Machine Learning classification of MRI features of Alzheimer's disease and mild cognitive impairment subjects to reduce the sample size in clinical trials

Javier Escudero; John P Zajicek; Emmanuel Ifeachor; Alzheimer’s Disease Neuroimaging Initiative

doi:10.1109/IEMBS.2011.6091962

Machine Learning classification of MRI features of Alzheimer's disease and mild cognitive impairment subjects to reduce the sample size in clinical trials

Javier Escudero, John P Zajicek, Emmanuel Ifeachor, Alzheimer’s Disease Neuroimaging Initiative

School of Medicine

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

27 Citations (Scopus)

Abstract

There is a need for objective tools to help clinicians to diagnose Alzheimer's Disease (AD) early and accurately and to conduct Clinical Trials (CTs) with fewer patients. Magnetic Resonance Imaging (MRI) is a promising AD biomarker but no single MRI feature is optimal for all disease stages. Machine Learning classification can address these challenges. In this study, we have investigated the classification of MRI features from AD, Mild Cognitive Impairment (MCI), and control subjects from ADNI with four techniques. The highest accuracy rates for the classification of controls against ADs and MCIs were 89.2% and 72.7%, respectively. Moreover, we used the classifiers to select AD and MCI subjects who are most likely to decline for inclusion in hypothetical CTs. Using the hippocampal volume as an outcome measure, we found that the required group sizes for the CTs were reduced from 197 to 117 AD patients and from 366 to 215 MCI subjects.

Original language	English
Title of host publication	Proceedings of the 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Publisher	IEEE
Pages	7957-60
Number of pages	4
Volume	2011
ISBN (Electronic)	978-1-4244-4122-8
ISBN (Print)	978-1-4244-4121-1
DOIs	https://doi.org/10.1109/IEMBS.2011.6091962
Publication status	Published - 2011

Keywords

Aged
Alzheimer Disease
Artificial Intelligence
Clinical Trials as Topic
Demography
Female
Humans
Magnetic Resonance Imaging
Male
Mild Cognitive Impairment
Sample Size

Access to Document

10.1109/IEMBS.2011.6091962

Cite this

Escudero, J., Zajicek, J. P., Ifeachor, E., & Alzheimer’s Disease Neuroimaging Initiative (2011). Machine Learning classification of MRI features of Alzheimer's disease and mild cognitive impairment subjects to reduce the sample size in clinical trials. In Proceedings of the 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (Vol. 2011, pp. 7957-60). IEEE. https://doi.org/10.1109/IEMBS.2011.6091962

@inproceedings{3803b34e298543f78b81d46e16cbf842,

title = "Machine Learning classification of MRI features of Alzheimer's disease and mild cognitive impairment subjects to reduce the sample size in clinical trials",

abstract = "There is a need for objective tools to help clinicians to diagnose Alzheimer's Disease (AD) early and accurately and to conduct Clinical Trials (CTs) with fewer patients. Magnetic Resonance Imaging (MRI) is a promising AD biomarker but no single MRI feature is optimal for all disease stages. Machine Learning classification can address these challenges. In this study, we have investigated the classification of MRI features from AD, Mild Cognitive Impairment (MCI), and control subjects from ADNI with four techniques. The highest accuracy rates for the classification of controls against ADs and MCIs were 89.2% and 72.7%, respectively. Moreover, we used the classifiers to select AD and MCI subjects who are most likely to decline for inclusion in hypothetical CTs. Using the hippocampal volume as an outcome measure, we found that the required group sizes for the CTs were reduced from 197 to 117 AD patients and from 366 to 215 MCI subjects.",

keywords = "Aged, Alzheimer Disease, Artificial Intelligence, Clinical Trials as Topic, Demography, Female, Humans, Magnetic Resonance Imaging, Male, Mild Cognitive Impairment, Sample Size",

author = "Javier Escudero and Zajicek, {John P} and Emmanuel Ifeachor and {Alzheimer{\textquoteright}s Disease Neuroimaging Initiative}",

year = "2011",

doi = "10.1109/IEMBS.2011.6091962",

language = "English",

isbn = "978-1-4244-4121-1",

volume = "2011",

pages = "7957--60",

booktitle = "Proceedings of the 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society",

publisher = "IEEE",

}

Escudero, J, Zajicek, JP, Ifeachor, E & Alzheimer’s Disease Neuroimaging Initiative 2011, Machine Learning classification of MRI features of Alzheimer's disease and mild cognitive impairment subjects to reduce the sample size in clinical trials. in Proceedings of the 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society . vol. 2011, IEEE, pp. 7957-60. https://doi.org/10.1109/IEMBS.2011.6091962

