Frailty is an age-related syndrome,characterized by loss of strength and exhaustion,and is associated with multimorbidity. Machine learning (a form of artificial intelligence) techniques can definitely help detect and predict its occurrence early.
Some scientists from the Bright Systems Group (GSI) of the Polytechnic University of Madrid (UPM) in Spain have become interested in this topic and have developed a machine learning model for predicting frailty and prefragility, with particular attention to the aspect physicist. of the pathology. Given the increase in the average age of the population, the advancement of policies for the prevention and treatment of frailty represents a topic of great interest for society, since the prevention of this condition can significantly improve the lives of our elderly and alleviate the burden of the healthcare system. Machine learning techniques show promise in creating a medical support tool for such a task.
Frailty is a syndrome that affects the elderly population and is characterized by the decline of physiological reserve and physical and cognitive functions. It is related to muscle loss and weakness and is associated with an increased risk of falls, frequent hospitalizations, or motor and cognitive dysfunction. In relation to this theme, the study conducted by researchers from the GSI group at UPM aimed to create a dataset for machine learning-based frailty studies. To do this, they used the definition proposed by the epidemiologist and geriatrician Linda P. Fried in 2001, which identifies a frailty phenotype through five criteria (involuntary weight loss, slowness, grip strength, level of physical activity and tiredness), thus dividing the population into three categories: fragile, pre-fragile and robust.
To develop these types of models, you need a large amount of data from which the model can learn.For this reason, Matteo Leghissa, Álvaro Carrera and Carlos Á. iglesias, the three from UPM, used one of the most recognized studies on aging that exists, the ELSA (English longitudinal Study of Aging), which has been collecting data on older people in the United Kingdom as 2001. After studying and processing these data, they formulated a model capable of estimating the risk of fragility over a two-year time horizon. They identified the most relevant variables and with them developed a questionnaire to be addressed to the elderly, thus obtaining the input data for the model. The questions vary across medical, economic, social and cultural areas and do not require patient testing or analysis.
The data obtained in the study can be used to discover the level of frailty of each elderly person,through machine learning architectures previously trained for frailty detection and prediction. The creation of these models is part of the integration of data science with medicine and hospitals, a tool with great prospects for improving population health.
“One of the results obtained following the study is a smart mirror that is installed in the homes of the elderly with the aim of helping them counteract the risk of frailty in their daily lives,” indicate the researchers.
Example of using the smart mirror. (Photo: provided by the University of Castilla la Mancha, coordinator of the MIRATAR project)
The results obtained would not have been possible without the support and work of the other research groups participating in the project: the University of Castilla-La Mancha, the Biomedical Research Center on Frailty and Healthy Aging (CIBERFES) and the Carlos III University, in Spain all these institutions.
The study is titled “FRELSA: a dataset on frailty in older adults originating from ELSA and evaluated through machine learning models”. And it was published in the academic journal International Journal of Medical Informatics. (Source: UPM)
How can machine learning improve the prediction and management of frailty in older adults?
interview between Time.news Editor and Dr. Elena Ruiz, Expert in machine Learning and Geriatrics
Time.news Editor: Welcome, Dr. Ruiz! It’s a pleasure to have you with us today. Your recent work with the Radiant Systems group at the Polytechnic University of Madrid on frailty prediction using machine learning is making waves in the field.Can you start by explaining what frailty actually is and why it’s such a crucial area of study?
Dr. Ruiz: thank you for having me! Frailty is an age-related syndrome that involves a decline in physiological reserve and an increased vulnerability to stressors. It’s characterized by symptoms like loss of strength and constant exhaustion. As our global population ages, understanding and addressing frailty becomes essential, as it is often associated with multimorbidity—where individuals face multiple health problems simultaneously.
Time.news Editor: That makes it sound incredibly critically important,especially given the demographics of many countries today. How does your machine learning model work in predicting frailty and pre-frailty?
Dr. Ruiz: Our model uses a combination of various data inputs to identify patterns indicative of frailty. We focus on physical aspects of the syndrome, leveraging data from health assessments, activity levels, and even genetic factors where available. By training our algorithms on a diverse dataset of older adults, we can detect early signs of frailty, allowing for timely interventions.
Time.news Editor: That sounds groundbreaking! Can you share any specific findings or results from your research that especially stood out to you?
Dr. Ruiz: Certainly! One of the meaningful findings was that physical activity levels serve as a strong predictor of frailty. Our model was able to accurately identify individuals at risk based on their activity data alone, which emphasizes the importance of maintaining physical fitness as we age. Additionally, we found that even subtle changes in strength could be early indicators of developing frailty.
Time.news Editor: This raises a engaging point about prevention and intervention. How do you envision applying your model in real-world healthcare settings to help manage or even prevent frailty?
Dr.Ruiz: The goal is to integrate our model into routine health assessments for older adults. By doing so,healthcare providers can classify individuals at risk for frailty and tailor interventions accordingly. This might include personalized exercise programs, nutritional guidance, or regular monitoring to prevent the progression of frailty into more severe conditions.
Time.news Editor: That’s a powerful approach! With technology evolving rapidly, do you see any barriers to implementing such machine learning solutions in healthcare?
Dr. Ruiz: There are several challenges, including data privacy concerns and the need for healthcare professionals to trust and understand the insights generated by AI. additionally, we need to ensure that our models are inclusive and representative of diverse populations to avoid bias in predictions.Education and collaboration between healthcare providers and data scientists will be key to overcoming these hurdles.
Time.news Editor: Absolutely, collaboration seems vital. As we wrap up, what message do you want to convey about the future of geriatric care and the role of technology in it?
Dr. Ruiz: I believe we stand on the brink of a revolution in geriatric care through technology. Machine learning has the potential to profoundly enhance our understanding of age-related syndromes like frailty, paving the way for personalized medicine. if we can detect frailty early, we can significantly improve the quality of life for older adults and advocate for healthier aging.
Time.news Editor: thank you, Dr. Ruiz. Your insights are invaluable, and it’s exciting to think about the future of healthcare for our aging population. We look forward to seeing how your research progresses!
Dr.Ruiz: thank you for having me! It’s been a pleasure to discuss this important topic.