Machine learning is widely used on stored data, recently it is developed to model real time streams. Applying machine learning on medical streams might lead to a breakthrough on emergency and critical care through online predictions. Modeling real time streams implies limitations to the current state-of-the-art of machine learning and requires different learning paradigm. In this paper, we investigate and evaluate two different machine learning paradigms for real time predictions of medical streams. Both the hierarchical temporal memory (HTM) and long short-term memory (LSTM) are employed. The performance assessment using both algorithms is provided in terms of the root mean square error (RMS) and mean absolute percentage error (MAPE). HTM is found advantageous as it provides efficient unsupervised predictions compared to the semi-supervised learning supported by LSTM in terms of the error measures.

No abstract

Mean arterial pressure (MAP) is an important clinical parameter to evaluate the health of critically ill patients in intensive care units. Thus, the real time clinical decision support systems detecting anomalies and deviations in MAP enable early interventions and prevent serious complications. The state-ofthe-art decision support systems are based on a three-phase method that applies offline training, transfer learning, and retraining at the bedside. Their applicability in critical care units is challenging with delay and inaccuracy. In this paper, we propose a real time clinical decision support system forecasting the MAP status at the bedside using a new machine learning structure. The proposed system works in real time at the bedside without requiring the offline phase for training using large datasets. It thereby enables timely interventions and improved healthcare services. The proposed machine learning structure includes two stages. Stage I applies online learning using hierarchical temporal memory (HTM) to enable real time stream processing and provides unsupervised predictions. To the best of our knowledge, this is the first time it is applied to medical signals. Stage II is a long short-term memory (LSTM) classifier that forecasts the status of the patient's MAP ahead of time based on Stage I stream predictions. We perform a thorough performance evaluation of the proposed system and compare it with the state-of-the-art systems employing logistic regression (LR). The comparison shows the proposed system outperforms LR in terms of the classification accuracy, recall, precision, and area under the receiver operation curve (AUROC). INDEX TERMS Clinical decision support, classification, hierarchical temporal memory (HTM), long shortterm memory (LSTM), machine learning, real time prediction.

No abstract

No abstract