Artificial neural network predicts hemorrhagic contusions following decompressive craniotomy in traumatic brain injury.

BACKGROUND: This study aimed to explore relevant factors of hemorrhagic contusions following decompressive craniotomy (DC) in traumatic brain injury (TBI) and create an artificial neural network (ANN) prediction model of the risk factors of hemorrhagic contusions. METHODS: This study analyzed 425 patients with TBI who underwent DC in the Neurosurgery Department of Shaoxing People's Hospital between 2009 and 2014. Patients were divided into two groups according to the first postoperative CT scans: hemorrhage group and non-hemorrhage group. Gender, age, preoperative situations (Initial Rotterdam CT Score, GCS Score, pupillary response, laboratory data and preoperative hematoma), the time gap between trauma and DC, postoperative CT scans, and Glasgow Outcome Scale (GOS) scores were recorded. ANN was used to predict hematoma. Correlation analysis was used to state the relationship between increased hemorrhage volumes and GOS scores. RESULTS: The ANN prediction model was established. This model included 11 parameters: initial Rotterdam CT score, GCS score, C-reactive protein, age, the time gap between trauma and DC, pupillary response, platelet count, bone-flap size, glucose level, hernia magnitude and preoperative hematoma volume. The overall predictive accuracy of the model was 73.0%. CONCLUSIONS: Initial Rotterdam CT scores and GCS scores may predict the risk of expansion contusions following DC. The ANN prediction model has a high accuracy to forecast hemorrhage.

3D printing of intracranial aneurysm based on intracranial digital subtraction angiography and its clinical application.

The study aimed to develop simulation models including intracranial aneurysmal and parent vessel geometries, as well as vascular branches, through 3D printing technology. The simulation models focused on the benefits of aneurysmal treatments and clinical education. This prospective study included 13 consecutive patients who suffered from intracranial aneurysms confirmed by digital subtraction angiography (DSA) in the Neurosurgery Department of Shaoxing People's Hospital. The original 3D-DSA image data were extracted through the picture archiving and communication system and imported into Mimics. After reconstructing and transforming to Binary STL format, the simulation models of the hollow vascular tree were printed using 3D devices. The intracranial aneurysm 3D printing simulation model was developed based on DSA to assist neurosurgeons in aneurysmal treatments and residency training. Seven neurosurgical residents and 15 standardization training residents received their simulation model training and gave high assessments for the educational course with the follow-up qualitative questionnaire. 3D printed simulation models based on DSA can perfectly reveal target aneurysms and help neurosurgeons select therapeutic strategies precisely. As an educational tool, the 3D aneurysm vascular simulation model is useful for training residents.

Mini-arteriotomy to remove misplaced Gugliemi detachable coils: case report and technical note.

Coil-related thromboembolic complications due to misplacement of coils in embolization of the intracranial aneurysms might result in severe neurological deficits. We describe an unusual case of a ruptured posterior communicating artery (PcomA) aneurysm in a woman who underwent a Mini-Arteriotomy to rescue error embolism in the left middle cerebral artery (MCA). This surgical procedure might be considered as an alternative route in selected patients with coil-related thromboembolic complications. This novel technology gives us a simple and practical method to remedy the misplacement of coils in a wide region of the cerebral vascular after interventional treatment.

Serum caspase-cleaved cytokeratin-18 levels and outcomes after aneurysmal subarachnoid hemorrhage.

OBJECTIVE: Cell apoptosis is involved in acute brain injury after aneurysmal subarachnoid hemorrhage (aSAH). The protein cytokeratin-18 (CK-18) is cleaved by the action of caspases during apoptosis, and the resulting fragments are released into the blood as caspase-cleaved CK (CCCK)-18. Our study examined the relationship between circulating CCCK-18 levels and long-term clinical outcomes among aSAH patients. METHODS: We recruited 128 aSAH patients and 128 controls (matched on age and sex). Serum was collected at admission to the emergency department. Unfavorable outcome was defined as the Glasgow Outcome Score scores of 1-3. After a 6-month follow-up period, outcomes were assessed using a logistic regression analyses. The prognostic predictive values were evaluated according to receiver operating curves analysis. RESULTS: aSAH patients had higher plasma CCCK-18 levels compared to controls (235.1 ± 86.8 U/L vs. 25.6 ± 23.4 U/L, P<0.001). CCCK-18 was independently associated with World Federation of Neurological Surgeons (WFNS) scores (t=4.460, P<0.001) and modified Fisher scores (t=3.781, P<0.001). Furthermore, CCCK-18 levels were markedly higher among patients with an unfavorable outcome and among non-survivors. CCCK-18 was yet identified as an independent prognostic predictor for mortality (odds ratio, 5.769; 95% confidence interval, 1.196-27.832; P=0.029) and unfavorable outcome (odds ratio, 4.909; 95% confidence interval, 1.521-15.838; P=0.008), as well as had similar predictive values for them compared with WFNS scores and modified Fisher scores. CONCLUSIONS: High circulating CCCK-18 levels were associated with injury severity and a poor clinical outcome after aSAH and CCCK-18 had the potential to be a good prognostic biomarker for aSAH.