Key result
Random forest models detect mild cognitive impairment with moderate accuracy using routine non-cognitive data.
Why the study?
It is unclear whether routinely collected non-cognitive data support mild cognitive impairment triage and whether machine learning outperforms regression in this context.
Do machine learning models outperform regression in identifying mild cognitive impairment from routine non-cognitive data in community-dwelling older adults?
Cross-Sectional (n=2,650)
Do machine learning models outperform regression in identifying mild cognitive impairment from routine non-cognitive data in community-dwelling older adults?
Routine non-cognitive data support moderate MCI discrimination, but machine learning adds little over standard regression.
Background: Community health check-ups routinely collect non-cognitive data. Whether these support mild cognitive impairment (MCI) triage, and whether machine learning outperforms regression, is unclear. Methods: Cross-sectional analysis of 2650 community-dwelling adults aged ≥65 in Akita, Japan (2018–2025). MCI was defined by the NCGG-FAT (1.5 SD, age/education-adjusted norms). Thirty-four pre-specified non-cognitive predictors were modelled using tree ensembles, penalised regression, other machine-learning families and simple reference scores, with stratified 70/30 splitting, DeLong tests, 100 repeated splits, training-derived thresholds, calibration metrics and decision-curve analysis. Results: MCI prevalence was 28.6%. Random forest discriminated best (ROC AUC 0.722, 95% CI 0.681–0.761; PR-AUC 0.542) and was well calibrated (slope 1.048; intercept −0.024), but its advantage over LASSO regression was marginal (ΔAUC +0.031, p = 0.044) and absent versus gradient boosting (p = 0.059). All multivariable models greatly outperformed the Kihon Checklist (AUC 0.550, p < 0.001). Neither operating point was deployable: at 0.5, sensitivity was 0.269 (166/227 cases missed); at the training-derived Youden threshold (0.321), sensitivity was 0.604, specificity 0.699, and PPV 0.445. Net benefit exceeded assess-all/assess-none between threshold probabilities 0.15–0.60. Conclusions: Routine non-cognitive data support moderate, well-calibrated MCI discrimination, but machine learning added little over regression. This is an exploratory triage aid requiring external validation.
No takes yet. Share an insight, caveat, or question.
Kodama et al. (2026) conducted a cross-sectional in Mild Cognitive Impairment (n=2,650). Machine learning models (Random forest) vs. LASSO regression was evaluated on MCI discrimination (ROC AUC 0.722, 95% CI 0.681-0.761, p=0.044). Random forest models using routine non-cognitive data discriminated mild cognitive impairment with an AUC of 0.722 (95% CI 0.681-0.761), providing marginal benefit over LASSO regression (p=0.044).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: