Aneurysm Location Affects Clinical Course and Mortality in Patients With Subarachnoid Hemorrhage

Machine learning-based prediction of clinical outcomes after traumatic brain injury: Hidden information of early physiological time series

AIMS

To assess the predictive value of early-stage physiological time-series (PTS) data and non-interrogative electronic health record (EHR) signals, collected within 24 h of ICU admission, for traumatic brain injury (TBI) patient outcomes.

METHODS

Using data from TBI patients in the multi-center eICU database, we focused on in-hospital mortality, neurological status based on the Glasgow Coma Score (mGCS) motor subscore at discharge, and prolonged ICU stay (PLOS). Three machine learning (ML) models were developed, utilizing EHR features, PTS signals collected 24 h after ICU admission, and their combination. External validation was performed using the MIMIC III dataset, and interpretability was enhanced using the Shapley Additive Explanations (SHAP) algorithm.

RESULTS

The analysis included 1085 TBI patients. Compared to individual models and existing scoring systems, the combination of EHR and PTS features demonstrated comparable or even superior performance in predicting in-hospital mortality (AUROC = 0.878), neurological outcomes (AUROC = 0.877), and PLOS (AUROC = 0.835). The model's performance was validated in the MIMIC III dataset, and SHAP algorithms identified six key intervention points for EHR features related to prognostic outcomes. Moreover, the EHR results (All AUROC >0.8) were translated into online tools for clinical use.

CONCLUSION

Our study highlights the importance of early-stage PTS signals in predicting TBI patient outcomes. The integration of interpretable algorithms and simplified prediction tools can support treatment decision-making, contributing to the development of accurate prediction models and timely clinical intervention.

The Effect of Age on Cerebral Vasospasm and Delayed Cerebral Ischemia in Patients with Aneurysmal Subarachnoid Hemorrhage

BACKGROUND

The association between patient age and cerebral arterial vasospasm (CVS) and delayed cerebral ischemia (DCI) risk following aneurysmal subarachnoid hemorrhage (aSAH) remains unclear. This study aims to assess the role of age on aSAH-related complications.

METHODS

Single-center retrospective study comprising aSAH patients treated between January 2009 and March 2023. Age was analyzed as continuous and categorical variables (<60 yrs vs. ≥60 yrs and by decade). Outcomes of interest included radiographic CVS, DCI, cerebral infarction, in-hospital mortality, length-of-stay (LOS), ventriculoperitoneal shunt placement, and modified Rankin Scale (mRS) scores at discharge and 3-month follow-up.

RESULTS

Nine hundred and twenty-five aSAH patients were included. Most (n = 598; 64.6%) were <60 yrs old (46 ± 9.1 yrs). CVS likelihood was lower in the older cohort (aOR = 0.56 [0.38-0.82]). Patients ≥60 yrs had higher mortality rates (aOR = 2.24 [1.12-4.47]) and worse mRS scores at discharge (aOR = 2.66 [1.91-3.72]) and 3-month follow-up (aOR = 2.19 [1.44-3.32]). Advanced age did not have a significant effect on DCI or cerebral infarction risk. Higher in-hospital mortality was documented with increasing age (P < 0.001). A significant interaction between CVS and age for the outcome of DCI was documented, with a stronger positive effect on poor outcomes (i.e., higher odds of DCI) among patients aged <60 years compared to those aged ≥60.

CONCLUSIONS

There is an inverse relationship between patient age and CVS incidence following aSAH. Nonetheless, patients ≥60 yrs had comparable DCI rates, higher in-hospital mortality, and worse functional outcomes than their younger counterparts. Routine screening and reliance on radiographic CVS as primary marker for aSAH-related complications should be reconsidered, particularly in older patients.

Construction and verification of risk predicting models to evaluate the possibility of hydrocephalus following aneurysmal subarachnoid hemorrhage

BACKGROUND

Hydrocephalus following a ruptured aneurysm portends a poor prognosis. The authors aimed to establish a nomogram to predict the risk of hydrocephalus after aneurysmal subarachnoid hemorrhage (aSAH).

METHODS

A total of 421 patients with aSAH who were diagnosed by digital subtraction angiography in The General Hospital of Northern Theater Command center from January 2020 to June 2021 were screened to establish the training cohort. An additional 135 patients who enrolled between July 2021 and May 2022 were used for the validation cohort. Variate difference analysis and stepwise logistic regression (model A) and univariate and multivariate logistic regressions (model B) were respectively used to construct two models. Then, the net reclassification improvement (NRI), integrated discrimination improvement (IDI), and receiver operating characteristic (ROC) curve were used to compare the predictive abilities of the two models. Finally, two nomograms were constructed and externally validated.

