Hunt-Hess Score at 48 Hours Improves Prognostication in Grade 5 Aneurysmal Subarachnoid Hemorrhage

Mittal, Aditya M; Pease, Matthew; McCarthy, David; Legarretta, Andrew; Belkhir, Raouf; Crago, Elizabeth; Lang, Michael J; Gross, Bradley A.

doi:10.1016/j.wneu.2023.01.018

Cited by 6 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was shown for HH grade 5 aSAH patients that a reassessment of the HH grade after 48 h, results in a significant less severe grading [ 14 ]. Accordingly, it has been shown that patients with early-onset seizures were significantly more often classified as poor grade, however this group had a significantly better outcome[ 15 ].…”

Section: Discussionmentioning

confidence: 99%

Clinical severity of aneurysmal subarachnoid hemorrhage over time: systematic review

Overstijns,

El Rahal,

Goldberg

et al. 2024

Neurosurg Rev

View full text Add to dashboard Cite

The incidence of aneurysmal subarachnoid hemorrhage (aSAH) is well studied. Yet, little is known about the trend of aSAH severity. This systematic review aims to analyze the distribution of aSAH severity over time. We performed a systematic review of the literature according to the PRISMA-P guidelines. We included studies from January 1968 up to December 2022. Studies were included if they either reported the severity of aSAH as single increments of the corresponding 5-point scale or as a binary measure (good grade 1-3, poor grade 4-5) on the Hunt and Hess (HH) or World Federation of Neurosurgical Societies (WFNS) scale. Studies with fewer than 50 patients, (systematic) reviews, and studies including non-aSAH patients were excluded. A total of 2465 publications were identified, of which 214 met the inclusion and exclusion criteria. In total, 102,845 patients with an aSAH were included. Over the last five decades the number of good-grade HH (0.741 fold, p = 0.004) and WFNS (0.749 fold, p < 0.001) has decreased. Vice versa, an increase in number of poor grade HH (2.427 fold, p = 0.004), WFNS (2.289 fold, p < 0.001), as well as HH grade 5 (6.737 fold, p = 0.010), WFNS grade 4 (1.235 fold, p = 0.008) and WFNS grade 5 (8.322 fold, p = 0.031) was observed. This systematic review shows a worldwide 2-3 fold increase of poor grade aSAH patients and an 6-8 fold increase of grade 5 patients, over the last 50 years. Whether this evolution is due to more severe hemorrhage, improvements in neuro-intensive care and prehospital management, or to a change in grading behavior is unknown. This study strongly emphasizes the necessity for an improved grading system to differentiate grade 4 and grade 5 patients for meaningful clinical decision- making.

show abstract

Section: Discussionmentioning

confidence: 99%

Clinical severity of aneurysmal subarachnoid hemorrhage over time: systematic review

Overstijns,

El Rahal,

Goldberg

et al. 2024

Neurosurg Rev

View full text Add to dashboard Cite

show abstract

“…Grade 5 is the most severe ( Table 1 ). Clinicians want to predict before surgery whether a patient’s neurologic function will change from below grade 3 to grade 3 and above after surgery ( 7 ).…”

Section: Introductionmentioning

confidence: 99%

Deep learning and machine learning predictive models for neurological function after interventional embolization of intracranial aneurysms

Peng,

Wang,

Wen

et al. 2024

Front. Neurol.

View full text Add to dashboard Cite

ObjectiveThe objective of this study is to develop a model to predicts the postoperative Hunt-Hess grade in patients with intracranial aneurysms by integrating radiomics and deep learning technologies, using preoperative CTA imaging data. Thereby assisting clinical decision-making and improving the assessment and prognosis of postoperative neurological function.MethodsThis retrospective study encompassed 101 patients who underwent aneurysm embolization surgery. 851 radiomic features were extracted from CTA images. 512 deep learning features are extracted from last layer of ResNet50 deep convolutional neural network model. The feature screening process pipeline encompassed intraclass correlation coefficient analysis, principal component analysis, U test, spearman correlation analysis, minimum redundancy maximum relevance algorithm and Lasso regression, to identify features most correlated with postoperative Hunt-Hess grading. In the model construction phase, three distinct models were constructed: radiomics feature-based model (RSM), deep learning feature-based model (DLM), and deep learning-radiomics feature fusion model (DLRSCM). The study also calculated the radiomics score and combined it with clinical data to construct a Nomogram for predictive modeling. DLM, RSM and DLRSCM model was constructed by 9 base algorithms and 1 ensemble learning algorithm – Stacking ensemble model. Model performance was evaluated based on the area under the Receiver Operating Characteristic (ROC) curve (AUC), Matthews Correlation Coefficient (MCC), calibration curves, and decision curves analysis.Results5 significant radiomic feature and 4 significant deep learning features were obtained through the feature selection process. These features were utilized for model construction. Bootstrap resampling method was used for internal validation of the models. In terms of model evaluation, the DLM model, the stacking ensemble algorithm results achieved an AUC of 0.959 and MCC of 0.815. In the RSM model, the stacking ensemble model AUC was 0.935 and MCC was 0.793. The stacking ensemble model in DLRSCM outperformed others, with an AUC of 0.968 and MCC of 0.820. Results indicated that the ANN performed optimally among all base models, while the stacked ensemble learning model exhibited the highest predictive performance.ConclusionThis study demonstrates that the combination of radiomics and deep learning is an effective approach to predict the postoperative Hunt-Hess grade in patients with intracranial aneurysms. This holds significant value in the early identification of postoperative neurological complications and in enhancing clinical decision-making.

show abstract

“…Postoperatively, the patients were categorized into 2 groups based on the presence of cerebral edema: a complication group )n=33( and a non-complication group )n=199(. The study retrospectively analyzed and compared various factors between the 2 groups, including age, gender, frequency of bleeding, location of aneurysm )in the anterior or posterior circulation(, number of aneurysms )single or multiple(, aneurysm diameter, modified Fisher grade of subarachnoid hemorrhage based on CT assessment, 6 World Federation of Neurosurgical Societies )WFNS( grade of nerve function, 7 Hunt-Hess grade, 8 presence or absence of hypertension, diabetes mellitus, coronary heart disease, hematoma, and duration from onset to operation.…”

mentioning

confidence: 99%

Risk factors for cerebral edema following aneurysm clipping in patients with aneurysmal subarachnoid hemorrhage

Xu,

Chen,

et al. 2024

NSJ

View full text Add to dashboard Cite

show abstract

Hunt-Hess Score at 48 Hours Improves Prognostication in Grade 5 Aneurysmal Subarachnoid Hemorrhage

Cited by 6 publications

References 13 publications

Clinical severity of aneurysmal subarachnoid hemorrhage over time: systematic review

Clinical severity of aneurysmal subarachnoid hemorrhage over time: systematic review

Deep learning and machine learning predictive models for neurological function after interventional embolization of intracranial aneurysms

Risk factors for cerebral edema following aneurysm clipping in patients with aneurysmal subarachnoid hemorrhage

Contact Info

Product

Resources

About