Work-Time Distribution of Physicians at a German University Hospital

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.

[Outsourcing of nursing staff costs in psychiatry? : A secondary data analysis of possible effects on the remuneration system in psychiatry]

BACKGROUND

Nursing staff were excluded from the German DRG system for somatic hospital treatment and will be funded separately in the future. In psychiatry and psychosomatic medicine, binding personnel requirements have been defined but there has been no regulation of how these personnel requirements are adequately financed.

OBJECTIVE

The objective of this study was to analyze the costs of inpatient psychiatry and psychosomatic medicine and to evaluate possible effects of funding nursing staff separately.

MATERIAL AND METHODS

This analysis is based on aggregated daily treatment costs of selected hospitals (data year 2018), which annually submit their performance and cost data to the Institute for the Hospital Remuneration System (InEK) for the empirical further development of the remuneration system.

RESULTS

Nursing staff represent the largest cost factor in inpatient psychiatry and psychosomatic medicine. Excluding nursing staff drastically reduces the variance of psychiatric DRG renumeration and even exceeds its proportion of the total costs. After outsourcing nursing costs, psychiatric DRGs achieve only a very limited cost separation.

CONCLUSION

The binding personnel requirements necessitate adequate financing of nursing staff. This raises the debate about the further development of psychiatric remuneration. The question arises as to whether the effort associated with using the psychiatric DRG system justifies its usefulness as an instrument for budgeting when core functions such as cost separation are only given to a limited extent. Alternative approaches to budgeting should also be examined for putting costs and benefits in a better ratio.

[Residency program under scrutiny (part 2)-How do residents prepare for emergency operations?]

BACKGROUND

Postgraduate medical education in trauma and orthopedic surgery residents largely relates to learning and teaching surgery. During this crucial stage of surgical development some of the didactic challenges are caused by heterogeneous and contradictory expectations of trainees and trainers alike. So how do residents prepare for emergency surgery? To date there is neither an expert consensus nor scientific investigations in the clinical context on this topic.

METHODS

Between February and April 2015 questionnaires were issued to all physicians active in the field of trauma and orthopedic surgery within the Trauma Network East Bavaria (27 clinics, 255 physicians). The participants were asked to rate the importance of certain elements functioning in the preparation of two emergency operations using a Likert scale. The intensity with which residents generally realize these elements of preparation was also documented. The aim was to objectify if and to what extent the presumed normal practices diverge from clinical reality.

RESULTS

A total of 150 questionnaires were analyzed (return rate 59%). Discussion with the consultant (85.3%, n = 128), examination of the patient (80.0%, n = 120), surgical approach (76.0%, n = 114) and study of patient files (68.0%, n = 102) were considered to be the most important elements; however, many of the participants admitted that these elements of preparation are not sufficiently performed.

CONCLUSION

The personal preparation of residents for an emergency operation should be classified as extremely important; however, the requirements and reality do not seem to hold true in the clinical environment. This seems to be most likely due to structural and organizational issues.

Predicting patient outcomes in psychiatric hospitals with routine data: a machine learning approach

BACKGROUND

A common problem in machine learning applications is availability of data at the point of decision making. The aim of the present study was to use routine data readily available at admission to predict aspects relevant to the organization of psychiatric hospital care. A further aim was to compare the results of a machine learning approach with those obtained through a traditional method and those obtained through a naive baseline classifier.

METHODS

The study included consecutively discharged patients between 1st of January 2017 and 31st of December 2018 from nine psychiatric hospitals in Hesse, Germany. We compared the predictive performance achieved by stochastic gradient boosting (GBM) with multiple logistic regression and a naive baseline classifier. We tested the performance of our final models on unseen patients from another calendar year and from different hospitals.

RESULTS

The study included 45,388 inpatient episodes. The models' performance, as measured by the area under the Receiver Operating Characteristic curve, varied strongly between the predicted outcomes, with relatively high performance in the prediction of coercive treatment (area under the curve: 0.83) and 1:1 observations (0.80) and relatively poor performance in the prediction of short length of stay (0.69) and non-response to treatment (0.65). The GBM performed slightly better than logistic regression. Both approaches were substantially better than a naive prediction based solely on basic diagnostic grouping.

CONCLUSION

The present study has shown that administrative routine data can be used to predict aspects relevant to the organisation of psychiatric hospital care. Future research should investigate the predictive performance that is necessary to provide effective assistance in clinical practice for the benefit of both staff and patients.

The impact of medical documentation assistants on process performance measures in a surgical emergency department

BACKGROUND

The administrative work of physicians, particularly documentation effort, consumes considerable time in surgical emergency departments. At the same time, the latter face an ever-growing influx of patients, leading to increasing waiting and flow times and thus patient dissatisfaction as well as overload of physicians and nurses. The deployment of medical documentation assistants, who specialize in and undertake documentation work currently performed by physicians, poses a solution to the problem. The goal of this study is to assess the impact of deploying medical documentation assistants on key performance indicators of a surgical emergency department, i.e. waiting and flow times of patients differentiated according to triage categories, utilization of physicians and time allocation of physicians.

METHODS

The underlying study has analysed the processes of the surgical emergency department of a major university medical centre and modelled them in a discrete event simulation. Data on patient arrivals as well as processing times in the X-ray department and the laboratory were obtained from the clinical information system, while processing times in the emergency department were recorded using time-motion studies. Though the emergency department currently does not deploy medical documentation assistants, the simulation model includes a variable number of such assistants.

RESULTS

The deployment of a medical documentation assistant frees up physician working time and decreases the waiting time and consequently the flow time of patients, in particular for standard and non-urgent patients. Adding additional documentation assistants leads to further improvements, however, with diminishing marginal returns. Under the assumption of medical documentation assistants being 35% more efficient than physicians in undertaking documentation work, one of the three physicians can be replaced in the analysed surgical emergency department with an average of 502 patient arrivals per week.

CONCLUSIONS

Medical documentation assistants are a viable way of improving the performance of surgical emergency departments. Depending on the goals of the hospital, medical documentation assistants can be used for an array of measures such as decreasing patients' waiting and flow times or increasing physicians' time spent on medical treatment.