Artificial intelligence provides insights into how deep-learned biochemistry clocks effectively determine biological age of smokers and predict smoking status
Insilico Medicine, one of the leaders in artificial intelligence for drug discovery, biomarker development, digital medicine, and aging research, announced the publication of a new collaborative research paper titled "Blood Biochemistry Analysis to Detect Smoking Status and Quantify Accelerated Aging in Smokers" in Scientific Reports.
Smoking has long been proven to negatively affect people's overall health in multiple ways. The study by Insilico scientists set out to determine biological age differences between smokers and non-smokers, and to evaluate the impact of smoking using blood biochemistry and recent advances in artificial intelligence. By employing age-prediction models developed by supervised deep learning techniques, the study analyzed a number of biochemical markers, including measures based on glycated hemoglobin, urea, fasting glucose and ferritin.
According to study's results, smokers demonstrated a higher aging ratio, and both male and female smokers were predicted to be twice as old as their chronological age as compared to nonsmokers. The results were carried out based on the blood profiles of 149,000 adults.
Other findings suggested that deep learning analysis of routine blood tests could replace the current unreliable method of self-reporting of smoking status and evaluate the influence that other lifestyle and environmental factors have on aging.
"I am pleased to be part of the research study, which provides fascinating scientific evidence that smoking is likely to accelerate aging. Smoking is a real problem that destroys people's health, causes premature deaths, and is often the cause of many serious diseases. We applied artificial intelligence to prove that smoking significantly increases your biological age," said Polina Mamoshina, a senior research scientist at Insilico Medicine.