Machine learning based prediction of chronic shunt-dependent hydrocephalus after spontaneous subarachnoid hemorrhage.

BACKGROUND: Chronic posthemorrhagic hydrocephalus often arises following spontaneous subarachnoid hemorrhage (SAH). Timely identification of patients predisposed to develop chronic shunt-dependent hydrocephalus may significantly enhance clinical outcomes. METHODS: We performed an analysis of 510 SAH-patients treated at our institution between 2013 and 2018. Clinical and radiological variables, including age, sex, Hunt & Hess grade, Fisher-Score, external ventricular drainage placement, central nervous system infection, aneurysm characteristics, and treatment modalities, were evaluated. Supervised machine learning models, trained and compared using Python and scikit-learn, were employed to predict chronic shunt-dependent hydrocephalus. Model performance was rigorously assessed through repeated cross-validation. To facilitate transparency and collaboration, we publicly released the dataset and code on GitHub (https://github.com/RISCSoftware/shuntclf) and developed an interactive web application (https://huggingface.co/spaces/risc42/shuntclf). RESULTS: Among the evaluated machine learning models, logistic regression exhibited superior performance, with an AUC-ROC of 0.819 and an AUC-PR of 0.482, along with the highest F1 score of 0.473. Although the balanced accuracy scores of the models were generally proximate, ranging from 0.735 to 0.764, logistic regression consistently outperform others in key metrics such as AUC-ROC and AUC-PR. Conversely, female gender and absence of aneurysm within the anterior communicating artery were associated with reduced shunt requirement likelihood. CONCLUSION: Machine learning models, including logistic regression, demonstrate strong predictive capability for early chronic shunt-dependent hydrocephalus following spontaneous SAH, which may potentially contribute to more timely shunt placement interventions. This predictive capability is supported by our web interface, which simplifies the application of these models, aiding clinicians in efficiently determining the need for shunt placement.

Turning the operating room into a mixed-reality environment: a prospective clinical investigation for cerebral aneurysm clipping.

OBJECTIVE: The overall aim of this study was to demonstrate the potential benefit of a novel mixed-reality-head-mounted display (MR-HMD) on the spatial orientation of surgeons. METHODS: In a prospective clinical investigation, the authors applied for the first time a new multicamera navigation technology in an operating room setting that allowed them to directly compare MR-HMD navigation to standard monitor navigation. In the study, which included 14 patients with nonruptured middle cerebral artery aneurysms, the authors investigated how intuitively and effectively surgical instruments could be guided in 5 different visual navigation conditions. RESULTS: The authors demonstrate that multicamera tracking can be reliably integrated in a clinical setting (usability score 1.12 ± 0.31). Moreover, the technology captures large volumes of the operating room, allowing the team to track and integrate different devices and instruments, including MR-HMDs. Directly comparing mixed-reality navigation to standard monitor navigation revealed a significantly improved intuition in mixed reality, leading to navigation times that were twice as fast (2.1×, p ≤ 0.01). Despite the enhanced speed, the same targeting accuracy (approximately 2.5 mm, freehand tool use) in comparison to monitor navigation could be observed. Intraoperative planning strategies with mixed reality clearly outperformed classic preoperative planning: surgeons scored the mixed-reality plan as the best trajectory in 63% of the cases (chance level 33%). CONCLUSIONS: The incorporation of mixed reality in neurosurgical operations marks a significant advancement in the field. The use of mixed reality in brain surgery enhances the spatial awareness of surgeons, enabling more instinctive and precise surgical interventions. This technological integration promises to refine the execution of complex procedures without compromising accuracy.

A randomized, single ascending dose safety, tolerability and pharmacokinetics study of NicaPlant® in aneurysmal subarachnoid hemorrhage patients undergoing clipping.

Introduction: Aneurysmal subarachnoid hemorrhage (aSAH) is associated with high morbidity and mortality. Post-hemorrhagic vasospasm with neurological deterioration is a major concern in this context. NicaPlant®, a modified release formulation of the calcium channel blocker nicardipine, has shown vasodilator efficacy preclinically and a similar formulation known as NPRI has shown anti-vasospasm activity in aSAH patients under compassionate use. Research question: The study aimed to assess pharmacokinetics and pharmacodynamics of NicaPlant® pellets to prevent vasospasm after clip ligation in aSAH. Material and methods: In this multicenter, controlled, randomized, dose escalation trial we assessed the safety and tolerability of NicaPlant®. aSAH patients treated by clipping were randomized to receive up to 13 NicaPlant® implants, similarly to the dose of NPRIs previous used, or standard of care treatment. Results: Ten patients across four dose groups were treated with NicaPlant® (3-13 implants) while four patients received standard of care. 45 non-serious and 13 serious adverse events were reported, 4 non-serious adverse events and 5 serious adverse events assessed a probable or possible causal relationship to the investigational medical product. Across the NicaPlant® groups there was 1 case of moderate vasospasm, while in the standard of care group there were 2 cases of severe vasospasm. Discussion and conclusion: The placement of NicaPlant® during clip ligation of a ruptured cerebral aneurysm raised no safety concern. The dose of 10 NicaPlant® implants was selected for further clinical studies.

