Master’s Thesis by Josefine Letzner, in cooperation with KTH, the Royal Institute of Technology in Stockholm, Sweden. 

Abstract

The selection of hospital once an ambulance has picked up its patient is today decided by the ambulance staff. This report describes a supervised machine learning approach for predicting hospital selection. This is a multi-class classification problem. The performance of random forest, logistic regression and neural network were compared to each other and to a baseline, namely the one rule-algorithm. The algorithms were applied to real world data from SOS Alarm, the company that operate Sweden’s emergency call services. Performance was measured with accuracy and f1-score. Random Forest got the best result followed by neural network. Logistic regression exhibited slightly inferior results but still performed far better than the baseline. The results point toward machine learning being a suitable method for learning the problem of hospital selection.

Conclusion

The main question to investigate with this project was to determine whether or not machine learning is a suitable task for predicting, and hence learning, the decision of hospital selection. It seems that machine learning is a possible tool for predicting this choice. The algorithms were clearly able to learn from the data and the results were significantly better than baseline.

More information

Letzner, Josefine. Analysis of Emergency Medical Transport Datasets using Machine Learning (2017).

Read more and download the Master’s Thesis as pdf