Development of machine learning models to prognosticate chronic shunt-dependent hydrocephalus after aneurysmal subarachnoid hemorrhage.

BACKGROUND: Shunt-dependent hydrocephalus significantly complicates subarachnoid hemorrhage (SAH), and reliable prognosis methods have been sought in recent years to reduce morbidity and costs associated with delayed treatment or neglected onset. Machine learning (ML) defines modern data analysis techniques allowing accurate subject-based risk stratifications. We aimed at developing and testing different ML models to predict shunt-dependent hydrocephalus after aneurysmal SAH. METHODS: We consulted electronic records of patients with aneurysmal SAH treated at our institution between January 2013 and March 2019. We selected variables for the models according to the results of the previous works on this topic. We trained and tested four ML algorithms on three datasets: one containing binary variables, one considering variables associated with shunt-dependency after an explorative analysis, and one including all variables. For each model, we calculated AUROC, specificity, sensitivity, accuracy, PPV, and also, on the validation set, the NPV and the Matthews correlation coefficient (ϕ). RESULTS: Three hundred eighty-six patients were included. Fifty patients (12.9%) developed shunt-dependency after a mean follow-up of 19.7 (± 12.6) months. Complete information was retrieved for 32 variables, used to train the models. The best models were selected based on the performances on the validation set and were achieved with a distributed random forest model considering 21 variables, with a ϕ = 0.59, AUC = 0.88; sensitivity and specificity of 0.73 (C.I.: 0.39-0.94) and 0.92 (C.I.: 0.84-0.97), respectively; PPV = 0.59 (0.38-0.77); and NPV = 0.96 (0.90-0.98). Accuracy was 0.90 (0.82-0.95). CONCLUSIONS: Machine learning prognostic models allow accurate predictions with a large number of variables and a more subject-oriented prognosis. We identified a single best distributed random forest model, with an excellent prognostic capacity (ϕ = 0.58), which could be especially helpful in identifying low-risk patients for shunt-dependency.

Spontaneous rupture of a secondary pituitary abscess causing acute meningoencephalitis: Case report and literature review.

BACKGROUND: Pituitary abscess (PA) is an uncommon finding that is rarely diagnosed preoperatively. If not properly treated it is associated with high morbidity and mortality rates. Nowadays standard diagnostic procedures allow early detection and successful treatment of this lesion in a high number of cases and mortality has been significantly reduced in recent years. PA arising de novo in a healthy gland are defined as primary, whereas those complicating a pre-existing disease of the hypophysis are called secondary abscesses. CASE DESCRIPTION: We present a case of a secondary PA mimicking a large pituitary adenoma extending in the nasal cavity, which was wrongly diagnosed as such. The abscess showed an unexpected evolution in 48 h from presentation due to a sudden, extensive intracranial leakage of pus. CONCLUSIONS: To our knowledge, it is rare to find PA showing a rapid evolution like this, and in the literature only one previous case of a PA not reaching medical or surgical therapy was reported. In that case, hypothalamus involvement was identified as the cause of death. This should be the first case reported of a spontaneous PA rupture causing acute meningoencephalitis. Along with a short review of the literature on the major features of PA, we also tried to identify some features which could be supportive of a diagnosis of secondary PA.

A rare association of ganglioglioma and cavernous malformation: Report of two cases and literature review.

BACKGROUND: Some glial tumors have been observed in association with different types of vascular malformations of the brain (angiogliomas). However, the association of ganglioglioma with other vascular malformations is extremely rare, with only few cases reported in the literature, one of which is referred to as "angioganglioglioma." CASE DESCRIPTION: Two patients presented with acute onset of neurological symptoms, with magnetic resonance imaging (MRI) finding of cavernoma of the left middle cerebellar penduncle, and small mass of the chiasmatic region, respectively. After microsurgical excision, histopathological examination revealed mixed ganglioglioma and cavernous malformation in both cases. Postoperative course was uneventful, and follow-up MRI showed complete removal of the tumor with no recurrence after 4 years. CONCLUSIONS: Angiogliomas are very uncommon tumors. In literature, we found different interpretations of such lesions, although they should most probably be considered as distinct pathological entities. Although the association of ganglioglioma with cavernoma is extremely rare, it could be considered as a most peculiar form of angioglioma, and supports the existence of angioganglioglioma.