Interpretable multivariate survival models: Improving predictions for conversion from mild cognitive impairment to Alzheimer's disease via data fusion and machine learning
Clinical Snapshot
PICO Framework
| P — Population | 564 participants with mild cognitive impairment (MCI) from the ADNI study who transitioned to Alzheimer's disease |
| I — Intervention | Multivariate Cox survival models incorporating quantitative MRI, cognitive assessments, CSF biomarkers, and APOE ε4 status |
| C — Comparator | Other predictive models (not clearly specified) |
| O — Outcomes | Progression from MCI to Alzheimer's disease, measured by sensitivity, specificity, and precision |
Bottom Line
This prognostic study developed Cox survival models to predict conversion from mild cognitive impairment to Alzheimer's disease using multimodal data from 564 ADNI participants. The best-performing model achieved 69% sensitivity and 87% specificity by integrating quantitative MRI, cognitive assessments, CSF biomarkers, and APOE ε4 status. While the multimodal approach shows promise for risk stratification, the study lacks external validation and has unclear follow-up methodology. The high specificity suggests potential utility for ruling in high-risk patients, but the moderate sensitivity means some converters would be missed. Clinical implementation would require comprehensive assessment capabilities and careful consideration of resource allocation. The interpretable nature of the Cox models is advantageous for clinical decision-making, though validation in independent cohorts is essential before routine clinical adoption.
Key Findings
P Value: Not reported
Effect Size: Sensitivity 0.69, Specificity 0.87, Precision 0.81
Primary Outcome: Progression from mild cognitive impairment to Alzheimer's disease
Nnt Or Sensitivity: Sensitivity 69%, Specificity 87% for MCI to AD conversion prediction
Confidence Interval: Sensitivity 95% CI [0.63, 0.76], Specificity 95% CI [0.83, 0.90]
Clinical Application
Requires multimodal assessment including MRI, CSF analysis, cognitive testing, and genetic testing - resource intensive Relevant to Australian memory clinics and geriatricians; CSF biomarkers and advanced MRI may have PBS limitations; aligns with RACGP cognitive assessment guidelines Patients with mild cognitive impairment in memory clinic or specialist settings with access to comprehensive assessment
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 [Formula: see text]4 (APOE [Formula: see text]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 [Formula: see text]4 status. Advanced machine learning (ML) methods were applied to evaluate the importance of these data sources, select relevant features, and develop interpretable Cox survival models within a cross-validation framework. The top optimized model achieved a sensitivity of 0.69, 95% CI [0.63, 0.76], and a specificity of 0.87, 95% CI [0.83, 0.90], and used all data sources. The results demonstrated that combining qMRI features with cognitive assessments, CSF biomarkers, and APOE [Formula: see text]4 status, analyzed using the BSWiMS model, resulted in a substantial improvement in the ability to predict progression from MCI to AD, achieving 81% precision and 87% specificity. These results exceed those obtained with other models evaluated. Finally, biomarker analysis showed that cognitive scores are the most relevant features to predict conversion, followed by CSF and qMRI biomarkers. These findings highlight the value of integrating multiple data sources in highly interpretable Cox survival models for the early identification of individuals at risk for AD.
References
- 1.Rosales-Gurmendi, D. S., Fumagal-González, G. A., Orozco, J., Farber, J., Treviño, V., Martinez-Ledesma, E., Martinez-Torteya, A., Rosales-Gurmendi, F., & Tamez-Peña, J. (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. https://doi.org/10.1371/journal.pone.0321671
Related Research
Sleep medicine
Concordance of wearable device sleep metrics with patient-reported sleep quality: A systematic review
3 Aug 2026
Sleep medicine reviews
Machine and deep learning in REM sleep behavior disorder: a scoping review and analysis of reporting quality
3 Aug 2026
Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology
Efficacy and safety of fecal microbiota transplantation in Parkinson's disease: a systematic review and meta-analysis of randomized controlled trials with GRADE assessment
1 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service