Annals of Data Science https://doi.org/10.1007/s40745-019-00223-6 Patient Discharge Classification Using Machine Learning Techniques Anthony Gramaje 1 · Fadi Thabtah 1 · Neda Abdelhamid 2 · Sayan Kumar Ray 1 Received: 20 March 2019 / Revised: 9 May 2019 / Accepted: 22 May 2019 © Springer-Verlag GmbH Germany, part of Springer Nature 2019 Abstract Patient discharge is one of the critical processes for medical providers from any health facility to transfer the care of the patient to another care provider after hospitalisa- tion. The discharge plan, final clinical and physical checks, patient education, patient readiness, and general practitioner appointments play an important role in the suc- cess of this procedure. However, it has loopholes that need to be addressed to lessen the complexity of managing this critical process. When this is left unchecked, seri- ous consequences and challenges may occur such as re-hospitalisation and financial pressure. This research investigates machine learning technology on the problem of patient discharge by using a real dataset. In particular, the applicability of techniques including Decision Trees, Bayes Net, and Random Forest have been investigated in order to predict the discharge outcome of a patient after surgery. The results of the analysis show that Bayes Net performed better than Decision Tree, and Random Forest in predicting the response variable (class) using tenfold cross validation with respect to classification accuracy. The target audiences of this research are the staff working in a healthcare facility such as clinicians, chief medical officer, and physicians among others. Keywords Bayes Net · Data analytics · Data processing · Hospitalisation · Machine learning · Patient discharge · Random Forest B Neda Abdelhamid Nedah@ais.ac.nz Anthony Gramaje gram10@manukaumail.com Fadi Thabtah fadi.fayez@manukau.ac.nz Sayan Kumar Ray Sayan.Ray@manukau.ac.nz 1 School of Digital Technologies, Manukau Campus & Manukau Train Station Davies Ave, Manukau, Auckland 2104, New Zealand 2 Auckland Institute of Studies, 28A Linwood Ave, Mount Albert, Auckland 1025, New Zealand 123