Long‐term Alzheimer's disease mortality prediction in adults aged ≥60 years: A prospective cohort study benchmarking survival machine learning algorithms
We benchmarked 10 survival machine learning (ML) algorithms using 116 clinical variables to predict long-term Alzheimer's disease (AD)-specific mortality.Feature importance analysis identified novel non-imaging clinical predictors, including arm circumference, self-rated physical activity, and alcohol consumption.This work highlights the underused potential of routine clinical data for AD mortality prediction and underscores the need for interpretable, population-based ML applications.
Authors
- Yunzhang Wang (ORCID: https://orcid.org/0000-0003-1165-3595)
- Dechao Tian (ORCID: https://orcid.org/0000-0001-9281-1633)
- Liuqing Li (ORCID: https://orcid.org/0000-0002-4869-3331)
- Ruitong Liao (ORCID: https://orcid.org/0000-0003-2442-5436)
- Yue Xu (ORCID: https://orcid.org/0000-0003-4205-5109)
- Qi Liu (ORCID: https://orcid.org/0000-0002-4192-757X)
- Xiaoping Huang (ORCID: https://orcid.org/0009-0005-3731-6695)
- Yiqiang Zhan (ORCID: https://orcid.org/0000-0001-5815-9725)
- Qianqian Ji (ORCID: https://orcid.org/0000-0003-2420-3024)
- Xiaogang Lv
- Qingya Zhao
Institutions
- Sun Yat-sen University (CN)
- Karolinska Institutet (SE)
Publication Details
- Journal
- Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring
- Published
- 2025-10-01
- DOI
- https://doi.org/10.1002/dad2.70229
- Primary Topic
- Dementia and Cognitive Impairment Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00