Death Risk Prediction of Intensive Care Unit Patients Combined with Treatment Process Mining
Faming Lu, Pengfei Li, Yunxia Bao, Cong Liu, Qingtian Zeng · Journal of Medical Imaging and Health Informatics · 2020
Precise death risk prediction of ICU patients plays an important role in developing follow-up treatment options and reducing rescue cost. Previous work mainly relied on the vital signs of patients to predict the risk of death. In fact, patients’ treatment process also implies valuable information about patient’s condition. To use the treatment process information in patient risk assessment, this paper proposes a new death risk prediction method combined with treatment process mining. Specifically, historical patients are firstly clustered into several classes according to their final treatment outcome and the drugs they took. Patients in one cluster are assumed to share the same treatment process. Then, these treatment processes are mined by means of the LDA topic model and the probability suffix tree training method. Next, for a patient to do death risk prediction, the similarity between his/her treatment procedure and those probability suffix trees is computed. The similarity value is taken as a new feature complementary to those traditional ones in disease severity scoring systems. Finally, the random forest algorithm is used to train the death risk prediction model based on the extended feature set. Taking the prescription data of sepsis patients in the MIMIC-III database as input, an experiment is conduced to evaluate the proposed method. As expected, the proposed method achieves better prediction accuracy, recall rate, and F1 score compared to methods.