Department of Cardiology, The Second Hospital of Hebei Medical University, Shijiazhuang, 050000, People's Republic of China.
Department of Cardiac Surgery, The Second Hospital of Hebei Medical University, Shijiazhuang, 050000, People's Republic of China.
Crit Care. 2024 Oct 29;28(1):349. doi: 10.1186/s13054-024-05138-0.
New-onset atrial fibrillation (NOAF) is the most common arrhythmia in critically ill patients admitted to intensive care and is associated with poor prognosis and disease burden. Identifying high-risk individuals early is crucial. This study aims to create and validate a NOAF prediction model for critically ill patients using machine learning (ML).
The data came from two non-overlapping datasets from the Medical Information Mart for Intensive Care (MIMIC), with MIMIC-IV used for training and subset of MIMIC-III used as external validation. LASSO regression was used for feature selection. Eight ML algorithms were employed to construct the prediction model. Model performance was evaluated based on identification, calibration, and clinical application. The SHapley Additive exPlanations (SHAP) method was used for visualizing model characteristics and individual case predictions.
Among 16,528 MIMIC-IV patients, 1520 (9.2%) developed AF post-ICU admission. A model with 23 variables was built, with XGBoost performing best, achieving an AUC of 0.891 (0.873-0.888) in validation and 0.769 (0.756-0.782) in external validation. Key predictors included age, mechanical ventilation, urine output, sepsis, blood urea nitrogen, percutaneous arterial oxygen saturation, continuous renal replacement therapy and weight. A risk probability greater than 0.6 was defined as high risk. A friendly user interface had been developed for clinician use.
We developed a ML model to predict the risk of NOAF in critically ill patients without cardiac surgery and validated its potential as a clinically reliable tool. SHAP improves the interpretability of the model, enables clinicians to better understand the causes of NOAF, helps clinicians to prevent it in advance and improves patient outcomes.
新发心房颤动（NOAF）是入住重症监护病房的危重病患者中最常见的心律失常，与不良预后和疾病负担相关。早期识别高危人群至关重要。本研究旨在使用机器学习（ML）为危重病患者创建和验证新发心房颤动预测模型。
数据来自两个来自医疗信息集市重症监护（MIMIC）的不重叠数据集，MIMIC-IV 用于训练，MIMIC-III 的子集用于外部验证。LASSO 回归用于特征选择。采用 8 种 ML 算法构建预测模型。根据识别、校准和临床应用评估模型性能。使用 Shapley 加法解释（SHAP）方法可视化模型特征和个体病例预测。
在 16528 名 MIMIC-IV 患者中，有 1520 名（9.2%）在 ICU 入院后发生 AF。建立了一个包含 23 个变量的模型，其中 XGBoost 表现最佳，在验证中 AUC 为 0.891（0.873-0.888），外部验证中 AUC 为 0.769（0.756-0.782）。关键预测因素包括年龄、机械通气、尿量、脓毒症、血尿素氮、经皮动脉血氧饱和度、连续肾脏替代治疗和体重。将风险概率大于 0.6 定义为高风险。已经开发了一个友好的用户界面供临床医生使用。
我们开发了一种 ML 模型来预测无心脏手术的危重病患者新发心房颤动的风险，并验证了其作为一种临床可靠工具的潜力。SHAP 提高了模型的可解释性，使临床医生能够更好地理解新发心房颤动的原因，帮助临床医生提前预防，改善患者预后。
Zotero 插件
