Vierula Jari-Pekka, Merisaari Harri, Heikkinen Jaakko, Happonen Tatu, Sirén Aapo, Velhonoja Jarno, Irjala Heikki, Soukka Tero, Mattila Kimmo, Nyman Mikko, Nurminen Janne, Hirvonen Jussi
Department of Radiology, Turku University Hospital, Turku, Finland.
Turku Brain and Mind Center, University of Turku, Turku, Finland.
Eur J Radiol Open. 2025 Apr 1;14:100648. doi: 10.1016/j.ejro.2025.100648. eCollection 2025 Jun.
We assessed risk factors and developed a score to predict intensive care unit (ICU) admissions using MRI findings and clinical data in acute neck infections.
This retrospective study included patients with MRI-confirmed acute neck infection. Abscess diameters were measured on post-gadolinium T1-weighted Dixon MRI, and specific edema patterns, retropharyngeal (RPE) and mediastinal edema, were assessed on fat-suppressed T2-weighted Dixon MRI. A multivariate logistic regression model identified ICU admission predictors, with risk scores derived from regression coefficients. Model performance was evaluated using the area under the curve (AUC) from receiver operating characteristic analysis. Machine learning models (random forest, XGBoost, support vector machine, neural networks) were tested.
The sample included 535 patients, of whom 373 (70 %) had an abscess, and 62 (12 %) required ICU treatment. Significant predictors for ICU admission were RPE, maximal abscess diameter (≥40 mm), and C-reactive protein (CRP) (≥172 mg/L). The risk score (0-7) (AUC=0.82, 95 % confidence interval [CI] 0.77-0.88) outperformed CRP (AUC=0.73, 95 % CI 0.66-0.80, p = 0.001), maximal abscess diameter (AUC=0.72, 95 % CI 0.64-0.80, p < 0.001), and RPE (AUC=0.71, 95 % CI 0.65-0.77, p < 0.001). The risk score at a cut-off > 3 yielded the following metrics: sensitivity 66 %, specificity 82 %, positive predictive value 33 %, negative predictive value 95 %, accuracy 80 %, and odds ratio 9.0. Discriminative performance was robust in internal (AUC=0.83) and hold-out (AUC=0.81) validations. ML models were not better than regression models.
A risk model incorporating RPE, abscess size, and CRP showed moderate accuracy and high negative predictive value for ICU admissions, supporting MRI's role in acute neck infections.
我们评估了危险因素，并利用急性颈部感染的MRI检查结果和临床数据制定了一个评分系统，以预测重症监护病房（ICU）收治情况。
这项回顾性研究纳入了MRI确诊的急性颈部感染患者。在钆增强T1加权狄克逊MRI上测量脓肿直径，并在脂肪抑制T2加权狄克逊MRI上评估特定的水肿模式，即咽后（RPE）和纵隔水肿。多变量逻辑回归模型确定了ICU收治的预测因素，并根据回归系数得出风险评分。使用受试者工作特征分析的曲线下面积（AUC）评估模型性能。对机器学习模型（随机森林、XGBoost、支持向量机、神经网络）进行了测试。
样本包括535例患者，其中373例（70%）有脓肿，62例（12%）需要ICU治疗。ICU收治的显著预测因素为RPE、最大脓肿直径（≥40mm）和C反应蛋白（CRP）（≥172mg/L）。风险评分（0 - 7）（AUC = 0.82，95%置信区间[CI]0.77 - 0.88）优于CRP（AUC = 0.73，95%CI 0.66 - 0.80，p = 0.001）、最大脓肿直径（AUC = 0.72，95%CI 0.64 - 0.80，p < 0.001）和RPE（AUC = 0.71，95%CI 0.65 - 0.77，p < 0.001）。截断值>3时的风险评分产生了以下指标：敏感性66%，特异性82%，阳性预测值33%，阴性预测值95%，准确性80%，比值比9.0。在内部验证（AUC = 0.83）和保留验证（AUC = 0.81）中，判别性能稳健。机器学习模型并不优于回归模型。
结合RPE、脓肿大小和CRP的风险模型对ICU收治情况显示出中等准确性和高阴性预测值，支持MRI在急性颈部感染中的作用。
