This event has ended. Visit the official site or create your own event on Sched.
Click here to return to main conference site. For a one page, printable overview of the schedule, see this.
Wednesday, June 29 • 2:30pm - 3:30pm
ALZCan: Predicting Future Onset of Alzheimer's Using Gender, Genetics, Cognitive Tests, CSF Biomarkers, and Resting State fMRI Brain Imaging

Log in to save this to your schedule, view media, leave feedback and see who's attending!

Poster #13

Due to a lack of preventive methods and precise diagnostic tests, only 45% of Alzheimer’s patients are told about their diagnosis. I hypothesized that one can create an accurate diagnostic/prognostic software tool for early detection of Alzheimer's using functional connectivity in resting-state fMRI brain imaging, genetic SNP data, cerebrospinal fluid (CSF) concentrations, demographic information, and psychometric tests.nnUsing R programming language and data from ADNI, an ongoing, longitudinal, global effort tracking clinical/imaging AD biomarkers, I examined 678 4D fMRI scans and 56847 observations of 1722 individuals across three diagnostic groups. ICA on fMRI scans yielded graph structures of connectivity between brain networks. For diagnosis, 4 support vector machines and 6 gradient boosting machines were trained 10 times each for fMRI, genetic, CSF biomarker, and cognitive data. For prognosis, 3 linear regression models predicted cognitive scores 6 to 60 months into the future. Forecasted cognitive scores and demographic information were used for prognosis.nnALZCan had 81.82% diagnostic accuracy. Prognostic accuracy for 6, 12, 18 months in future was 75.4%, 68.3%, 68.6%. AD patients showed significantly lower transitivity and average path length between functional brain networks. I examined relative influence/predictive power of multiple biomarkers, confirming previous findings that gender has higher influence than genetic factors on AD diagnosis. Overall, this study engineered a novel neuroimaging feature selection method by using machine learning and graph-theoretic functional network connectivity properties for diagnosis/prognosis of disease states. This analytical tool is capable of predicting future onset of Alzheimer’s and Mild Cognitive Impairment with significant accuracy.


Wednesday June 29, 2016 2:30pm - 3:30pm PDT
Sponsor Pavilion