Skip to main content Accessibility help

A clinically-translatable machine learning algorithm for the prediction of Alzheimer’s disease conversion: further evidence of its accuracy via a transfer learning approach

  • Massimiliano Grassi (a1), David A. Loewenstein (a2) (a3) (a4), Daniela Caldirola (a1), Koen Schruers (a5), Ranjan Duara (a3) (a6) (a7) and Giampaolo Perna (a1) (a2) (a5) (a8) (a9)...



In a previous study, we developed a highly performant and clinically-translatable machine learning algorithm for a prediction of three-year conversion to Alzheimer’s disease (AD) in subjects with Mild Cognitive Impairment (MCI) and Pre-mild Cognitive Impairment. Further tests are necessary to demonstrate its accuracy when applied to subjects not used in the original training process. In this study, we aimed to provide preliminary evidence of this via a transfer learning approach.


We initially employed the same baseline information (i.e. clinical and neuropsychological test scores, cardiovascular risk indexes, and a visual rating scale for brain atrophy) and the same machine learning technique (support vector machine with radial-basis function kernel) used in our previous study to retrain the algorithm to discriminate between participants with AD (n = 75) and normal cognition (n = 197). Then, the algorithm was applied to perform the original task of predicting the three-year conversion to AD in the sample of 61 MCI subjects that we used in the previous study.


Even after the retraining, the algorithm demonstrated a significant predictive performance in the MCI sample (AUC = 0.821, 95% CI bootstrap = 0.705–0.912, best balanced accuracy = 0.779, sensitivity = 0.852, specificity = 0.706).


These results provide a first indirect evidence that our original algorithm can also perform relevant generalized predictions when applied to new MCI individuals. This motivates future efforts to bring the algorithm to sufficient levels of optimization and trustworthiness that will allow its application in both clinical and research settings.


Corresponding author

Correspondence should be addressed to: Massimiliano Grassi, Department of Clinical Neurosciences, Villa San Benedetto Menni, Hermanas Hospitalarias, FoRiPsi, via Roma 16, 22032 Albese con Cassano (Como), Italy. Phone: +39 031 4291511; Fax: +39 031 427246. Email:


