Key result
Task-aware gradient boosting tree variants improved overall across-department AUC performance for VTE risk assessment compared with state-of-the-art rule-based and multi-task tree-based methods.
Why the study?
Traditional rule-based VTE risk assessment scaling tools are difficult to apply to large populations across multiple hospital departments with heterogeneous and imbalanced data.
Does a multi-task gradient boosting tree model improve VTE risk prediction across multiple hospital departments compared to traditional rule-based and other tree-based methods?
Does a multi-task gradient boosting tree model improve VTE risk prediction across multiple hospital departments compared to traditional rule-based and other tree-based methods?
Answers are grounded in this paper and cite their sources.
A novel multi-task gradient boosting tree model improves VTE risk prediction across heterogeneous hospital departments compared to traditional methods.
Venous thromboembolism (VTE) is the world's third most common cause of vascular mortality and a serious complication from multiple departments. Risk assessment of VTE guides clinical intervention in time and is of great importance to in-hospital patients. Traditional VTE risk assessment methods based on scaling tools, which always require rules carefully designed by human experts, are difficult to apply to large-population scenarios since the manually designed rules are not guaranteed to be accurate to all populations. In contrast, with the development of the electronic health record (EHR) datasets, data-driven machine-learning-based risk assessment methods have proven superior predictability in many studies in recent years. This paper uses the gradient boosting tree model to study the VTE risk assessment problem with multi-department data. There exist two distinct characteristics of VTE data collected at the level of the entire hospital: its wide distribution and heterogeneity across multiple departments. To this end, we consider the prediction task over multiple departments as a multi-task learning process, and introduce the algorithm of a task-aware tree-based method TSGB to tackle the multi-task prediction problem. Although the introduction of multi-task learning improves overall across-department performance, we reveal the problem of task-wise performance decline while dealing with imbalanced VTE data volume. According to the analysis, we finally propose two variants of TSGB to alleviate the problems and further boost the prediction performance. Compared with state-of-the-art rule-based and multi-task tree-based methods, the experimental results show the proposed methods not only improve the overall across-department AUC performance effectively, but also ensure the improvement of performance over every single department prediction.
No takes yet. Share an insight, caveat, or question.
Ma et al. (2022) studied Venous thromboembolism (VTE). Task-aware tree-based method TSGB and variants vs. State-of-the-art rule-based and multi-task tree-based methods was evaluated on VTE risk prediction performance (AUC). Task-aware gradient boosting tree variants improved overall across-department AUC performance for VTE risk assessment compared with state-of-the-art rule-based and multi-task tree-based methods.
Synapse has enriched 10 related papers. Consider them for comparative context: