Related Experiment Video
Updated: Jul 6, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Predictive items of 2-year mortality in nonagenarians with cognitive impairment at baseline: the NonaSantfeliu study
Francesc Formiga1, Assumpta Ferrer, Enric Duaso
1Geriatric Unit, Hospital Universitari de Bellvitge, L'Hospitalet de Llobregat, Barcelona, Spain. fformiga@csub.scs.es
Abstract:
We aimed to identify a set of predictors of mortality at 2-year follow-up in a cohort of nonagenarians with cognitive impairment at baseline. The following variables were evaluated; functional status determined by the indices of Barthel Index for basic and Lawton and Brody for instrumental activities of daily living, while cognition was assessed using the Spanish version of the mini-mental state examination (MEC). Cognitive impairment was graded as severe for those having MEC scores of 0-17 and mild for scores of 18-23. A total of 77 nonagenarians with a MEC score of 23 or below were included: 61 women (79.25%) and 16 men, with a mean age of 93.7 (3.4) years. The rate of mortality was 55.8%. According to MEC scores the proportion of deaths during the 2-year follow-up period ranged from 35.2% (6 out of 17) among mildly impaired participants to 61.6% (37 out of 60) among severely impaired participants (p=0.05). Multivariate regression analysis showed that the risk of dying in this cohort was associated with being older (p<0.01, OR 1.23, 95% CI 1.03-1.4) and having a previous history of heart failure (p<0.0001, OR 8.72, 95% CI 2.66-28.5). In conclusion age and heart failure predict mortality among nonagenarians with prior cognitive impairment.
Related Concept Videos
Actuarial Approach
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
Cognitive Development During Adulthood
