Emergency Department Visit Forecasting and Dynamic Nursing Staff Allocation Using Machine Learning Techniques With Readily Available Open-Source Software.

Although emergency department visit forecasting can be of use for nurse staff planning, previous research has focused on models that lacked sufficient resolution and realistic error metrics for these predictions to be applied in practice. Using data from a 1100-bed specialized care hospital with 553,000 patients assigned to its healthcare area, forecasts with different prediction horizons, from 2 to 24 weeks ahead, with an 8-hour granularity, using support vector regression, M5P, and stratified average time-series models were generated with an open-source software package. As overstaffing and understaffing errors have different implications, error metrics and potential personnel monetary savings were calculated with a custom validation scheme, which simulated subsequent generation of predictions during a 4-year period. Results were then compared with a generalized estimating equation regression. Support vector regression and M5P models were found to be superior to the stratified average model with a 95% confidence interval. Our findings suggest that medium and severe understaffing situations could be reduced in more than an order of magnitude and average yearly savings of up to €683,500 could be achieved if dynamic nursing staff allocation was performed with support vector regression instead of the static staffing levels currently in use.

Lifting the weight of a diagnosis-related groups family change: a comparison between refined and non-refined DRG systems for top-down cost accounting and efficiency indicators.

Public healthcare providers in all Spanish Regions - Autonomous Communities (ACs) use All Patients Diagnosis-Related Groups (AP-DRGs) for billing non-insured patients, cost accounting and inpatient efficiency indicators. A national migration to All Patients Refined Diagnosis-Related Groups (APR-DRGs) has been scheduled for 2016. The analysis was performed on 202,912 inpatient care episodes ranging from 2005 to 2010. All episodes were grouped using AP-DRG v25.0 and APR-DRG v24.0. Normalised DRG weight variations for an AP-DRG to APR-DRG migration scenario were calculated and compared. Major differences exist between normalised weights for inpatient episodes depending on the DRGs family used. The usage of the APR-DRG system in Spain without any adjustments, as it was developed in the United States, should be approached with care. In order to avoid reverse incentives and provider financial risks, coding practices should be reviewed and structural differences between DRG families taken into account.