Related Experiment Video
Updated: Jun 15, 2026
12:18
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Utilizing machine learning to identify fall predictors in India's aging population: findings from the LASI
Mrinmoy Pratim Bharadwaz1, Jumi Kalita2, Anandita Mitro3
1RWE/HEOR/ES, Axtria India Pvt. Limited, Pune, Maharashtra, India.
BMC Geriatrics
|March 18, 2025
Summary
Depression significantly increases fall risk in older adults by 80%. Machine learning identified region, multimorbidity, and gender as key fall predictors, highlighting the need for integrated mental and physical health strategies.
Area of Science:
- Gerontology
- Public Health
- Data Science
Background:
- Depression negatively impacts mental and musculoskeletal health, increasing fall risk in older adults.
- Falls are a major concern for older adults, leading to significant morbidity and mortality.
- Identifying predictors of falls is crucial for developing targeted prevention strategies.
Purpose of the Study:
- To investigate the association between depression and falls in older adults.
- To identify predictors of falls in older adults using a machine learning approach.
- To quantify the increased risk of falls associated with depression.
Main Methods:
- Utilized data from the Longitudinal Ageing Study in India (LASI) with 44,066 participants aged 45 and above.
- Employed the Conditional Inference Trees (CIT) machine learning method to assess associations and identify predictors.
- Measured depression using the CIDI-SF scale and analyzed fall prevalence through bivariate cross-tabulations.
Main Results:
- 10.8% of older adults reported fall incidents.
- The CIT model identified region as a significant predictor of falls, with multimorbidity, depression, sleep problems, and gender also being prominent factors.
- Depressed older adults experienced approximately 80% higher fall incidents compared to non-depressed individuals.
Conclusions:
- A significant association exists between depression and an increased risk of falls in older adults.
- The Conditional Inference Trees (CIT) method effectively identified key fall predictors with high precision.
- A multilevel, cross-sectoral approach focusing on both physical and mental health, particularly depression, is essential for fall prevention in older populations.