Virtual Cerebral Aneurysm Clipping with Real-Time Haptic Force Feedback in Neurosurgical Education.

OBJECTIVE: Realistic, safe, and efficient modalities for simulation-based training are highly warranted to enhance the quality of surgical education, and they should be incorporated in resident training. The aim of this study was to develop a patient-specific virtual cerebral aneurysm-clipping simulator with haptic force feedback and real-time deformation of the aneurysm and vessels. METHODS: A prototype simulator was developed from 2012 to 2016. Evaluation of virtual clipping by blood flow simulation was integrated in this software, and the prototype was evaluated by 18 neurosurgeons. In 4 patients with different medial cerebral artery aneurysms, virtual clipping was performed after real-life surgery, and surgical results were compared regarding clip application, surgical trajectory, and blood flow. RESULTS: After head positioning and craniotomy, bimanual virtual aneurysm clipping with an original forceps was performed. Blood flow simulation demonstrated residual aneurysm filling or branch stenosis. The simulator improved anatomic understanding for 89% of neurosurgeons. Simulation of head positioning and craniotomy was considered realistic by 89% and 94% of users, respectively. Most participants agreed that this simulator should be integrated into neurosurgical education (94%). Our illustrative cases demonstrated that virtual aneurysm surgery was possible using the same trajectory as in real-life cases. Both virtual clipping and blood flow simulation were realistic in broad-based but not calcified aneurysms. Virtual clipping of a calcified aneurysm could be performed using the same surgical trajectory, but not the same clip type. CONCLUSIONS: We have successfully developed a virtual aneurysm-clipping simulator. Next, we will prospectively evaluate this device for surgical procedure planning and education.

Functional Outcomes in Individuals Undergoing Very Early (< 5 h) and Early (5-24 h) Surgical Decompression in Traumatic Cervical Spinal Cord Injury: Analysis of Neurological Improvement from the Austrian Spinal Cord Injury Study.

Our study aim was to assess the neurological outcomes of surgical decompression and stabilization within 5 and 24 h after injury. We performed a multi-center, retrospective cohort study in adolescents and adults 15-85 years of age presenting cervical spinal cord injury (CSCI) at one of 6 Austrian trauma centers participating in the Austrian Spinal Cord Injury Study (ASCIS). Neurological outcomes were measured using the American Spinal Injury Association Impairment Scale (AIS) grade according to the International Standards For Neurological Classification Of Spinal Cord Injury (ISNCSCI) form after at least 6 months of follow-up (FU). Of the 49 enrolled patients with acute CSCI, 33 underwent surgical decompression within 5 h (mean 3.2 h ± 1.1 h; very early group) after injury, and 16 underwent surgical decompression between 5 and 24 h (mean 8.6 h ± 5.5 h; early group). Significant neurological improvement was observed among the entire study population between the preoperative assessment and the FU. We identified a significant difference in the AIS grade at the last FU between the groups the using Jonckheere-Terpstra test for doubly ordered crosstabs (p = 0.011) and significantly different AIS improvement rates in the early group (Poisson model, p = 0.018). Improvement by one AIS grade was observed in 31% and 42% of the patients in the early and very early groups, respectively (p = 0.54). Improvement by two AIS grades was observed in 31% and 6% of the patients in the early and very early groups, respectively (p = 0.03; relative risk [RR], 5.2; 95% CI, 1.1-35). Improvement by three AIS grades was observed in 6% and 3% of patients in the early and very early groups, respectively (p = 1.0). Decompression of the spinal cord within 24 h after SCI was associated with an improved neurological outcome. No additional neurological benefit was observed in patients who underwent decompression within 5 h of injury.

Intraspinal Lumbar Juxtaarticular Cyst Treatment Through CT-Guided Percutaneus Induced Rupture Results in a Favorable Patient Outcome.

Juxta-articular cysts are synovial cysts originating from the facet joints or the flava ligaments. If they grow intra-spinally they can compress nervous structures and cause a variety of symptoms. Micro-neurosurgery is usually the treatment of choice. Alternatively to surgical treatment the cyst can be approached and treated with a CT guided percutaneous injection inducing rupture. After fulfilling strict selection criteria twenty patients (25% of all treated lumbar synovial cyst patients), were treated minimally invasive by this method from 2010-2016. The facet joint was punctured under CT guidance and a mixture of a local anesthetic and contrast liquid was injected until the cyst was blasted. The mean follow-up period was 1.1 years (range 2 weeks - 5 years). Fifteen of twenty procedures were successful and cyst rupture was confirmed by CT-scans. Twelve of these fifteen patients experienced a significant improvement of their symptoms and needed no further intervention or surgical procedure up until now, three patients showed no clinical improvement and were treated surgically within one week after cyst rupture. In five patients it was technically not possible to rupture the cyst. These patients were treated microsurgically by cyst resection and dynamic stabilization or fusion procedures. The percutaneus rupture of juxtaarticular cysts has fewer risks and is cost effective compared to microsurgical resection. It may be an alternative to surgical treatment for a selected group of patients. However there are some limitations to the procedure though, such as difficult patient selection, unpredictable outcome or technical problems due to highly degenerated facet joints.