Dascena Inc., San Francisco, CA, United States.
Dascena Inc., San Francisco, CA, United States.
J Crit Care. 2020 Dec;60:96-102. doi: 10.1016/j.jcrc.2020.07.019. Epub 2020 Jul 24.
Acute respiratory distress syndrome (ARDS) is a serious respiratory condition with high mortality and associated morbidity. The objective of this study is to develop and evaluate a novel application of gradient boosted tree models trained on patient health record data for the early prediction of ARDS.
9919 patient encounters were retrospectively analyzed from the Medical Information Mart for Intensive Care III (MIMIC-III) data base. XGBoost gradient boosted tree models for early ARDS prediction were created using routinely collected clinical variables and numerical representations of radiology reports as inputs. XGBoost models were iteratively trained and validated using 10-fold cross validation.
On a hold-out test set, algorithm classifiers attained area under the receiver operating characteristic curve (AUROC) values of 0.905 when tested for the detection of ARDS at onset and 0.827, 0.810, and 0.790 for the prediction of ARDS at 12-, 24-, and 48-h windows prior to onset, respectively.
Supervised machine learning predictions may help predict patients with ARDS up to 48 h prior to onset.
急性呼吸窘迫综合征（ARDS）是一种死亡率高且伴有相关发病率的严重呼吸系统疾病。本研究的目的是开发并评估一种基于患者健康记录数据的梯度提升树模型在 ARDS 早期预测中的新应用。
从医疗信息监护 III 数据库（MIMIC-III）中回顾性分析了 9919 例患者就诊情况。使用常规收集的临床变量和放射学报告的数值表示作为输入，创建了用于早期 ARDS 预测的 XGBoost 梯度提升树模型。使用 10 折交叉验证对 XGBoost 模型进行迭代训练和验证。
在一个保留测试集上，当用于检测 ARDS 发作时，算法分类器的接收者操作特征曲线下面积（AUROC）值为 0.905，当用于预测 ARDS 在发作前 12、24 和 48 小时的窗口时，分别为 0.827、0.810 和 0.790。
有监督机器学习预测可能有助于在 ARDS 发作前 48 小时预测患者。
