Project Description
HOW TO ENSURE OPTIMAL PLANNING IN THE HOSPITAL
PREDICTING HOSPITAL BED CAPACITY

BRIEF
A country’s healthcare system is a critical infrastructure that requires long-term capacity planning. Our client, a hospital located in the south of the Netherlands, faced a major bed shortage during the COVID-19 outbreak. In order to plan optimally, avoid logistical problems and take more effective preventive measures, having insight into the number of available hospital beds and patient movements is of the utmost importance.
Moving patients from one ward to another involves more than it seems. Departments often place patients temporarily in free beds from sister wards until their own beds become available. This requires timely coordination, so an early request would reduce logistical problems. With high patient inflows, it is important that the hospital has enough staff to ensure that patients can be properly accommodated and receive clinical care. Last but not least, by gaining insight into the right information, hospital staff could take more efficient preventive action, for instance by carrying out more discharge rounds when there is a peak of patients coming in.
During this project, our Data Science experts supported the client with:
- Patients inflow forecast
- Statistic simulation of patient movements within the hospitals
Dashboard development

CHALLENGES
To ensure accurate simulations, we had to constantly refine the data to obtain a high-quality medical dataset. In addition, it was also a challenge to find a balance where you have to be specific enough to generate an accurate prediction, but not too specific so that you could still run a simulation, otherwise you have no pattern to predict. Last but not least, there was the challenge related to trend distortion; no data were available before COVID-19, which affected the chosen model.

THE CONCEPT
To overcome all the challenges and provide our client with the best possible solution, the team created a hybrid model. We had to ensure that the model could not only predict the number of patients admitted to the hospital, but also indicate upper and lower thresholds with a degree of confidence. This would allow you to strategically plan for worse-case scenarios, so that even if you end up admitting more patients than statistically expected, you still have enough capacity. The information obtained from this prediction would then be used as input to simulate the movement of patients from one ward to another. We then developed a user-friendly dashboard that provides a clear and better overview.
MEDIAAN IN ACTION
During this project, Data Scientists from Mediaan took the lead. We worked closely with our client, especially with their Data Scientists, Data Analysts and Application Specialists. The following methods and technologies were used:
Python
Time-Series Forecasting
Machine Learning
Microsoft SQL
Tableau
Docker
Apache Airflow


RESULTS
Despite the challenges, we were able to help our client solve their problem. The solution we provided gave our client insight into the predicted number of patients inflow and the simulated movement of patients from one ward to another. This resulted in solid predictions of the number of beds needed across the hospital, which was useful for maintaining long-term capacity planning.
WANT TO SEE MORE?