University of Portsmouth, Buckingham Building, Lion Terrace, Portsmouth PO1 3HE, UK.
University of Portsmouth, Buckingham Building, Lion Terrace, Portsmouth PO1 3HE, UK.
Int J Med Inform. 2017 Dec;108:185-195. doi: 10.1016/j.ijmedinf.2017.10.002. Epub 2017 Oct 5.
Mortality prediction of hospitalized patients is an important problem. Over the past few decades, several severity scoring systems and machine learning mortality prediction models have been developed for predicting hospital mortality. By contrast, early mortality prediction for intensive care unit patients remains an open challenge. Most research has focused on severity of illness scoring systems or data mining (DM) models designed for risk estimation at least 24 or 48h after ICU admission.
This study highlights the main data challenges in early mortality prediction in ICU patients and introduces a new machine learning based framework for Early Mortality Prediction for Intensive Care Unit patients (EMPICU).
The proposed method is evaluated on the Multiparameter Intelligent Monitoring in Intensive Care II (MIMIC-II) database. Mortality prediction models are developed for patients at the age of 16 or above in Medical ICU (MICU), Surgical ICU (SICU) or Cardiac Surgery Recovery Unit (CSRU). We employ the ensemble learning Random Forest (RF), the predictive Decision Trees (DT), the probabilistic Naive Bayes (NB) and the rule-based Projective Adaptive Resonance Theory (PART) models. The primary outcome was hospital mortality. The explanatory variables included demographic, physiological, vital signs and laboratory test variables. Performance measures were calculated using cross-validated area under the receiver operating characteristic curve (AUROC) to minimize bias. 11,722 patients with single ICU stays are considered. Only patients at the age of 16 years old and above in Medical ICU (MICU), Surgical ICU (SICU) or Cardiac Surgery Recovery Unit (CSRU) are considered in this study.
The proposed EMPICU framework outperformed standard scoring systems (SOFA, SAPS-I, APACHE-II, NEWS and qSOFA) in terms of AUROC and time (i.e. at 6h compared to 48h or more after admission).
The results show that although there are many values missing in the first few hour of ICU admission, there is enough signal to effectively predict mortality during the first 6h of admission. The proposed framework, in particular the one that uses the ensemble learning approach - EMPICU Random Forest (EMPICU-RF) offers a base to construct an effective and novel mortality prediction model in the early hours of an ICU patient admission, with an improved performance profile.
住院患者的死亡率预测是一个重要问题。在过去的几十年中，已经开发了几种严重程度评分系统和机器学习死亡率预测模型，用于预测医院死亡率。相比之下，重症监护病房患者的早期死亡率预测仍然是一个未解决的挑战。大多数研究都集中在疾病严重程度评分系统或数据挖掘 (DM) 模型上，这些模型旨在 ICU 入院后至少 24 或 48 小时进行风险估计。
本研究强调了 ICU 患者早期死亡率预测中的主要数据挑战，并介绍了一种用于重症监护患者早期死亡率预测的新的基于机器学习的框架（EMPICU）。
该方法在 Multiparameter Intelligent Monitoring in Intensive Care II (MIMIC-II) 数据库上进行评估。为年龄在 16 岁及以上的患者开发了在医疗 ICU (MICU)、外科 ICU (SICU) 或心脏外科恢复病房 (CSRU) 的死亡率预测模型。我们使用集成学习随机森林 (RF)、预测决策树 (DT)、概率朴素贝叶斯 (NB) 和基于规则的投射自适应共振理论 (PART) 模型。主要结果是医院死亡率。解释变量包括人口统计学、生理学、生命体征和实验室测试变量。使用交叉验证接收者操作特征曲线下的面积 (AUROC) 计算性能度量，以最小化偏差。考虑了 11722 名 ICU 单次住院患者。仅考虑年龄在 16 岁及以上的在医疗 ICU (MICU)、外科 ICU (SICU) 或心脏外科恢复病房 (CSRU) 的患者。
与 SOFA、SAPS-I、APACHE-II、NEWS 和 qSOFA 等标准评分系统相比，提出的 EMPICU 框架在 AUROC 和时间方面（即入院后 6 小时与 48 小时或更长时间相比）表现更好。
结果表明，尽管 ICU 入院最初几个小时有很多值缺失，但仍有足够的信号可以有效地预测入院后前 6 小时的死亡率。所提出的框架，特别是使用集成学习方法的框架-EMPICU 随机森林 (EMPICU-RF)，为构建 ICU 患者入院早期的有效新型死亡率预测模型提供了基础，具有改进的性能特征。
