40–80%
prediction quality for cognitive symptoms varied widely across participants and symptom types
Exact: 40% to 80%
F1 scores for cognitive symptom prediction ranged from 40% to 80% across participants
F1 scores, which balance precision and recall, ranged from 40% to 80% under random train-test splitting conditions. This variability suggests that the predictive value of IEQ factors and temporal patterns differs meaningfully across individuals and symptom types, underscoring the importance of personalised models.
Under random train-test splitting, accuracy generally exceeded 70% with F1 scores ranging from 40% to 80%.
Related findings
higher indoor humidity tracks greater insomnia severity in older adults
Higher indoor humidity linked to greater insomnia severity in older adults
Youngmin Cho et al., 2025, Innovation in Aging
higher indoor CO2 levels linked to poorer delayed memory recall in older adults
Higher indoor CO2 levels associated with poorer delayed memory recall in older adults
Youngmin Cho et al., 2025, Innovation in Aging
evening indoor light closely tracks perceived stress in older adults
Higher evening indoor light exposure strongly linked to greater stress in older adults
Youngmin Cho et al., 2025, Innovation in Aging
Read more in
Workplace What your office costs
Four design variables that move cognitive performance and who pays for them
Education What school spaces do to children
Where the evidence on classroom air, acoustics, light and green is robust, where it is thin, and what to measure before the build.
Healthcare Built to Wake: How Hospital Noise and Light Undermine Patient Sleep
Of the two environmental levers on inpatient sleep, noise control is the better proven and the cheaper, while tunable lighting for the general ward is the one the evidence does not yet support.
More from The Built Review
Workplace Pricing biophilia: what the evidence is worth
Read at the primary sources, the business case for nature in buildings is narrower than advertised and strong enough to act on.
Workplace Germany's missing indoor-air bill
France, Britain and Australia have priced bad indoor air. Germany's missing number is a political choice, not a methodological limit.
Housing What insurers don't ask about buildings
Health insurers price age, tobacco and zip code. Building quality is in no model, and the law is only half the reason.