Patients requiring prolonged mechanical ventilation (PMV), defined as receiving mechanical ventilation for longer than 21 days, affects 5-10% of all patients requiring mechanical ventilation. PMV has led to a substantial economic and ethic impacts in Taiwan and the world, and there is a unmet of using multifaceted time-series data to establish prediction model for the treatment outcomes, including weaning from ventilator and overall survival. There is still lack of predictive model for PMV by using electronic health records (EHR). EHR has been successfully used for predicting occurrences of a variety of diseases. However, inadequate predictive performances have been observed in cases of rare occurrences due to both insufficient training samples and highly imbalanced class distribution.

In our recent work, we have successfully applied active data augmenter for young stroke prediction and deep multimodal fusion algorithms for bleeding event prediction. These methods can achieve higher performance for prediction of disease occurrence than traditional approaches. In this study project, clinical databases will be analyzed by using deep multimodal fusion algorithms with active data augmenter approach. We aim to use the novel method for leveraging cross database information to achieve an intelligent prediction model for PMV.