Related Experiment Video
Updated: Aug 5, 2026
12:18
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
An Effective Machine Learning for Prioritizing Hearing Loss Screening in Older Adults: A Primary Care Approach
Simone Seixas da Cruz1, Edilson José Rodrigues2, Michelle de Santana Xavier Ramos1,3
1Federal University of Recôncavo da Bahia (UFRB), Santo Antônio de Jesus, Bahia, Brazil.
Journal of the American Geriatrics Society
|July 31, 2026
Summary
Artificial intelligence can help prioritize hearing tests for older adults. A decision tree model showed high accuracy in identifying individuals needing further audiological evaluation in primary care settings.
Area of Science:
- Gerontology
- Artificial Intelligence
- Public Health
Background:
- Hearing impairment is common in older adults.
- Primary health care (PHC) lacks sufficient resources for hearing diagnostics.
- AI offers potential solutions for hearing health management.
Purpose of the Study:
- To develop and evaluate an AI-based decision tree model.
- To prioritize hearing examinations for older adults in PHC.
- To address the diagnostic resource gap in geriatric audiology.
Main Methods:
- An observational study utilized 60 clinical profiles.
- A decision tree model was developed using R (rpart package).
- Data preprocessing included cleaning, dichotomization, and multiple imputation (MICE).
Main Results:
- The decision tree model achieved an AUC of 0.825, surpassing logistic regression (AUC 0.700).
- Key predictors identified: tinnitus, social isolation, female sex, comorbidities (hypertension/diabetes), and age (≥65).
- A web-based dashboard was created for clinical application.
Conclusions:
- The decision tree model demonstrates technical viability for hearing loss screening prioritization.
- AI integration in PHC for audiological screening is a promising advancement.
- Further validation is needed for widespread clinical adoption.
