TY - GEN
T1 - Robust prediction of cognitive test scores in Alzheimer's patients
AU - Izquierdo, W.
AU - Martin, H.
AU - Cabrerizo, M.
AU - Barreto, A.
AU - Andrian, J.
AU - Rishe, N.
AU - Gonzalez-Arias, S.
AU - Loewenstein, D.
AU - Duara, Ranjan
AU - Adjouadi, M.
PY - 2017/7/1
Y1 - 2017/7/1
N2 - Predicting future cognitive status from current and past scores on objective cognitive tests and imaging measures would be useful in diagnosing Alzheimer's disease (AD) and to assess the progression of the disease. We used stochastic gradient boosting of decision trees on over 1,141 individuals whose clinical and imaging studies were available from the Alzheimer's disease Neuroimaging Initiative (ADNI) database. The proposed method outperformed all the algorithms tested in all five cognitive scores (MMSE, CDRS, RAVLT, ADAS11 and ADAS13), outranking all other state-of-the-art algorithms in terms of both Pearson's correlation coefficient and root mean square error. All correlation measures between predicted and actual cognitive scores were higher than 0.9. Given the large number of subjects included in this study, all correlations were statistically significant. For the subset of MCI patients, we compared the proposed method with state of the art algorithms. Here, the proposed method outperformed all the algorithms tested in all five cognitive scores.
AB - Predicting future cognitive status from current and past scores on objective cognitive tests and imaging measures would be useful in diagnosing Alzheimer's disease (AD) and to assess the progression of the disease. We used stochastic gradient boosting of decision trees on over 1,141 individuals whose clinical and imaging studies were available from the Alzheimer's disease Neuroimaging Initiative (ADNI) database. The proposed method outperformed all the algorithms tested in all five cognitive scores (MMSE, CDRS, RAVLT, ADAS11 and ADAS13), outranking all other state-of-the-art algorithms in terms of both Pearson's correlation coefficient and root mean square error. All correlation measures between predicted and actual cognitive scores were higher than 0.9. Given the large number of subjects included in this study, all correlations were statistically significant. For the subset of MCI patients, we compared the proposed method with state of the art algorithms. Here, the proposed method outperformed all the algorithms tested in all five cognitive scores.
UR - http://www.scopus.com/inward/record.url?scp=85050564093&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85050564093&partnerID=8YFLogxK
U2 - 10.1109/SPMB.2017.8257059
DO - 10.1109/SPMB.2017.8257059
M3 - Conference contribution
AN - SCOPUS:85050564093
T3 - 2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017 - Proceedings
SP - 1
EP - 7
BT - 2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2017
Y2 - 2 December 2017
ER -