Systematic Modality Ablation of Multimodal Machine Learning for Predicting 24-Month Progression from Mild Cognitive Impairment to Alzheimer's Disease
- 1Clinovia.ai
Abstract
INTRODUCTIONMultimodal biomarkers have transformed Alzheimers disease research, but the incremental contribution of each modality to predicting progression from mild cognitive impairment (MCI) remains unclear. We systematically evaluated individual biomarker modalities using a comprehensive ablation framework.
METHODSWe analyzed 2,430 participants with MCI from the Alzheimers Disease Neuroimaging Initiative with known 24-month progression status. XGBoost models were trained using combinations of demographic variables, cognitive assessments, apolipoprotein E (APOE) genotype, structural MRI, cerebrospinal fluid (CSF) biomarkers, and PET biomarkers. Performance was evaluated using repeated stratified 5x10 cross-validation; discrimination was assessed using the area under the receiver operating characteristic curve (AUC), with pairwise comparisons via DeLongs test on single-pass out-of-fold predictions, Holm-Bonferroni corrected. Complete-case analyses evaluated the impact of missing data and median imputation.
RESULTSThe full multimodal model achieved the highest discrimination (AUC=0.934). Excluding cognitive assessments produced the largest reduction (AUC=0.883, P<0.001 vs. multimodal), the only comparison to remain significant after correction. Removing APOE, CSF, or MRI produced only modest, statistically indistinguishable reductions (AUC=0.933, 0.931, 0.932). Removing PET produced a similarly small reduction in the primary analysis (AUC=0.932), but complete-case sensitivity analysis showed imputation significantly inflated this estimate (P=0.005); PETs true contribution may exceed the other three. The baseline clinical model performed near chance (AUC=0.556).
DISCUSSIONCognitive assessment contributes substantially more predictive information for 24-month progression than structural imaging, molecular biomarkers, or genetic risk, whose removal produces only modest, largely statistically indistinguishable performance loss -- with the exception of PET, whose apparent equivalence may be an imputation artifact. These findings establish an evidence-based hierarchy of biomarker utility and provide a quantitative framework for designing cost-effective prediction models and prioritizing biomarker acquisition in clinical research and multimodal AI systems.
Related
- Comparative Value of Cognitive and Functional Assessments for Predicting 24-Month Progression from Mild Cognitive Impairment to Alzheimer's Disease: An ADNI Cohort Study
- A Multimodal Nomogram Predicting the Risk of Cognitive Impairment in Parkinson Disease.
- Joint modeling approaches for predicting conversion from mild cognitive impairment to Alzheimer's disease: A systematic review (1999-2025).
- Sex‐specific brain reserve and progression from mild cognitive impairment to Alzheimer's disease dementia
- Multimodal neuroimaging and electrophysiological signatures in amnestic mild cognitive impairment with different amyloid-β deposition status: correlations with cognitive function and diagnostic value
BibTeX
@misc{choe2026systematic,
title = {{Systematic Modality Ablation of Multimodal Machine Learning for Predicting 24-Month Progression from Mild Cognitive Impairment to Alzheimer's Disease}},
author = {S. Choe},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.01.26360413},
url = {https://www.medrxiv.org/content/10.64898/2026.09.01.26360413v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Systematic Modality Ablation of Multimodal Machine Learning for Predicting 24-Month Progression from Mild Cognitive Impairment to Alzheimer's Disease
AU - S. Choe
PY - 2026
DA - 2026/09/01
PB - medRxiv
DO - 10.64898/2026.09.01.26360413
UR - https://www.medrxiv.org/content/10.64898/2026.09.01.26360413v1
AB - INTRODUCTIONMultimodal biomarkers have transformed Alzheimers disease research, but the incremental contribution of each modality to predicting progression from mild cognitive impairment (MCI) remains unclear. We systematically evaluated individual biomarker modalities using a comprehensive ablation framework. METHODSWe analyzed 2,430 participants with MCI from the Alzheimers Disease Neuroimaging Initiative with known 24-month progression status. XGBoost models were trained using combinations of demographic variables, cognitive assessments, apolipoprotein E (APOE) genotype, structural MRI, cerebrospinal fluid (CSF) biomarkers, and PET biomarkers. Performance was evaluated using repeated stratified 5x10 cross-validation; discrimination was assessed using the area under the receiver operating characteristic curve (AUC), with pairwise comparisons via DeLongs test on single-pass out-of-fold predictions, Holm-Bonferroni corrected. Complete-case analyses evaluated the impact of missing data and median imputation. RESULTSThe full multimodal model achieved the highest discrimination (AUC=0.934). Excluding cognitive assessments produced the largest reduction (AUC=0.883, P<0.001 vs. multimodal), the only comparison to remain significant after correction. Removing APOE, CSF, or MRI produced only modest, statistically indistinguishable reductions (AUC=0.933, 0.931, 0.932). Removing PET produced a similarly small reduction in the primary analysis (AUC=0.932), but complete-case sensitivity analysis showed imputation significantly inflated this estimate (P=0.005); PETs true contribution may exceed the other three. The baseline clinical model performed near chance (AUC=0.556). DISCUSSIONCognitive assessment contributes substantially more predictive information for 24-month progression than structural imaging, molecular biomarkers, or genetic risk, whose removal produces only modest, largely statistically indistinguishable performance loss -- with the exception of PET, whose apparent equivalence may be an imputation artifact. These findings establish an evidence-based hierarchy of biomarker utility and provide a quantitative framework for designing cost-effective prediction models and prioritizing biomarker acquisition in clinical research and multimodal AI systems.
ER -