RESULTS

After screening, 556 patients were included. The area under the ROC curve of models A and B in the training cohort were respectively 0.884 (95 % confidence interval [CI]: 0.847-0.921) and 0.834 (95 % CI: 0.787-0.881). The prediction ability of the model A was superior to model B (NRI > 0, IDI > 0, p < 0.05). The C-index of models A and B was 0.8835 and 0.8392, respectively. Regarding clinical usefulness, the two models offered a net benefit with a threshold probability of between 0.12 and 1 in the decision curve analysis, suggesting that the two models can accurately predict hydrocephalus events.

CONCLUSIONS

Both models have good prediction accuracy. Compared with model B, model A has better discrimination and calibration. Further, the easy-to-use nomogram can help neurosurgeons to make rapid clinical decisions and apply early treatment measures in high-risk groups, which ultimately benefits patients.

Evaluation of DeGIR registry data on endovascular treatment of cerebral vasospasm in Germany 2018-2021: an overview of the current care situation

BACKGROUND

Evaluation of endovascular therapies for cerebral vasospasm (CVS) documented in the DeGIR registry from 2018-2021 to analyse the current clinical care situation in Germany.

METHODS

Retrospective analysis of the clinical and procedural data on endovascular spasm therapies (EST) documented anonymously in the DeGIR registry. We analysed: pre-interventional findings of CTP and consciousness; radiation dose applied, interventional-technical parameters (local medication, devices, angiographic result), post-interventional symptoms, complications and mortality.

RESULTS

3584 patients received a total of 7628 EST (median age/patient: 53 [range: 13-100, IQR: 44-60], 68.2 % women) in 91 (2018), 92 (2019), 100 (2020) and 98 (2021) centres; 5388 (70.6 %) anterior circulation and 378 (5 %) posterior circulation (both involved in 1862 cases [24.4 %]). EST was performed once in 2125 cases (27.9 %), with a mean of 2.1 EST/patient. In 7476 times, purely medicated EST were carried out (nimodipine: 6835, papaverine: 401, nitroglycerin: 62, other drug not specified: 239; combinations: 90). Microcatheter infusions were documented in 1132 times (14.8 %). Balloon angioplasty (BA) (additional) was performed in 756 EST (9.9 %), other mechanical recanalisations in 154 cases (2 %) and stenting in 176 of the EST (2.3 %). The median dose area product during ET was 4069 cGycm² (drug: 4002/[+]BA: 8003 [p < 0.001]). At least 1 complication occurred in 95 of all procedures (1.2 %) (drug: 1.1 %/[+]BA: 4.2 % [p < 0.001]). Mortality associated with EST was 0.2 % (n = 18). After EST, overall improvement or elimination of CVS was found in 94.2 % of cases (drug: 93.8 %/[+]BA: 98.1 % [p < 0.001]). In a comparison of the locally applied drugs, papaverine eliminated CVS more frequently than nimodipine (p = 0.001).

CONCLUSION

EST have a moderate radiation exposure and can be performed with few complications. Purely medicated EST are predominantly performed, especially with nimodipine. With (additional) BA, radiation exposure, complication rates and angiographic results are higher or better. When considering drug EST alone, there is evidence for an advantage of papaverine over nimodipine, but a different group size has to be taken into account. In the analysis of EST, the DeGIR registry data are suitable for answering more specific questions, especially due to the large number of cases; for this purpose, further subgroupings should be sought in the data documentation.

KEY POINTS

· In Germany, there are currently no guidelines for the endovascular treatment of cerebral vasospasm following spontaneous subarachnoid hemorrhage.. · In addition to oral nimodipine administration endovascular therapy is used to treat cerebral vasospasm in most hospitals.. · This is the first systematic evaluation of nationwide registry data on endovascular treatment of cerebral vasopasm in Germany.. · This real-world data shows that endovascular treatment for cerebral vasospasm has a moderate radiation exposure and can be performed with few complications overall. With (additional) balloon angioplasty, radiation exposure, complication rates and angiographic therapy results are higher or better..

CITATION FORMAT

· Neumann A, Weber W, Küchler J et al. Evaluation of DeGIR registry data on endovascular treatment of cerebral vasospasm in Germany 2018-2021: an overview of the current care situation. Fortschr Röntgenstr 2023; 195: 1018 - 1026.