Machine learning model prediction of 6-month functional outcome in elderly patients with intracerebral hemorrhage.

Spontaneous intracerebral hemorrhage (ICH) has an increasing incidence and a worse outcome in elderly patients. The ability to predict the functional outcome in these patients can be helpful in supporting treatment decisions and establishing prognostic expectations. We evaluated the performance of a machine learning (ML) model to predict the 6-month functional status in elderly patients with ICH leveraging the predictive value of the clinical characteristics at hospital admission. Data were extracted by a retrospective multicentric database of patients ≥ 70 years of age consecutively admitted for the management of spontaneous ICH between January 1, 2014 and December 31, 2019. Relevant demographic, clinical, and radiological variables were selected by a feature selection algorithm (Boruta) and used to build a ML model. Outcome was determined according to the Glasgow Outcome Scale (GOS) at 6 months from ICH: dead (GOS 1), poor outcome (GOS 2-3: vegetative status/severe disability), and good outcome (GOS 4-5: moderate disability/good recovery). Ten features were selected by Boruta with the following relative importance order in the ML model: Glasgow Coma Scale, Charlson Comorbidity Index, ICH score, ICH volume, pupillary status, brainstem location, age, anticoagulant/antiplatelet agents, intraventricular hemorrhage, and cerebellar location. Random forest prediction model, evaluated on the hold-out test set, achieved an AUC of 0.96 (0.94-0.98), 0.89 (0.86-0.93), and 0.93 (0.90-0.95) for dead, poor, and good outcome classes, respectively, demonstrating high discriminative ability. A random forest classifier was successfully trained and internally validated to stratify elderly patients with spontaneous ICH into prognostic subclasses. The predictive value is enhanced by the ability of ML model to identify synergy among variables.

Airgun Wound with Superior Sagittal Sinus Involvement in a Child: Case Report and Review of the Literature.

INTRODUCTION: Although still considered quite harmless, nonpowder guns (NPG) may cause severe head injuries in children. We present the case of a depressed skull fracture with superior sagittal sinus involvement following NPG injury. Decision-making and surgical management are discussed, and the current literature concerning NPG-related pediatric head injuries is reviewed. CASE PRESENTATION: A 4-year-old boy hit by a compressed-air rifle came to our center. CT scan showed a depressed skull fracture of the occipital bone on the midline and intracranial penetration of some fragments of the pellet. CT angiography documented a compression of the superior sagittal sinus without thrombosis. Soon after hospital admission, the patient showed deterioration of the neurological status suggesting intracranial hypertension. Surgery was performed with fracture elevation, removal of metal fragments, and wound debridement. The patient had a full recovery without subsequent neurological deficits. DISCUSSION/CONCLUSION: Modern airguns may produce severe penetrating head injuries in children. Parents and physicians should be aware of the danger of NPG. Depressed skull fracture and dural venous sinus involvement can occur, and even a stable neurological condition may worsen. In such instances, a thorough preoperative assessment including vascular imaging is mandatory. The surgical risk is not negligible due to the possible injury of the sinus wall and subsequent intraoperative bleeding. This has to be weighted against potential complications of the penetrating injury, such as infection, sinus thrombosis, and intracranial hypertension. Our case suggests that prompt surgical treatment can be a safe and effective option.

Radiological outcomes for endovascular treatment of posterior communicating artery aneurysms: a retrospective multicenter study of the occlusion rate.

Although several innovations in techniques and implantable devices were reported over the last decades, a consensus on the best endovascular treatment for intracranial aneurysms originating from the posterior communicating artery is still missing. This work investigates radiological outcomes of different endovascular techniques for posterior communicating artery aneurysms treatment in a retrospective multi-centric cohort. We included patients endovascularly treated for posterior communicating artery aneurysms from 2015 through 2020 in six tertiary referral hospitals. We evaluated the relationship between patients and aneurysms characteristics, baseline neurological status, radiological outcomes, and the different endovascular techniques. Overall, 250 patients were included in this study. Simple coiling was the most frequent treatment in 171 patients (68%), followed by flow-diverter stenting in 32 cases (13%). Complete occlusion was reported in 163 patients (65%), near-complete occlusion in 43 (17%), and incomplete occlusion in 44 (18%). Radiological follow-up was available for 247 (98%) patients. The occlusion rate was stable in 149 (60%), improved in 49 (19%), and worsened in 51 (21%). No significant difference in exclusion rate was seen between ruptured and unruptured aneurysms at the last follow-up (p = 0.4). Posterior communicating artery thrombosis was reported in 25 patients (9%), transient ischemic attack in 6 (2%), and in 38 patients (15%), subsequent procedures were needed due to incomplete occlusion or reperfusion. Endovascular strategies for posterior communicating artery aneurysms represent effective and relatively safe treatments. Simple coiling provides a higher immediate occlusion rate, although recanalization has been frequently reported, conversely, flow-diversion devices provide good long-term radiological outcomes.

Filthy operative rooms and other mistakes during movies on neurosurgical procedures: Fascinating and powerful neurosurgical scenarios presented, in different ways, to non-neurosurgical society. How many mistakes and stereotypes can be made in movies for people not daily involved in medical life?

OBJECTIVES: The brain and people "manipulating" it, provide a very mysterious and fascinating substrate for a movie. Faithful representation of reality often represent a key for the success of a film. Nonetheless, while watching movies with neurosurgical scenes, we often observed actions and elements containing incredible errors that aroused opposing emotions. The aim of this study was to perform an extensive review examining the representations of neurosurgery in movies, especially focused on the analysis of neurosurgical gross mistakes. PATIENT AND METHODS: We looked for any movie that featured a neurosurgeon or a scene including a neurosurgical disease or procedure. We used one of the largest internet movie databases available online (IMDb.com) with searching for keywords such as "neurosurgeon", "neurosurgery", and "craniotomy". Title, year, genre and cost of production were collected. The first three features were detected on IMDb.com; the costs of production were found in websites the-numbers.com and boxofficemojo.com. Analysis and selection were performed by AM and PDB. RESULT: 73 movies were found. After the application of inclusion/exclusion criteria, 58 have been eligible for inclusion in the study (Table 1) and 15 have been excluded from the final analysis". Out of 45 movies watched, we found 32 neurosurgical mistakes. Mistakes were classified into four big groups, namely: "surgical asepsis and principles of sterile technique" (n = 13, 40 %); "conceptual mistakes (n = 10, 31.5 %)"; "incorrect use of surgical tools (n = 7, 22 %)" ; "anatomical and radiological mistakes (n = 2, 6.5 %)". The costs of production started from 11.000 US dollars (Vsivaci, 2014) to 200 millions dollars (Spiderman 2, 2004), with a median value of 8.2 millions dollars each. All mistakes were not useful for the correct progress of the movie. CONCLUSION: Our review shows that several mistakes, especially on asepsis during surgery are present in films dealing with neurosurgery. Several movies costed up to millions of dollars. Would a consultation of a Neurosurgeon before/during the shooting narrow the gap between the reality and fiction?