scholarly journals Machine Learning Analytics of Resting-State Functional Connectivity Predicts Survival Outcomes of Glioblastoma Multiforme Patients

2021 ◽  
Vol 12 ◽  
Author(s):  
Bidhan Lamichhane ◽  
Andy G. S. Daniel ◽  
John J. Lee ◽  
Daniel S. Marcus ◽  
Joshua S. Shimony ◽  
...  
Keyword(s):  
Machine Learning ◽  
Glioblastoma Multiforme ◽  
Functional Connectivity ◽  
Resting State ◽  
Learning Analytics ◽  
Support Vector ◽  
Resting State Functional Connectivity ◽  
Term Survival ◽  
Long Term Survival

Glioblastoma multiforme (GBM) is the most frequently occurring brain malignancy. Due to its poor prognosis with currently available treatments, there is a pressing need for easily accessible, non-invasive techniques to help inform pre-treatment planning, patient counseling, and improve outcomes. In this study we determined the feasibility of resting-state functional connectivity (rsFC) to classify GBM patients into short-term and long-term survival groups with respect to reported median survival (14.6 months). We used a support vector machine with rsFC between regions of interest as predictive features. We employed a novel hybrid feature selection method whereby features were first filtered using correlations between rsFC and OS, and then using the established method of recursive feature elimination (RFE) to select the optimal feature subset. Leave-one-subject-out cross-validation evaluated the performance of models. Classification between short- and long-term survival accuracy was 71.9%. Sensitivity and specificity were 77.1 and 65.5%, respectively. The area under the receiver operating characteristic curve was 0.752 (95% CI, 0.62–0.88). These findings suggest that highly specific features of rsFC may predict GBM survival. Taken together, the findings of this study support that resting-state fMRI and machine learning analytics could enable a radiomic biomarker for GBM, augmenting care and planning for individual patients.

scholarly journals Twenty Years After Glioblastoma Multiforme Diagnosis: A Case of Long-Term Survival

Cureus ◽  
2021 ◽  
Author(s):  
Omar Rabab'h ◽  
Ali Al-Ramadan ◽  
Jawad Shah ◽  
Hugo Lopez-Negrete ◽  
Abeer Gharaibeh
Keyword(s):  
Glioblastoma Multiforme ◽  
Term Survival ◽  
Long Term Survival

Long-Term Survival After Glioblastoma Multiforme

2008 ◽  
Vol 101 (9) ◽  
pp. 971-972 ◽  
Author(s):  
Mohammad Sami Walid ◽  
Hugh F. Smisson ◽  
Joe Sam Robinson
Keyword(s):  
Glioblastoma Multiforme ◽  
Term Survival ◽  
Long Term Survival

scholarly journals Effects of long-term cocaine self-administration on brain resting-state functional connectivity in nonhuman primates

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Stephen J. Kohut ◽  
Dionyssios Mintzopoulos ◽  
Brian D. Kangas ◽  
Hannah Shields ◽  
Kelly Brown ◽  
...  
Keyword(s):  
Functional Connectivity ◽  
Cognitive Processing ◽  
Resting State ◽  
Resting State Fmri ◽  
Brain Regions ◽  
Anterior Cingulate ◽  
Resting State Functional Connectivity ◽  
Self Administration ◽  
Chronic Cocaine

AbstractLong-term cocaine use is associated with a variety of neural and behavioral deficits that impact daily function. This study was conducted to examine the effects of chronic cocaine self-administration on resting-state functional connectivity of the dorsal anterior cingulate (dACC) and putamen—two brain regions involved in cognitive function and motoric behavior—identified in a whole brain analysis. Six adult male squirrel monkeys self-administered cocaine (0.32 mg/kg/inj) over 140 sessions. Six additional monkeys that had not received any drug treatment for ~1.5 years served as drug-free controls. Resting-state fMRI imaging sessions at 9.4 Tesla were conducted under isoflurane anesthesia. Functional connectivity maps were derived using seed regions placed in the left dACC or putamen. Results show that cocaine maintained robust self-administration with an average total intake of 367 mg/kg (range: 299–424 mg/kg). In the cocaine group, functional connectivity between the dACC seed and regions primarily involved in motoric behavior was weaker, whereas connectivity between the dACC seed and areas implicated in reward and cognitive processing was stronger. In the putamen seed, weaker widespread connectivity was found between the putamen and other motor regions as well as with prefrontal areas that regulate higher-order executive function; stronger connectivity was found with reward-related regions. dACC connectivity was associated with total cocaine intake. These data indicate that functional connectivity between regions involved in motor, reward, and cognitive processing differed between subjects with recent histories of cocaine self-administration and controls; in dACC, connectivity appears to be related to cumulative cocaine dosage during chronic exposure.

