AI Models Predict Dementia Risk in American Indian/Alaska Native Elders

AI Predicts Dementia Risk in Underserved Population

A groundbreaking study led by the University of California, Irvine has demonstrated the effectiveness of machine learning algorithms in predicting dementia risk among American Indian/Alaska Native adults aged 65 and older. This research, published in The Lancet Regional Health - Americas, marks the first time AI has been used to assess dementia risk in this historically understudied population 1

1

2

2

.

Study Methodology and Findings

Researchers analyzed seven years of data from the Indian Health Service's National Data Warehouse and related electronic health records. The study included nearly 17,400 American Indian/Alaska Native adults aged 65 years or older who were dementia-free at baseline, with almost 60% being female 1

1

2

2

.

Key findings include:

1. Over a two-year follow-up, 611 individuals (3.5%) were diagnosed with dementia.
2. Four machine-learning algorithms were evaluated and compared.
3. The three top-performing models identified 12 common predictors for dementia out of their 15 highest-ranked predictors.
4. Novel predictors of all-cause dementia, such as health service utilization, were identified across these algorithms 1

   1

   2

   2

   .

Significance for Public Health

The population of older American Indian and Alaska Native adults is projected to increase nearly threefold between 2020 and 2060. With dementia being a leading cause of disability and mortality in this age group, the study's findings are particularly timely and relevant 1

1

2

2

.

Dr. Luohua Jiang, professor of epidemiology and biostatistics at UC Irvine, emphasized the potential impact: "If future studies confirm these results, our findings could prove valuable to the Indian Health Service and Tribal health clinicians in identifying high-risk individuals, facilitating timely interventions and improving care coordination" 1

1

.

AI's Role in Healthcare

This study showcases the power of machine learning in healthcare, particularly in analyzing large datasets efficiently and accurately. By enabling computers to make predictions using vast datasets without explicit programming for each task, these models enhance scalability in health data analysis 1

1

2

2

.

Implications and Future Directions

The research provides a valuable framework for other healthcare systems, especially those serving resource-limited populations. It demonstrates how AI can be leveraged to address health disparities and improve care for underserved communities 1

1

2

2

.

As the aging population grows and the prevalence of dementia increases, such predictive models could play a crucial role in early intervention and care planning. The study's findings may inform future policies and practices in geriatric care, particularly for American Indian and Alaska Native communities 1

1

2

2

.

The research was supported by the National Institutes of Health and involved collaboration with the Centers for American Indian & Alaska Native Health at the Colorado School of Public Health 1

1

2

2

. As AI continues to evolve, its application in predicting and managing age-related cognitive decline could significantly impact public health strategies and individual patient care.