Patel Dhavalkumar, Cheetirala Satya Narayan, Raut Ganesh, Tamegue Jules, Kia Arash, Glicksberg Benjamin, Freeman Robert, Levin Matthew A, Timsina Prem, Klang Eyal
Mount Sinai Health System, New York, NY 10017, USA.
Department of Anesthesiology, Perioperative and Pain Management, Mount Sinai Hospital, New York, NY 10017, USA.
J Clin Med. 2022 Nov 22;11(23):6888. doi: 10.3390/jcm11236888.
We analyzed an inclusive gradient boosting model to predict hospital admission from the emergency department (ED) at different time points. We compared its results to multiple models built exclusively at each time point.
This retrospective multisite study utilized ED data from the Mount Sinai Health System, NY, during 2015-2019. Data included tabular clinical features and free-text triage notes represented using bag-of-words. A full gradient boosting model, trained on data available at different time points (30, 60, 90, 120, and 150 min), was compared to single models trained exclusively at data available at each time point. This was conducted by concatenating the rows of data available at each time point to one data matrix for the full model, where each row is considered a separate case.
The cohort included 1,043,345 ED visits. The full model showed comparable results to the single models at all time points (AUCs 0.84-0.88 for different time points for both the full and single models).
A full model trained on data concatenated from different time points showed similar results to single models trained at each time point. An ML-based prediction model can use used for identifying hospital admission.
我们分析了一种包容性梯度提升模型，以预测急诊科（ED）在不同时间点的住院情况。我们将其结果与在每个时间点专门构建的多个模型进行了比较。
这项回顾性多中心研究利用了纽约西奈山医疗系统2015 - 2019年期间的急诊科数据。数据包括表格形式的临床特征和使用词袋法表示的自由文本分诊记录。在不同时间点（30、60、90、120和150分钟）可用数据上训练的完整梯度提升模型，与仅在每个时间点可用数据上训练的单一模型进行了比较。这是通过将每个时间点可用的数据行连接到一个用于完整模型的数据矩阵来进行的，其中每行被视为一个单独的病例。
该队列包括1,043,345次急诊科就诊。完整模型在所有时间点的结果与单一模型相当（完整模型和单一模型在不同时间点的AUC均为0.84 - 0.88）。
在从不同时间点连接的数据上训练的完整模型显示出与在每个时间点训练的单一模型相似的结果。基于机器学习的预测模型可用于识别住院情况。
