A Machine Learning-Based Holistic Approach to Predict the Clinical Course of Patients within the Alzheimer’s Disease Spectrum¹

Article type: Research Article

Authors: Massetti, Noemi^{a; b; 2} | Russo, Mirella^{a; b; 2} | Franciotti, Raffaella^{b; 2} | Nardini, Davide^c | Mandolini, Giorgio Maria^c | Granzotto, Alberto^{a; b; d} | Bomba, Manuela^{a; b} | Delli Pizzi, Stefano^{a; b} | Mosca, Alessandra^{a; b} | Scherer, Reinhold^e | Onofrj, Marco^{a; b} | Sensi, Stefano L.^{a; b; f; g; *} | for the Alzheimer’s Disease Neuroimaging Initiative (ADNI)³ | the Alzheimer’s Disease Metabolomics Consortium (ADMC)⁴

Affiliations: [a] Center for Advanced Studies and Technology - CAST, University G. d’Annunzio of Chieti-Pescara, Italy | [b] Department of Neuroscience, Imaging, and Clinical Sciences, University G. d’Annunzio of Chieti-Pescara, Italy | [c] Biomedical Unit, ASC 27 s.r.l., Rome, Italy | [d] Sue and Bill Gross Stem Cell Research Center, University of California - Irvine, Irvine, CA, USA | [e] Brain-Computer Interfaces and Neural Engineering Laboratory, School of Computer Science and Electronic Engineering, University of Essex, Colchester, United Kingdom | [f] Institute for Mind Impairments and Neurological Disorders – iMIND, University of California - Irvine, Irvine, CA, USA | [g] Institute for Advanced Biomedical Technologies, University G. d’Annunzio of Chieti-Pescara, Italy

Correspondence: [*] Correspondence to: Prof. Stefano L. Sensi, Center for Advanced Studies and Technology – CAST, University G. d’Annunzio of Chieti-Pescara, Via Colle dell’Ara, Chieti 66100, Italy. Tel.: +39 0871 541544; Fax: +39 0871 541542; E-mail: [email protected].

Note: [1] This article received a correction notice (Erratum) with the reference: 10.3233/JAD-229016, available at http://doi.org/10.3233/JAD-229016.

Note: [2] These authors contributed equally to this work.

Note: [3] Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database (http://adni.loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at: http://adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf

Note: [4] Data used in preparation of this article were generated by the Alzheimer’s Disease Metabolomics Consortium (ADMC). As such, the investigators within the ADMC provided data but did not participate in analysis or writing of this report. A complete listing of ADMC investigators can be found at: https://sites.duke.edu/adnimetab/team/

Abstract: Background:Alzheimer’s disease (AD) is a neurodegenerative condition driven by multifactorial etiology. Mild cognitive impairment (MCI) is a transitional condition between healthy aging and dementia. No reliable biomarkers are available to predict the conversion from MCI to AD. Objective:To evaluate the use of machine learning (ML) on a wealth of data offered by the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and Alzheimer’s Disease Metabolomics Consortium (ADMC) database in the prediction of the MCI to AD conversion. Methods:We implemented an ML-based Random Forest (RF) algorithm to predict conversion from MCI to AD. Data related to the study population (587 MCI subjects) were analyzed by RF as separate or combined features and assessed for classification power. Four classes of variables were considered: neuropsychological test scores, AD-related cerebrospinal fluid (CSF) biomarkers, peripheral biomarkers, and structural magnetic resonance imaging (MRI) variables. Results:The ML-based algorithm exhibited 86% accuracy in predicting the AD conversion of MCI subjects. When assessing the features that helped the most, neuropsychological test scores, MRI data, and CSF biomarkers were the most relevant in the MCI to AD prediction. Peripheral parameters were effective when employed in association with neuropsychological test scores. Age and sex differences modulated the prediction accuracy. AD conversion was more effectively predicted in females and younger subjects. Conclusion:Our findings support the notion that AD-related neurodegenerative processes result from the concerted activity of multiple pathological mechanisms and factors that act inside and outside the brain and are dynamically affected by age and sex.

Keywords: Alzheimer’s disease, conversion, dementia, machine learning, mild cognitive impairment, random forest

DOI: 10.3233/JAD-210573

Journal: Journal of Alzheimer's Disease, vol. 85, no. 4, pp. 1639-1655, 2022