Improving the forecasting of hospital services: A comparison between projections and actual utilization of hospital services

Does increasing the number of beds or health workers contribute to the rational use of scarce public health resources?

Turkey makes substantial investments to increase the number of qualified beds in hospitals, the shortage in health professionals remains one of the main obstacles of the health system in the country. To address this research gap, the study aims to formulate a rational solution for the dilemma on whether to invest in beds or health professionals contribute to the rational use of scarce public health resources. Data for testing the model were derived from the Turkish Statistical Institute across 81 provinces in Turkey. The path analytic approach was used to determine the associations among hospital size, utilization/facility, health workforce, and indicators of health outcomes. The results point to a strong link between quantity of qualified beds, utilization of health services, and facility indicators, and health workforce. Rational use of scarce resources, optimal capacity planning, and increased quantity of health professionals will be beneficial for the sustainability of health care services.

Internal Regulation Center in hospitals: Repercussions of its implementation on the health services' indicators

Objective

To evaluate the hospital indicators and their repercussions on the number of monthly admissions to a public university hospital, before and after implementing the Internal Regulation Center.

Method

An evaluative research study, of the Case Study type, developed in a public university hospital. A total of 28 indicators related to structure, production, productivity and quality were measured, which are part of internal Benchmarking. The data were analyzed by means of descriptive statistics and multiple regression to identify the independent factors and those associated with the number of monthly hospitalizations with 95% confidence intervals.

Results

Implementation of the Center significantly increased (p<0.001) the number of discharges, the bed utilization factor and the bed renewal rate, emergency hospitalization, bed occupancy percentage, surgical procedures performed and the patient-day mean value (p=0.027). There was a reduction (p<0.001) in the number of visits to the medical, obstetric and orthopedic emergency room, in the rates of in-hospital infection and infant mortality, as well as a mean reduction of 0.81/day, approximately one day less of hospitalization per patient, or a gain of 40 available beds per month.

Conclusion

Although the number of available beds was lower in the post-implementation period, the bed replacement interval was reduced, representing an increase of 40 more beds per month due to the reduction in the patients’ length of stay in the institution.

Productivity analysis of regional-level hospital care in the Czech republic and Slovak Republic

Background

Providing hospital care is an essential objective of national health policies. The countries that share common history, when they emerged from the same health system and similar conditions in the early 1990s, after the division of Czechoslovakia, became the objects of evaluation of the development of technical efficiency of hospital care. The subsequent development of their health care system also was very similar, but no longer entirely identical. The article aims to identify the trends and disparities in the productivity of the capacities of hospital care on the regional level (NUTS III.) in the Czech Republic and the Slovak Republic in 2009–2018 before the COVID-19 pandemic using the multi-criteria decision methods.

Methods

The window analysis as a dynamic DEA method based on moving averages and also the Malmquist Index, that allows the evaluation of changes in relative efficiency and of changes in the production possibilities frontier have become the key methods for evaluating the over time efficiency evolution. To model technical efficiency, an output-oriented method assuming constant returns to scale was chosen. Aggregated input and output parameters for each region were the object of study.

Results

The results showed that differences in the efficiency trends in terms of the examined parameters among the individual regions are slightly greater in the Czech Republic than in the Slovak Republic. The least efficient regions are those where capital cities are located. Furthermore, the analysis showed that in 2018 all of the Slovak Republic regions improved its productivity compared to 2009 and that technological conditions had a significant impact on this improvement. The results of the Czech Republic regions show productivity improvement in 57% of the regions that, on the contrary, was due to changes in technical efficiency.

Conclusions

It should be recommended to the state- and regional-level governments to refrain from unilaterally preferring the orientation of public policies on the efficiency of the provision of hospital care, and rather focus on increasing the quality and availability of hospital care, especially in smaller, rural, and border regions, in the interest of population safety during pandemics and other emergencies.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12913-022-07471-y.

How New Mexico Leveraged a COVID-19 Case Forecasting Model to Preemptively Address the Health Care Needs of the State: Quantitative Analysis

BACKGROUND

Prior to the COVID-19 pandemic, US hospitals relied on static projections of future trends for long-term planning and were only beginning to consider forecasting methods for short-term planning of staffing and other resources. With the overwhelming burden imposed by COVID-19 on the health care system, an emergent need exists to accurately forecast hospitalization needs within an actionable timeframe.

