Background: The interpretability of results predicted by the machine learning models is vital, especially in the critical fields like healthcare. With the increasingly adoption of electronic healthcare records (EHR) by the medical organizations in the last decade, which accumulated abundant electronic patient data, neural networks or deep learning techniques are gradually being applied to clinical tasks by utilizing the huge potential of EHR data. However, typical deep learning models are black-boxes, which are not transparent and the prediction outcomes of which are difficult to interpret. Methods: To remedy this limitation, we propose an attention neural network model for interpretable clinical prediction. In detail, the proposed model employs an attention mechanism to capture critical/essential features with their attention signals on the prediction results, such that the predictions generated by the neural network model can be interpretable. Results: We evaluate our proposed model on a real-world clinical dataset consisting of 736 samples to predict readmissions for heart failure patients. The performance of the proposed model achieved 66.7 and 69.1% in terms of accuracy and AUC, respectively, and outperformed the baseline models. Besides, we displayed patient-specific attention weights, which can not only help clinicians understand the prediction outcomes, but also assist them to select individualized treatment strategies or intervention plans. Conclusions: The experimental results demonstrate that the proposed model can improve both the prediction performance and interpretability by equipping the model with an attention mechanism.
24 December 2019 in IEEE Journal of Biomedical and Health Informatics
Healthcare process leaves patient treatment trajectory (PTT), described as a sequence of interdependent clinical events affiliated with a large volume of longitudinal therapy and treatment information. Predicting the future clinical event in PTT, as a vital and essential task for providing insights into the entire treatment trajectory, can serve as an efficient and proactive altering service for health service delivery. However, it is challenging because there are long-term dependencies between clinical events, which are irregularly distributed along the temporal axis with varying time intervals. This characteristic inevitably impedes the performance of clinical event prediction (CEP) using the existing approaches. To address this challenge, we propose a novel approach to learn representative and discriminative PTT features for CEP. In detail, multivariate Hawkes process (HP) is adopted to uncover the mutual excitation intensities between clinical event pairs in an interpretable manner. Thereafter, the captured spontaneous and interactional intensities of events are incorporated into recurrent neural networks (RNN) to encode PTT in latent representations, while jointly performing the CEP task based on the extracted trajectory representations. We evaluate the performance of the proposed approach on a real clinical dataset consisting of 13,545 visits of 2,102 heart failure patients. Compared to state-of-the-art methods, our best model achieves 6.4% and 4.1% AUC performance gains on three-months and one-year CEP tasks, respectively. The experimental results demonstrate that the proposed approach outperforms state-of-the-art models in CEP, and can be profitably exploited as a basis for PTT analysis and optimization.
9 January 2019 in BMC Medical Informatics and Decision Making
Main adverse cardiac events (MACE) are essentially composite endpoints for assessing safety and efficacy of treatment processes of acute coronary syndrome (ACS) patients. Timely prediction of MACE is highly valuable for improving the effects of ACS treatments. Most existing tools are specific to predict MACE by mainly using static patient features and neglecting dynamic treatment information during learning. We address this challenge by developing a deep learning-based approach to utilize a large volume of heterogeneous electronic health record (EHR) for predicting MACE after ACS. Specifically, we obtain the deep representation of dynamic treatment features from EHR data, using the bidirectional recurrent neural network. And then, the extracted latent representation of treatment features can be utilized to predict whether a patient occurs MACE in his or her hospitalization. We validate the effectiveness of our approach on a clinical dataset containing 2930 ACS patient samples with 232 static feature types and 2194 dynamic feature types. The performance of our best model for predicting MACE after ACS remains robust and reaches 0.713 and 0.764 in terms of AUC and Accuracy, respectively, and has over 11.9% (1.2%) and 1.9% (7.5%) performance gain of AUC (Accuracy) in comparison with both logistic regression and a boosted resampling model presented in our previous work, respectively. The results are statistically significant. We hypothesize that our proposed model adapted to leverage dynamic treatment information in EHR data appears to boost the performance of MACE prediction for ACS, and can readily meet the demand clinical prediction of other diseases, from a large volume of EHR in an open-ended fashion.
1 November 2015 in Artificial Intelligence in Medicine
Acute coronary syndrome (ACS), as an emergent and severe syndrome due to decreased blood flow in the coronary arteries, is a leading cause of death and serious long-term disability globally. ACS is usually caused by one of three problems: ST elevation myocardial infarction (STEMI), non-ST elevation myocardial infarction (NSTEMI), or unstable angina (UA). Major adverse cardiac event (MACE) prediction, as a critical tool to estimate the likelihood an individual is at risk of ACS, has been widely adopted in the early prevention and intervention of ACS. Although valuable, existing MACE prediction models are designed to predict the overall probability of MACE occurrence for ACS patients, and lack the ability to look for insight into the disease to distinguish the different subtypes of ACS in a fine-grained manner. It is interesting to exploit the different subtypes of ACS and mine their private and shared underlying knowledge to improve the performance of MACE prediction. In this study, we propose utilizing a large volume of heterogeneous electronic health records for the application of MACE prediction. In detail, we address the multi-subtype-oriented MACE prediction for ACS as a multi-task learning (MTL) problem, present a MTL-based model to predict MACE of ACS patients with the different subtypes, and incorporate adversarial learning into the model to alleviate both the shared and private latent feature spaces of each subtype of ACS from interfering with each other. A real-world clinical dataset containing 2,863 ACS patient samples is collected from a Chinese hospital to validate the proposed model. Experimental results demonstrate that the prediction performance of our proposed model obtains a significant improvement, compared to single-subtype-oriented MACE prediction models.
Background: Clinical major adverse cardiovascular event (MACE) prediction of acute coronary syndrome (ACS) is important for a number of applications including physician decision support, quality of care assessment, and efficient healthcare service delivery on ACS patients. Admission records, as typical media to contain clinical information of patients at the early stage of their hospitalizations, provide significant potential to be explored for MACE prediction in a proactive manner. Methods: We propose a hybrid approach for MACE prediction by utilizing a large volume of admission records. Firstly, both a rule-based medical language processing method and a machine learning method (i.e., Conditional Random Fields (CRFs)) are developed to extract essential patient features from unstructured admission records. After that, state-of-the-art supervised machine learning algorithms are applied to construct MACE prediction models from data. Results: We comparatively evaluate the performance of the proposed approach on a real clinical dataset consisting of 2930 ACS patient samples collected from a Chinese hospital. Our best model achieved 72% AUC in MACE prediction. In comparison of the performance between our models and two well-known ACS risk score tools, i.e., GRACE and TIMI, our learned models obtain better performances with a significant margin. Conclusions: Experimental results reveal that our approach can obtain competitive performance in MACE prediction. The comparison of classifiers indicates the proposed approach has a competitive generality with datasets extracted by different feature extraction methods. Furthermore, our MACE prediction model obtained a significant improvement by comparison with both GRACE and TIMI. It indicates that using admission records can effectively provide MACE prediction service for ACS patients at the early stage of their hospitalizations.