Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1070
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-09-13T06:56:25.820195Z
status: published
lens: g_space
sector: health
headline: Machine learning identifies depression risk in older adults with chronic diseases: Clarifying shared risk factors stratified by cognitive impairment status
dek: Background The prevalence of depression is higher among older adults with chronic diseases and cognitive impairment than the general population. The comorbidity of cognitive impairment and chronic diseases significantly impacts the lives of these patients. This study aims to develop machine learning models to identify depression risk among older adults with chronic illnesses across different levels of cognitive impairment. Methods Data were derived from the Chinese Longitudinal Healthy Longevity Survey (n = 5798…
gain_title: XGBoost models trained on 5798 participants identified depression risk among older adults with chronic diseases across cognitive impairment levels with accuracy up to 0.767 and good calibration.
problem_title: (none)
trace_subject: (none)
gain_reading: XGBoost models trained on 5798 participants identified depression risk among older adults with chronic diseases across cognitive impairment levels with accuracy up to 0.767 and good calibration.
gain_evidence: The proposed models demonstrated promising performance in identifying depression risk among older adults with chronic illnesses across different levels of cognitive impairment. | The accuracy of the three models ranged from 0.755 to 0.767, and all Brier scores were 0.160 or lower, indicating good predictive performance.
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers developed three XGBoost models to identify depression risk among older adults with chronic illnesses, stratified by cognitive impairment status, using 5798 participants from the Chinese Longitudinal Healthy Longevity Survey and SHAP for interpretability.

The work matters because depression prevalence is higher in this group and predictors differed by cognition, suggesting tailored screening could improve detection, but the models have only internal performance reported as of September 2026 and require external validation before clinical use.
limitation: 
tag: Evidence-backed gain
key_points: Study used Chinese Longitudinal Healthy Longevity Survey data with n = 5798 older adults with chronic diseases. | Three cognition-stratified XGBoost models were built and interpreted with SHapley Additive exPlanations. | Feeling energetic was top predictor in cognitively unimpaired and mildly impaired groups, while sleep duration per day was top in severely impaired group.
rundown: Researchers derived data from the Chinese Longitudinal Healthy Longevity Survey (n = 5798) and trained models using the XGBoost algorithm, enhancing interpretability with SHapley Additive exPlanations and simplifying each model based on feature importance.

Performance was reported as accuracy 0.755 to 0.767 with Brier scores at or below 0.160, and predictor importance shifted by cognitive status, supporting cognition-stratified screening strategies pending further validation.
sources:
- peer_reviewed | Geriatric Nursing | https://doi.org/10.1016/j.gerinurse.2026.104346 | 2026-09-11
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

09174fdf43531302552410f4ffe77a36cf2fa55dd640313707628fb12249d291

previous

0000000000000000000000000000000000000000000000000000000000000000