Forecasting admissions in psychiatric hospitals before and during Covid-19: a retrospective study with routine data

The COVID-19 pandemic has strong effects on most health care systems. Forecasting of admissions can help for the efficient organisation of hospital care. We aimed to forecast the number of admissions to psychiatric hospitals before and during the COVID-19 pandemic and we compared the performance of machine learning models and time series models. This would eventually allow to support timely resource allocation for optimal treatment of patients. We used admission data from 9 psychiatric hospitals in Germany between 2017 and 2020. We compared machine learning models with time series models in weekly, monthly and yearly forecasting before and during the COVID-19 pandemic. A total of 90,686 admissions were analysed. The models explained up to 90% of variance in hospital admissions in 2019 and 75% in 2020 with the effects of the COVID-19 pandemic. The best models substantially outperformed a one-step seasonal naïve forecast (seasonal mean absolute scaled error (sMASE) 2019: 0.59, 2020: 0.76). The best model in 2019 was a machine learning model (elastic net, mean absolute error (MAE): 7.25). The best model in 2020 was a time series model (exponential smoothing state space model with Box-Cox transformation, ARMA errors and trend and seasonal components, MAE: 10.44). Models forecasting admissions one week in advance did not perform better than monthly and yearly models in 2019 but they did in 2020. The most important features for the machine learning models were calendrical variables. Model performance did not vary much between different modelling approaches before the COVID-19 pandemic and established forecasts were substantially better than one-step seasonal naïve forecasts. However, weekly time series models adjusted quicker to the COVID-19 related shock effects. In practice, multiple individual forecast horizons could be used simultaneously, such as a yearly model to achieve early forecasts for a long planning period and weekly models to adjust quicker to sudden changes.

A comprehensive modelling framework to forecast the demand for all hospital services

BACKGROUND

Because of increasing demand, hospitals in England are currently under intense pressure resulting in shortages of beds, nurses, clinicians, and equipment. To be able to effectively cope with this demand, the management needs to accurately find out how many patients are expected to use their services in the future. This applies not just to one service but for all hospital services.

PURPOSE

A forecasting modelling framework is developed for all hospital's acute services, including all specialties within outpatient and inpatient settings and the accident and emergency (A&E) department. The objective is to support the management to better deal with demand and plan ahead effectively.

METHODOLOGY/APPROACH

Having established a theoretical framework, we used the national episodes statistics dataset to systematically capture demand for all specialties. Three popular forecasting methodologies, namely, autoregressive integrated moving average (ARIMA), exponential smoothing, and multiple linear regression were used. A fourth technique known as the seasonal and trend decomposition using loess function (STLF) was applied for the first time within the context of health-care forecasting.

RESULTS

According to goodness of fit and forecast accuracy measures, 64 best forecasting models and periods (daily, weekly, or monthly forecasts) were selected out of 760 developed models; ie, demand was forecasted for 38 outpatient specialties (first referrals and follow-ups), 25 inpatient specialties (elective and non-elective admissions), and for A&E.

CONCLUSION

This study has confirmed that the best demand estimates arise from different forecasting methods and forecasting periods (ie, one size does not fit all). Despite the fact that the STLF method was applied for the first time, it outperformed traditional time series forecasting methods (ie, ARIMA and exponential smoothing) for a number of specialties.

PRACTISE IMPLICATIONS

Knowing the peaks and troughs of demand for an entire hospital will enable the management to (a) effectively plan ahead; (b) ensure necessary resources are in place (eg, beds and staff); (c) better manage budgets, ensuring enough cash is available; and (d) reduce risk.

A decision support system for demand and capacity modelling of an accident and emergency department

Accident and emergency (A&E) departments in England have been struggling against severe capacity constraints. In addition, A&E demands have been increasing year on year. In this study, our aim was to develop a decision support system combining discrete event simulation and comparative forecasting techniques for the better management of the Princess Alexandra Hospital in England. We used the national hospital episodes statistics data-set including period April, 2009 - January, 2013. Two demand conditions are considered: the expected demand condition is based on A&E demands estimated by comparing forecasting methods, and the unexpected demand is based on the closure of a nearby A&E department due to budgeting constraints. We developed a discrete event simulation model to measure a number of key performance metrics. This paper presents a crucial study which will enable service managers and directors of hospitals to foresee their activities in future and form a strategic plan well in advance.

Management decision of hospital surge: assessing seasonal upsurge in inpatient medical bed occupancy rate among public acute hospitals in Hong Kong

BACKGROUND

There were recurrent upsurges in demand for public hospital services in Hong Kong. An understanding of the contribution of some possible factors for the rise in health care burden would help to inform hospital management strategies.

AIM

To evaluate the utilization patterns of hospitalizations in medical wards among public acute hospitals in Hong Kong during surge periods.

DESIGN

Retrospective study.

METHODS

By extracting the information in press releases between 2014 and 2018, descriptive statistics about medical ward occupancy situation during six surge periods were generated. A time series model was constructed to estimate the occupancy rate at each hospital and assess its relationship with the intensity of seasonal influenza activity, extreme weather, day of week and long holidays.

RESULTS

There was a significant increase in the number of admissions to medical wards in all six surge periods. A significant variation in occupancy rate between weekdays and geographic regions was observed. The occupancy rate in 10, out of 15, hospitals was significantly associated with the influenza activity, while there was limited effect of weather on the occupancy rate. A significant holiday effect was observed during Christmas and Chinese New Year, resulting in a lower bed occupancy rate.

CONCLUSIONS

A differential burden in public hospitals during surge periods was reported. Contingency bed and staff management shall be tailored to individual hospitals, given their differences in the determinants for inpatient bed occupancy.

[The trial of business data analysis at the Department of Radiology by constructing the auto-regressive integrated moving-average (ARIMA) model]

This study aimed to contribute to the management of a healthcare organization by providing management information using time-series analysis of business data accumulated in the hospital information system, which has not been utilized thus far. In this study, we examined the performance of the prediction method using the auto-regressive integrated moving-average (ARIMA) model, using the business data obtained at the Radiology Department. We made the model using the data used for analysis, which was the number of radiological examinations in the past 9 years, and we predicted the number of radiological examinations in the last 1 year. Then, we compared the actual value with the forecast value. We were able to establish that the performance prediction method was simple and cost-effective by using free software. In addition, we were able to build the simple model by pre-processing the removal of trend components using the data. The difference between predicted values and actual values was 10%; however, it was more important to understand the chronological change rather than the individual time-series values. Furthermore, our method was highly versatile and adaptable compared to the general time-series data. Therefore, different healthcare organizations can use our method for the analysis and forecasting of their business data.