scholarly journals Discriminating Suicide Attempters and Predicting Suicide Risk Using Altered Frontolimbic Resting-State Functional Connectivity in Patients With Bipolar II Disorder

2020 ◽  
Vol 11 ◽  
Author(s):  
Rongxin Zhu ◽  
Shui Tian ◽  
Huan Wang ◽  
Haiteng Jiang ◽  
Xinyi Wang ◽  
...  
Keyword(s):  
Functional Connectivity ◽  
Resting State ◽  
Suicide Risk ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Resting State Functional Connectivity ◽  
Bipolar Ii Disorder ◽  
Individual Level ◽  
Bipolar Ii ◽  
The Individual

Bipolar II disorder (BD-II) major depression episode is highly associated with suicidality, and objective neural biomarkers could be key elements to assist in early prevention and intervention. This study aimed to integrate altered brain functionality in the frontolimbic system and machine learning techniques to classify suicidal BD-II patients and predict suicidality risk at the individual level. A cohort of 169 participants were enrolled, including 43 BD-II depression patients with at least one suicide attempt during a current depressive episode (SA), 62 BD-II depression patients without a history of attempted suicide (NSA), and 64 demographically matched healthy controls (HCs). We compared resting-state functional connectivity (rsFC) in the frontolimbic system among the three groups and explored the correlation between abnormal rsFCs and the level of suicide risk (assessed using the Nurses' Global Assessment of Suicide Risk, NGASR) in SA patients. Then, we applied support vector machines (SVMs) to classify SA vs. NSA in BD-II patients and predicted the risk of suicidality. SA patients showed significantly decreased frontolimbic rsFCs compared to NSA patients. The left amygdala-right middle frontal gyrus (orbital part) rsFC was negatively correlated with NGASR in the SA group, but not the severity of depressive or anxiety symptoms. Using frontolimbic rsFCs as features, the SVMs obtained an overall 84% classification accuracy in distinguishing SA and NSA. A significant correlation was observed between the SVMs-predicted NGASR and clinical assessed NGASR (r = 0.51, p = 0.001). Our results demonstrated that decreased rsFCs in the frontolimbic system might be critical objective features of suicidality in BD-II patients, and could be useful for objective prediction of suicidality risk in individuals.

The influence of sex and the presence of giant cells on postoperative long-term survival in adult patients with supratentorial glioblastoma multiforme

2004 ◽  
Vol 101 (2) ◽  
pp. 219-226 ◽  
Author(s):  
Naoki Shinojima ◽  
Masato Kochi ◽  
Jun-Ichiro Hamada ◽  
Hideo Nakamura ◽  
Shigetoshi Yano ◽  
...  
Keyword(s):  
Glioblastoma Multiforme ◽  
Giant Cell ◽  
Adult Patients ◽  
Term Survival ◽  
Long Term Survival ◽  
Content Type ◽  
Free Interval ◽  
Younger Age ◽  
Fine Print

Object. Glioblastoma multiforme (GBM) remains incurable by conventional treatments, although some patients experience long-term survival. A younger age, a higher Karnofsky Performance Scale (KPS) score, more aggressive treatment, and long progression-free intervals have been reported to be positively associated with long-term postoperative patient survival. The aim of this retrospective study was the identification of additional favorable prognostic factors affecting long-term survival in surgically treated adult patients with supratentorial GBM. Methods. Of 113 adult patients newly diagnosed with histologically verified supratentorial GBM who were enrolled in Phase III trials during the period between 1987 and 1998, six (5.3%) who survived for longer than 5 years were defined as long-term survivors, whereas the remaining 107 patients served as controls. All six were women and were compared with the controls; they were younger (mean age 44.2 years, range 31–60 years), and their preoperative KPS scores were higher (mean 85, range 60–100). Four of the six patients underwent gross-total resection. In five patients (83.3%) the progression-free interval was longer than 5 years and in three a histopathological diagnosis of giant cell GBM was made. This diagnosis was not made in the other 107 patients. Conclusions. Among adult patients with supratentorial GBM, female sex and histopathological characteristics consistent with giant cell GBM may be predictive of a better survival rate, as may traditional factors (that is, younger age, good KPS score, more aggressive resection, and a long progression-free interval).

Is the long-term survival of patients with intracranial glioblastoma multiforme overstated?

Cancer ◽  
2003 ◽  
Vol 98 (8) ◽  
pp. 1745-1748 ◽  
Author(s):  
Roger E. McLendon ◽  
Edward C. Halperin
Keyword(s):  
Glioblastoma Multiforme ◽  
Term Survival ◽  
Long Term Survival
Sign in / Sign up

Export Citation Format

Share Document