Researchers at the Icahn School of Medicine at Mount Sinai and other institutions have utilized machine learning technology to identify key predictors of mortality in dementia patients. The study, newly released in the online issue of Communications Medicine, focuses on the challenges in dementia care, particularly in predicting mortality risks and contributing factors in various types of dementia.
Dementia has become a leading cause of death in aging populations, making it essential to accurately anticipate mortality risks in patients. The study, which analyzed data from over 45,000 participants and 163,000 visit records, developed machine learning models based on clinical and neurocognitive features to predict mortality at one, three, five, and 10 years. This research highlighted the significance of neuropsychological testing in predicting mortality risks in dementia patients compared to age-related factors like cancer and heart disease.
The findings emphasize the potential of machine learning models in improving patient care and guiding healthcare providers towards more informed decisions. While machine learning shows great promise in enhancing dementia care, it is crucial to understand that these models are not definitive predictors of individual outcomes. The research team plans to enhance their models by integrating treatment effects and genetic data to further refine predictions and explore advanced deep-learning techniques.
Dementia presents a growing public health concern with its escalating prevalence and economic burden. The study’s outcomes lay the groundwork for future predictive modeling in dementia care and emphasize the role of machine learning in unraveling the complexities of neurodegenerative diseases. With Alzheimer’s and other dementias affecting millions globally and their costs continuing to rise, innovative approaches like machine learning are crucial in addressing this pressing health issue.
