Analytic Methods

Modern techniques utilizing machine-learning and cloud-computing enable improved neuroscientific investigations. Our data science team at Omniscient Neurotechnology is keenly interested In discovering new methods of analysis and testing previous methods in neuroscientific settings

 

e hubdb f
{id=48099191200, createdAt=1622359777094, 1='{type=string, value=Hollow-tree Super: a directional and scalable approach for feature importance in boosted tree models}', 2='{type=list, value=[{id=17, name='Mental Illness', order=4}, {id=18, name='Connectomics', order=5}, {id=19, name='Machine-learning', order=6}]}', 3='{type=string, value=https://www.o8t.com/hubfs/Clinical%20Papers/Hollow%20tree%20super%20preprint.pdf}', 4='{type=image, value=Image{width=435, height=320, url='https://www.o8t.com/hubfs/ResearchPageImage_15.jpg'}}', 5='{type=string, value=Current limitations in methodologies used throughout machine-learning to investigate feature importance in boosted tree modelling prevent the effective scaling to datasets with a large number of features, particularly when one is investigating both the magnitude and directionality of various features on the classification into a positive or negative class. This manuscript presents a novel methodology, “Hollow-tree Super” (HOTS), designed to resolve and visualize feature importance in boosted tree models involving a large number of features. Further, this methodology allows for accurate investigation of the directionality and magnitude various features have on classification, and incorporates cross-validation to improve the accuracy and validity of the determined features of importance.}', 7='{type=list, value=[{id=10, name='Novel analytic techniques', order=3}]}', 8='{type=number, value=1617753600000}', 9='{type=number, value=0}'}

Hollow-tree Super: a directional and scalable approach for feature importance in boosted tree models

View more  
{id=48072093356, createdAt=1622254006917, 1='{type=string, value=Unexpected hubness: a proof‑of‑concept study of the human connectome using pagerank centrality and implications for intracerebral neurosurgery}', 2='{type=list, value=[{id=18, name='Connectomics', order=5}, {id=19, name='Machine-learning', order=6}]}', 3='{type=string, value=https://www.o8t.com/hubfs/Clinical%20Papers/Yeung%20et%20al.%202020%20Unexpected%20Hubness.pdf}', 4='{type=image, value=Image{width=435, height=320, url='https://www.o8t.com/hubfs/ResearchPageImage_8.jpg'}}', 5='{type=string, value=Understanding the human connectome by parcellations allows neurosurgeons to foretell the potential efects of lesioning parts of the brain during intracerebral surgery. However, it is unclear whether there exist variations among individuals such that brain regions that are thought to be dispensable may serve as important networking hubs.}', 7='{type=list, value=[{id=10, name='Novel analytic techniques', order=3}]}', 8='{type=number, value=1604448000000}', 9='{type=number, value=0}', 13='{type=option, value={id=4, name='Image', order=3}}'}

Unexpected hubness: a proof‑of‑concept study of the human connectome using pagerank centrality and implications for intracerebral neurosurgery

View more  
{id=48099538352, createdAt=1622358781857, 1='{type=string, value=Beyond eloquence and onto centrality: a new paradigm in planning supratentorial neurosurgery}', 2='{type=list, value=[{id=15, name='Neurosurgery', order=2}, {id=18, name='Connectomics', order=5}]}', 3='{type=string, value=https://www.o8t.com/hubfs/Clinical%20Papers/Beyond%20Eloquence%20And%20Onto%20Centrality%20a%20new%20paradigm%20in%20planning%20supratentorial%20neurosurgery.pdf}', 4='{type=image, value=Image{width=435, height=320, url='https://www.o8t.com/hubfs/ResearchPageImage_14.jpg'}}', 5='{type=string, value=Minimizing post-operational neurological defcits as a result of brain surgery has been one of the most pertinent endeavours of neurosurgical research. Studies have utilised fMRIs, EEGs and MEGs in order to delineate and establish eloquent areas, however, these methods have not been utilized by the wider neurosurgical community due to a lack of clinical endpoints. We sought to ascertain if there is a correlation between graph theory metrics and the neurosurgical notion of eloquent brain regions. We also wanted to establish which graph theory based nodal centrality measure performs the best in predicting eloquent areas.}', 7='{type=list, value=[{id=10, name='Novel analytic techniques', order=3}]}', 8='{type=number, value=1577836800000}', 9='{type=number, value=0}'}

Beyond eloquence and onto centrality: a new paradigm in planning supratentorial neurosurgery

View more  
{id=48073832743, createdAt=1622260662572, 1='{type=string, value=Measuring graphical strength within the connectome: a neuroanatomic, parcellation-based study}', 2='{type=list, value=[{id=13, name='fMRI', order=0}, {id=14, name='DTI', order=1}, {id=18, name='Connectomics', order=5}]}', 3='{type=string, value=https://www.o8t.com/hubfs/Clinical%20Papers/Measuring%20graphical%20strength%20in%20the%20connectome.pdf}', 4='{type=image, value=Image{width=435, height=320, url='https://www.o8t.com/hubfs/ResearchPageImage_11.jpg'}}', 5='{type=string, value=Graph theory is a promising mathematical tool to study the connectome. However, little research has been undertaken to correlate graph metrics to functional properties of the brain. In this study, we report a unique association between the strength of cortical regions and their function.}', 7='{type=list, value=[{id=10, name='Novel analytic techniques', order=3}]}', 8='{type=number, value=1570579200000}', 9='{type=number, value=0}', 13='{type=option, value={id=6, name='Website page', order=5}}'}

Measuring graphical strength within the connectome: a neuroanatomic, parcellation-based study

View more