Emergency Care Units (ECUs) are medical facilities that deal with unplanned patient turnout, for a very large range of conditions, often urgent or acute, and frequently life-threatening. Therefore, ECUs need to find a difficult balance between having enough resources (human and others) to deal with an unexpected surge in patients, while reducing wasteful practices of sustaining more resources than required. Thus, timely information regarding possible variations in patient inflow is fundamental for proper planning and quality of service. But since a large number of reasons lead people to ECUs, hospital admissions vary significantly. From acute events, to lack of alternatives, or just out of concern, different reasons have different underlying dynamics, and are guided by different factors, timings, and motivations. Thus, a combination of uncertainty and large variability, makes the problem of emergency forecasting a very complex challenge, with great impact on quality of care.
We focus on top drivers of ECU seeking behavior and use a Data Science and Machine Learning (ML) approach to ask:
- How do emergency peaks vary (in seasonal and non-seasonal periods)?
- What external factors might predict such variation?
- Can we offer short-term predictions to help decision-makers and reduce uncertainty in ECU patient inflow?
This project is being developed in collaboration with Claudia Soares and is supported by an FCT research grant.