Interpretable multivariate survival models: Improving predictions for conversion from mild cognitive impairment to Alzheimer’s disease via data fusion and machine learning
Diana Sofia Rosales-Gurmendi, Gerardo Alejandro Fumagal-González, Jorge Orozco, Joshua Farber, Victor Treviño, Emmanuel Martinez-Ledesma, Antonio Martinez-Torteya, Fabiola Rosales-Gurmendi, Jose Tamez-Peña, for the Alzheimer’s Disease Neuroimaging Initiative
Abstract
Accurately predicting which individuals with mild cognitive impairment (MCI) will progress to Alzheimer’s disease (AD) can improve patient care. This study examines the role of quantitative MRI (qMRI), cognitive evaluations, apolipoprotein 4 (APOE 4), and cerebrospinal fluid (CSF) biomarkers in Cox survival models to predict progression from MCI to AD. Data from 564 participants in the ADNI study, who transitioned from MCI to AD, were analyzed. The data set included 330 features encompassing qMRI, cognitive assessments, CSF biomarkers, and APOE 4 status.
Introduction
Alzheimer’s disease (AD) is one of the most common cognitive disorders in old age [1]. The development of effective treatments or disease-modifying therapies is hampered by the complexity of aging and the lack of a clear understanding of the etiology and pathogenesis of AD [2]. The diagnosis of AD in the early stages of the disease is complex. Despite their mostly distinct pathophysiological features, these conditions are often misdiagnosed antemortem due to their overlapping cognitive dysfunction symptoms.
Materials and methods
The ADNI/TADPOLE challenge datasets considered for this study were “D1—a comprehensive longitudinal data set for training,” and “D2—a comprehensive longitudinal data set on rollover subjects for forecasting”. The challenge included 1,737 individuals from the ADNI database with longitudinal observations.
Results
The preceding section detailed the materials and methods used to construct and evaluate various machine learning (ML) models aimed at predicting the conversion from mild cognitive impairment (MCI) to Alzheimer’s disease (AD). This section presents the findings obtained by applying these models to the TADPOLE dataset.
Discussion
In this section, we explore the potential of machine learning techniques combined with Cox models, with the aim of predicting the conversion from MCI to AD using multimodal data from subjects with MCI. As mentioned in the introduction, combining biomarkers from CSF, cognitive assessments, MRI features, and APOE 4 status allows for a more comprehensive understanding of the dynamics associated with disease progression.
Acknowledgments
Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database (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.
Citation: Rosales-Gurmendi DS, Fumagal-González GA, Orozco J, Farber J, Treviño V, Martinez-Ledesma E, et al. (2026) Interpretable multivariate survival models: Improving predictions for conversion from mild cognitive impairment to Alzheimer’s disease via data fusion and machine learning. PLoS One 21(4): e0321671. https://doi.org/10.1371/journal.pone.0321671
Editor: Moeko Noguchi-Shinohara, Kanazawa university, JAPAN
Received: March 8, 2025; Accepted: March 18, 2026; Published: April 30, 2026
Copyright: © 2026 Rosales-Gurmendi et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Data Availability: All relevant data are within the paper and its Supporting Information files. Data used in this study were obtained from the TADPOLE challenge dataset (https://tadpole.grand-challenge.org). This dataset has been made publicly available and anonymized since 16 June 2017, and it was derived from the ADNI database (adni.loni.usc.edu). The ADNI was launched in 2003 as a public-private partnership, led by Principal Investigator Michael W. Weiner, MD. ADNI is a cross-sectional and longitudinal follow-up observational study. The main goal of ADNI has been to see how neuroimaging, cognitive tests, fluid, and genetic biomarkers can be used together to figure out how MCI and early AD will progress. For up-to-date information, see www.adni-info.org.
Furthermore, we have set the baseline data and the reduced data we used in the study on the following GitHub repository: https://github.com/joseTamezPena/SurvivalTadpole/tree/main csv of the data can be found under the folder “Data”.
Funding: This research was supported by the Secretaría de Ciencia, Humanidades, Tecnología eInnovación (Secihti), with cloud computing resources provided through Microsoft’s AI for Good Lab. In addition, the work was also partially supported by Secretaría de Educación Superior, Ciencia, Tecnología e Innovación, part of Gobierno de la República del Ecuador, and by the Strategic Research Group of Bioinformatics for Clinical Diagnosis from Tecnólogico de Monterrey.
Competing interests: The authors have declared that no competing interests exist.
