Evolving Role of Artificial Intelligence and Radiomics in Precision Population Medicine for Cancer Care: Head and Neck Cancer

Saturday, April 13, 2024

10:00 AM - 10:00 PM ET

Location: Foyer Kiosk

First Author(s)

BH

Bradley Hathaway, BA

Medical Student
University of Mississippi Medical Center
University of Mississippi Medical Center, United States

Co-Author(s)

JY

Johnny Yang, BS, BA

Medical Student
University of Mississippi Medical Center
University of Mississippi Medical Center, United States
GV

Gregory R. Vance, BE

Medical student
University of Mississippi Medical Center
University of Mississippi Medical Center, United States
CC

Chanukya Cherukuri, BS

Medical Student
University of Mississippi Medical Center
University of Mississippi Medical Center, United States
JR

Jeffrey A. Roux, BA

Medical Student
University of Mississippi Medical Center
University of Mississippi Medical Center, United States
CG

Camille Grady, BS

Medical Student
University of Mississippi Medical Center, United States
MN

Mary Nittala, DrPH

Assistant Professor
University of Mississippi Medical Center, United States
VV

Vani Vijayakumar, MD

Professor
University of Mississippi Medical Center, United States
SV

Srinivasan Vijayakumar, MD

Advisor
CANCER CARE ADVISORS AND CONSULTANTS LLC, United States

Purpose: To review how the integration of artificial intelligence (AI) and radiomics improves the outcome for various head and neck cancers (HNC) through precision population medicine (PPM).

Methods/Materials: This is a narrative review where databases such as MEDLINE/PubMed and Google Scholar were used for the literature search between 1998 and 2023. The databases were screened with the individual medical subject heading keywords and key term combinations specific to “precision medicine,” “head and neck cancer,” and “AI”.

Results: The authors intend to explore the evolving role of PPM in cancer care through a series of reviews; HNC will be the third cancer discussed. PPM tailors individualized prevention, intervention and treatment plans for HNC to specific populations by isolating genetic and environmental factors unique to each population. For example, HPV-related HNC is more prevalent among Caucasians than African Americans, which may be attributed to genetic variation and environmental risks. AI data mining can efficiently create databases to effectively make multifactorial comparisons that test HNC distribution.

Combined radiotherapy and surgery exhibited improvements in prognosis and disease response in HPV-related oropharyngeal carcinoma when compared to other treatment modalities. Epigenetic factors were found as beneficial targets in the pathogenesis of HNC. Aberrant DNA methylation due to high-risk HPV strains and the PI3K pathway show the most potential for medical intervention. Radiomic data analyses via AI based machine learning yields clinical relevance regarding prognostic determination, diagnostics, and various medical applications. Prognostic models derived from big data and multiomics benefit PPM and give rise to therapeutic advancements and diagnostics on an individual level regarding HNC.

Conclusions: Integrating radiomics and AI along with support from big data creates a driving force for major advancements in HNC care and intervention through PPM. This paper brings light to the innovative approaches and suggestions regarding the various modalities that are taken into consideration by PPM.