Glioblastoma Pseudoprogression Discrimination Using Multiparametric Magnetic Resonance Imaging, Principal Component Analysis, and Supervised and Unsupervised Machine Learning.

BACKGROUND: One of the most frequent phenomena in the follow-up of glioblastoma is pseudoprogression, present in up to half of cases. The clinical usefulness of discriminating this phenomenon through magnetic resonance imaging and nuclear medicine has not yet been standardized; in this study, we used machine learning on multiparametric magnetic resonance imaging to explore discriminators of this phenomenon. METHODS: For the study, 30 patients diagnosed with IDH wild-type glioblastoma operated on at both study centers in 2011-2020 were selected; 15 patients corresponded to early tumor progression and 15 patients to pseudoprogression. Using unsupervised learning, the number of clusters and tumor segmentation was recorded using gap-stat and k-means method, adjusting to voxel adjacency. In a second phase, a class prediction was carried out with a multinomial logistic regression supervised learning method; the outcome variables were the percentage of assignment, class overrepresentation, and degree of voxel adjacency. RESULTS: Unsupervised learning of the tumor in its diagnosis shows up to 14 well-differentiated tumor areas. In the supervised learning phase, there is a higher percentage of assigned classes (P < 0.01), less overrepresentation of classes (P < 0.01), and greater adjacency (55% vs. 33%) in cases of true tumor progression compared with pseudoprogression. CONCLUSIONS: True tumor progression preserves the multidimensional characteristics of the basal tumor at the voxel and region of interest level, resulting in a characteristic differential pattern when supervised learning is used.

Protocolo de consenso en el tratamiento antitrombótico (anticoagulación y antiagregación) durante el periodo perioperatorio y periprocedimiento en neurocirugía / Antithrombotic treatment consensus protocol (anticoagulation and antiplatelet therapy) during the perioperative and periprocedural period in neurosurgery

El uso de medicación antitrombótica (antiagregante y/o anticoagulante) se encuentra ampliamente extendido. El manejo de los pacientes neuroquirúrgicos que reciben este tipo de terapia continúa siendo, a día de hoy, un problema de especial importancia. Los pacientes en tratamiento antitrombótico pueden necesitar atención neuroquirúrgica bien por presentar sangrados secundarios a dicho tratamiento, lesiones neuroquirúrgicas no hemorrágicas pero que precisen intervención urgente, o simplemente procedimientos neuroquirúrgicos electivos. Además, las consecuencias de la reintroducción de la anticoagulación temprana (sangrado o resangrado) o tardía (trombóticas o tromboembólicas) pueden ser devastadoras. En este documento presentamos el protocolo de consenso en el tratamiento antitrombótico durante el periodo perioperatorio y periprocedimiento, tanto en cirugía emergente como en procedimientos electivos de neurocirugía

The use of antithrombotic medication (antiplatelet and/or anticoagulant therapy) is widespread. Currently, the management of neurosurgical patients receiving this type of therapy continues to be a problem of special importance. Patients receiving antithrombotic treatment may need neurosurgical care because of bleeding secondary to such treatment, non-haemorrhagic neurosurgical lesions requiring urgent attention, or simply elective neurosurgical procedures. In addition, the consequences of reintroducing early (bleeding or rebleeding) or late (thrombotic or thromboembolic) anticoagulation can be devastating. In this paper we present the antithrombotic treatment consensus protocol during the perioperative and periprocedural period, both in emergent surgery and in elective neurosurgical procedures

[Antithrombotic treatment consensus protocol (anticoagulation and antiplatelet therapy) during the perioperative and periprocedural period in neurosurgery]. / Protocolo de consenso en el tratamiento antitrombótico (anticoagulación y antiagregación) durante el periodo perioperatorio y periprocedimiento en neurocirugía.

The use of antithrombotic medication (antiplatelet and/or anticoagulant therapy) is widespread. Currently, the management of neurosurgical patients receiving this type of therapy continues to be a problem of special importance. Patients receiving antithrombotic treatment may need neurosurgical care because of bleeding secondary to such treatment, non-haemorrhagic neurosurgical lesions requiring urgent attention, or simply elective neurosurgical procedures. In addition, the consequences of reintroducing early (bleeding or rebleeding) or late (thrombotic or thromboembolic) anticoagulation can be devastating. In this paper we present the antithrombotic treatment consensus protocol during the perioperative and periprocedural period, both in emergent surgery and in elective neurosurgical procedures.

Subarachnoid hemorrhage in systemic lupus erythematosus: systematic review and report of three cases.

OBJECTIVE: Systemic lupus erythematosus (SLE) is an autoimmune disorder of multifactorial etiology with a broad range of clinical manifestations. Cerebral disorders such as psychosis, seizures and cerebrovascular accidents are commonly described in SLE patients. Subarachnoid hemorrhage (SAH) presents a higher incidence than in the general population. Saccular aneurysms are the most frequent cause, but uncommon forms of SAH had been repeatedly reported in SLE patients. Through three case examples we outline these uncommon patterns, which we hypothesized, might be responsible for the higher incidence of SAH in SLE patients. METHODS: We present three patients previously diagnosed with SLE, who suffered a SAH and we perform a systematic literature review. RESULTS: All three cases presented with a Fisher grade IV bleeding. One harbored a distal middle cerebral artery aneurysm, another had multiple aneurysms, and the youngest patient had no findings on the cerebral angiography. A focal vasculitic process seemed most likely responsible for the two aneurismal cases. The angiography negative case was attributed to severe SLE systemic complications and had an unexpected bad outcome. Literature review yielded 39 previously reported cases. CONCLUSIONS: The uncommon SAH patterns make etiological diagnosis challenging. Management can also be daunting due to both local and systemic consequences of SLE. Awareness of these uncommon patterns, management challenges, and higher likelihood of bad outcomes may help physicians dealing with this disease. Further research to unveil the mechanisms behind it is granted to fully understand SAH in SLE patients.