Machine Learning classification of MRI features of Alzheimer's disease and mild cognitive impairment subjects to reduce the sample size in clinical trials. / Escudero, Javier; Zajicek, John P; Ifeachor, Emmanuel et al.
Proceedings of the 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society . Vol. 2011 IEEE, 2011. p. 7957-60.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Machine Learning classification of MRI features of Alzheimer's disease and mild cognitive impairment subjects to reduce the sample size in clinical trials

AU - Escudero, Javier

AU - Zajicek, John P

AU - Ifeachor, Emmanuel

AU - Alzheimer’s Disease Neuroimaging Initiative

PY - 2011

Y1 - 2011

N2 - There is a need for objective tools to help clinicians to diagnose Alzheimer's Disease (AD) early and accurately and to conduct Clinical Trials (CTs) with fewer patients. Magnetic Resonance Imaging (MRI) is a promising AD biomarker but no single MRI feature is optimal for all disease stages. Machine Learning classification can address these challenges. In this study, we have investigated the classification of MRI features from AD, Mild Cognitive Impairment (MCI), and control subjects from ADNI with four techniques. The highest accuracy rates for the classification of controls against ADs and MCIs were 89.2% and 72.7%, respectively. Moreover, we used the classifiers to select AD and MCI subjects who are most likely to decline for inclusion in hypothetical CTs. Using the hippocampal volume as an outcome measure, we found that the required group sizes for the CTs were reduced from 197 to 117 AD patients and from 366 to 215 MCI subjects.

AB - There is a need for objective tools to help clinicians to diagnose Alzheimer's Disease (AD) early and accurately and to conduct Clinical Trials (CTs) with fewer patients. Magnetic Resonance Imaging (MRI) is a promising AD biomarker but no single MRI feature is optimal for all disease stages. Machine Learning classification can address these challenges. In this study, we have investigated the classification of MRI features from AD, Mild Cognitive Impairment (MCI), and control subjects from ADNI with four techniques. The highest accuracy rates for the classification of controls against ADs and MCIs were 89.2% and 72.7%, respectively. Moreover, we used the classifiers to select AD and MCI subjects who are most likely to decline for inclusion in hypothetical CTs. Using the hippocampal volume as an outcome measure, we found that the required group sizes for the CTs were reduced from 197 to 117 AD patients and from 366 to 215 MCI subjects.

KW - Aged

KW - Alzheimer Disease

KW - Artificial Intelligence

KW - Clinical Trials as Topic

KW - Demography

KW - Female

KW - Humans

KW - Magnetic Resonance Imaging

KW - Male

KW - Mild Cognitive Impairment

KW - Sample Size

U2 - 10.1109/IEMBS.2011.6091962

DO - 10.1109/IEMBS.2011.6091962

M3 - Conference contribution

C2 - 22256186

SN - 978-1-4244-4121-1

VL - 2011

SP - 7957

EP - 7960

BT - Proceedings of the 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society

PB - IEEE

ER -

Escudero J, Zajicek JP, Ifeachor E, Alzheimer’s Disease Neuroimaging Initiative. Machine Learning classification of MRI features of Alzheimer's disease and mild cognitive impairment subjects to reduce the sample size in clinical trials. In Proceedings of the 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society . Vol. 2011. IEEE. 2011. p. 7957-60 doi: 10.1109/IEMBS.2011.6091962

Machine Learning classification of MRI features of Alzheimer's disease and mild cognitive impairment subjects to reduce the sample size in clinical trials

Abstract

Keywords

Access to Document

Fingerprint

Cite this