Machine learning models predict Alzheimer’s risk

alzheimer y polucion.jpg
alzheimer y polucion.jpg

Although Alzheimer’s is something we touch on daily at, sometimes there are interferences with the world of technology that are worth mentioning here.

Alzheimer’s is a degenerative disease that affects millions of people around the world. Although age is known to be an important risk factor for Alzheimer’s, a new study suggests that, after age 65, genetic risk may be more important than age as a predictor of the disease. The study, recently published in the journal Scientific Reports, is the first to build machine learning models using genetic risk scores, non-genetic information, and electronic medical record data from nearly half a million individuals to rank risk factors in order of its association with the eventual development of Alzheimer’s.

What does the study reveal?

The study used the models to classify predictive risk factors for two UK Biobank populations: white individuals over 40 years of age and a subset of adults over 65 years of age. The results showed that age, which accounts for one-third of the total risk at age 85, according to the Alzheimer’s Association, was the most important risk factor for Alzheimer’s in the entire population, but for older adults, genetic risk determined by a polygenic risk score was more predictive.

According to Xiaoyi Raymond Gao, lead author of the study and associate professor of ophthalmology and visual sciences and biomedical informatics at The Ohio State University College of Medicine, “We all know Alzheimer’s is a late-onset disease, so we know that age is an important risk factor. But when we consider risk only for people older than 65, then the genetic information captured by a polygenic risk score ranks higher than age. That means it’s really important to consider genetic information when we work on Alzheimer’s disease.”

The study found that low family income also emerged as a major risk factor, ranking third or fourth after the effects of age and genes. This could be because income can be a big factor in determining what you can afford to eat, where you can afford to live, education level, access to health care, all of which could contribute to Alzheimer’s disease.

Identification of non-genetic risk factors

Although the study found age and genetic risk to be the most important risk factors for Alzheimer’s, it also identified some non-genetic risk factors that differed between people with and without Alzheimer’s. These factors included high systolic blood pressure and low diastolic blood pressure, diabetes, lower income and education, recent falls, hearing difficulties, and a history of Alzheimer’s in the mother.

The study also identified other risk factors in the total adult population, such as a diagnosis of high blood pressure, urinary tract infection, depressive episodes, fainting spells, unspecified chest pain, disorientation, and abnormal weight loss. Other risk factors in the top 20 for people older than 65 included high cholesterol and gait abnormalities. These findings highlight the power of adding electronic medical record condition codes to models.

According to Gao, “Machine learning can explore the relationships between all those features or variables, pick out the important features, and rank certain features on top that contribute much more to Alzheimer’s disease risk than the rest of the features. Usually it is not good to be very obese, but we also see here that a lower BMI is not good. High blood pressure is not good, but here we see lower diastolic blood pressure is also not good. The models revealed some interesting patterns.”

The power of prevention

Building machine learning models to predict Alzheimer’s risk could aid in the development of effective and inexpensive new drugs and screening programs. It could also give people the power to take preventive measures and adjust their lifestyle to reduce their risk of Alzheimer’s disease.

According to Gao, “If people know more about risk factors, they can adjust their lifestyle. For Alzheimer’s and glaucoma, there is no cure, so prevention can go a long way. I hope that building models to make these predictions can help with the development of effective and inexpensive drugs and screening programs.”

The study highlights the importance of considering genetic and non-genetic factors in the prevention of Alzheimer’s. Machine learning models can be a valuable tool in identifying and ranking the most important risk factors and providing people with the information they need to take preventative action and reduce their risk of developing Alzheimer’s disease.

Ultimately, Alzheimer’s prevention is a matter of taking proactive steps to maintain good cognitive and physical health throughout life. Building machine learning models to predict Alzheimer’s risk is only one piece of the puzzle, but it can be a valuable tool in helping people take preventative action and maintain their cognitive health as they age.

Previous articleGoogle Recorder gets update with Material You in web version
Next articleThe best mobiles for children [2023]
Brian Adam
Professional Blogger, V logger, traveler and explorer of new horizons.