U.S. Veterans Affairs Nursing Home ADL Trajectory Clusters and Mortality Risk

1.3 million Activities of Daily Living assessments from 265,530 U.S. Veterans Affairs nursing home residents were analyzed to identify 13 distinct functional trajectory clusters. The dataset, created by Ghazal Khalili and last updated in 2026, summarizes these clusters and their association with mortality risk. The highest-risk cluster showed approximately 48% cumulative mortality within the first year.

Use Cases

• Identify high-risk patient phenotypes for targeted care planning based on ADL trajectory clusters.
• Evaluate the prognostic value of functional trajectory patterns for mortality risk based on the described clustering framework.
• Inform resource allocation in long-term care settings based on the heterogeneity of functional loss and recovery described.
• Develop personalized care models using the interpretable trajectory phenotypes identified in the analysis.

Strengths

• Based on a large-scale analysis of 1.3 million ADL assessments from 265,530 residents.
• Identifies 13 distinct, clinically interpretable trajectory clusters with clear mortality associations.
• The clustering framework was designed to preserve temporal structure while being computationally feasible for large data.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the summary dataset is unknown, which may limit suitability assessment.
• The data is specific to U.S. Veterans Affairs nursing homes and may not generalize to other populations.

Provenance

Source

U.S. Veterans Affairs nursing homes.

Collection Method

Analysis of longitudinal ADL assessments using a hybrid trajectory clustering framework.

Freshness

Last updated 2026-05-27 17:50:58; freshness should be verified.

Geography

United States