Ultrasound-based radiomics and clinical factors-based nomogram for early intracranial hypertension detection in patients with decompressive craniotomy

• Published in: Frontiers in medical technology Vol. 7; p. 1485244
• Main Authors: Fu, Zunfeng, Peng, Lin, Guo, Laicai, Qin, Chao, Yu, Yanhong, Zhang, Jiajun, Liu, Yan
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Media S.A 05.02.2025
• Subjects: intracranial pressure; machine learning; Medical Technology; optic nerve sheath diameter; severe traumatic brain injury; ultrasound imaging; ultrasound radiomics; ultrasound imaging; ultrasound radiomics; intracranial pressure; transcranial color doppler; machine learning; optic nerve sheath diameter; severe traumatic brain injury
• DOI: 10.3389/fmedt.2025.1485244
• ISSN: 2673-3129

This study aims to develop and validate a nomogram that combines traditional ultrasound radiomics features with clinical parameters to assess early intracranial hypertension (IH) following primary decompressive craniectomy (DC) in patients with severe traumatic brain injury (TBI). The study incorporates the Shapley Additive Explanations (SHAP) method to interpret the radiomics model. This study included 199 patients with severe TBI (training cohort:  = 159; testing cohort:  = 40). Postoperative ultrasound images of the optic nerve sheath (ONS) were obtained at 6 and 18 h after DC. Based on invasive intracranial pressure (ICPi) measurements, patients were grouped according to threshold values of 15 mmHg and 20 mmHg. Radiomics features were extracted from ONS images, and feature selection methods were applied to construct predictive models using logistic regression (LR), support vector machine (SVM), random forest (RF), and K-Nearest Neighbors (KNN). Clinical-ultrasound variables were incorporated into the model through univariate and multivariate logistic regression. A combined nomogram was developed by integrating radiomics features with clinical-ultrasound variables, and its diagnostic performance was evaluated using Receiver Operating Characteristic (ROC) curve analysis and decision curve analysis (DCA). The SHAP method was adopted to explain the prediction models. Among the machine learning models, the LR model demonstrated superior predictive efficiency and robustness at threshold values of 15 mmHg and 20 mmHg. At a threshold of 20 mmHg, the AUC values for the training and testing cohorts were 0.803 and 0.735 for the clinical model, 0.908 and 0.891 for the radiomics model, and 0.918 and 0.902 for the nomogram model, respectively. Similarly, at a threshold of 15 mmHg, the AUC values were consistent across models: 0.803 and 0.735 for the clinical model, 0.908 and 0.891 for the radiomics model, and 0.918 and 0.902 for the nomogram model. Notably, the nomogram model outperformed the clinical model. Decision curve analysis (DCA) further confirmed a higher net benefit for predicting intracranial hypertension across all models. The nomogram model, which integrates both clinical-semantic and radiomics features, demonstrated strong performance in predicting intracranial hypertension across different threshold values. It shows promise for enhancing non-invasive ICP monitoring and supporting individualized therapeutic strategies.