OBJECTIVE

Our goal was to leverage an existing COVID-19 case and death forecasting tool to generate the expected number of concurrent hospitalizations, occupied intensive care unit (ICU) beds, and in-use ventilators 1 day to 4 weeks in the future for New Mexico and each of its five health regions.

METHODS

We developed a probabilistic model that took as input the number of new COVID-19 cases for New Mexico from Los Alamos National Laboratory's COVID-19 Forecasts Using Fast Evaluations and Estimation tool, and we used the model to estimate the number of new daily hospital admissions 4 weeks into the future based on current statewide hospitalization rates. The model estimated the number of new admissions that would require an ICU bed or use of a ventilator and then projected the individual lengths of hospital stays based on the resource need. By tracking the lengths of stay through time, we captured the projected simultaneous need for inpatient beds, ICU beds, and ventilators. We used a postprocessing method to adjust the forecasts based on the differences between prior forecasts and the subsequent observed data. Thus, we ensured that our forecasts could reflect a dynamically changing situation on the ground.

RESULTS

Forecasts made between September 1 and December 9, 2020, showed variable accuracy across time, health care resource needs, and forecast horizon. Forecasts made in October, when new COVID-19 cases were steadily increasing, had an average accuracy error of 20.0%, while the error in forecasts made in September, a month with low COVID-19 activity, was 39.7%. Across health care use categories, state-level forecasts were more accurate than those at the regional level. Although the accuracy declined as the forecast was projected further into the future, the stated uncertainty of the prediction improved. Forecasts were within 5% of their stated uncertainty at the 50% and 90% prediction intervals at the 3- to 4-week forecast horizon for state-level inpatient and ICU needs. However, uncertainty intervals were too narrow for forecasts of state-level ventilator need and all regional health care resource needs.

CONCLUSIONS

Real-time forecasting of the burden imposed by a spreading infectious disease is a crucial component of decision support during a public health emergency. Our proposed methodology demonstrated utility in providing near-term forecasts, particularly at the state level. This tool can aid other stakeholders as they face COVID-19 population impacts now and in the future.

Models and methods for determining the optimal number of beds in hospitals and regions: a systematic scoping review

BACKGROUND

Determining the optimal number of hospital beds is a complex and challenging endeavor and requires models and techniques which are sensitive to the multi-level, uncertain, and dynamic variables involved. This study identifies and characterizes extant models and methods that can be used to determine the required number of beds at hospital and regional levels, comparing their advantages and challenges.

METHODS

A systematic search was conducted using Web of Science, Scopus, Embase and PubMed databases, with the search terms hospital bed capacity, hospital bed need, hospital, bed size, model, and method.

RESULTS

Twenty-three studies met the criteria to be included in the review. Of these studies, a total of 11 models and 5 methods were identified, mainly designed to determine hospital bed capacity at the regional level. Common determinants of the required number of hospital beds in these models included demographic changes, average length of stay, admission rates, and bed occupancy rates.

CONCLUSIONS

There are no specific norms for the required number of beds at hospital and regional levels, but some of the identified models and methods may be used to estimate this number in different contexts. Moreover, it is important to consider alternative approaches to planning hospital capacity like care pathways to fix the limitations of "bed numbers".

Predicting Outpatient Appointment Demand Using Machine Learning and Traditional Methods

Traditional methods have long been used for clinical demand forecasting. Machine learning methods represent the next evolution in forecasting, but model choice and optimization remain challenging for achieving optimal results. To determine the best method to predict demand for outpatient appointments comparing machine learning and traditional methods, this retrospective study analyzed "appointment requests" at a major outpatient department in a destination medical center. Two separate locations (A and B) were assessed with 20 traditional, hybrid (traditional + machine learning) and machine learning methods to determine the best forecasting outcome (lowest Forecast Standard Error, FSE). Data characteristics from both datasets were examined. 20 forecasting models were then assessed and compared for the best result. Location A's data displayed a cyclical and non-trending pattern while Location B's displayed a cyclical and trending pattern. Both Location A and B yielded the feature engineered XGBoost model (machine learning) with the lowest out-of-sample FSE. It is important to carefully analyze and understand the underlying data set pattern and then test a variety of traditional, machine learning, and hybrid prediction methods to achieve optimal predictive results. Additionally, the use of feature engineering or hybrid methods can augment the usefulness of machine learning methods.