Development and validation of a parsimonious and noninvasive clinical decision machine learning model for…

AI / informaticsInternational journal of medical informatics· Jul 2026

Development and validation of a parsimonious and noninvasive clinical decision machine learning model for predicting the risk of long-term mild cognitive impairment in older adults: A multinational cohort study.

Hao Du, Ping Zhao, Zhe Yang … Xin Shi

Prediction Models & Risk ScoresAI / informaticsPrognosisQ1IF 6.2

Five noninvasive factors predicted long-term mild cognitive impairment risk with high accuracy

Development and validation of a parsimonious and noninvasive clinical decision machine learning model for predicting the risk of long-term mild cognitive impairment in older adults: A multinational cohort study.

Hao Du … Xin Shi

International journal of medical informatics · Jul 2026 · Q1 in Health Informatics

Background

Early identification of mild cognitive impairment (mild cognitive impairment) is crucial for delaying the progression of dementia.

Methods

We included 11,069 participants aged ≥60 years who were free of cognitive impairment at baseline.

n = 11,069 participants

Results

higher score means more accurate prediction, 1.0 would be perfect

AUC 0.87 (95% CI 0.84 to 0.90)

null 0

0.84

0.90

CI excludes the null - significant

More results

Five easily accessible baseline predictors were selected: age, sex, education, instrumental activities of daily living, and baseline cognitive score.

It maintained robust generalizability during external validation in the English Longitudinal Study of Ageing (AUC 0.786, 95% CI 0.76-0.81) and Health and Retirement Study (AUC 0.745, 95% CI 0.73-0.76) cohorts.

More results

Furthermore, an interactive web tool incorporating Shapley additive explanations was deployed to conduct a transparent risk assessment.

“

Conclusion · 1 of 2

This study developed and externally validated a parsimonious, cross-national machine learning model utilizing five noninvasive features to predict long-term mild cognitive impairment risk.

Conclusion · 2 of 2

Integrated with a transparent SHAP framework and deployed as an interactive web application, it provides a cost-effective clinical decision support tool for early mild cognitive impairment screening in primary care (https://mcipredictor.streamlit.app/).

Development and validation of a parsimonious and noninvasive clinical decision machine learning model for predicting the risk of long-term mild cognitive impairment in older adults: A multinational cohort study.

Development and validation of a parsimonious and noninvasive clinical decision machine learning model for predicting the risk of long-term mild cognitive impairment in older adults: A multinational cohort study.

Related papers