over- and undertriage; sensitivity, specificity and predictive values for each of the ambulance priorities; proportion of calls dispatched with a medical condition in concordance with the ambulance personnel’s assessment. Proportions were reported with 95% confidence intervals. χ2-test was used for comparisons. P-levels < 0.05 were regarded as significant. Results A total of 25,025 calls were included (EMD n = 23,723, EMD + RN n = 1302). Analyses relating to priority and medical condition were performed on 23,503 and 21,881 calls, respectively. A dispatched priority in concordance with the ambulance personnel’s assessment were: EMD n = 11,319 (50.7%) and EMD + RN n = 481 (41.5%) (p < 0.01). The proportion of overtriage was equal for both groups: EMD n = 5904, EMD + RN n = 306, (26.4%) p = 0.25). The proportion of undertriage for each group was: EMD n = 5122 (22.9%) and EMD + RN n = 371 (32.0%) (p < 0.01). Sensitivity for the most urgent priority was 54.6% for EMD, compared to 29.6% for EMD + RN (p < 0.01), and specificity was 67.3% and 84.8% (p < 0.01) respectively. A dispatched medical condition in concordance with the ambulance personnel’s assessment were: EMD n = 13,785 (66.4%) and EMD + RN n = 697 (62.2%) (p = 0.01). Conclusions A higher precision of emergency medical dispatching was not observed when the EMD was supported by an RN. How patient safety is affected by the observed divergence in dispatched priorities is an area for future research.