By Admin 
SleepFM Health Risk Prediction: Earlier, you used to know about any disease only when your condition had become very bad. But with the advancement of science, now you get to know which disease is prevalent and which disease may occur in the future. Similarly, researchers have prepared an artificial intelligence model which, based on sleep data, can predict the risk of 130 diseases in a person in the future. This model has been named Sleep FM.
This model has been created jointly by researchers from many institutions including Stanford University of America. It was trained with about 6 lakh hours of sleep data, which was collected from 65,000 people. The results of this research have been published in the medical journal Nature Medicine. Let us tell you how this device works and how you can know which disease you are going to suffer from in future.
How does Sleep FM work?
Initially, this AI system was tested to identify common things related to sleep, such as tracking different stages of sleep or indicating the severity of sleep apnea. After this, by linking the sleep data with the medical records of the patients, it was seen which diseases could be at risk in the future. The researcher said that out of more than 1,000 diseases present in the health records, this model could predict 130 diseases with great accuracy.
Important signs of health are hidden in sleep
According to Emmanuel Mignot, professor of sleep medicine at Stanford University, “A lot of signals are recorded from the body during sleep. For eight hours, the normal activities of the body are studied in such depth that the data becomes extremely rich.”
What kind of data is captured?
Polysomnography was used to examine sleep, which is considered the most reliable method of sleep study. In this, through sensors-
- brain activity
- heartbeat
- breathing pattern
- eye movement
- muscle activity
As many signals are recorded. SleepFM takes all these data streams together and analyzes their relationships.
New way to train AI
The team adopted a technique called ‘leave-one-out’ contrastive learning to train the AI. In this, a type of data is deliberately hidden and the AI is challenged to guess that missing information based on the remaining signals. This improves the understanding and accuracy of the model.
Best at identifying which diseases?
Research found that this AI is especially
- cancer
- Pregnancy related problems
- Heart and blood flow related diseases
- mental health
Like it is very strong in all predictions. In many cases its C-Index score was more than 0.8, which indicates good prediction. According to the researcher, the diseases for which Sleep FM was able to predict the risk from just one night’s sleep data include-
- dementia
- heart attack
- heart failure
- chronic kidney disease
- stroke
- atrial fibrillation
Apart from this, this model also proved to be effective in predicting the risk of diseases like Parkinson’s and developmental problems in children. Overall, this research shows that your sleep is not only a means of relieving fatigue but can also be a mirror of your future health.
Also read: Oversleeping Side Effects: Are you sleeping more than necessary? This could be a serious problem, expert warned
Disclaimer: This information is based on research studies and expert opinion. Do not consider this as a substitute for medical advice. Before adopting any new activity or exercise, please consult your doctor or relevant specialist.
Check out below Health Tools-
Calculate Your Body Mass Index (BMI)
Calculate The Age Through Age Calculator