Khaniyev Taghi, Cekic Efecan, Koc Muhammet Abdullah, Dogan Ilke, Hanalioglu Sahin
Faculty of Engineering, Department of Industrial Engineering, Bilkent University, Ankara, Turkey.
National Magnetic Resonance Research Center, Bilkent University, Ankara, Turkey.
Neurocrit Care. 2025 May 6. doi: 10.1007/s12028-025-02246-9.
Predicting intensive care unit (ICU) discharge for neurosurgical patients is crucial for optimizing bed sources, reducing costs, and improving outcomes. Our study aims to develop and validate machine learning (ML) models to predict ICU discharge within 24 h for patients undergoing craniotomy.
The 2,742 patients undergoing craniotomy were identified from Medical Information Mart for Intensive Care dataset using diagnosis-related group and International Classification of Diseases codes. Demographic, clinical, laboratory, and radiological data were collected and preprocessed. Textual clinical examinations were converted into numerical scales. Data were split into training (70%), validation (15%), and test (15%) sets. Four ML models, logistic regression (LR), decision tree, random forest, and neural network (NN), were trained and evaluated. Model performance was assessed using area under the receiver operating characteristic curve (AUC), average precision (AP), accuracy, and F1 scores. Shapley Additive Explanations (SHAP) were used to analyze importance of features. Statistical analyses were performed using R (version 4.2.1) and ML analyses with Python (version 3.8), using scikit-learn, tensorflow, and shap packages.
Cohort included 2,742 patients (mean age 58.2 years; first and third quartiles 47-70 years), with 53.4% being male (n = 1,464). Total ICU stay was 15,645 bed days (mean length of stay 4.7 days), and total hospital stay was 32,008 bed days (mean length of stay 10.8 days). Random forest demonstrated highest performance (AUC 0.831, AP 0.561, accuracy 0.827, F1-score 0.339) on test set. NN achieved an AUC of 0.824, with an AP, accuracy, and F1-score of 0.558, 0.830, and 0.383, respectively. LR achieved an AUC of 0.821 and an accuracy of 0.829. The decision tree model showed lowest performance (AUC 0.813, accuracy 0.822). Key predictors of SHAP analysis included Glasgow Coma Scale, respiratory-related parameters (i.e., tidal volume, respiratory effort), intracranial pressure, arterial pH, and Richmond Agitation-Sedation Scale.
Random forest and NN predict ICU discharge well, whereas LR is interpretable but less accurate. Numeric conversion of clinical data improved performance. This study offers framework for predictions using clinical, radiological, and demographic features, with SHAP enhancing transparency.
预测神经外科患者的重症监护病房（ICU）出院情况对于优化床位资源、降低成本和改善治疗结果至关重要。我们的研究旨在开发并验证机器学习（ML）模型，以预测开颅手术患者在24小时内的ICU出院情况。
使用诊断相关分组和国际疾病分类代码，从重症监护医学信息数据库中识别出2742例接受开颅手术的患者。收集并预处理人口统计学、临床、实验室和放射学数据。将文本形式的临床检查结果转换为数字量表。数据被分为训练集（70%）、验证集（15%）和测试集（15%）。对逻辑回归（LR）、决策树、随机森林和神经网络（NN）这四种ML模型进行训练和评估。使用受试者操作特征曲线下面积（AUC）、平均精度（AP）、准确率和F1分数评估模型性能。使用Shapley值相加解释（SHAP）分析特征的重要性。使用R（版本4.2.1）进行统计分析，使用Python（版本3.8）并结合scikit-learn、tensorflow和shap包进行ML分析。
队列包括2742例患者（平均年龄58.2岁；第一和第三四分位数为47 - 70岁），其中男性占53.4%（n = 1464）。ICU总住院天数为15645床日（平均住院时间4.7天），总住院天数为32008床日（平均住院时间10.8天）。随机森林在测试集上表现出最高性能（AUC为0.831，AP为0.561，准确率为0.827，F1分数为0.339）。神经网络的AUC为0.824，AP、准确率和F1分数分别为0.558、0.830和0.383。逻辑回归的AUC为0.821，准确率为0.829。决策树模型表现最差（AUC为0.813，准确率为0.822）。SHAP分析的关键预测因素包括格拉斯哥昏迷量表、呼吸相关参数（即潮气量、呼吸努力）、颅内压、动脉pH值和里士满躁动镇静量表。
随机森林和神经网络能很好地预测ICU出院情况，而逻辑回归虽可解释但准确性较低。临床数据的数值转换提高了性能。本研究提供了使用临床、放射学和人口统计学特征进行预测的框架，SHAP增强了透明度。
