No abstract

Background Due to the complexity and high heterogeneity of the acute exacerbation of chronic obstructive pulmonary disease (AECOPD), the guidelines (global initiative for chronic obstructive, GOLD) is unable to fully guide the treatment of AECOPD. Objectives To provide a rapid treatment in line with the development of the AECOPD after admission. In this paper, we propose a multi-stage feature fusion (MSFF) framework combining machine learning to track the diseases deterioration risk of the AECOPD. Methods First, we identify 408 AECOPD patients as the study population. Then, feature segment and fusion methods are applied to generate the phased data set. Finally, human studies are designed to evaluate the performance of the MSFF framework. Results The experimental results show that the proposed framework is potential to obtain the full-process tracking of deterioration risk for the AECOPD patients. The proposed MSFF framework achieves a higher overall accuracy average and F1 scores than the four physician groups i.e., IM, Surgery, Emergency, and ICU. Conclusions The proposed MSFF model may serve as a useful disease tracking tool to estimate the deterioration risk at each stage, and finally achieve the disease monitoring and management for AECOPD patients.

BackgroundRandom forest (RF) is a powerful ensemble algorithm for medical decision-making supporting (MDS). However the requirement of higher accuracy and smaller ensemble size remain significant burdens for the current RF, particularly for the risk identification of disease deterioration. To achieve the goal of higher accuracy and smaller ensemble size for the risk identification of disease deterioration, a diversity enhancement random forest (DERF) model is proposed.MethodsWe explored the idea of integrating trees that are accurate and diverse to build the DERF model. First, we calculated the accuracy of the out of bag data to select the best K trees. Then, we assessed the diversity of these trees using logarithmic loss functions on the validation data set. Further, we utilized the greedy stepwise backward search to increase the diversity of the random forest. Finally, public bench mark data sets on disease deterioration from KEEL and real data sets from tertiary hospitals in the last three years were used to assess the performance of the proposed DERF model and compared it with the existing model. ResultsExperiments show that the proposed model can improve the prediction performance and reduce the ensemble size of random forest model. Compared with the existing model random forest, the extreme random tree and the ensemble of optimal tree, our proposed DERF model obtains a higher predictive accuracy and a smaller ensemble size. ConclusionIt reveals that the proposed DERF could reduce the size of the ensemble and achieve good classification results in the risk identification of disease deterioration