Is There a Role for Machine Learning in Liquid Biopsy for Brain Tumors? A Systematic Review.

The paucity of studies available in the literature on brain tumors demonstrates that liquid biopsy (LB) is not currently applied for central nervous system (CNS) cancers. The purpose of this systematic review focused on the application of machine learning (ML) to LB for brain tumors to provide practical guidance for neurosurgeons to understand the state-of-the-art practices and open challenges. The herein presented study was conducted in accordance with the PRISMA-P (preferred reporting items for systematic review and meta-analysis protocols) guidelines. An online literature search was launched on PubMed/Medline, Scopus, and Web of Science databases using the following query: "((Liquid biopsy) AND (Glioblastoma OR Brain tumor) AND (Machine learning OR Artificial Intelligence))". The last database search was conducted in April 2023. Upon the full-text review, 14 articles were included in the study. These were then divided into two subgroups: those dealing with applications of machine learning to liquid biopsy in the field of brain tumors, which is the main aim of this review (n = 8); and those dealing with applications of machine learning to liquid biopsy in the diagnosis of other tumors (n = 6). Although studies on the application of ML to LB in the field of brain tumors are still in their infancy, the rapid development of new techniques, as evidenced by the increase in publications on the subject in the past two years, may in the future allow for rapid, accurate, and noninvasive analysis of tumor data. Thus making it possible to identify key features in the LB samples that are associated with the presence of a brain tumor. These features could then be used by doctors for disease monitoring and treatment planning.

Stereoscopic Monitoring Technique for Motor Area Tumors.

BACKGROUND: The balance between comprehensive intraoperative neurophysiological monitoring (IONM) for both upper and lower limbs while ensuring the reliability of motor evoked potentials (MEPs) is paramount in motor area surgery. It is commonly difficult to obtain good simultaneous stimulation of both upper and lower limbs. A series of factors can bias MEP accuracy, and inappropriate stimulation intensity can result in unreliable monitoring. The presented IONM technique is based on the concurrent use of both transcranial and cortical strip electrodes to facilitate simultaneous monitoring of both upper and lower limbs at optimized stimulation intensities to increase IONM accuracy during motor area surgery. METHODS: Ten nonconsecutive motor area tumors were studied. Good visualization of both limbs was observed in the series at a low amperage (1.2 mA from the strip electrode and 165.3 mA from the transcranial electrode). RESULTS: Our analysis confirms concordance between the IONM data and postoperative outcomes. An MEP reduction >20% and >50% correlated with postoperative modified Rankin scale score changes without false-negative IONM findings. CONCLUSIONS: The technique was demonstrated to be accurate in providing a good simultaneous neurophysiological evaluation of both upper and lower limbs with an optimized and stimulation amplitude. The technique results in a low encumbrance of electrodes in the surgical field. Our results have confirmed the "proof of concept," its reliability and feasibility.

Predicting Role of GFAP and UCH-L1 biomarkers in Spontaneous Subarachnoid Hemorrhage: a preliminary study to evaluate in the short-term their correlation with severity of bleeding and prognosis.

BACKGROUND: Spontaneous non-traumatic subarachnoid hemorrhage (sSAH) is a severe brain vascular accident. Glial fibrillary acidic protein (GFAP) and ubiquitin carboxy-terminal hydrolase L1 (UCH-L1) can be theoretically assayed to predict a patient's progression, picturing different aspects of clinical failure after sSAH. The study aims to: a) explore the correlation between sSAH blood volume and biomarkers variation; b) evaluate if these can be predictive of the neurogenic response after sSAH and be prognostic of patient outcome; c) establish eventual threshold levels of biomarkers to define patients' clinical outcome. METHODS: Blood volumetry at CT scan upon admission, GFAP and UCH-L1 were collected at 24 h, at 72 h, and after 7 days from hemorrhage. Trends and cut-off serum sampling were determined. Clinical outcome was assessed with mRS scale at 14 days. RESULTS: A strong correlation between GFAP and UCH-L1 and blood diffusion volume in all explored serum intervals related to unfavorable outcome. GFAP and UCH-L1 were very early predictors of unfavorable outcomes at 24 h from sSAH (p = 0.002 and 0.011 respectively). Threshold levels of UCH-L1 apparently revealed a very early, early and late predictor of unfavorable outcomes. CONCLUSION: GFAP and UCH-L1 represent a potential tool for prompt monitoring and customization of therapies in neurosurgical patients.

Paths of Evolution of Progressive Anaplastic Meningiomas: A Clinical and Molecular Pathology Study.

Grade 3 meningiomas are rare malignant tumors that can originate de novo or from the progression of lower grade meningiomas. The molecular bases of anaplasia and progression are poorly known. We aimed to report an institutional series of grade 3 anaplastic meningiomas and to investigate the evolution of molecular profile in progressive cases. Clinical data and pathologic samples were retrospectively collected. VEGF, EGFR, EGFRvIII, PD-L1; and Sox2 expression; MGMT methylation status; and TERT promoter mutation were assessed in paired meningioma samples collected from the same patient before and after progression using immunohistochemistry and PCR. Young age, de novo cases, origin from grade 2 in progressive cases, good clinical status, and unilateral side, were associated with more favorable outcomes. In ten progressive meningiomas, by comparing molecular profile before and after progression, we identified two subgroups of patients, one defined by Sox2 increase, suggesting a stem-like, mesenchymal phenotype, and another defined by EGFRvIII gain, suggesting a committed progenitor, epithelial phenotype. Interestingly, cases with Sox2 increase had a significantly shortened survival compared to those with EGFRvIII gain. PD-L1 increase at progression was also associated with worse prognosis, portending immune escape. We thus identified the key drivers of meningioma progression, which can be exploited for personalized treatments.