Roswell Park Researchers Contribute to AI-Enabled Study That Unravels The Mechanics of Aging And Disease Progression

Newly published work demonstrates age reversal in an experimental medical intervention

BUFFALO, N.Y. — Researchers from Roswell Park Comprehensive Cancer Center, in collaboration with Gero and Genome Protection Inc., recently published new work in Nature Communications that demonstrates the power of artificial intelligence (AI) combined with analytical tools borrowed from the physics of complex systems to provide insights into the nature of aging, resilience, and future medical interventions for age-related diseases including cancer.

Modern AI systems exhibit superhuman-level performance in medical diagnostics, like identifying cancer on MRI scans. For this project, the research team went one step further and used AI to figure out principles that describe how the biological process of aging unfolds in time.

The researchers trained an AI algorithm on a large dataset composed of multiple blood tests taken along the life course of tens of thousands of aging mice to predict the future health state of an animal from its current state. The artificial neural network applied by the research team precisely projected the health condition of an aging mouse with the help of a single variable, which was termed dynamic frailty indicator (dFI) that accurately characterizes the damage that an animal accumulates throughout life.

“Mice usually live about 100 weeks (two years). We noticed that already at the age of 25 weeks, animals lose resilience, the ability to recover from damage that occurs in the course of natural aging. This creates conditions for progressive damage accumulation, as reflected by the exponential growth we observed in dFI. The damage doubling time we observed appeared to be the same as the mortality rate doubling time. Thus, the dynamics of dFI explained the acceleration of death risk and predicted the remaining lifespan of an animal,” Konstantin Avchaciov, PhD, the study’s first author and Senior Researcher with Gero, explains.

In addition, dFI was observed to accurately track the effects of treatments and lifestyle changes on longevity. For instance, it predicted sex-specific aging acceleration caused by a high-fat diet.

“Most importantly, the loss of resilience documented in this study means that anti-aging interventions may produce long-lasting age-reversal effects. Thus, we show that even a short treatment with rapamycin — which has been shown in previous preclinical studies to extend life — produces a reduction in damage markers such as dFI that persist long after the end of treatment,” says Peter Fedichev, PhD, Co-Founder and CEO at Gero.

The authors expect that their findings will help lead to better understanding of human aging and diseases.

“A key point to underscore is that dFI came out of the analysis of hematological parameters, reflecting the critical role that blood, and particularly its myeloid components, hold for aging. Our findings are in line with the conclusions suggested by numerous earlier experimental observations, thus confirming a biological sense of this variable. We expect that dFI will be applicable to the analysis of human data and may help to reveal both aging-accelerating and aging-decelerating conditions for developing antiaging treatments — making this work highly relevant for efforts to improve the quality of life of cancer patients and cancer survivors dealing with the short- and long-term effects of cancer treatment,” says Andrei Gudkov, PhD, DSci, Chair of the Department of Cell Stress Biology at Roswell Park Comprehensive Cancer Center, Co-Founder of Genome Protection Inc., and co-author of the manuscript.

“The volume of available medical and genetic information this work may have significance for is mind-blowing. Future AI systems combining the recent breakthroughs in computer and physical sciences will unravel the intricate relationship between aging and chronic diseases and lead to the development of transformative medicines,” adds Dr. Fedichev.

The work builds off earlier findings demonstrating that most humans are resilient to aging-related damage until they approach age 60 and that the number of individuals exhibiting signs of the loss of dynamic stability increases exponentially with age. The authors note that the current findings appear to effectively model human late-life mortality and morbidity.

This international team has further investigations underway assessing the effects of drugs on resilience toward the goal of designing and developing effective interventions against aging and chronic diseases in humans.