Artificial Intelligence Integrates Multi-Omic Data to Predict HPV Lesion Progression

Infection with human papillomavirus (HPV) is extremely common and, in the vast majority of cases, clears up on its own. However, in some people, it persists and can develop into precancerous lesions or even cancer.

How can these high-risk situations be identified at an early stage? This is the central question of a study led by researchers from the University of Liège.

For several decades, researchers have been attempting to identify biomarkers capable of accurately predicting the progression of infection with high-risk oncogenic HPV. Despite significant progress, no viral, immune or molecular marker currently allows us to reliably predict which infections will resolve spontaneously and which will progress to a more severe disease.

This difficulty stems in particular from the complexity and dynamic nature of carcinogenesis (the biological process by which a healthy cell transforms into a cancer cell) associated with HPV. The course of an infection depends on multiple factors, including viral characteristics, the host's immune response, genetic and epigenetic factors, the microbiota, hormonal influences and the environment. Added to these interactions are random events, notably the accumulation of mutations linked to virus-induced genomic instability. "Perhaps the main challenge is no longer to discover a new biomarker, but to understand how all the biological mechanisms interact to determine the outcome of an HPV infection,"emphasizes Michael Herfs, an oncologist at GIGA-ULiège.

Artificial Intelligence as a New Hope

Faced with this complexity, Diane Bruyère, Romane Geuzaine and Michael Herfs believe that approaches relying on a single biomarker have probably reached their limits. Recent advances in high-throughput molecular analysis and artificial intelligence are now opening up new avenues.

These technologies make it possible to simultaneously integrate vast amounts of biological data in order to build more comprehensive predictive models. The aim is to better distinguish between the various possible trajectories of an infection or a low-grade precancerous lesion: spontaneous regression, persistence or progression to a more serious lesion, or even invasive cancer. These integrative approaches are now regarded as one of the most promising avenues for improving risk stratification. 

Artificial intelligence and integrative models could help us better understand the diversity of biological trajectories observed in patients and, ultimately, offer a more personalized risk assessment."

Diane Bruyère, Researcher, Laboratory of Experimental Pathology, University of Liège

Towards More Personalized Care

Whilst these new models offer great hope, they have not yet been sufficiently validated for use in routine clinical practice. At present, care still relies on HPV testing, cytology and histopathological analysis, supplemented by monitoring that is not highly personalized.

For researchers, the future lies in a better overall understanding of the biology of HPV infections rather than in the search for a single indicator. Ultimately, a more accurate prediction of individual risk could make it possible to tailor patient follow-up, reduce unnecessary interventions and improve the management of those infected.