Progress towards a brain scan for diagnosis

twinklestars · March 21, 2018, 10:04pm

ncbi.nlm.nih.gov

Non-negative discriminative brain functional connectivity for identifying schizophrenia on resting-state fMRI.

Q Zhu, J Huang and X Xu, Biomedical engineering online, Mar 2018 13

Schizophrenia is a clinical syndrome, and its causes have not been well determined. The objective of this study was to investigate the alteration of brain functional connectivity between schizophrenia and healthy control, and present a practical solution for accurately identifying schizophrenia at single-subject level.24 schizophrenia patients and 21 matched healthy subjects were recruited to undergo the resting-state functional magnetic resonance imaging (rs-fMRI) scanning. First, we constructed the brain network by calculating the Pearson correlation coefficient between each pair of the brain regions. Then, this study proposed a novel non-negative discriminant functional connectivity selection method, i.e. non-negative elastic-net based method (N2EN), to extract the alteration of brain functional connectivity between schizophrenia and healthy control. It ranks the significance of the connectivity with a uniform criterion by introducing the non-negative constraint. Finally, kernel discriminant analysis (KDA) is exploited to classify the subjects with the selected discriminant brain connectivity features.The proposed method is applied into schizophrenia classification, and achieves the sensitivity, specificity and accuracy of 100, 90.48 and 95.56%, respectively. Our findings also indicate the alteration of functional network can be used as the biomarks for guiding the schizophrenia diagnosis. The regions of cuneus, superior frontal gyrus, medial, paracentral lobule, calcarine fissure, surrounding cortex, etc. are highly relevant to schizophrenia.This study provides a method for accurately identifying schizophrenia, which outperforms several state-of-the-art methods, including conventional brain network classification, multi-threshold brain network based classification, frequent sub-graph based brain network classification and support vector machine. Our investigation suggested that the selected discriminant resting-state functional connectivities are meaningful features for classifying schizophrenia and healthy control.

Chess24 · March 21, 2018, 10:05pm

Awesome @twinklestars !!!
Thank you for posting!

saynow · March 21, 2018, 10:43pm

my doc once said to me everything exist after i asked him to objectivly diagnose me by chemical or other tests
i hope such test exist

twinklestars · March 21, 2018, 10:46pm

One of these days.

ablue · March 21, 2018, 11:12pm

Fist of all. Don’t understand what they are saying. It’s all science lingo. Second I don’t think schizophrenia is an organic insanity.

NewHope · March 22, 2018, 12:23am

We need something to identify schizophrenia brain no matter what the cause. Many cases might be wrongly diagnosed sz and would suffer unnecessarily for life.

twinklestars · March 22, 2018, 1:52am

An inorganic insanity?

Chess24 · March 22, 2018, 2:04am

@ablue @twinklestars really now, schizophrenia is much more severe than sanity or insanity.
Although schizophrenia is sometimes equated with psychosis, this is not the worst aspect of the disease.
I suffered from hostile thought content for the entire duration of my illness.
I suffered terrible humiliations.
Severe sleep disturbances. Severe cognitive problems and impairments.
Severe functioning deficits. My SZ weakens my freedom to talk to people.
Prevents me from doing household chores, working, studying, or sleeping properly or having a social life.

I was on the verge of death at a very young age.

ablue · March 22, 2018, 2:48am

Insanity is just an older term. I still find it valid.

ablue · March 22, 2018, 2:50am

Yes it would have to be. Because the mind doesn’t exist in the body it’s something we tap into like a collective.