Your SlideShare is downloading. ×

Thanks for flagging this SlideShare!

Oops! An error has occurred.

×
Saving this for later? Get the SlideShare app to save on your phone or tablet. Read anywhere, anytime – even offline.
Text the download link to your phone
Standard text messaging rates apply

Intelligent System for Alzheimer's Disease

237

Published on

0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
237
On Slideshare
0
From Embeds
0
Number of Embeds
1
Actions
Shares
0
Downloads
0
Comments
0
Likes
0
Embeds 0
No embeds

Report content
Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
No notes for slide

Transcript

  • 1. Intelligent System for Early Detection ofAlzheimers disease using neuroimaging Domingo López Rodríguez Ricardo de Abajo llamero Antonio García Linares
  • 2. The diagnosis of Alzheimers disease (AD) due to itsevolution, occurs when neurological damage ispresent and is irreversible. The goal is to developand implement an automated system for earlydetection of AD, by processing neuroimaging, andconstruction of automated and objective tools basedin Artificial Intelligence and Data Mining.
  • 3. MEN WOMEN TOTALHEALTHY 694 493 1187MCI 348 434 782AD 55 76 131TOTAL 1097 1003 2100Age range: from 18 to 96. MCI and AD were present in some subjects older than 55.Images were procedent from available MRI databases after passing a check to ensurethe necessary quality
  • 4. Morphometric processing of these images was carried out using standard methodologies and packages such as SPM or FSL, besides our own developments. The results of this processing fed Computational Intelligence systems such as decision trees, support vector machines and genetic algorithms, apart from artificial neural networks, to develop a system to classify the state of the AD by neuroimaging.
  • 5. Parameter ValueCorrect Classification 91,48%Sensitivity 90,80%Specificity 92,30%Positive Predictive Value 0,886Negative Predictive Value 0,939To avoid over-training of the model, 10-fold cross validation was used.The resulting model incorporated SVMs, GGAA and Decision Trees.
  • 6. We have developed a computer system that isable to classify, based on structuralneuroimaging studies, and with great accuracy,if the subject is in a normal state or have anychance of developing AD. Its a tool with greatpotential for application in early diagnosis of AD.
  • 7. Berr C, Vercambre MN, Akbaraly TN. Epidémiologie de la maladie d’Alzheimer: aspectsméthodologiques et nouvelles perspectives. Psychol NeuroPsychiatr Vieil 2009 ; 7 (spécial) : 7-14.Flicker C, Ferris SH, Reisberg B. Mild cognitive impairment in the elderly: predictors ofdementia. Neurology 1991; 41: 1006-9.Webb, G.I. (2007). Discovering Significant Patterns. Machine Learning 68(1). Netherlands:Springer, pages 1-33.Biomarkers for Alzheimers disease. The research advances incrementally, but clinical use isstill years away. Harv Ment Health Lett. 2010 Nov;27(5):1-3.Valls-Pedret C, Molinuevo JL, Rami. Diagnóstico precoz de la enfermedad de Alzheimer:faseprodrómica y preclínica. Rev Neurol 2010;51:471_80K. Herrup. Reimagining Alzheimer’s Disease - An Age-Based Hypothesis. Journal ofNeuroscience, 2010; 30 (50): 16755Shaw LM, Vanderstichele H, Knapik-Czajka M, et al. Cerebrospinal fluid biomarker signature inAlzheimer’s disease neuroimaging initiative subjects. Ann Neurol 2009; 65: 403–13.

×