Radiological scales predicting delayed cerebral ischemia in subarachnoid hemorrhage: systematic review and meta-analysis.

PURPOSE: Delayed cerebral ischemia (DCI) is a severe complication of aneurysmal subarachnoid hemorrhage (aSAH). The extent of subarachnoid blood is a strong predictor of DCI and is frequently estimated with the Fisher scale, modified Fisher scale, or Hijdra sum score. It is unclear which scale has the strongest association with clinical DCI. To evaluate this, we performed a systematic review of the literature. METHODS: We performed a MEDLINE and EMBASE search from 1980 to 20th of June 2017. Radiological grade and occurrence of clinical DCI were extracted along with odds ratios (ORs) for DCI. When possible, pooled ORs with 95% confidence intervals were calculated per grade increase on the radiological scale. RESULTS: Fifty-three studies were included. The Fisher scale was significantly associated with DCI in 62% of the studies compared to 88-100% for the other scales. In studies using the Fisher scale, Fisher 3 had the strongest association with DCI (pooled OR 3.21 (1.87-5.49)). In studies using the modified Fisher score, DCI occurred most frequently (42%) in modified Fisher 4. No pooled OR could be calculated for the other scales. CONCLUSION: The Fisher scale, modified Fisher scale, and Hijdra sum score are all associated with clinical DCI. The risk of DCI, however, does not increase with increasing Fisher grade as opposed to the modified Fisher scale. Furthermore, the modified Fisher scale was more commonly significantly associated with DCI than the Fisher scale, which may advocate using the modified Fisher in future SAH-related studies.

Aortic disease in patients with Marfan syndrome: aortic volume assessment for surveillance.

PURPOSE: To assess the reproducibility of aortic volume estimates and to serially test their use in patients with Marfan syndrome. MATERIALS AND METHODS: The study was approved by the medical ethics committee and all subjects gave written informed consent. In 81 patients with Marfan syndrome and seven healthy control subjects, aortic volumes and diameters at baseline were estimated by means of contrast material-enhanced magnetic resonance (MR) imaging. At 3 years of follow-up, aortic expansion rate were calculated in a subgroup of 22 patients with Marfan syndrome. Total aortic volume was defined as volume measurement from the level of the aortic annulus to the aortic bifurcation. Intra- and interobserver agreement of aortic volume were calculated by using the intraclass correlation coefficient. Differences in variables were analyzed with the Student t test and logistic regression. Effect size was calculated. RESULTS: Intra- and interobserver agreement of aortic volume calculation was 0.996 and 0.980, respectively. Mean aortic volume was significantly greater in patients with Marfan syndrome than in control subjects (104 mL/m(2); 95% confidence interval [CI]: 95, 114 mL/m(2) vs 74 mL/m(2); 95% CI: 62, 87 mL/m(2); P < .001). In 22 patients with Marfan syndrome, mean aortic volume was increased at 3 years of follow-up (17 mL; 95% CI: 8, 26 mL; P = .001; effect size, 0.29), while mean aortic diameter did not increase significantly (0.4 mm; 95% CI: 0.0, 0.9 mm; P = .171; effect size, 0.13). CONCLUSION: Assessment of aortic volume is highly reproducible and may be suited for use in the detection of aortic expansion in patients with Marfan syndrome. SUPPLEMENTAL MATERIAL: http://radiology.rsna.org/lookup/suppl/doi:10.1148/radiol.13122310/-/DC1.

Machine learning improves prediction of delayed cerebral ischemia in patients with subarachnoid hemorrhage.

BACKGROUND AND PURPOSE: Delayed cerebral ischemia (DCI) is a severe complication in patients with aneurysmal subarachnoid hemorrhage. Several associated predictors have been previously identified. However, their predictive value is generally low. We hypothesize that Machine Learning (ML) algorithms for the prediction of DCI using a combination of clinical and image data lead to higher predictive accuracy than previously applied logistic regressions. MATERIALS AND METHODS: Clinical and baseline CT image data from 317 patients with aneurysmal subarachnoid hemorrhage were included. Three types of analysis were performed to predict DCI. First, the prognostic value of known predictors was assessed with logistic regression models. Second, ML models were created using all clinical variables. Third, image features were extracted from the CT images using an auto-encoder and combined with clinical data to create ML models. Accuracy was evaluated based on the area under the curve (AUC), sensitivity and specificity with 95% CI. RESULTS: The best AUC of the logistic regression models for known predictors was 0.63 (95% CI 0.62 to 0.63). For the ML algorithms with clinical data there was a small but statistically significant improvement in the AUC to 0.68 (95% CI 0.65 to 0.69). Notably, aneurysm width and height were included in many of the ML models. The AUC was highest for ML models that also included image features: 0.74 (95% CI 0.72 to 0.75). CONCLUSION: ML algorithms significantly improve the prediction of DCI in patients with aneurysmal subarachnoid hemorrhage, particularly when image features are also included. Our experiments suggest that aneurysm characteristics are also associated with the development of DCI.

Predicting Delayed Cerebral Ischemia with Quantified Aneurysmal Subarachnoid Blood Volume.

BACKGROUND: The amount of blood detected on brain computed tomography scan is frequently used in prediction models for delayed cerebral ischemia (DCI) in patients with aneurysmal subarachnoid hemorrhage (aSAH). These models, which include coarse grading scales to assess the amount of blood, have only moderate predictive value. Therefore, we aimed to develop a predictive model for DCI including automatically quantified total blood volume (TBV). METHODS: We included patients from a prospective aSAH registry. TBV was assessed with an automatic hemorrhage quantification algorithm. The outcome measure was clinical deterioration due to DCI. Clinical and radiologic variables were included in a logistic regression model. The final model was selected by bootstrapped backward selection and internally validated by assessing the optimism-corrected R2 value, c-statistic, and calibration plot. The c-statistic of the TBV model was compared with models that used the (modified) Fisher scale instead. RESULTS: We included 369 patients. After backward selection, only TBV was included in the final model. The internally validated R2 value was 6%, and the c-statistic was 0.64. The c-statistic of the TBV model was higher than both the Fisher scale model (0.56; P < 0.001) and the modified Fisher scale model (0.58; P < 0.05). CONCLUSIONS: In our registry, only TBV independently predicted DCI. TBV discriminated better than the (modified) Fisher scale, but still had only moderate value for predicting DCI. Our findings suggest that other factors need to be identified to achieve better accuracy for predicting DCI.