summary: New machine learning techniques predict your body clock to help improve your sleep and wellness. The technology provides personalized sleep and meal plans to suit your individual biology, reducing your risk of illness. This approach uses blood samples to predict circadian timings and provides a simple way to estimate our own circadian rhythms.
sauce: University of Surrey
New machine learning techniques can help time our body clocks, helping us all make better health decisions, such as when and how long to sleep.
This study, conducted by the University of Surrey and the University of Groningen, used a machine learning program to analyze metabolites in the blood to predict times in the body’s circadian timing system.
To date, the standard method of determining the timing of the circadian system is to measure the timing of our natural melatonin rhythms, specifically the timing to initiate melatonin production, known as the dim melatonin onset (DLMO).
Co-author of the study, Professor Debra Skene of the University of Surrey, said:
“After taking two blood samples from participants, our method was able to predict individual DLMO with accuracy equal to or better than previous, more intrusive estimation methods.”
The research team collected time-series blood samples from 24 people (12 men and 12 women). All participants were healthy, did not smoke, and slept regularly for 7 days prior to his visit to the university’s clinical research facility. The research team then used a targeted metabolomics approach to measure more than 130 metabolic rhythms. These metabolic data were then used in a machine learning program to predict circadian timing.
Professor Skane continued:
“We are excited about the new approach to predicting DLMO, but we are cautious because it is more convenient and requires less sampling than currently available tools. Although it needs to be validated in a large population, it may pave the way for optimizing the treatment of circadian rhythm sleep disorders and injury recovery.
“While smart devices and wearables provide valuable guidance on sleep patterns, our research has the potential to help individuals optimize their health and reduce their risk of serious illnesses associated with poor sleep. It paves the way for a truly personalized sleep and meal plan that’s aligned with the biology of your child: Did you eat at the wrong time?”
Professor Roelof Hut, co-author of the study from the University of Groningen, said:
“Our results may help develop affordable methods for estimating our own circadian rhythms that optimize behavior, diagnostic sampling, and timing of treatments.”
About this Machine Learning and Circadian Rhythm Research News
author: Dalizzo Nyorinjo
sauce: University of Surrey
contact: Dalitso Njolinjo – University of Surrey
image: image is public domain
Original research: closed access.
“Machine learning estimation of human body time using metabolomics profiling” Debra Skene et al. PNAS
overview
Machine learning estimation of human body time using metabolomics profiling
Circadian rhythms influence the physiology, metabolism, and molecular processes of the human body. Therefore, estimation of an individual’s body time (circadian phase) is highly relevant for optimizing individual behavior (sleep, eating, sports), diagnostic sampling, medical care, and treatment of circadian rhythm disorders.
Here, we provide a partial least squares regression (PLSR) machine learning approach to estimate dim light melatonin onset (DLMO) as a proxy for human circadian phases using plasma-derived metabolomics data in one or more samples. . To this end, our protocol was intended to approximate real-world conditions.
We found that metabolomics approaches optimized for either females or males under synchronized conditions were comparable or superior to existing approaches using more laborious RNA-sequencing-based methods.
Estimation of circadian body time using blood-targeted metabolomics requires further validation in shift work and other real-world conditions, but is currently lacking in appropriate post-validation behavioral and personalized clinical treatments. It may provide a robust and feasible technique with relatively high accuracy to aid in optimization. patient population.
