Abstract

The Magnetic Resonance Imaging (MRI) data, which are a prevalent source of insight in understanding the inner functioning of the human body is one of the most preliminarymechanisms in the analysis of the human brain, including and not limited to detecting the presence of dementia. In this article, 7 machine learning models are proposed in the analysis and detection of dementiain the subjects ofOpen Access Series of Imaging Studies(OASIS) Brains 1, using OASIS 2 MRI and demographic data. The article also compares the performances of the machine learning models in terms of accuracy and prediction duration. The proposed model, eXtreme Gradient Boosting (XGB) algorithm performs with the highest accuracy of 97.87% and the fastest prediction durationof 0.031s/sample.

Highlights

  • Dementia – A severe disorder that impacts the memory, thinking and communication capability of the brain,that affects over 50 million individuals world-wide according to Statista [1]

  • The Magnetic Resonance Imaging (MRI) scans data along with demographic assessments data such as the Mini-Mental State Exam (MMSE) scores, the education level of the subject, the socio-economic status of the subject, etc. collectively named as MR(Magnetic Resonance) session, are considered in developing machine learning models that predicts the presence of dementia in the subject

  • The experiment models are trained and tested using the data obtained from the MRI scans and the demographic data obtained during each scan from the test subjects(MR session)

Read more

Summary

INTRODUCTION

Dementia – A severe disorder that impacts the memory, thinking and communication capability of the brain,that affects over 50 million individuals world-wide according to Statista [1]. A fast and simple system capable of identifying the presence of dementia, utilizing the clinical and demographic data of a person could be effective in providing swift diagnosis. In this experiment, the Magnetic Resonance Imaging (MRI) scans data along with demographic assessments data such as the Mini-Mental State Exam (MMSE) scores, the education level of the subject, the socio-economic status of the subject, etc. Collectively named as MR(Magnetic Resonance) session, are considered in developing machine learning models that predicts the presence of dementia in the subject.

RELATED WORKS ON DEMENTIA
EXPERIMENT AND RESULTS
Dataset
OASIS 1
OASIS 2
Data Preparation
Dimensionality Reduction
Navïe Bayes
Support Vector Machine
Random Forest Classifier
Extreme Gradient Boosting
Ensemble Classification
Results
CONCLUSION
Limitations

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.