Xing Han Lu1, Aihua Liu2, Shih-Chieh Fuh1, Yi Lian3, Liming Guo2, Yi Yang4, Ariane Marelli2, Yue Li1. 1. School of Computer Science, McGill University, Montreal, Canada. 2. McGill Adult Unit for Congenital Heart Disease Excellence (MAUDE Unit), Montreal, Canada. 3. Department of Epidemiology, Biostatistics and Occupational Health, McGill University, Montreal, Canada. 4. Department of Mathematics and Statistics, McGill University, Montreal, Canada.
Abstract
MOTIVATION: Recurrent neural networks (RNN) are powerful frameworks to model medical time series records. Recent studies showed improved accuracy of predicting future medical events (e.g., readmission, mortality) by leveraging large amount of high-dimensional data. However, very few studies have explored the ability of RNN in predicting long-term trajectories of recurrent events, which is more informative than predicting one single event in directing medical intervention. METHODS: In this study, we focus on heart failure (HF) which is the leading cause of death among cardiovascular diseases. We present a novel RNN framework named Deep Heart-failure Trajectory Model (DHTM) for modelling the long-term trajectories of recurrent HF. DHTM auto-regressively predicts the future HF onsets of each patient and uses the predicted HF as input to predict the HF event at the next time point. Furthermore, we propose an augmented DHTM named DHTM+C (where "C" stands for co-morbidities), which jointly predicts both the HF and a set of acute co-morbidities diagnoses. To efficiently train the DHTM+C model, we devised a novel RNN architecture to model disease progression implicated in the co-morbidities. RESULTS: Our deep learning models confers higher prediction accuracy for both the next-step HF prediction and the HF trajectory prediction compared to the baseline non-neural network models and the baseline RNN model. Compared to DHTM, DHTM+C is able to output higher probability of HF for high-risk patients, even in cases where it is only given less than 2 years of data to predict over 5 years of trajectory. We illustrated multiple non-trivial real patient examples of complex HF trajectories, indicating a promising path for creating highly accurate and scalable longitudinal deep learning models for modeling the chronic disease.
MOTIVATION: Recurrent neural networks (RNN) are powerful frameworks to model medical time series records. Recent studies showed improved accuracy of predicting future medical events (e.g., readmission, mortality) by leveraging large amount of high-dimensional data. However, very few studies have explored the ability of RNN in predicting long-term trajectories of recurrent events, which is more informative than predicting one single event in directing medical intervention. METHODS: In this study, we focus on heart failure (HF) which is the leading cause of death among cardiovascular diseases. We present a novel RNN framework named Deep Heart-failure Trajectory Model (DHTM) for modelling the long-term trajectories of recurrent HF. DHTM auto-regressively predicts the future HF onsets of each patient and uses the predicted HF as input to predict the HF event at the next time point. Furthermore, we propose an augmented DHTM named DHTM+C (where "C" stands for co-morbidities), which jointly predicts both the HF and a set of acute co-morbidities diagnoses. To efficiently train the DHTM+C model, we devised a novel RNN architecture to model disease progression implicated in the co-morbidities. RESULTS: Our deep learning models confers higher prediction accuracy for both the next-step HF prediction and the HF trajectory prediction compared to the baseline non-neural network models and the baseline RNN model. Compared to DHTM, DHTM+C is able to output higher probability of HF for high-risk patients, even in cases where it is only given less than 2 years of data to predict over 5 years of trajectory. We illustrated multiple non-trivial real patient examples of complex HF trajectories, indicating a promising path for creating highly accurate and scalable longitudinal deep learning models for modeling the chronic disease.
Authors: Fei Wang; Lee H Sterling; Aihua Liu; James M Brophy; Gilles Paradis; Ariane Marelli Journal: Int J Cardiol Date: 2020-06-21 Impact factor: 4.164
Authors: Paul Khairy; Raluca Ionescu-Ittu; Andrew S Mackie; Michal Abrahamowicz; Louise Pilote; Ariane J Marelli Journal: J Am Coll Cardiol Date: 2010-09-28 Impact factor: 24.094
Authors: Sarah Cohen; Aihua Liu; Fei Wang; Liming Guo; James M Brophy; Michal Abrahamowicz; Judith Therrien; Luc M Beauchesne; Elisabeth Bédard; Jasmine Grewal; Paul Khairy; Erwin Oechslin; S Lucy Roche; Candice K Silversides; Isabelle F Vonder Muhll; Ariane J Marelli Journal: Int J Cardiol Date: 2020-08-14 Impact factor: 4.164