Medical AI Research Team, Chungbuk National University Hospital, Cheongju-si, Chungcheongbuk-do, 28644, Rep. of Korea.
Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Chungbuk National University Hospital, Chungbuk National University College of Medicine, Cheongju-si, Chungcheongbuk-do, 28644, Rep. of Korea.
Comput Methods Programs Biomed. 2023 Oct;240:107673. doi: 10.1016/j.cmpb.2023.107673. Epub 2023 Jun 14.
Intensive care unit (ICU) physicians perform weaning procedures considering complex clinical situations and weaning protocols; however, liberating critical patients from mechanical ventilation (MV) remains challenging. Therefore, this study aims to aid physicians in deciding the early liberation of patients from MV by developing an artificial intelligence model that predicts the success of spontaneous breathing trials (SBT).
We retrospectively collected data of 652 critical patients (SBT success: 641, SBT failure: 400) who received MV at the Chungbuk National University Hospital (CBNUH) ICU from July 2020 to July 2022, including mixed and trauma ICUs. Patients underwent SBTs according to the CBNUH weaning protocol or physician's decision, and SBT success was defined as extubation performed by the physician on the SBT day. Additionally, our dataset comprised 11 numerical and 2 categorical features that can be obtained for any ICU patient, such as vital signs and MV setting values. To predict SBT success, we analyzed tabular data using a graph neural network-based approach. Specifically, the graph structure was designed considering feature correlation, and a novel deep learning model, called feature tokenizer graph attention network (FT-GAT), was developed for graph analysis. FT-GAT transforms the input features into high-dimensional embeddings and analyzes the graph via the attention mechanism.
The quantitative evaluation results indicated that FT-GAT outperformed conventional models and clinical indicators by achieving the following model performance (AUROC): FT-GAT (0.80), conventional models (0.69-0.79), and clinical indicators (0.65-0.66) CONCLUSIONS: Through timely detection critical patients who can succeed in SBTs, FT-GAT can help prevent long-term use of MV and potentially lead to improvement in patient outcomes.
重症监护病房（ICU）的医生在考虑复杂的临床情况和撤机方案的情况下进行撤机操作；然而，使危重症患者脱离机械通气（MV）仍然具有挑战性。因此，本研究旨在通过开发一种人工智能模型来帮助医生决定患者早期脱离 MV，该模型可以预测自主呼吸试验（SBT）的成功。
我们回顾性收集了 2020 年 7 月至 2022 年 7 月在忠北国立大学医院（CBNUH）重症监护病房（ICU）接受 MV 的 652 例危重症患者（SBT 成功：641 例，SBT 失败：400 例）的数据，包括混合和创伤 ICU。患者根据 CBNUH 撤机方案或医生的决定进行 SBT，SBT 成功定义为医生在 SBT 当天进行的拔管。此外，我们的数据集包括 11 个数值和 2 个类别特征，这些特征可用于任何 ICU 患者，如生命体征和 MV 设置值。为了预测 SBT 成功，我们使用基于图神经网络的方法分析了表格数据。具体来说，考虑到特征相关性设计了图结构，并开发了一种名为特征标记图注意力网络（FT-GAT）的新型深度学习模型用于图分析。FT-GAT 将输入特征转换为高维嵌入，并通过注意力机制分析图。
定量评估结果表明，FT-GAT 优于传统模型和临床指标，其模型性能（AUROC）如下：FT-GAT（0.80）、传统模型（0.69-0.79）和临床指标（0.65-0.66）。
通过及时检测可以成功进行 SBT 的危重症患者，FT-GAT 可以帮助预防 MV 的长期使用，并有可能改善患者的预后。