Hide All
Agarwal, S., Ghanty, P. and Pal, N. R. (2015). Identification of a small set of plasma signalling proteins using neural network for prediction of Alzheimer’s disease. Bioinformatics, 31, 25052513. doi: 10.1093/bioinformatics/btv173.
American Psychiatric Association. (2000). Diagnostic and Statistical Manual of Mental Disorders DSM-IV-TR (Text Revision), 4 edn. Washington, DC: American Psychiatric Association.
Apostolova, L. G., et al. (2014). ApoE4 effects on automated diagnostic classifiers for mild cognitive impairment and Alzheimer’s disease. Neuroimage Clinical, 4, 461472. doi: 10.1016/j.nicl.2013.12.012.
Benedict, R. H. and Zgaljardic, D. J. (1998). Practice effects during repeated administrations of memory tests with and without alternate forms. Journal of Clinical and Experimental Neuropsychology, 20, 339352. doi: 10.1076/jcen.20.3.339.822.
Brooks, L. G. and Loewenstein, D. A. (2010). Assessing the progression of mild cognitive impairment to Alzheimer’s disease: current trends and future directions. Alzheimers Research & Therapy, 2, 28. doi: 10.1186/alzrt52.
Cheng, B., Zhang, D., Chen, S., Kaufer, D. I., Shen, D. and Alzheimer’s Disease Neuroimaging Initiative. (2013). Semi-supervised multimodal relevance vector regression improves cognitive performance estimation from imaging and biological biomarkers. Neuroinformatics, 11, 339353. doi: 10.1007/s12021-013-9180-7.
Clark, D. G., et al. (2014). Latent information in fluency lists predicts functional decline in persons at risk for Alzheimer disease. Cortex, 55, 202218. doi: 10.1016/j.cortex.2013.12.013.
Collij, L. E., et al. (2016). Application of machine learning to arterial spin labeling in mild cognitive impairment and Alzheimer disease. Radiology, 281, 865875. doi: 10.1148/radiol.2016152703.
Cui, Y., et al. (2011). Identification of conversion from mild cognitive impairment to Alzheimer’s disease using multivariate predictors. PLoS One, 6, e21896. doi: 10.1371/journal.pone.0021896.
Duara, R., et al. (2008). Medial temporal lobe atrophy on MRI scans and the diagnosis of Alzheimer disease. Neurology, 71, 19861992. doi: 10.1212/01.wnl.0000336925.79704.9f.
Duara, R., et al. (2010). Diagnosis and staging of mild cognitive impairment, using a modification of the clinical dementia rating scale: the mCDR. International Journal of Geriatric Psychiatry, 25, 282289. doi: 10.1002/gps.2334.
Dukart, J., Sambataro, F. and Bertolino, A. (2016). Accurate prediction of conversion to Alzheimer’s disease using imaging, genetic, and neuropsychological biomarkers. Journal of Alzheimer’s Disease, 49, 11431159. doi: 10.3233/JAD-150570.
Efron, B. (1987). Better bootstrap confidence intervals. Journal of the American Statistical Association, 82, 171185. doi: 10.1080/01621459.1987.10478410.
Grassi, M., et al. (2018). A clinically-translatable machine learning algorithm for the prediction of Alzheimer’s disease conversion in individuals with mild and premild cognitive impairment. Journal of Alzheimer’s Disease, 61, 15551573. doi: 10.3233/jad-170547.
Hinrichs, C., Singh, V., Xu, G., Johnson, S. C. and Alzheimers Disease Neuroimaging Initiative. (2011). Predictive markers for AD in a multi-modality framework: an analysis of MCI progression in the ADNI population. Neuroimage, 55, 574589. doi: 10.1016/j.neuroimage.2010.10.081.
Hojjati, S. H., Ebrahimzadeh, A., Khazaee, A., Babajani-Feremi, A. and Alzheimer’s Disease Neuroimaging Initiative. (2017). Predicting conversion from MCI to AD using resting-state fMRI, graph theoretical approach and SVM. Journal of Neuroscience Methods, 282, 6980. doi: 10.1016/j.jneumeth.2017.03.006.
Loewenstein, D. A., Curiel, R. E., Duara, R. and Buschke, H. (2017). Novel cognitive paradigms for the detection of memory impairment in preclinical Alzheimer’s disease. Assessment, 25, 348359. doi: 10.1177/1073191117691608.
Loewenstein, D. A., et al. (2004). Semantic interference deficits and the detection of mild Alzheimer’s disease and mild cognitive impairment without dementia. Journal of the International Neuropsychological Society, 10, 91100. doi: 10.1017/s1355617704101112.
Long, X., Chen, L., Jiang, C., Zhang, L. and Alzheimer’s Disease Neuroimaging Initiative. (2017). Prediction and classification of Alzheimer disease based on quantification of MRI deformation. PLoS One, 12, e0173372. doi: 10.1371/journal.pone.0173372.
Mathotaarachchi, S., et al. (2017). Identifying incipient dementia individuals using machine learning and amyloid imaging. Neurobiology of Aging, 59, 8090. doi: 10.1016/j.neurobiolaging.2017.06.027.
McKhann, G., et al. (1984). Clinical diagnosis of Alzheimer’s disease: report of the NINCDS-ADRDA Work Group under the auspices of Department of Health and Human Services task force on Alzheimer’s disease. Neurology, 34, 939. doi: 10.1212/WNL.34.7.939.
Minhas, S., Khanum, A., Riaz, F., Alvi, A. and Khan, S. A. (2016). A non parametric approach for mild cognitive impairment to AD conversion prediction: results on longitudinal data. IEEE Journal of Biomedical and Health Informatics, 21, 14031410. doi: 10.1109/JBHI.2016.2608998.
Moradi, E., Pepe, A., Gaser, C., Huttunen, H., Tohka, J. and Alzheimer’s Disease Neuroimaging Initiative. (2015). Machine learning framework for early MRI-based Alzheimer’s conversion prediction in MCI subjects. Neuroimage, 104, 398412. doi: 10.1016/j.neuroimage.2014.10.002.
Morris, J. C. (1993). The clinical dementia rating (CDR): current version and scoring rules. Neurology, 43, 24122414. doi: 10.1212/WNL.43.11.2412-a.
Nho, K., et al. (2010). Automatic prediction of conversion from mild cognitive impairment to probable Alzheimer’s disease using structural magnetic resonance imaging. AMIA Annual Symposium Proceedings, 2010, 542546.
Plant, C., et al. (2010). Automated detection of brain atrophy patterns based on MRI for the prediction of Alzheimer’s disease. Neuroimage, 50, 162174. doi: 10.1016/j.neuroimage.2009.11.046.
Retico, A., et al. (2015). Predictive models based on support vector machines: whole-brain versus regional analysis of structural MRI in the Alzheimer’s disease. Journal of Neuroimaging, 25, 552563. doi: 10.1111/jon.12163.
Scheltens, P., et al. (1992). Atrophy of medial temporal lobes on MRI in “probable” Alzheimer’s disease and normal ageing: diagnostic value and neuropsychological correlates. Journal of Neurology, Neurosurgery, and Psychiatry, 55, 967972. doi: 10.1136/jnnp.55.10.967.
Urs, R. et al. (2009). Visual rating system for assessing magnetic resonance images: a tool in the diagnosis of mild cognitive impairment and Alzheimer disease. Journal of Computer Assisted Tomography, 33, 7378. doi: 10.1097/RCT.0b013e31816373d8.
Wechsler, D. (1997). WMS-III: Wechsler Memory Scale Administration and Scoring Manual. San Antonio: Psychological Corporation.
Weiss, K., Khoshgoftaar, T. M. and Wang, D. (2016). A survey of transfer learning. Journal of Big Data, 3, 9. doi: 10.1186/s40537-016-0043-6.
Westman, E., Aguilar, C., Muehlboeck, J. S. and Simmons, A. (2013). Regional magnetic resonance imaging measures for multivariate analysis in Alzheimer’s disease and mild cognitive impairment. Brain Topography, 26, 923. doi: 10.1007/s10548-012-0246-x.
Young, J., et al. (2013). Accurate multimodal probabilistic prediction of conversion to Alzheimer’s disease in patients with mild cognitive impairment. Neuroimage Clinical, 2, 735745. doi: 10.1016/j.nicl.2013.05.004.


Related content

Powered by UNSILO

A clinically-translatable machine learning algorithm for the prediction of Alzheimer’s disease conversion: further evidence of its accuracy via a transfer learning approach

  • Massimiliano Grassi (a1), David A. Loewenstein (a2) (a3) (a4), Daniela Caldirola (a1), Koen Schruers (a5), Ranjan Duara (a3) (a6) (a7) and Giampaolo Perna (a1) (a2) (a5) (a8) (a9)...


Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed.