Machine learning for COPD exacerbation prediction

Introduction: TelEPOC is a telemedicine project developed for COPD patients with frequent admissions in the hospital. Machine Learning (ML) is a branch of AI focused in developing software that enables computers to learn patterns and use them to predict the outcome of previously unseen events. Objectives: In this work we show an Early Warning System (EWS), based on ML, that is capable of predicting when a patient of the TelEPOC program is going to exacerbate. Also, we find the configuration to make the system optimal both from the medical and computational points of view. Besides we will identify the most informative factors to predict the exacerbations. Methods: TelEPOC database is composed by daily reports sent by the patients with the following information: heart rate, temperature, oxygen saturation, respiratory rate, steps walked and a questionnaire form about symptoms. According to this, an alarm system composed by three levels of exacerbation (green, yellow and red) is established. On this data the Random Forests Algorithm was applied to predict when a patient will present a red alarm. We used a 10-fold cross validation to estimate the performance of the model. The development was implemented using the packages Scikit-Learn and Pandas from the programming language Python. Results and Conclusions: We achieved an Area under the ROC curve of 0.87 for the task of predicting whether a patient will suffer an exacerbation within the next three days. The EWS was capable of making reliable predictions with enough time in advance when a patient is going to present a red alarm. The more informative variables for this prediction were the heart rate and the number of walked steps. Partially funded by SEPAR grant 156|2012.